Of the 100,000 railroad bridges in the United States, 50% are over 100 years old. Many of these bridges do not meet the minimum vertical clearance standards, making them susceptible to impacts from over-height vehicles. Impacts can cause structural damage and unwanted disruption to railroad bridge services; rapid notification of the railroad authorities is crucial to ensure that the bridges are safe for continued use and to affect timely repairs. Therefore, researchers have developed approaches to identify these impacts to railroad bridges. Some recent approaches use machine learning to more effectively identify impacts from the sensor data. Typically, the collected sensor data is transmitted to a central location for processing. However, the challenge with this centralized approach is that the transfer of data to a central location can take considerable time, which is undesirable for time-sensitive events like impact detection that require rapid assessment and response to potential damage. To address the challenges posed by the centralized approach, this study develops a framework for edge implementation of machine learning predictions on wireless smart sensors. Wireless sensors are used because of their ease of installation and lower costs compared to their wired counterparts. The framework is implemented on the Xnode wireless smart sensor platform, thus bringing artificial intelligence models directly to the sensor nodes and eliminating the need to transfer data to a central location for processing. This framework is demonstrated using data obtained from events on a railroad bridge near Chicago; results illustrate the efficacy of the proposed edge computing framework for such time-sensitive structural health monitoring applications.

This study evaluates the use of remote sensing to improve real-time adaptive management of grasslands. By quantifying grassland biomass through changes in sward height from pre- and post-grazing events using unmanned aerial systems (UAS), we derived accurate biomass estimates. Additionally, we aimed to enhance the biomass estimation with spectral data from Sentinel-2 imagery, which is often hindered by cloud contamination, by combining it with a random forest algorithm. The calibration of UAS biomass using field measurements from sward height changes through 3D photogrammetry produced strong regression metrics (R2= 0.75, RMSE= 1240 kg DM/ha and MAE=980 kg DM/ha). Integrating this UAS-derived data with Sentinel-2 imagery, the satellite based biomass model (R2= 0.56, RMSE=2140 kg DM/ha and MAE=1585 kg DM/ha) compared to using the Sentinel-2 random forest-enabled model alone (R2= 0.56, RMSE=2140 kg DM/ha and MAE=1585 kg DM/ha). This study emphasise the importance of timely and accurate biomass estimation for adaptive gazing management at the field level, highlighting the balance between utilising advanced remote sensing technologies and addressing operational complexities. By optimising the integration of UAS and satellite data, we aim to enhance grassland utilisation, ecosystem functions, nutrient cycling, and sustainability in land use.

Named Entity Recognition (NER) is a fundamental and pivotal stage in the development of various knowledge-based support systems, including knowledge retrieval and question-answering systems. In the domain of pig diseases, Chinese NER models encounter several challenges such as the scarcity of annotated data, domain-specific vocabulary, diverse entity categories, and ambiguous entity boundaries. To address these challenges, we propose PDCNER, a Pig Disease Chinese Named Entity Recognition method leveraging lexicon-enhanced BERT and contrastive learning. Firstly, we construct a domain-specific lexicon and pre-train word embeddings in the pig disease domain. Secondly, we integrate lexicon information of pig diseases into the lower layers of BERT using a Lexicon Adapter layer, which employs char-word pair sequences. Thirdly, to enhance feature representation, we propose a lexicon-enhanced contrastive loss layer on top of BERT. Finally, a Conditional Random Field (CRF) layer is employed as the model's decoder. Experimental results show that our proposed model demonstrates superior performance over several mainstream models, achieving a precision of 87.76%, a recall of 86.97%, and an F1-score of 87.36%. The proposed model outperforms BERT-BiLSTM-CRF and LEBERT by 14.05% and 6.8%, respectively, with only 10% of the samples available, showcasing its robustness in data scarcity scenarios. Furthermore, the model exhibits generalizability across publicly available datasets. Our work provides reliable technical support for the information extraction of pig diseases in Chinese and can be easily extended to other domains, thereby facilitating seamless adaptation for named entity identification across diverse contexts. The codes have been open-sourced at https://github.com/tufeifei923/pdcner.

Antiviral peptides (AVPs) represent a promising strategy for addressing the global challenge of viral infections and their growing resistance to traditional drugs. Lab-based AVP discovery methods are resource-intensive, highlighting the need for efficient computational alternatives. In this study, we developed five non-trained but supervised Multi-Query Similarity Search Models (MQSSMs) integrated into the StarPep toolbox. Rigorous testing and validation across diverse AVP datasets confirmed the models' robustness and reliability. The top-performing model, M13+, demonstrated impressive results with an accuracy of 0.969 and a Matthew’s correlation coeffi-cient of 0.71. To assess their competitiveness, the top five models were benchmarked against 14 publicly available machine learning and deep learning AVP predictors. The MQSSMs outper-formed these predictors, highlighting their efficiency in terms of resource demand and public ac-cessibility. Another significant achievement of this study is the creation of the most comprehensive dataset of antiviral sequences to date.

This paper systematically discusses the application of reinforcement learning in automatic driving system. Reinforcement learning frameworks show significant advantages in optimizing decision making, predictive perception, path planning, and controller design, exceeding the limitations of traditional supervised learning methods. The paper highlights the critical role of components such as scene understanding, positioning, and map making in autonomous driving systems, which provide reliable environmental awareness through deep learning and sensor fusion technologies to support intelligent decision-making in complex urban environments. In addition, the paper discusses innovative approaches to safety reinforcement learning to reduce risk in autonomous driving and ensure that systems adhere strictly to safety constraints while maximizing expected rewards. These findings provide an important theoretical and practical basis for further improving algorithm robustness, managing multi-agent interactions, and integrating ethical considerations in the future.

Estimating the ocean’s subsurface thermohaline information from satellite measurements is essential for understanding ocean dynamics and El Niño phenomenon. This paper proposes an improved double-output Residual Neural Network (DO-ResNet) model to concurrently estimate the ocean subsurface temperature (OST) and ocean subsurface salinity (OSS) in the tropical Western Pacific using multi-source remote sensing data, including sea surface temperature (SST), sea surface salinity (SSS), sea surface height anomaly(SSHA), sea surface wind (SSW), and geographical information (including longitude (LON) and latitude (LAT)). In the model experiment, Argo data were used to train and validate the model, and the root mean square error (RMSE), normalized root mean square error (NRMSE) and coefficient of determination (R²) were employed to evaluate the model's performance. The results showed that the sea surface parameters selected in this study have a positive effect on the estimation process, and the average RMSE and R² values for estimating OST (OSS) by the proposed model are 0.34 °C (0.05 psu) and 0.91 (0.95), respectively. Under the data conditions considered in this study, DO-ResNet demonstrates superior performance relative to the extreme gradient boosting model, random forest model, and artificial neural network model. Additionally, this study evaluates the model’s accuracy by comparing its estimations of OST and OSS across different depths with Argo-derived data, demonstrating the model's ability to effectively capture the most spatial features, and by comparing NRMSE across different depths and seasons, the model displays strong seasonal adaptability. In conclusion, this research introduces a novel artificial intelligence technique for estimating OST and OSS in the tropical Western Pacific Ocean.

Case studies (CS) attempt to help students increase critical thinking skills and engagement while working through a real-life scenario in various disciplines, including medicine, law, and business. However, the CS method has not been heavily utilized in biological sciences. The present study investigated the effect of the CS method on undergraduate biology students’ conceptual understanding, academic outcomes, and perspectives. A case study was applied in a one-semester undergraduate biology course, which was compared to ten semesters of standard sections. Participants completed course pre- and post-tests, pre- and post-case tests, and an online survey to assess their conceptual understanding and engagement. The initial lowest quartiles were determined from the individual course pre-test scores, which were lower than class averages. Results suggested that the CS method helped students in learning outcomes, critical thinking, and conceptual understanding toward biology. In post-test learning gains, the CS group did 20% better than the non-CS group, with the largest benefit seen in the initially lowest pre-test quartile of the class. Moreover, post-case learning gains were 55% improved in the case test. Survey results indicated that students had positive attitudes toward CS for their engagement in plant biology content. Overall, the distribution of A grades improved by 2.6-fold from standard to CS groups. We conclude that the use of CS may address course content engagement and have the potential to effectively boost academic performance, especially for the initially lowest quartile in undergraduate plant biological sciences courses.

This study explores advanced feature engineering and semantic enrichment methods to enhance text classification, focusing on detecting figurative language in tweets. The novel features introduced, Syno\_Lower\_Mean and Syn\_Mean, measure the use of uncommon synonyms and the mean frequency of synonyms, capturing semantic richness crucial for detecting figurative expressions. Using resources like SenticNet and Framester, we enrich our feature set with sentiment and frame semantic information. Our approach includes extensive data preprocessing, sophisticated feature selection, and implementing various classification models, such as SVM, KNN, Logistic Regression, Decision Trees, Random Forest, BERT, and LSTM networks. We rigorously evaluate each model's performance to assess the effectiveness of our features and enrichment methods. Putting emphasis on model explainability, we use decision tree analysis, feature importance analysis, and the TREPAN algorithm to approximate SVM decisions. Although we focus on figurative language detection, our methods have broader implications for various NLP text classification tasks. Our findings demonstrate significant improvements in classification accuracy and interpretability through innovative feature design and dataset enrichment.

Despite ongoing efforts, the relationship between groin strength and injury remains unclear. The challenge of accurately predicting injuries presents an opportunity for researchers to develop pre-vention strategies to reduce the occurrence of such injuries. Consequently, this issue requires further investigation to obtain insights into effective mitigation strategies. In 120 male soccer players the maximum isometric strength of the hip muscle groups was measured, and the strength ratios were calculated. Previous injury and anthropometric data were registered. Injury data were collected following the FIFA/UEFA consensus. The K- Nearest Neighbour (k-NN), was used to predict the incidence of injury, while the significant predictive variables of the k-NN algorithm were fitted into a multivariate logistic regression model (LR) to analyze the likelihood of players sustaining a groin injury. The LR model determined two variables as significant predictors of groin injury. Players were less likely to sustain a groin injury by 76% for each decrease of the Adductors/Abductors isometric strength ratio in the non-dominant limb (OR = 0.238, CI 95%= [(0.098-0.572]). Players with a history of previous injury had a 67% greater risk of sustaining an injury (OR = 0.333, CI 95%= [(0.1068-1.038]). Isometric hip adductor and abductor strength im-balances of the non-dominant lower limb and a history of previous injury were risk factors for groin injury in soccer players.

With the widespread application of artificial intelligence technology in various industries, users' attention to privacy and data security has increased significantly. Federated learning, as a new technology paradigm combining privacy-enhanced computing and artificial intelligence, resolves the contradiction between data security and open sharing. This paper presents the benefits of federated learning in terms of privacy, real-time processing, model robustness, compliance and cross-industry applications. At the same time, when combined with Edge AI technology, federated learning promotes the decentralisation of intelligent systems, improving data privacy protection and model accuracy. This paper also discusses the application cases of federated learning in the medical field, through local data processing and model training, effectively protecting user privacy, realizing medical data sharing and model optimization, and promoting the development of artificial intelligence.

This paper systematically discusses the application and development of federated learning in data privacy protection and data value sharing. With the rapid development of global information technology, especially the explosive growth of data from Internet of Things devices, data security and privacy protection are facing unprecedented challenges. This paper first analyzes the growth trend of global data volume and its importance to next generation technologies such as artificial intelligence technologies such as deep learning. Second, the paper provides an in-depth look at the impact of current data privacy regulations on data flows and value creation, particularly the EU's GDPR and China's Data Security and Personal Information Protection Law. Then, this paper introduces in detail federated learning, as a new distributed machine learning paradigm, which effectively solves the contradiction between existing data sharing and privacy protection by protecting individual data privacy and realizing global model collaborative construction. Finally, this paper discusses the combination of blockchain technology and federated learning, and proposes BeFL architecture as a new secure, decentralized and trusted federated learning system, which is expected to provide a comprehensive solution for large-scale data processing and value creation in multi-party scenarios. The research in this paper not only deepens the understanding of federation learning in theory, but also provides important reference and enlightenment for future research and application in related fields.

This paper investigates the integration of SHM within the frame of Industry 4.0 technologies, highlighting the potential for intelligent infrastructure management through the utilization of Big Data analytics, Machine Learning, and the Internet of Things (IoT). The study also presents a success case focused on a novel SHM methodology for detecting and locating damages in metallic aircraft structures, employing dimensional reduction techniques such as Principal Component Analysis (PCA). By analyzing strain data collected from a network of sensors and comparing it to a baseline pristine condition, the methodology aims to identify subtle changes in local strain distribution indicative of damage. Through extensive Finite Element Analysis (FEA) simulations and a PCA contribution analysis, the research explores the influence of various factors on damage detection, including sensor placement, noise levels, and damage size and type. The findings demonstrate the effectiveness of the proposed methodology in detecting cracks and holes as small as 2mm in length, showcasing the potential for early damage identification and targeted interventions in diverse sectors such as aerospace, civil engineering, and manufacturing. Ultimately, this paper underscores the synergistic relationship between SHM and Industry 4.0, paving the way for a future of intelligent, resilient, and sustainable infrastructure.

Automatic emotion recognition using portable sensors is gaining attention due to its potential use in real-life scenarios. Existing studies have not explored Galvanic Skin Response and Photoplethysmography sensors exclusively for emotion recognition using nonlinear features with machine learning (ML) classifiers such as Random Forest, Support Vector Machine, Gradient Boosting Machine, K-Nearest Neighbor, and Decision Tree. In this study, we proposed a genuine window sensitivity analysis on a continuous annotation dataset to determine the window duration and percentage of overlap that optimize the classification performance using ML algorithms and nonlinear features, namely Lyapunov Exponent, Approximate Entropy, and Poincaré’s indices. We found an optimum window duration of 11 seconds and 16 seconds for valence and arousal, respectively, with 50% overlap, and achieved an accuracy of 0.76 in both dimensions. In addition, we proposed a Strong Labeling Scheme that kept only the extreme values of the labels, which raised the accuracy score to 0.92. Under certain conditions mentioned, traditional ML models offer a good compromise between performance and low computational cost. Our results suggest that well-known ML algorithms can still contribute to the field of emotion recognition, provided that window duration, overlap percentage, and nonlinear features are carefully selected.

Technological developments within the maritime sector are resulting in rapid progress that will see the commercial use of autonomous vessels, known as Maritime Autonomous Surface Ships (MASS). Such ships are equipped with a range of advanced technologies, such as IoT devices, artificial intelligence (AI) systems, machine learning (ML) based algorithms and augmented reality (AR) tools. Through such technologies, the autonomous vessels can be remotely controlled from Shore Control Centres (SCC) by using real-time data to optimise their operations, enhance safety and reduce the possibility of human error. Apart from the regulatory aspects, which are under definition by the International Maritime Organisation (IMO), cybersecurity aspects must be considered and properly addressed to prevent such complex systems from being tampered with. In this paper, we propose an approach to secure communication channels between the SCCs and the vessels using SECOM standard and the underlying digital infrastructure in charge of data collection, storage and processing by relying on a set of machine learning (ML) algorithms for anomaly detection. The proposed approach is validated against a real implementation of the SCC deployed at Livorno seaport premises. Finally, the experimental results and the performance evaluation are provided to assess its effectiveness accordingly.

"Eureka" is a transformative platform designed to address the academic challenges faced by students by fostering an inclusive and collaborative learning environment. Through an online Q\&A discussion format, it facilitates knowledge sharing, coursework discussions, and peer support, thereby enhancing collaborative learning. Key features such as Q\&A, Answer Validation, and Leaderboard ensure efficient and reliable information exchange, motivating active student participation and mutual support. The platform's development using Agile methodologies has proven effective, emphasizing iterative development, constant user feedback, and collaborative efforts. This approach has significantly boosted student engagement and improved learning outcomes. "Eureka" not only aids in students' understanding of course material but also contributes to overall academic performance, serving as a powerful tool in creating a supportive academic environment. Its Agile-based development ensures ongoing responsiveness to student needs, enabling continuous improvement and a sustained positive impact on learning experiences.

From the various perspectives of Machine Learning (ML) and the multiple models used in this discipline, there is an approach aimed at training models for the Early Detection (ED) of anoma-lies. The early detection of anomalies is crucial in multiple areas of knowledge since identifying and classifying them allows for early decision-making and provides a better response to mitigate the negative effects caused by late detection in any system. This article presents a literature review to examine which machine learning models (MLM) operate with a focus on ED in a multidisci-plinary manner and specifically how these models work in the field of fraud detection. A variety of models were found, including Logistic Regression (LR), Support Vector Machines (SVM), De-cision Trees (DT), Random Forests (RF), Naive Bayesian Classifier (NB), K-Nearest Neighbors (KNN), Artificial Neural Networks (ANN), Extreme Gradient Boosting (XGB), among others. It was identified that MLMs operate as isolated models, categorized in this article as Single Base Models (SBM) and Stacking Ensemble Models (SEM). It was identified that MLMs for ED in multiple areas under SBM and SEM implementation achieved accuracies greater than 80% and 90%, respectively. n fraud detection, accuracies greater than 90% were reported by the authors. The article concludes that MLMs for ED in multiple applications, including fraud, offer a viable way to identify and classify anomalies robustly, with a high degree of accuracy and precision. MLMs for ED in fraud are useful as they can quickly process large amounts of data to detect and classify suspicious transactions or activities, helping to prevent financial losses.

The solar energy can mitigate the power supply shortage in remote regions for portable irrigation systems. The accurate prediction of solar irradiance is crucial for determining the quantity of solar panels and the power capacity of photovoltaic power generation (PVPG) systems for mobile sprinkler machines. In this study, a prediction method is proposed to forecast the solar irradiance of typical irrigation areas. The impact of the meteorological parameters on the solar irradiance is studied, and four different parameter combinations are formed and considered as input to the prediction model. Based on meteorological data provided by ten typical radiation stations uniformly distributed nationwide, an Extreme Gradient Boosting (XGBoost) model optimized using the Whale Optimization Algorithm (WOA) is developed to predict the solar radiation. The prediction accuracy and stability of the proposed method are then evaluated for different input parameters through training and testing. The differences between the prediction performances of models trained based on single-station data and mixed data from multiple stations are also compared. The obtained results show that the proposed model achieves the highest prediction accuracy when the maximum temperature, minimum temperature, sunshine hours ratio, relative humidity, wind speed, and extraterrestrial radiation are used as the input parameters. The prediction effectiveness is also verified based on measured data. The WOA-XGBoost model has higher prediction accuracy than the XGBoost model, with predicted values falling within acceptable ranges. The model developed using mixed data of multiple stations can be applied for forecasting solar irradiance in different regions. This study provides a foundation for the optimization of the configuration of PVPG systems for mobile sprinkler machines.

Electric Transformers make up some of the most critical components of a power system. Their reliable operation is critical for an efficient power grid as well as economic viability for the transformer operators and owners. Power transformers, like other High Voltage (HV) electrical equipment experience aging and insulation degradation due to chemical, mechanical and electrical forces during their operation. Partial Dischargers (PD) are localized electrical discharges that develop within insulation systems of HV electrical equipment such as transformers. In transformers, PD occurs in different forms and various locations and insulation both internal and external of the transformer. PD originates as small pulses but tends to increase in size and intensity which can result in complete insulation failure. Monitoring partial discharges has proven to provide valuable information on the state of the insulation systems of the power transformer, allowing transformer operators to make calculated decisions for the maintenance and life of plant plans. This systematic literature review aims to systematically examine the use of machine learning techniques in classifying PD in transformers to present a complete indicator to allow for future research in the field. The systematic review surveyed a total of 81 research literature published from 2010 to 2023 that fulfilled a specific methodology which was developed as part of this study. The results revealed that supervised learning has been the most widely used Artificial Intelligence (AI) algorithm utilized, primarily in the form of Support Vector Machine (SVM). Regarding PD, the survey revealed that most researchers tend to use numerous types of PD and compare them to one another. Furthermore, the use of artificial PD defect models to simulate the occurrence of PD is widely used versus the use of actual power transformers. Most of the literature tends to not specify the physical characteristics of PD, such as the magnitude of PD, PD inception voltage and PD extinction voltage.

Predicting type 2 diabetes mellitus (T2DM) using phenotypic data with machine learning (ML) techniques has received significant attention in recent years. PyCaret, an ML tool that enables the simultaneous application of 16 different algorithms, was used to predict T2DM using phenotypic variables from the “Nurses’ Health Study” and “Health Professionals’ Follow-up Study” datasets. Ridge classifier, Linear Discriminant Analysis, and Logistic Regression (LR) were the best-performing models for the male-only data subset. For the female-only data subset, LR, Gra-dient Boosting Classifier, and CatBoost Classifier were the strongest models. The AUC, accuracy, and precision were 0.77, 0.70, and 0.70 for males and 0.79, 0.70, and 0.71 for females, respective-ly. The feature importance plot showed that familial history of diabetes (famdb), never having smoked, and high blood pressure (hbp) were the most influential features in females, while famdb, hbp, and current smoking were the major variables in males. In conclusion, PyCaret was used successfully for speed analysis for the prediction of T2DM by simplifying complex ML tasks. Gen-der differences are an important consideration for T2DM prediction. Despite this comprehensive ML tool, phenotypic variables alone may not be sufficient for early T2DM prediction; genotypic variables could also be used in combination for future studies.

The challenging terrain and deep ravines characteristic of mountainous regions often result in slower path planning and suboptimal flight paths for Unmanned Aerial Vehicles (UAVs) when traditional meta-heuristic optimization algorithms are employed. This study investigates the application of an Improved Enhanced Snake Optimizer (IESO) for three-dimensional path planning in a simulated rugged mountainous terrain. The initialization process in the enhanced snake optimizer is refined by integrating the Chebyshev chaotic map. Additionally, a non-monotonic factor is introduced to modulate the "temperature," and a boundary condition is incorporated into the dynamic opposition learning mechanism. These modifications collectively reduce the likelihood of population convergence to local optima during optimization. The feasibility of IESO is validated through time complexity and global convergence analyses. Comparative simulation experiments benchmarked IESO against five state-of-the-art optimization algorithms across test functions and path-planning simulated scenarios. The experimental results indicate that the enhanced algorithm achieves superior optimization precision, faster convergence speeds, and improved quality in the planned trajectories by 30%.

This work presents a methodology for the generation and classification of phase resolved partial discharges (PRPD) patterns based on the use of a printed UHF monopole antenna and signal con-ditioning circuit to reduce hardware requirements. For this purpose, envelope detection technique was applied. In addition, test objects such as a hydrogenerator bar, dielectric disks with internal cavities in an oil cell, potential transformer, and tip-tip electrodes immersed in oil were used to generate partial discharge (PD) signals. To detect and classify partial discharges, the standard IEC 60270 (2000) method was used as reference. After acquisition of conditioned UHF signals, digital signal filtering threshold technique was used, and peaks of partial discharges envelopes pulses were extracted. Feature selection techniques were used to classify the discharges and choose the best features to train machine learning algorithms, such as multilayer perceptron, support vector ma-chine and decision tree. Accuracies greater than 84% were met, revealing the classification potential of the methodology proposed in this work.

E-tourism is one of the most important modern services to achieve the development of the tourism sector while relying on sophisticated communication technologies. Certainly, these innovations in the field of tourism have disrupted this sector with new and different dimensions of tourism development. This has led various regions and countries to accelerate the search for the tools that are necessary to achieve excellence and sustainable development in tourism. This research aims to study the development factors of e-tourism to achieve excellence and sustainable development in the tourism of the Ha’il region. Therefore, we applied two analyses: in the first one, we used a statistical analysis based on the survey sent to employees from tourism companies. The objective of this analysis is to determine the main factors of e-tourism to achieve excellence in tourism in the Ha’il region. The results of the statistical analysis have given us the following elements: There are only four main factors that allow authorities to achieve excellence in tourism in the Ha’il region, namely ST, CP, HRS, and SC factors. Then we proceed with a second analysis, to determine the main factors of excellence in tourism that drive the achievement of sustainable development in tourism in the Ha’il region. For this reason, we applied an artificial intelligence method based on the unsupervised machine learning technique. The results obtained from the machine learning technique show that five factors determine the excellence in tourism and reveal the sustainable development of Ha’il’s tourism. These factors are ST, CP, FP, HRS, and GC. Consequently, we consider that all the factors found in both analyses are important to realise excellence in tourism and sustainable development in tourism. However, to achieve sustainable development in tourism in Ha’il, Saudi authorities must develop the three common factors found in the two analyses, namely ST, CP, and HRS.

Archaeometry can help archaeologists in multiple instances, one of the common archaeometric goals are the provenance analyses. Volcanic stones appear frequently in archaeological sites as materials used to build grinding tools like millstones and mortars or as building materials. Petrographic characterization is commonly applied to identify their main mineralogical components. However, provenance of volcanic stones is usually undertaken by comparison with geochemical data from reference outcrops using common descriptive statistical tools such as biplots of chemical elements, and unsupervised multivariate data analysis like principal component analysis (PCA). Recently, the use of supervised classification methods has shown a superior performance in assigning provenance to archaeological samples. However, these methods require the use of reference databases for every possibly provenance class to be able to train the used classification algorithms. The existence of comprehensive collections of published geochemical analyses of igneous rocks enables the use of the supervised approach for provenance determination of volcanic stones. In this paper, the provenance of volcanic grinding tools from two archaeological sites (Iulia Libica, Spain and Sidi Zahruni, Tunisia) is attempted using data from the GEOROC Database through unsupervised and supervised approaches.

Heart sounds and murmurprovidecrucial diagnosis information for valvular heart diseases (VHD). Phonocardiogram (PCG) combined with modern digital processing techniques, provides a complementary tool for clinicians. This article proposes a benchmark different time-frequency representations, which are spectogram, mel-spectogram and cochleagram for obtaining images, in addition to the use of two interpolation techniques to improve the quality of the images, which are Bicubic and Lanczos. Deep features are extracted from a pre-trained model called VGG16 and for feature reduction the Boruta algorithm is applied. To evaluate the models and obtain more precise results, nested cross-validation is used. The best results achieved in this study were for coclegram with 99.2% accuracy and mel-spectogram representation with the bicubic interpolation technique which reached 99.4% accuracy, both having support vector machine (SVM) as classifier 10 algorithm. Overall, this study highlights the potential of time-frequency representations of PCG 11 signals combined with modern digital processing techniques and machine learning algorithms for 12 accurate diagnosis of VHD.

In the rapidly evolving FinTech sector, risk management is paramount for dealers and brokers. This paper underscores the significance and progression of risk management within this realm. Initially, it reviews the traditional risk management technologies and their inherent limitations. The discourse then shifts to contemporary solutions, specifically emphasizing the role of artificial intelligence, machine learning algorithms, and big data analytics in forecasting and mitigating potential risks. The paper also presents case studies of companies effectively utilizing these advanced techniques, highlighting their benefits in real-world scenarios. Additionally, it addresses forthcoming challenges, including regulatory compliance, data privacy issues, and the imperative for strengthened cybersecurity measures. The conclusion acknowledges that the adoption of these innovative technologies not only boosts operational efficiency but also markedly diminishes financial risks, thereby contributing to a more stable and reliable financial market

Recent years have witnessed significant advances in reinforcement learning (RL), which has registered remarkable success in solving various sequential decision-making problems in machine learning. Most of the successful RL applications, e.g., the games of Go and Poker, robotics, and autonomous driving, involve the participation of more than one single agent, which naturally fall into the realm of multi-agent RL (MARL), a domain with a relatively long history, and has recently re-emerged due to advances in single-agent RL techniques. Although, typically, the communication protocol between agents is manually specified and not altered during training, recently, some papers have shown signs of trying to emerge a communication between agents on the one hand and, on the other hand, to understand what is exchanged between agents. So, there is a growing body of literature on this topic which includes qualitative and quantitative studies and the ones that apply mixed methods. This study presents the scoping review of the methodological strategies undertaken in a total of 16 research articles. The results present the critical appraisal of quantitative methods in terms of validity and reliability and for qualitative methods considering four trustworthiness factors. In the end, relevant insights are further explored with implications and reflections on how they can benefit one's research in the field.

In the field of business environments, the integration of novel artificial intelligence (AI) techniques has been identified in the literature and theoretical discourse as an essential catalyst for enhancing the decision-making processes. In the contemporary landscape of digital transformation, the application of these techniques becomes essential, despite encountering various hurdles that impede their seamless integration into the rational decision-making process within e-government, which constitutes a critical component of digital government initiatives. This study explores whether similar advancements can be observed within the e-government sector and investigates the impact of using machine learning (ML) as a technique of artificial intelligence on rational decision-making (RDM). Employing an empirical research approach, the study utilized a quantitative methodology, relying on an electronically structured questionnaire survey administered to 163 employees in the e-government sector in Jordan through purposive random sampling. Data analysis was conducted using the SPSS v25 program, complemented by a media-tion analysis using AMOS v23 software. The research findings revealed a significant contribution of using machine learning to enhance rational decision-making and trust levels, with trust positively impacting RDM. Trust was identified as a beneficial mediator in the relationship between machine learning and rational decision-making. Despite certain limitations, this study's outcomes offer substantial insights for researchers and government policy-makers alike, contributing to the advancement of sustainable practices in the e-government domain.

Bacterial infections and resistance to antibiotic drugs represent the highest challenges to public health. The search for new and promising compounds with anti-bacterial activity is a very urgent matter. In order to promote the development of platforms enabling to the discovery of compounds with anti-bacterial activity, Fourier Transformed Mid-Infrared (FT-MIR) spectroscopy associated with the machine learning algorithms were used to predict the impact of compounds extracted from Cynara cardunculus against Escherichia coli cells. According to the plant tissue (seeds, dry and fresh leaves, and flowers) and the solvents (ethanol, methanol, acetone, ethyl acetate, and water), compounds with different compositions concerning, phenol content, antioxidant, and antimicrobial activity were obtained. Principal component analysis of spectra, allowed to discriminate compounds that inhibit the E. coli growth, according to the conventional assay. The supervised classification models enabled the prediction of the compound's impact on the E. coli growth, with the accuracy for the test data: Partial least squares-discriminant analysis of 94%; Support vector machines of 89%; k-Nearest neighbor of 72%; and a Backpropagation network of 100%. According to the promising results, the integration of FT-MIR spectroscopy with machine learning presents a high potential to promote the discovery of new compounds with antibacterial activity, thereby streamlining the drug exploratory process.

This paper presents the development of a novel anti-violence device titled "no pAIn" (an acronym for Never Oppressed Protected by Artificial Intelligence Nonviolence system), which harnesses the power of artificial intelligence (AI). Primarily designed to combat violence against women, the device offers personal safety benefits for individuals across diverse demographics. Operating autonomously, it necessitates no user interaction post-activation. The AI engine conducts real-time speech recognition and effectively discerns genuine instances of aggression from non-violent disputes or conversations. Facilitated by its Internet connectivity, in the event of detected aggression, the device promptly issues assistance requests with real-time precise geolocation tracking to predetermined recipients, for immediate assistance. Its compact size enables discreet concealment within commonplace items like candy wrappers, or within purpose-built casings, or as wearable accessories. The device is battery-operated. The prototype was developed using a microcontroller board (Arduino Nano RP2040 Connect), incorporating an omnidirectional microphone and Wi-Fi module, all at a remarkably low cost. Subsequent functionality testing, performed in debug mode using the Arduino IDE serial monitor, yielded successful results. The AI engine exhibited exceptional accuracy in word recognition, complemented by a robust logic implementation, rendering the device highly reliable in discerning genuine instances of aggression from non-violent scenarios

Scholars and policymakers see sustainability as depending on the interrelationships between the three pillars of the environment, society and the economy. However, it remains less clear how key stakeholders with a responsibility for educating the next generation perceive the concept of sustainability and act accordingly. In order to gain new insights, this research scrutinises participant perceptions on sustainability and climate change in two eco-schools in England for primary children (aged 5-11 years). Our case study involved individual interviews with classroom teachers and headteachers, group interviews with fourth- and fifth-year students (ages 10-12 years), and in-class observations. We also analysed data from student exercise books and photographs of school grounds to understand participants’ self-reported knowledge and perceptions of sustainability and climate change. Within a framework drawing on theories of science communication and transformative learning (a learning approach based on having challenging experiences), the results show that the integration of sustainability into the curriculum was limited and problematic. That is despite the fact that all students and teachers were aware of the environmental dimensions of sustainability, like climate change and the overuse of natural sources. These findings suggest that schools are no different to other institutional settings when it comes to dealing with the challenges of integrating sustainability into daily practice. We conclude that there is a need for in-service teacher education programmes to enable and motivate teachers to provide richer teaching-learning environments so as to enable effective learning in schools about sustainability and climate change.

This study uses a wind turbine case study to showcase an architecture for implementing a distributed digital twin in which all important aspects of a predictive maintenance solution in a DT use a fog computing paradigm, and the typical predictive maintenance DT is improved to offer better asset utilization and management through real time condition monitoring, predictive analytics, and health management of selected components of Wind turbines in a wind farm.. Digital twin (DT) is a technology that sits at the intersection of Internet of Things, Cloud Computing and Software Engineering to provide a suitable tool for replicating physical objects in the digital space. This can facilitate the implementation of asset management in manufacturing systems through predictive maintenance solutions leveraged by Machine Learning (ML). With DTs, a solution architecture can easily use data and software to implement asset management solutions such as Condition Monitoring and Predictive Maintenance using acquired sensor data from physical objects and computing capabilities in the digital space. While DT offers a good solution, it is an emerging technology that could be improved with better standards, architectural framework, and implementation methodologies. Researchers in both academia and industry have showcased DT implementations with different levels of success. However, DTs remain limited in standards and architectures that offer efficient predictive maintenance solutions with real time sensor data, and intelligent DT capabilities. An appropriate feedback mechanism is also needed to improve asset management operations.

Recently, there has been considerable research on deepfake detection. However, most existing methods face challenges in adapting to the advancements in new generative models within unknown domains. In addition, the emergence of new generative models capable of producing and editing high-quality images, such as Diffusion, Consistency, and LCM, poses a challenge for traditional deepfake training models. These advancements highlight the need for adapting and evolving existing deepfake detection techniques to effectively counter the threats posed by sophisticated image manipulation technologies. In this paper, our objective is to detect deepfake videos in unknown domains using unlabeled data. Specifically, our proposed approach employs Meta Pseudo Labels (MPL) with Supervised Contrastive Learning, so-called SupCon-MPL, allowing the model to be trained on unlabeled images. MPL involves the simultaneous training of both a Teacher model and a Student model, where the Teacher model generates Pseudo Labels utilized to train the Student model. This method aims to enhance the adaptability and robustness of deepfake detection systems against emerging unknown domains. Supervised Contrastive Learning utilizes labels to compare samples within similar classes more intensively, while encouraging greater distinction from samples in dissimilar classes. This facilitates the learning of features in a diverse set of deepfake images by the model, consequently contributing to the performance of deepfake detection in unknown domains. When utilizing the ResNet50 model as the backbone, SupCon-MPL exhibited an improvement of 1.58% in accuracy compared to traditional MPL in known domain detection. Moreover, in the same generation of unknown domain detection, there was a 1.32% accuracy enhancement, while in the detection of post-generation unknown domains, there was an 8.74% increase in accuracy.

Floods, recognized for their erratic behavior and devastating effects, are a significant threat as a natural disaster. In Brunei Darussalam, the impact of climate change is becoming increasingly evident through higher temperatures and an expected increase in annual rainfall (5.0mm per year from 2021 to 2050), highlighting the critical need for updated flood risk management techniques. In line with the climate resilience and adaptation objectives of WAWASAN 2035, this paper introduces an innovative approach—a cutting-edge flood risk management framework that utilizes the capabilities of big data analytics, sophisticated machine learning algorithms, and smart Internet of Things (IoT) sensors. Traditional methods, which rely on numerical and physical data modeling, often do not provide precise short-term flood forecasts. Our suggested framework uses machine learning to analyze real-time flood forecasting, sensor data and enhance warning systems, addressing the shortcomings of traditional approaches. The key advantage of this approach is its potential to drastically decrease flood-related damages, protect lives, and boost infrastructure resilience. This proposal is not only in aligns with Brunei's vision for a safe and climate-adaptable future but also marks a significant step forward in adopting innovative and sustainable flood risk management solutions amidst an evolving climate.

The objective of this study was to analyze the mental workload using EEG and eye tracking data and classify it using machine learning algorithms. The machine learning model was developed based on the simultaneous recording of eye tracking and EEG measurements during the experimental process. The experiments involved 15 university students, consisting of 7 women and 8 men. Throughout the experiments, the researchers utilized the n-back memory task and the NASA-Task Load Index (TLX) subjective rating scale to assess various levels of mental workload. The findings revealed that as the task difficulty increased, there was an increase in the diameter of both the right and left pupils, the number of fixations, the number and duration of saccades, and the number and duration of blinks. Conversely, variables related to fixation duration decreased. The EEG results indicated that theta power in the prefrontal, frontal, and front central regions increased with task difficulty. Additionally, alpha power increased in the frontal regions but decreased in the temporal, parietal, and occipital regions as the task became more challenging. Furthermore, low beta power significantly decreased in almost all brain regions as the task difficulty increased. In terms of the four-class classification problem, the mental workload level can be predicted with an accuracy rate of 76.59% using 34 selected features. This study has made a significant contribution to the literature by presenting a four-class mental workload estimation model that utilizes different machine learning algorithms.

Predictions of crop production in the Chi basin are of major importance for decision support tools in countries such as Thailand, which aim to increase domestic income and global food security by implementing the appropriate policies. This research aims to establish a predictive model for predicting crop production for an internal crop growth season prior of harvest at the province scale for fourteen provinces in Thailand's Chi basin between 2011 and 2019. We provide approaches for reducing redundant variables and multicollinearity in remotely sensed (RS) and meteorological data to avoid overfitting models using correlation analysis (CA) and variance inflation factor (VIF). Temperature condition index (TCI), normalized difference vegetation index (NDVI), land surface temperature (LSTnight), and mean temperature (Tmean) were the resulting variables in the prediction model with a p-value < 0.05 and a VIF < 5. The baseline data (2011–2017: June to November) were used to train four regression models, which revealed that eXtreme Gradient Boosting (XGBoost), random forest (RF), and XGBoost achieved R2 values of 0.95, 0.94, and 0.93, respectively. In addition, the testing dataset (2018–2019) displayed a minimum root mean square error (RMSE) of 0.18 ton/ha for the optimal solution by integrating variables and applying the XGBoost model. Accordingly, it is estimated that between 2020 and 2022, the total crop production in the Chi basin region would be 7.88, 7.64, and 7.72 million tons, respectively. The results demonstrated that the proposed model is proficient at greatly improving crop yield prediction accuracy when compared to a conventional regression method and that it may be deployed in different regions to assist farmers and policymakers in making more informed decisions about agricultural practices and resource allocation.

The objective of this study was to investigate the liquefaction resistance of chemically improved sandy soils in a straightforward and accurate manner. Using only the existing experimental databases and artificial intelligence, the goal was to make predictions without conducting physical experiments. Emphasis was placed on the significance of data from 20 loading cycles of cyclic undrained triaxial tests to determine the liquefaction resistance and the contribution of each explanatory variable. Different combinations of explanatory variables were considered. Regarding the predictive model, it was observed that a case with the liquefaction resistance ratio as the dependent variable and other parameters as explanatory variables yielded favorable results. In terms of exploring combinations of explanatory variables, it was found advantageous to include all variables as doing so consistently resulted in a high coefficient of determination. The inclusion of the liquefaction resistance ratio in the training data was found to improve the predictive accuracy. In addition, the results obtained when using a linear model for the prediction suggested the potential to accurately predict the liquefaction resistance using historical data.

Stress can reduce the accuracy of radiation therapy owing to muscle contraction and changes in breathing patterns. This study aimed to predict stress in patients before each treatment session using artificial intelligence (AI) from biological signals to enhance treatment accuracy. We measured 123 stress cases in 41 patients and calculated stress scores by analyzing seven stress-related features derived from heart rate variability obtained from photoplethysmography. The study analyzed stress score distribution and observed its trend changes throughout the treatment. Before-treatment information was used to predict changes in stress features during treatment. AI models included both non-pre-trained (Decision Tree, Random Forest, Support Vector Machine, Long Short-Term Memory (LSTM), Transformer) and pre-trained (ChatGPT) models. The performance was evaluated using 10-fold cross-validation, exact match ratio, accuracy, recall, precision, and F1 score. More than 90% of the patients experienced stress during radiation therapy. From all the classifications, LSTM and prompt engineering GPT4.0 had the highest accuracy (feature classification, LSTM: 0.703, GPT4.0: 0.659, stress classification: LSTM: 0.846, GPT4.0: 0.769). Our research pioneers the use of AI and biological signals for stress prediction in radiation therapy, potentially identifying patients needing psychological support, and suggesting methods to improve radiotherapy effectiveness through stress management.

Existing reinforced concrete buildings with seismically-deficient column details affect the overall behavior depending on the failure type of column. The purpose of this study is to develop and validate a machine learning-based prediction model for the column failure modes (shear, flexure-shear and flexure failure modes). For this purpose, artificial neural network (ANN), K-nearest neighbor (KNN), decision tree (DT), and random forest (RF) models were used considering previously-collected experimental data. Using four machine learning methodologies, we developed a classification learning model that can predict the column failure modes in terms of the input variables using concrete compressive strength, steel yield strength, axial load ratio, height-to-dept aspect ratio, longitudinal reinforcement ratio, and transverse reinforcement ratio. The performance of each machine learning model was compared and verified by calculating accuracy, precision, recall, F1-Score, and ROC. Based on the performance measurements of the classification model, the RF model represents the highest average value of the classification model performance measurements among the considered learning methods, and it can conservatively predict the shear failure mode. Thus, the RF model can rapidly predict the column failure modes with the simple column details. Additionally, it was demonstrated that the predicted failure modes from the selected model were exactly same as the failure mode determined from a code-defined equation (traditional method)

The visual perception of leisure spaces between residences in cold regions is important for public health. To compensate for the existing researches` lack of ignoring the cold snow season`s influence, this study selected two types of outdoor leisure space environments in non-snow and snow seasons as research objects. An eye tracker combined with a Semantic Difference (SD) questionnaire was used to verify the feasibility of the application of virtual reality technology, screen out leisure gaze characteristics, and reveal the environmental factors related to leisure visual perception. In snow season, spatial aspect ratio (SAR), building elevation saturation (BS), and grass proportion in the field of view (GP) showed strong correlation to the leisure visual perception scores (W). In non-snow season, apart from the above three factors, roof height difference (RHD), tall tree height (TTH) and color contrast (HC) also influenced W obviously. The effects of factors on W were revealed in immersive virtual en-vironment (IVE) orthogonal experiments and genetic algorithm (GA) and k-nearest neighbor algorithm (KNN) were combined to optimized the environmental factors. The optimized threshold ranges in the non-snow season environment were SAR: 1.82‒2.15, RHD: 10.81 m‒20.09 m, BS: 48.53‒61.01, TTH: 14.18 m‒18.29 m, GP: 0.12‒0.15, and HC: 18.64‒26.83. In the snow season environment, the optimized threshold ranges were SAR: 2.22‒2.54, BS: 68.47‒82.34, and GP: 0.1‒0.14.

Industrial Control Systems (ICS) are integral to managing and optimizing processes in various industries, including manufacturing, power generation, and more. However, the scarcity of widely adopted ICS datasets hampers research efforts in areas like optimization and security. This scarcity arises due to the substantial cost and technical expertise required to create physical ICS environments. In response to these challenges, this paper presents a groundbreaking approach to generating synthetic ICS data through a data-driven ICS network simulation. We circumvent the need for expensive hardware by recreating the entire ICS environment in software. Moreover, rather than manually replicating the control logic of ICS components, we leverage existing data to autonomously generate control logic. The core of our method involves the stochastic setting of setpoints, which introduces randomness into the generated data. Setpoints serve as target values for controlling the operation of the ICS process. This approach enables us to augment existing ICS datasets and cater to the data requirements of machine learning-based ICS intrusion detection systems and other data-driven applications. Our simulated ICS environment employs virtualized containers to mimic the behavior of real-world PLCs and SCADA systems, while control logic is deduced from publicly available ICS datasets. Setpoints are generated probabilistically to ensure data diversity. Experimental results validate the fidelity of our synthetic data, emphasizing its ability to closely replicate temporal and statistical characteristics of real-world ICS networks. In conclusion, this innovative data-driven ICS network simulation offers a cost-effective and scalable solution for generating synthetic ICS data. It empowers researchers in the field of ICS optimization and security with diverse, realistic datasets, furthering advancements in this critical domain. Future work may involve refining the simulation model and exploring additional applications for synthetic ICS data.

The vehicular ad hoc network (VANET) when augmented with internet is called internet of vehicles (IoV). In the IoV, vehicles have on board units (OBUs), use communication technologies and customized software to communicate with infrastructure around them. The vehicles can have permanent connectivity and global network awareness based on cloud computing. IoV technologies are still being assessed to ensure that the network is protected from attacks, supports a dynamic vehicular mobility scenarios and meets the low latency communication requirements between the vehicles and the surrounding infrastructure. To meet these strict Quality of Service (QoS) demands, Unmanned Aerial Vehicles (UAVs) play a vital role in IoV ecosystems. An UAV can serve as a mobile roadside unit (mRSU) to transmit data between vehicles, stationery RSUs and other UAVs. The UAVs have better line of sight (LOS) connections which result in better channel states and lower path loss than fixed RSUs. Although the inclusion of UAVs in vehicular networks has improved the system performance by providing better resource management and routing solutions, the traditional optimization techniques with their limitations are often not applicable. Therefore, in recent years, research community is integrating Artificial Intelligence (AI) and Machine Learning (ML) into UAV based IoV ecosystem to better manage resource allocation, routing and mobility management issues to optimize the overall network performance. In this survey paper we review the existing research done in AI/ML based UAV-IoV networks and communications with focus on resource management and routing from year 2019 to 2023. We have studied different AI techniques, their training attributes and architectures in various research works. The limitations of AI-based approaches in terms of required computational resources, availability of real world data and AI models’ complexity for the UAV-IoV environment are also discussed. Finally, the future directions for UAV-IoV research opportunities that can leverage the full potential of AI are presented.

Temperature increases mediated through climate change threaten the survival of species. It is of foremost importance to engage citizens and future generations in understanding the mechanisms through which temperatures imposes its affect. For educators though this is not straight forward as tools for examined the impact of temperature over the lifetime of an animal are prohibitively expensive. At the same time environmental educators need guidance on the appropriate study systems to use with a balance between the species having an obvious response and ensuring the outcomes are ethical and sustainable. In our study, we created and tested a cost-effective experiment meant to be used for environmental education purposes. More specifically, we tested the sensitivity of the Painted lady butterfly Vanessa cardui to temperature variations using a homemade incubator. We describe the design of this experiment and report findings on survival rate, morphological variations, pupation time, and wingspan of adults across a range of biologically relevant temperatures. The information provided give educators options for testing a variety of hypotheses with regards to the impacts of temperature using an affordable and flexible set-up. Furthermore, the findings can be used by students to develop an understanding of the ramifications of the butterflies responses in an ecological context.

Estimating the Remaining Useful Life (RUL) of aircraft engines holds a pivotal role in enhancing safety, optimizing operations, and promoting sustainability, thus being a crucial component of modern aviation management. Precise RUL predictions offer valuable insights into an engine’s condition, enabling informed decisions regarding maintenance and crew scheduling. In this context, we propose a novel RUL prediction approach in this paper, harnessing the power of Bi-directional LSTM and Transformer architectures, known for their success in sequence modeling, such as natural languages. We adopt the encoder part of the full Transformer as the backbone of our framework, integrating it with a self-supervised denoising autoencoder that utilizes Bidirectional LSTM for improved feature extraction. Within our framework, a sequence of multivariate time series sensor measurements serves as the input, initially processed by the Bidirectional LSTM autoencoder to extract essential features. Subsequently, these feature values are fed into our Transformer encoder backbone for RUL prediction. Notably, our approach simultaneously trains the autoencoder and Transformer encoder, different from the naive sequential training method. Through a series of numerical experiments carried out on the C-MAPSS datasets, we demonstrate that the efficacy of our proposed models either surpasses or stands on par with that of other existing methods.

Multiple sclerosis is a chronic, autoimmune disease that mainly affects the central nervous system, including the brain, spinal cord, and optic nerve. This disease can cause clinical symptoms such as cognitive decline, muscle weakness, spasms, and fatigue in patients, and the onset tends to be younger. Current medication can only prevent or alleviate symptoms, so early diagnosis of this disease can increase patients' chances of treatment. Although the use of nuclear magnetic resonance detection can improve the efficiency of early auxiliary diagnosis, it still requires experienced doctors to spend too much time and energy on comprehensive judgment. To reduce the time cost and improve the efficiency of multiple sclerosis diagnosis, this article proposes a detection and recognition algorithm for multiple sclerosis based on wavelet entropy and self-adaptive particle swarm optimization. Firstly, a triple discrete wavelet transform is performed on the brain image of multiple sclerosis, and then 10 wavelet entropies are extracted from the decomposed wavelet subbands, which can reduce the feature dimensions of the image; Then, the algorithm of self-adaptive particle swarm optimization is used to optimize the feedforward neural network, in order to obtain the optimal connection weights and thresholds during the training process. The result of the model is with an average sensitivity of 92.29±1.89, specificity of 92.54±0.67, precision of 92.48±0.59, accuracy of 92.42±0.88, and F1 score of 84.85±1.74, Matthews correlation coefficient of 92.37±0.96, and Fowlkes223 Mallows Index of 92.38±0.96. The experimental results indicate that this algorithm has a very important data support role in detecting multiple sclerosis.

Background: A personalized approach to occupational medicine allows specialists to 1 prevent professional hazards such as stress-related depression and anxiety in extreme work environments. Objective: we aim to detect genetic markers of low resilience to stress. Methods: The study cohort included 97 elite athletes and 167 special forces personnel. The research team collected buccal mucosa samples and examined psychological status with the Hospital Anxiety and Depression Scale (HADS). We assessed 35 variants within selected genes that are most often associated with low resilience to stress, anxiety, and depression. Fisher’s Exact test was used to determine nonrandom associations between scores in the HADS scale and the genetic variants. We also trained machine learning models to predict score values from genotyping findings and ranked genetic biomarkers according to their predictive power. Results: High-risk depression profiles included C/T genotype of MTHFR C677T and A/C variant of MTHFR A1298C. Susceptibility to anxiety was associated with several polymorphisms regulating neuroactive substances, immune response, and coagulation. The ML models accurately detect depression or anxiety levels with MAE/ROV of 17.69±1.35 and 17.86±2.09% respectively. Conclusions: The study findings justify a polymorphic nature of anxiety and confirm the immune system's involvement in regulating stress response.

Human activity recognition (HAR) using wearable sensors is gaining popularity in the healthcare domain, enabling continuous monitoring and timely interventions. The conventional HAR systems are centralised and need data sharing with a server for processing and model training. However, this data sharing leads to various challenges, such as privacy concerns, increased communication and storage costs, inefficient computational algorithms, data scarcity due to unwillingness to share, and difficulty achieving high accuracy and personalised models simultaneously. To overcome these challenges, this paper introduces a privacy and energy-aware federated learning (FL) framework for model training without data sharing. The proposed scheme incorporates spiking neural networks (SNNs), which are particularly suited for resource-constrained devices due to their event-driven information processing. The key idea is to synergise the strengths of SNNs and long short-term memory (LSTM) to create a hybrid model for robust HAR. The proposed hybrid spiking LSTM (S-LSTM) model uses the LSTM as an input layer to capture temporal dependencies efficiently, followed by spiking layers that replace the typical activation using leaky integrate-and-fire neurons. We employ the combination of surrogate gradient learning and backpropagation through time (BPTT) to update the weights of SNN layers in a supervised manner. The performance of the proposed model is evaluated using two publicly available datasets for both indoor and outdoor scenarios. The results show that the proposed S-LSTM performs much better than spike convolutional neural networks (S-CNN) and simple CNN, achieving the accuracy of 97% and 87% for indoor and outdoor datasets, respectively. Personalisation, also known as fine-tuning the global model using local data, is crucial in HAR. It allows the model to adapt to individual behaviour and preferences, making predictions more accurate. The results also show that personalisation improves the performance of participants up to 9% on average. Additionally, analysis with 50% random client participation reduces communication costs by 50% with minimal impact on accuracy.

This article reviews the introduction of Alzheimer's Disease (AD), neural networks, training and learning of neural networks, applications of neural networks in early diagnosis of AD, applications of neural networks in AD drug discovery, other brain diseases, and challenges faced by AD. First, the paper introduces the background and characteristics of AD. AD is a degenerative neurological disorder characterized by impaired memory, decreased cognitive function, and loss of neurons. These characteristics place a huge burden on the lives and families of patients. Next, the basic principle and structure of neural network are discussed. A neural network is a computational model made up of multiple neurons that can perform tasks by learning and adapting to input data. In particular, the key concepts of neural network hierarchy, activation function and weight adjustment are discussed. Then, the training and learning methods of neural networks are discussed. Common techniques such as backpropagation algorithm and gradient descent optimizer are introduced in detail, as well as the importance of data preprocessing and model evaluation. Next, the paper focuses on the application of neural network in early diagnosis of AD. By extracting features from brain image data, neural networks can automatically identify differences between AD patients and healthy subjects, enabling early diagnosis and intervention. In addition, the application of neural networks in AD drug discovery is also discussed. By analyzing and predicting a database of known drugs, neural networks can help discover potential treatments for AD and speed up the drug discovery process. The paper further explores the application of neural networks in other brain diseases and highlights the challenges faced by AD, such as the lack of reliable biomarkers, complex pathological mechanisms, etc. In summary, this paper presents a systematic overview of AD, neural networks, training and learning of neural networks, applications of neural networks in early diagnosis of AD and drug discovery, and other brain diseases and challenges associated with AD.

Background: Obesity and its attendant conditions have become major health problems worldwide and is currently ranked as the fifth most common leading cause of death globally. Complex environmental and genetic factors are the cause of the current obesity epidemic. Diet, lifestyle, chemical exposures, and other confounding factors are difficult to manage in humans. The mice model is helpful in researching genetics BW gain because genetic and environmental risk factors can be controlled in mice. Studies in mouse strains with various genetic backgrounds and established genetic structures provide unparalleled opportunities to find and analyze trait-related genomic loci. In this study, we used the Collaborative Cross (CC), a large panel of recombinant inbred mouse strains, to present a predictive study using CC mice SMAD4 knockout profiles to understand and effectively identify predisposition to body weight gain. Materials and Methods: Male C57Bl / 6J Smad4+/- mice were mated with female mice from 10 different CC lines to create F1 mice (Smad4+/- x CC). Body weight (BW) was measured weekly until week 16, then monthly until the end (week 48). The heritability H2 of the assessed traits was estimated and presented. Comparative analysis of various machine learning algorithms for predicting the BW changes and genotype of mice was conducted. Results and conclusions: Our data showed that the body weight records of F1 mice with different CC lines differed between wildtype and mutant Smad4 mice during the experiment. Genetic background affects weight gain and some lines gained more weight in the presence of Smad4 knockout, while others gained less, but in general, the mutation caused overweight mice, except for a few lines. In both control and mutant groups, female %BW had a higher heritability H2 value than males. Additionally, both sexes with wildtype genotypes showed higher heritability values than the mutant group. Logistic Regression provides the most accurate mouse genotype predictions using machine learning. We plan to validate the proposed method on more CC lines and mice per line to expand machine learning for BW prediction.

Machine Learning (ML) has brought about a transformative era in reactor operations, reshaping monitoring, control, and optimization strategies. This survey comprehensively explores the diverse spectrum of ML applications in industrial reactors. From real-time sensor analysis ensuring reactor functionality to adaptive control algorithms ensuring stability, ML's impact is profound and multifaceted. The benefits of ML are equally evident in optimization, encompassing performance trend prediction, proactive maintenance, and fine-tuning of operations for enhanced efficiency. This review identifies dominant ML techniques, operations stages receptive to ML integration, core data sources, and critical input-output parameters. Aimed at both academics and practitioners, this exploration enriches reactor technologies, unlocking their full potential through insights driven by ML.

The rapid increase in the number of mobile phone base stations (MPBS) has raised global concerns about the potential adverse health effects of exposure to radiofrequency electromagnetic fields (RF-EMF). The application of machine learning techniques can enable healthcare professionals and policymakers to proactively address concerns surrounding RF-EMF exposure near MPBS. In this study, we investigated the potential of machine learning models to predict health symptoms associated with RF-EMF exposure in individuals residing near MPBS.We utilized support vector machine (SVM) and random forest (RF) algorithms, incorporating 11 predictors related to participants' living conditions. A total of 699 adults participated in the study, and model performance was assessed using sensitivity, specificity, accuracy, and the area under the receiver operating characteristic curve (AUC). The SVM-based model demonstrated strong performance, achieving accuracies of 85.3%, 82%, 84%, 82.4%, and 65.1% for headache, sleep disturbance, dizziness, vertigo, and fatigue, respectively. The corresponding AUC values were 0.99, 0.98, 0.920, 0.89, and 0.81. Compared to the RF model and a previously developed model, the SVM-based model exhibited higher sensitivity, particularly for fatigue, with sensitivities of 70.0%, 83.4%, 85.3%, 73.0%, and 69.0% for these five health symptoms. Particularly for predicting fatigue, sensitivity and AUC were significantly improved (70% vs 8% and 11.1% for SVM, MLPNN, and RF, respectively, and 0.81 vs 0.62 and 0.64, for SVM, MLPNN, and RF, respectively). These findings suggest that machine learning methods, specifically SVM, hold promise in effectively managing health symptoms in individuals residing near or planning to settle in the vicinity of MPBS.

COVID-19 transmission models have conferred great value in informing public health understanding, planning, and response. However, the pandemic also demonstrated the infeasibility of basing public health decision-making on transmission models with pre-set assumptions. No matter how favourably evidenced when built, a model with fixed assumptions is challenged by numerous factors that are difficult to predict. Ongoing planning associated with rolling back and re-instituting measures, initiating surge planning, and issuing public health advisories can benefit from approaches that allow state estimates for transmission models to be continuously updated in light of unfolding time series. A model being continuously regrounded by empirical data in this way can provide a consistent, integrated depiction of the evolving underlying epidemiology and acute care demand, offer the ability to project forward such a depiction in a fashion suitable for triggering the deployment of acute care surge capacity or public health measures, support quantative evaluation of tradeoffs associated with prospective interventions in light of the latest estimates of the underlying epidemiology. We describe here the design, implementation and multi-year daily use for public health and clinical support decision-making of a particle filtered COVID-19 compartmental model, which served Canadian federal and provincial governments via regular reporting starting in June 2020. The use of the Bayesian Sequential Monte Carlo algorithm of Particle Filtering allows the model to be re-grounded daily and adapt to new trends within daily incoming data – including test volumes and positivity rates, endogenous and travel-related cases, hospital census and admissions flows, daily counts dose-specific vaccinations administered, measured concentration of SARS-CoV-2 in wastewater, and mortality. Important model outputs include estimates (via sampling) of the count of undiagnosed infectives, the count of individuals at different stages of the natural history of frankly and pauci-symptomatic infection, the current force of infection, effective reproductive number, and current and cumulative infection prevalence. Following a brief description of model design, we describe how the machine learning algorithm of particle filtering is used to continually reground estimates of dynamic model state, support probabilistic model projection of epidemiology and health system capacity utilization and service demand and probabilistically evaluate trade-offs between potential intervention scenarios. We further note aspects of model use in practice as an effective reporting tool in a manner that is parameterized by jurisdiction, including support of a scripting pipeline that permits a fully automated reporting pipeline other than security-restricted new data retrieval, including automated model deployment, data validity checks, and automatic post-scenario scripting and reporting. As demonstrated by this multi-year deployment of Bayesian machine learning algorithm of particle filtering to provide industrial-strength reporting to inform public health decision making across Canada, such methods offer strong support for evidence-based public health decision making informed by ever-current articulated transmission models whose probabilistic state and parameter estimates are continually regrounded by diverse data streams.

Recent digital transformations have significantly impacted the current society, economy, and culture. This includes adoption of rapidly emerging technologies, such as artificial intelligence (AI), immersive technology (e.g., virtual, augmented, mixed and extended reality (VR/AR/MR/XR)), cloud services, and internet of things, in our day-to-day life. `Metaverse’ has emerged as a technology that incorporates many of these transforming technologies to deliver personalised immersive experience related to specific application areas. A potential major beneficiary of Metaverse is the educational ecosystem, where highly immersive learning experiences can be delivered to students, catering to their personal learning needs and train them on life skills such as empathy, ethical qualities, and communication skills. The present-day Metaverse allows physical engagement, enabling users to utilise limb movements to interact with the presented materials. However, ethical concerns and technical limitations impede the widespread implementation of the Metaverse in the real-world. This paper provides a comprehensive survey of the existing literature covering the architecture, type and components of Metaverse, followed by practical aspects of metaverse implementation. The paper is concluded by discussing on the open challenges and issues along with their mitigation strategies and future research directions after the detailed usecase of Metaverse in Education.

With technological transformations such as big data, blockchain, artificial intelligence, and cloud computing, digital techniques are penetrating the field of finance. Digital finance is a resource-saving and environmentally friendly innovative financial service. It shows great green attributes and can drive the flow of financial resources towards environmentally friendly enterprises, thereby promoting green and low-carbon development. This paper investigates the effects of digital finance on green and low-carbon cyclic development and the mechanism. First, the level of green and low carbon cyclic development in China is estimated from multiple aspects based on the panel data of 31 provinces by using the spatio-temporal range entropy weight method. Then, the working mechanism of digital finance on green and low carbon cyclic development is revealed by performing empirical tests based on panel regression models, mediating effect models, and threshold models. Finally, the effects of digital finance and conventional variables on green and low-carbon cyclic development are investigated by using a random forest model and a CatBoost model in based on the machine learning. The results show that digital finance has significant positive effects on green and low-carbon cyclic development, and technological innovation plays a key role in the effects of digital finance on green and low-carbon cyclic development; meanwhile, the driving effect of digital finance on green and low carbon cyclic development shows nonlinear features with increasing “marginal effect”; besides, both digital finance and conventional factors have significant impacts on green and low carbon cyclic development. This study provides an empirical basis and path reference for digital finance to achieve “carbon peak, carbon neutralization” in China.

: The effects of the main parameters on the air entrainment rate, Qa, were investigated experimentally in a confined plunging liquid jet reactor CPLJR. Various downcomer diameters (Dc), jet lengths (Lj), liquid volumetric flow rates (Qj), nozzle diameters (dn), and jet velocity (Vj) were used to measure air entrainment, Qa. The non-linear relationship between the air entrainment ratio and confined plunging jet reactor parameters suggests that applying unconventional regression algorithms to predict the air entrainment ratio is appropriate. This study applied machine learning algorithms to the confined plunging jet reactor parameters to predict Qa. The obtained results showed that K-Nearest Neighbour (KNN) gave the best prediction abilities, R2 = 0.900, RMSE = 0.069, and MAE = 0.052. The sensitivity analysis was applied to determine the most effective predictor. The liquid volumetric flow rate (Qj) and jet velocity (Vj) were the most influential among all the input variables. Our findings support using machine learning algorithms to accurately forecast the CPLJR system’s experimental results.

During the COVID-19 pandemic, the education sector of Bangladesh suffered a lot. To adapt to this uncertain situation, the online teaching-learning method was introduced for the first time in the dental colleges to continue regular classes. This qualitative study explored the in-depth perception among students of this new, affordable, flexible online learning method and to find out the scope of improvement of the delivery method. Two focus group discussions (FGD) were conducted, each including 6-8 participants (N=16, the male: female ratio was 7:9) for gaining an in-depth understanding of the perception of online teaching among the dental students. With the help of the trigger questions, the facilitator and moderators conducted both the FGDs. By analysing the Focus group discussion, four distinct themes were identified. The main themes extracted from the data refer to the difficulties which students faced during participation in online classes (e.g., low attention span, unusual timing of classes, internet accessibility, power cut, boring content, etc.), advantages of online learning (e.g., saves time, able to continue studying during the lockdown, saves money, avoids commuting, being safe during a pandemic situation, one can participate in classes if sick, etc.), disadvantages of online classes (e.g., not feasible for clinical classes and lab works, lack of social interactions, lack of group study, long screen time, lack of after class peer discussion, lack of engagement, etc.), and also scopes of improvements (e.g., technological training for staff, recorded classes, technological orientation for students, more engaging contents, online support, more interactive lessons, short duration of the class, break after 30-45 minutes and also teachers training for online facilitation, etc.). In Bangladesh, the online teaching-learning method is not a regular practice. Most of the institutions were forced to adopt this method on very short notice because of the COVID-19 pandemic lockdown. Online education in a clinical subject like dentistry requires a special training program, online content preparation, and interactive lesson delivery setup which are big challenges for a re-source-constrained medical education setup. The focus group discussion unveiled some key issues which indicated that there are many scopes for improvement in online teaching methods. With the help of the medical education department and through faculty development the online learning sessions can be made attractive as well as beneficiary for the key stakeholders.

The Internet of Things technology opens the horizon for a broader scope of intelligent applications in smart cities. However, the massive amount of traffic exchanged among devices may cause security risks, significantly when devices are compromised or vulnerable to cyber-attack. An intrusion detection system is the most powerful tool to detect unauthorized attempts to access smart systems. It identifies malicious and benign traffic by analyzing network traffic. In most cases, only a fraction of network traffic can be considered malicious. As a result, it is difficult for an intrusion detection system to detect attacks at high detection rates while maintaining a low false alarm rate. This work proposes an integrated framework to detect suspicious traffic to address secure data communication in smart cities. This paper presents an approach to developing an intrusion detection system to detect various attack types. It can be done by implementing a Principal Component Analysis method that eliminates redundancy and reduces system dimensionality. Furthermore, the proposed model shows how to improve intrusion detection system performance by implementing an ensemble model.

Recently, federated learning (FL) has been receiving great attention as an effective machine learning method to avoid the security issue in raw data collection as well as to distribute the computing load to edge devices. However, even though wireless communications is a essential part for implementing FL in edge networks, there have been a few works that analyze the effect of wireless networks on FL. In this paper, we investigate FL in small-cell networks where multiple base stations (BSs) and users are located according to homogeneous Poisson point process (PPP) with different densities. We comprehensively analyze the effects of geographic node deployment on the model aggregation in FL on the basis of stochastic geometry-based analysis. We derive the closed-form expressions of coverage probability with tractable approximations and discuss the minimum required BS density for achieving a target model aggregation rate in small-cell networks. Our analysis and simulation results provide insightful information for understanding the behaviors of FL in small-cell networks, and it can be exploited as a guideline for designing the network facilitating the wireless FL.

Accurately distinguishing between indolent and aggressive tumors is a crucial unmet need in the clinical management of prostate cancer (PCa). The traditional Gleason grading system has been utilized for this purpose; however, there is often ambiguity in classifying tumors with a Gleason grade of 7. Clinicians commonly resort to using secondary Gleason grades, such as 3+4 or 4+3, to classify these tumors as indolent or aggressive, respectively. Unfortunately, such classifications are prone to misinterpretation, leading to erroneous diagnoses and prognoses. To address this challenge, we investigated the application of Machine Learning (ML) techniques to classify PCa patients based on gene expression data sourced from The Cancer Genome Atlas. By comparing gene expression levels between indolent and aggressive tumors, we sought to identify distinctive features for developing and validating a range of ML algorithms and stacking techniques. The stacking based model achieved an impressive accuracy of 96% for all samples encompassing primary Gleason grades 6 to 10. Notably, when excluding Gleason grade 7 from the analysis, the accuracy further improved to 97%. This study underscores the effectiveness of the stacked ML algorithm for accurately classifying indolent versus aggressive PCa. Leveraging gene expression data and employing a combination of classifiers, this approach offers a powerful solution to address the unmet need in robustly distinguishing between different types of PCa tumors. Future implementation of this methodology may significantly impact clinical decision-making and patient outcomes in the management of prostate cancer.

The potential of quantum computing for scientific and industrial breakthroughs is immense, however, we are still in the Noisy Intermediate-Scale Quantum (NISQ) era, where the currently available quantum devices contain small numbers of qubits, are very sensitive to environmental conditions and prone to quantum decoherence. Even so, existing NISQ computers have already been shown to outperform conventional computers on specific problems and the key question is how to make use of today’s NISQ devices to achieve quantum advantage in the field of computational science and engineering (CSE). In this direction, this work proposes a hybrid computing formulation by combining quantum computing with machine learning for accelerating the solution of parameterized linear systems in NISQ devices. In particular, it focuses on the Variational Quantum Linear Solver (VQLS), which is a hybrid quantum- classical algorithm for solving linear systems of equations. VQLS employs a short-depth quantum circuit to efficiently evaluate a cost function related to the system solution. The algorithm’s circuit consists of a quantum gate sequence (unitary operators) that involves a set of tunable parameters. Then, well-established classical optimizers are utilized to tune the parameters of the sequence in order to minimize the cost function, which is equivalent to finding the system solution at an acceptable level of accuracy. In this work, it is demonstrated that machine learning tools such as feed-forward neural networks and nearest-neighbor interpolation techniques can be successfully employed to accelerate the convergence of the VQLS algorithm towards the optimal values for the circuit parameters when applied to parameterized linear systems that need to be solved for multiple parameter instances.

Even if the field of medicine has made great strides in recent years, infectious diseases caused by novel viruses that damage the respiratory system continue to plague people all over the world. This type of virus is very dangerous, especially for people who deal with serious long-term breathing problems, like triggering asthma, pneumonia, or bronchitis infections. Thus, this paper demonstrates a new Secure Machine Learning Monitoring System for a model for virus detection. Our proposed model makes use of 4 basic emerging technologies, Internet of Things (IoT), Wireless Sensor Networks (WSN), Cloud Computing (CC), and Machine Learning (ML), to detect dangerous types of viruses that infect people or animals causing panic worldwide and deregulating human daily life. The proposed system is a robust system that could be established in various buildings, like hospitals, entertainment halls, universities, etc., and will provide accuracy, speed, and privacy for data collected in the detection of viruses.

In this study, we developed a model that can predict whether patients with cerebral arteriovenous malformation (AVM) will be cured 36 months after intervention by means of stereotactic radiosurgery (SRS), and identified the most important predictors that explain the probability of being cured. A machine learning (ML) approach was applied using decision tree (DT) and logistic regression (LR) techniques on historical data (sociodemographic, clinical, treatment, angioarchitecture, and radiosurgery procedure) of 202 patients with AVM who underwent SRS at the Instituto de Radiocirugía del Perú (IRP) between 2005 and 2018. The LR model obtained the best results for predicting AVM cure with an accuracy of 92.16%, sensitivity of 92.86%, specificity of 88.89%, precision of 97.50%, and AUC of 97.62%, which shows that ML models are suitable for use for predicting the prognosis of medical conditions such as AVM and can be a support tool for medical decision-making. In addition, several factors were identified that could explain whether patients with AMV would be cured at 36 months with the highest likelihood: the location of the AVM, the occupation of the patient, and the presence of hemorrhage.

Lung cancer is the leading cause of cancer death worldwide, with non-small cell lung cancer (NSCLC) making up 80% of cases. Some genetic factors leading to NSCLC development include genetic mutations and PD-L1 expression. PD-L1 proteins are targeted in an NSCLC treatment called targeted gene therapy. However, this treatment is effective in a low percentage of patients. This study aimed to create machine learning models to use features like the number of mutations and the level of PD-L1 proteins in cancer cells, along with others, to predict whether a patient will receive clinical benefit from gene therapy treatment. This was done by downloading and merging datasets from cbioportal.org to create a sample size for the model. Features with high correlations to clinical benefit were identified. Three machine-learning models were created using these features to predict clinical benefits in patients, and each model’s accuracy was evaluated. All three models were accurate between 55-85%, with two of the models averaging an accuracy around 75%. Doctors can use these models to more accurately predict whether gene therapy treatment is likely to work in a patient before prescribing it to them.

This article presents a comparative analysis of three Machine Learning models, namely Logistic Regression, Decision Tree Classifier, and Random Forest Classifier, for prostate cancer detection. The models were trained and evaluated using clinical data, and their performance was assessed using various evaluation metrics. The results show that Logistic Regression achieved the highest accuracy (90%) among the three models, followed by Random Forest Classifier (76.67%) and Decision Tree Classifier (73.33%). Similarly, Logistic Regression demonstrated superior precision (95.65%) and F1 Score (93.62%), indicating its effectiveness in identifying true positive cases. However, the Decision Tree Classifier exhibited higher recall for the negative class (83.33%) compared to the positive class (70.83%), while Random Forest Classifier showed balanced recall for both classes (66.67% for negative and 79.17% for positive). These findings suggest that Logistic Regression outperforms the other models in terms of accuracy and precision, while the Decision Tree Classifier and Random Forest Classifier provide better recall for certain classes. The results highlight the potential of Machine Learning in prostate cancer detection and provide insights for further research and improvement of the models.

In recent years, there has been a growing interest in remote sensing image-text cross-modal retrieval due to the rapid development of space information technology and the significant increase in remote sensing image data volume. One approach that has shown promising results in cross-modal retrieval of natural images is the multimodal fusion encoding method. However, remote sensing images have unique characteristics that make the retrieval task challenging. Firstly, the semantic features of remote sensing images are fine-grained, meaning they can be divided into multiple basic units of semantic expression. Additionally, these images exhibit variations in resolution, color, and perspective. Different combinations of basic units of semantic expression can generate diverse text descriptions. These characteristics pose considerable challenges for cross-modal retrieval. To address these challenges, this paper proposes a multi-task guided fusion encoder (MTGFE) based on the multimodal fusion encoding method. The model incorporates three tasks: image-text matching (ITM), masked language modeling (MLM), and the newly introduced multi-view joint representations contrast (MVJRC) task. By jointly training the model with these tasks, we aim to enhance its capability to capture fine-grained correlations between remote sensing images and texts. Specifically, the MVJRC task is designed to improve the model’s consistency in feature expression and fine-grained correlation, particularly for remote sensing images with significant differences in resolution, color, and angle. Furthermore, to address the computational complexity associated with large-scale fusion models and improve retrieval efficiency, this paper proposes a retrieval filtering method. This method achieves higher retrieval efficiency while minimizing accuracy loss. Extensive experiments were conducted on four public datasets to evaluate the proposed method, and the results validate its effectiveness. Overall, this study focuses on remote sensing image-text cross-modal retrieval and introduces the MTGFE model, which combines multimodal fusion encoding with multiple tasks to enhance the model’s ability to capture fine-grained correlations. Additionally, a retrieval filtering method is proposed to improve retrieval efficiency. Experimental results demonstrate the effectiveness of the proposed method.

Despite being an abundant marine organism in Indonesia, black sea cucumber is still underutilised due to its slightly bitter taste. Previous studies have hinted at the potential of black sea cucumber as an anti-cancer agent. However, specific identification of bioactive compounds that can interact with cancer proteins is still lacking. In the same place, cancer ranks third as Indonesia's leading cause of death. Therefore, this study aims to identify potential anti-cancer compounds from black sea cucumbers using a comprehensive in silico drug discovery approach. This research uses machine learning, molecular docking, and ADMET analysis to identify bioactive compounds that specifically interact with cancer proteins. A combination of the Cascade Deep Forest algorithm and ECFP-AAIndex1 feature combination proved to be the most effective in predicting these interactions. Through molecular docking validation, four bioactive compounds with strong binding affinity were identified: Afimoxifene, Danazol, Taxifolin, and Terfenadine. ADMET analysis highlighted Taxifolin as the most promising candidate, as it passed most ADMET parameters. Further wet laboratory studies are required to confirm the effects and potential of these compounds as anti-cancer agents. This study builds a foundation for future investigations into alternative cancer treatments using abundant natural resources.

In this work, an IoT system with edge computing capability is proposed facilitating postoperative surveillance of patients who have undergone knee surgery. The main objective is to reliably identify whether a set of orthopedic rehabilitation exercises are executed correctly, which is critical since, it is often necessary to supervise patients during the rehabilitation period so as to avoid injuries or long recovery periods. The proposed system leverages Internet of Things (IoT) paradigm, in combination with Deep Learning and Edge Computing to classify the extend-flex movement of one’s knee via embedded Machine Learning (ML) classification algorithms. The contribution of the proposed work is multilayered. Furthermore as an outcome of this work a dataset of labeled knee movements is freely available on https://www.kaggle.com/datasets/billskarm/knee-range-of-motion to the research community. It also provides real time movement detection with an accuracy reaching 100%, which is achieved with a ML model trained to fit a low cost, off the shelf, Bluetooth Low Energy platform. The proposed Edge Computing approach allows predictions to be performed on-device rather than solely relying on a cloud service. This yields critical benefits in terms of wireless bandwidth and power conservation, drastically enhancing device autonomy, while delivering reduced event detection latency. In particular, the “on device” implementation is able to yield a drastic 99,9% wireless data transfer reduction, a critical 39% prediction delay reduction and a valuable 17% increase of prediction event. Finally, enhanced privacy comprises another significant benefit from the implemented Edge Computing ML model as sensitive data can be processed on-site and only events or predictions are shared with the medical personnel.

Humans’ performance varies due to the mental resources that are available to successfully pursue a task. To monitor users’ current cognitive resources in naturalistic scenarios, it is essential to not only measure demands induced by the task itself but also consider situational and environmental influences. We conducted a multimodal study with 18 participants (nine female, M = 25.9 with SD = 3.8 years). In this study, we recorded, respiratory, ocular, cardiac, and brain activity using functional near-infrared spectroscopy (fNIRS) while participants performed an adapted version of the warship commander task with concurrent emotional speech distraction. We tested the feasibility of decoding the experienced mental effort with a multimodal machine learning architecture. The architecture comprised feature engineering, model optimisation, and model selection to combine multimodal measurements in a cross-subject classification. Our approach reduces possible overfitting and reliably distinguishes two different levels of mental effort. These findings contribute to the prediction of different states of mental effort and pave the way toward generalised state monitoring across individuals in realistic applications.

The dominance of social media has added to the channels of bullying to perpetrators. Unfortunately, cyberbullying (CB) is the most prevalent phenomenon in today’s cyber world and is a severe threat to the mental and physical health of citizens. This opens the need to develop a robust system to prevent bullying content from online forums, blogs, and social media platforms to manage the impact in our society. Several machine learning (ML) algorithms have been proposed for this purpose. However, their performances are not consistent due to high class imbalance issue and generalisation. In recent years, large language models (LLM) like BERT and RoBERTa have achieved state of the art (SOTA) results in several natural language processing (NLP) tasks. Unfortunately, the LLMs have not been applied extensively. In our paper, we explored the use of these models for cyberbullying (CB) detection. We have prepared a new dataset (D2) from existing studies (Formspring and Twitter). Our experimental results for dataset D1 and D2 showed RoBERTa outperformed other models.

A high performance Driver State Monitoring (DSM) application for the detection of driver drowsiness is presented in this paper. It relies on the usage of an Ensemble of Regression Trees (ERTs) machine learning method that aligns 68 facial landmarks. Special focus is given on the acceleration of the frame processing using reconfigurable hardware. Reducing the frame processing latency saves time that can be used to apply frame-to-frame facial shape coherency rules. False face detection and false shape estimations can be ignored for higher robustness and accuracy in the operation of the DSM application without reducing the frame processing rate that can reach 65 frames per second. The sensitivity and precision in yawning recognition can reach 93% and 97%, respectively. The implementation of the employed DSM algorithm in reconfigurable hardware is challenging since the kernel arguments require large data transfers and the degree of data reuse in the computational kernel is low. Due to this, unconventional hardware acceleration techniques have been employed that can also be useful for the acceleration of several other applications.

Personalized recommendation is an important part of ecommerce platform. In the recommendation system, the neural network is used to enhance collaborative filtering to accurately capture user preferences, so as to obtain better recommendation performance. Traditional recommendation methods focused on the results of a single user behavior, ignoring the modeling of multiple interactive behaviors of users, such as click, add to cart and purchase. Although many studies had also focused on Multi-Behavior modeling, two important challenges remained. 1)Since multiple behavioral context information was ignored, it was still a challenge to identify the multimodal relationships of behaviors. 2) Surveillance signals were still sparse. In order to solve this problem, this paper proposes Two-path Multi-behavior Sequence Modeling(TP_MB). First, a two-path learning strategy is introduced to maximize the multiple interaction information of user items learned by the two paths, which effectively enhances the robustness of the model. Second, a multi-behavior dependent encoder is designed. Contextual information is obtained through behavior dependencies in the interaction of different user. In addition, three contrastive learning methods are designed, which not only obtain additional auxiliary supervision signals, but also alleviate the problem of sparse supervision signals. Extensive experiments on two real datasets demonstrate that our method outperforms state-of-the-art multi-behavior recommendation methods.

Address parsing is a crucial task in natural language processing, particularly for Chinese addresses. The complex structure and semantic features of Chinese addresses present challenges due to their inherent ambiguity. Additionally, different task scenarios require varying levels of granularity in address components, further complicating the parsing process. To address these challenges and adapt to low-resource environments, we propose CapICL, a novel Chinese address parsing model based on the In-Context Learning (ICL) framework. CapICL leverages a sequence generator, regular expression matching, BERT semantic similarity computation, and GPT modeling to enhance parsing accuracy by incorporating contextual information. We construct the sequence generator using a small annotated dataset, capturing distribution patterns and boundary features of address types to model address structure and semantics, mitigating interference from unnecessary variations. We introduce the REB-KNN algorithm, which selects similar samples for ICL-based parsing using regular expression matching and BERT semantic similarity computation. The selected samples, raw text, and explanatory text are combined to form prompts, and inputted into the GPT model for prediction and address parsing. Experimental results demonstrate significant achievements of CapICL in low-resource environments, reducing dependency on annotated data and computational resources. Our model's effectiveness, adaptability, and broad application potential are validated, showcasing its positive impact in natural language processing and geographical information systems.

This study aims to focus on using the Volterra series and machine learning for forecasting random and chaotic wind speed regimes, since the calm weather is mostly noticed at the local site, making the dataset selection difficult. A novel method is proposed to predict Volterra kernels up to the third order, using a forward-back propagation neural network with 12-month measurements at Fujairah site (UAE). Both daily and monthly wind speed data sets are investigated for forecasting. The three dominant hourly and daily kernels are extracted for each day and each month. Predicted future Volterra kernels are estimated from past values using both statistical analysis and individual neuro networks for each of the Volterra kernel coefficients. Due to the random nature of wind speed at the local site, a two-layer with 4 neurons per layer neuro network is used to locate the most variable and intense speed during 8-hours in the day. Forecasted wind speed is determined with errors arising from different sources such as the utilization of only 3rd-order Volterra kernels and the difficulty of machine training of the employed shallow network. Nevertheless, this work depicts a useful algorithm to forecast chaotic and random wind speed regimes. Computational time is a trade of the complexity of Volterra mathematical analysis.

Abstract This qualitative research study was aimed at exploring Covid-19 pandemic and its impact via online engagement on disadvantaged undergraduate students resulting in digital divide. The study was supported by the connectivism theory. The methodology approach was an eight year (2014-2022) duration systematic literature review using Educational Resources Information Center (ERIC), Google Scholar, Scopus, and Web of Science (WoS) databases as advanced search strategies. Findings from the SLR provided 56 included relevant publications as confirmed in the Reference Section. Here, findings justified factors responsible for digital divide and the digital divide impacts. Connectivism was suggested as an approach to control digital divide. This study recommends connectivism to control digital divide experienced among disadvantaged undergraduate students in South African universities via numerous supports for free trainings in computer skills, while the government provides low data cost and free Wi-Fi services.

The exponential growth of digital media content has introduced new challenges in managing and classifying internet traffic. Digital media traffic is composed of various applications such as video, audio, social media, and search, and its data structure is complex, incorporating a vast array of features. The classification of traffic data is a crucial aspect of internet traffic management and network security, and it forms the basis for several scenarios, including content distribution, advertising recommendations, and data analysis. Traditional classification methods rely mainly on deep packet inspection and port-based techniques, which have become increasingly ineffective due to the rapid evolution of network traffic. To address this issue, this study proposes a machine learning-based traffic classification method aimed at enhancing the accuracy and efficiency of digital media traffic classification to meet the current needs of traffic management and network security. The paper also analyzes and evaluates the classification effect and prediction capability of various algorithms under different training set sizes to validate the feasibility and effectiveness of the proposed method. The result demonstrates that the neural network algorithm has superior classification and prediction capabilities compared to the decision tree and support vector machine algorithms. Furthermore, our proposed method achieves the highest accuracy of 96.88% with a large training sample of 40,000 data streams, proving its superiority in handling high-dimensional data and complex datasets. The research results are significant for the development of digital media traffic classification and prediction methods and are expected to be applied in practical scenarios.

The global Covid-19 crisis has seen the push for many education institutions substituting traditional classroom learning to online platforms. This change in the learning experience has been expected to cause major and likely unequal interruption not only in students’ learning, but their well-being overall. Given this, the present study aims to investigate how online or open distance learning, implemented during times of a health crisis, impacted the mental well-being of UiTM students. The study was conducted via an online survey and an online group discussion during the last week of online classes between 29th June to 1st July 2020. Following research on negative emotional states, the short form of the Depression Anxiety Stress Scales (DASS-21) was included in the survey. Results indicate that students experienced varying levels of negative emotions, specifically feeling anxious over situations that might cause panic, feeling emotionally sensitive as well as feeling less motivated to do things. Discussions include how the government of Malaysia needs to ensure for students to be equipped with the right amenities that will offer a smoother ODL experience and that educational institutions provide their stakeholders with clear information so that students can make a more informed choice about their education.

Background and Purpose: Open-source Artificial intelligence (AI) applications are fast transforming access to information and allow students to prepare assignments and offer quite accurate responses to a wide range of exam questions which are routinely used in assessments of students across the board including undergraduate dental students. This study aims to evaluate the performance ChatGPT, an AI-based application, on a wide range of dental assessments and discusses the implications for undergraduate dental education. Methods: This was an exploratory study investigating the accuracy of ChatGPT to attempt a range of recognized assessments in undergraduate dental curricula. ChatGPT was used to attempt ten items based on each of the five commonly used question formats including single-best answer (SBA) multiple-choice questions (MCQs); short answer questions (SAQs); short essay questions (SEQs); True/False questions and fill in the blanks items. In addition, ChatGPT was used to generate reflective reports based on multisource feedback (MSF); research methodology; critical appraisal of the literature. Results: ChatGPT application provided accurate responses to majority of knowledge-based assessments based on MCQs, SAQs, SEQs, Tue/False and fill in the blanks items. However, it was only able to answer text-based questions and did not allow processing of questions based on images. Responses generated to written assignments were also of good quality apart from those for critical appraisal of literature. Word count was the key limitation observed in outputs by ChatGPT as it was only able to produce reports limited to approximately 650 words. Conclusion: Notwithstanding their current limitations, AI-based applications have the potential to revolutionize virtual learning. Instead of treating it as a threat, dental educators need to adapt teaching and assessments in dental education to the benefits of the learners whilst mitigating against dishonest use of AI-based applications.

The constant increase in volume and wide variety of available Internet of Things (IoT) devices leads to highly diverse software and hardware stacks, which opens new avenues for exploiting previously unknown vulnerabilities. The ensuing risks are amplified by the inherent IoT resource constraints both in terms of performance and energy expenditure. At the same time, IoT devices often times generate or collect sensitive, real-time data used in critical application scenarios (e.g. health monitoring, transportation, smart energy, etc.). All these factors combined make IoT networks a primary target and potential victims for malicious actors. In this paper, we present a brief overview of existing attacks and defense strategies against urban IoT networks. The goal of this work is twofold: First, it presents a summary of some of the common attack vectors and the corresponding solutions available in the research literature. Then, the paper lays out a theoretical plan and a corresponding pipeline of steps (i.e. development and implementation process) for the design and application of the solutions encountered throughout the course of the research efforts. The end goal of following this plan is the deployment of the proposed IoT security measures in a real-world urban IoT infrastructure.

Caries is a prevalent oral disease that primarily affects children and teenagers. Advances in ma-chine learning have caught the attention of scientists working with decision support systems to predict early tooth decay. Current research has developed machine learning algorithm for caries classification and reached high accuracy especially in ML for image data. Unfortunately, most studies on dental caries only focus on classification and prediction tasks, meanwhile dental carries prevention is more important. Therefore, this study aims to design an efficient feature for decision support system machine learning based that can identify various risk factors that cause dental caries and its prevention. The data used in the research work was obtained from the 2018 Korean Children's Oral Health Survey, which totaled nine datasets. The experimental results show that combining the mRMR and GINI Feature Importance methods when training with the GBDT model achieved the optimum performance of 95%, 93%, 99%, and 88% for accuracy, F1 score, precision, and recall, respectively. So, the proposed method has provided effective predictive model for dental caries prediction.

Aim: This study aimed to evaluate the sociodemographic, behavioral, and biological profile and its relationship with the emergence of chronic non-communicable diseases in riverside populations in the Xingu region, Pará, Brazil. Methods: Characteristics related to health indicators and which risk factors are considered most important were also analyzed. This is a cross-sectional, exploratory, and descriptive study. The sample consisted of riverside people over 18 years of both sexes. The sample size (n.86) was calculated with a confidence level of 95% and a sample error of 5%. To divide the groups, the K-means clustering algorithm was adopted through an unsupervised method and the values were expressed as median. For continuous and categorical data, the Mann-Whitney and Chi-square tests were used, respectively, and the significance level was set at p<5%. To classify the degree of importance of each variable, the multi-layer perceptron algorithm was applied. Results: Based on this information, the sample was divided into two groups: the group with low or no education, with bad habits and worse health conditions, and the group with opposite characteristics. The risk factors considered for cardiovascular diseases and diabetes in the groups were low education (p < 0.001), sedentary lifestyle (p < 0.01), smoking, alcoholism, body mass index (p < 0.05) and the waist-hip ratio, with values above the expected, in both groups. Conclusions: The factors considered important to have a good health condition or not were the educational and social conditions of these communities and a part of the riverside population was considered healthier than the other.

Currently, skin cancer is the most commonly diagnosed form of cancer in humans and is one of the leading causes of death in patients with cancer. Biopsy methods are an invasive research method and are not always available for primary diagnosis. Imaging methods have low accuracy and depend on the experience of the dermatologist. Artificial intelligence technologies can match and surpass visual analysis methods in accuracy, but they have the risk of a false negative response when a malignant pigmented lesion can be recognized as benign. One possible way to improve accuracy and reduce the risk of false negatives is to analyze heterogeneous data, combine different preprocessing methods, and use modified loss functions to eliminate the negative impact of unbalanced dermatological data. The paper proposes a multimodal neural network system with a modified cross-entropy loss function that is sensitive to unbalanced heterogeneous dermatological data. The accuracy of recognition in 10 diagnostically significant categories for the proposed system was 85.19%. The novelty of the proposed system lies in the use of cross-entropy loss when training the modified function with the help of weight coefficients. The introduction of weighting factors has reduced the number of false negative forecasts, as well as improved accuracy by 1.02-4.03 percentage points compared to the original multimodal systems. The introduction of the proposed multimodal system as an auxiliary diagnostic tool can reduce the consumption of financial and labor resources involved in the medical industry, as well as increase the chance of early detection of skin cancer.

In this work, we adapt the fine-tuning algorithm of the Naïve Bayesian (FTNB) classifier to make it more suitable for imbalanced datasets. In particular, we boost misclassified instance probability terms by an amount that is disproportional to the harmonic mean of actual and predicted classes. The intuition is that discriminative attributes when the instance is misclassified would have small probability term pair values in both the actual class due to data scarcity and the predicted class due to weak correlation. Conversely, if both values are relatively high, then the attribute has good data coverage (support) and it should not be a cause for misclassification. Since the harmonic average is dominated by the smaller value and we have an imbalanced dataset, we should enact a large update if both or either term probabilities of actual and predicted classes are small. We used several benchmark datasets (60 different balanced and imbalanced datasets) to determine if the poor performance of the NB classifier is due to the scarcity of data and compared the performance of the proposed algorithm with NB, original FTNB, and other relatively new SOTA Ensemble Imbalanced Classifiers. Our empirical results reveal that the new proposed algorithm significantly outperforms all other classifiers.

The national-scale evaluation and modelling of the impact of agricultural management and cli-mate change on soils, crop growth, and the environment require soil information at a spatial res-olution addressing individual agricultural fields. This manuscript presents a data science ap-proach which agglomerates the soil parameter space into a limited number of functional soil pro-cess units (SPUs) which may be used to run agricultural process models. In fact, two unsupervised classification methods were developed to generate a multivariate 3D data product consisting of SPUs, each being defined by a multivariate parameter distribution along the depth profile from 0 to 100 cm. The two methods account for differences in variable types and distributions and in-volve genetic algorithm optimization to identify those SPUs with the lowest internal variability and maximum inter-unit difference with regards to both, their soil characteristics and landscape setting. The high potential of the methods was demonstrated by applying them to the agricultural German soil landscape. The resulting data product consists of twenty SPUs. It has a 100 m raster resolution in the 2D mapping space, and its resolution along the depth profile is 1 cm. It includes the soil properties texture, stone content, bulk density, hydromorphic properties, total organic carbon content, and pH.

Research has been growing on object detection using semi-supervised methods in past few years. We examine the intersection of these two areas for floor-plan objects to promote the research objective of detecting more accurate objects with less labelled data. The floor-plan objects include different furniture items with multiple types of the same class, and this high inter-class similarity impacts the performance of prior methods. In this paper, we present Mask R-CNN based semi-supervised approach that provides pixel-to-pixel alignment to generate individual annotation masks for each class to mine the inter-class similarity. The semi-supervised approach has a student-teacher network that pulls information from the teacher network and feeds it to the student network. The teacher network uses unlabeled data to form pseudo-boxes, and the student network uses both unlabeled data with the pseudo boxes and labelled data as ground truth for training. It learns representations of furniture items by combining labelled and unlabeled data. On the Mask R-CNN detector with ResNet-101 backbone network, the proposed approach achieves mAP of 98.8%, 99.7%, and 99.8% with only 1%, 5% and 10% labelled data, respectively. Our experiment affirms the efficiency of the proposed approach as it outperforms the fully supervised counterpart using only 10% of the labels.

This paper investigates if Corporate Social Responsibility (CSR) reports published by a selected group of Nordic companies are aligned with the Global Reporting Initiative (GRI) standards. To achieve this goal, several natural language processing, and text mining techniques were implemented and tested. We extracted strings, corpus, and hybrid semantic similarities from the reports and evaluated the models through the intrinsic assessment methodology. A quantitative ranking score based on index matching was developed to complement the semantic valuation. The final results show that Latent Semantic Analysis (LSA) and Global Vectors for Word Representation (GloVE) are the best methods for our study. Our findings will open the door to the automatic evaluation of sustainability reports which could have a strong impact on the environment.

An early hypothesis in robot-assisted stroke therapy was that sensorimotor stimulation through robotic assistance is beneficial for recovery. Despite 25 years of upper-limb rehabilitation robotics research, this hypothesis remains untested barring a few studies with small sample sizes. This review aims to provide a critical summary of the current state of this hypothesis by collating evidence from rehabilitation robotics and other related therapeutic approaches. The review starts with a causal model to expose the various direct and indirect routes through which robotic assistance can aid sensorimotor recovery. The indirect routes include the influence of robotic assistance on therapy intensity, patient motivation, and active participation. The direct route is through changes in cortical networks through Hebbian(-like) learning and changes in peripheral tissue properties. There is currently mixed evidence for the direct causal effect of robotic assistance on recovery from the upper-limb rehabilitation robotics literature. However, evidence from the neuromuscular electrical stimulation literature provides some support for this causal role. Based on the data at hand, we hypothesize that the enhanced movement-related sensory feedback from robotic assistance has a direct, possibly small, causal role in the sensorimotor recovery of the upper-limb, and this effect might be detectable with high-intensity therapy. Large, high-intensity, controlled studies are warranted to support or refute the role of robotic assistance on recovery, which is both scientifically and practically important.

Precipitation type is a key parameter used for better retrieval of precipitation characteristics as well as to understand the cloud-convection-precipitation coupling processes. Ice crystals and water droplets inherently exhibit different characteristics in different precipitation regimes (e.g., convection, stratiform), which reflect on satellite remote sensing measurements that help us distinguish them. The Global Precipitation Measurement (GPM) Core Observatory’s Microwave Imager (GMI) and Dual-Frequency Precipitation Radar (DPR) together provide ample information on global precipitation characteristics. As an active sensor, DPR provides an accurate precipitation type assignment, while passive sensors like GMI are traditionally only used for empirical understanding of precipitation regimes. Using collocated precipitation type flags from DPR as the “truth”, this paper employs machine learning (ML) models to train and test the predictability and accuracy of using passive GMI-only observations together with ancillary information from reanalysis and GMI surface emissivity retrieval products. Out of six ML models, four simple ones (Support Vector Machine, Neural Network, Random Forest, and Gradient Boosting) and the 1-D convolutional neural network (CNN) model are identified to produce 90% - 94% prediction accuracy globally for 5 types of precipitation (convective, stratiform, mixture, no precipitation, and other precipitation), which is much more robust than previous similar effort. One novelty of this work is to introduce data augmentation (subsampling and bootstrapping) to handle extremely unbalanced samples in each category. Careful evaluation of Impact matrices demonstrate that polarization difference (PD) and surface emissivity at high-frequency channels dominate the decision process, which are consistent with the physical understanding of polarized microwave radiative transfer over different surface types, as well as in snow and liquid clouds with different microphysical properties. Furthermore, the view-angle dependency artifact that DPR precipitation flag bears with does not propagate into the conical-viewing GMI retrievals. This work provides a new and promising way for future physics-based ML retrieval algorithm development.

Many dedicated designs for real-time operations provide functionality on fixed-sized operators, but where speed, scalability, and flexibility are required, extensive research is demanded. Dedicated designs can provide real-time processing for many applications. This paper presents an FPGA-based design of a general image processor. The proposed design is based on a fixed-point representation of binary numbers. The proposed design provides a mechanism to manage matrices on-chip along with matrix arithmetic. The matrices are represented with simple identifiers and microinstruction that assist in the computation of many operations which are useful for solving complex problems. The design was successfully implemented and tested using VHDL language. The proposed design is an efficient architecture as a standalone processor with all embedding computational resources necessary for an embedded image processing application.

Object segmentation is still considered a challenging problem in autonomous driving, particularly in consideration of real world conditions. Following this line of research, this paper approaches the problem of object segmentation using LiDAR-camera fusion and semi-supervised learning implemented in a fully-convolutional neural network. Our method is tested on real-world data acquired using our custom vehicle iseAuto shuttle. The data include all-weather scenarios, featuring night and rainy weather. In this work, it is shown that LiDAR-camera fusion with only a few annotated scenarios and semi-supervised learning, it is possible to achieve robust performance on real-world data in a multi-class object segmentation problem. The performance of our algorithm is measured in terms of intersection over union, precision, recall and area-under-the-curve average precision. Our network achieves 82% IoU in vehicle detection in day fair scenarios and 64% IoU in vehicle segmentation in night rain scenarios.

Satellite communication is expected to play a vital role in realizing Internet of Remote Things (IoRT) applications. This article considers an intelligent reflecting surface (IRS)-assisted downlink low Earth orbit (LEO) satellite communication network, where IRS provides additional reflective links to enhance the intended signal power. We aim to maximize the sum-rate of all the terrestrial users by jointly optimizing the satellite’s precoding matrix and IRS’s phase shifts. However, it is difficult to directly acquire the instantaneous channel state information (CSI) and optimal phase shifts of IRS due to the high mobility of LEO and the passive nature of reflective elements. Moreover, most conventional solution algorithms suffer from high computational complexity and are not applicable to these dynamic scenarios. A robust beamforming design based on graph attention networks (RBF-GAT) is proposed to establish a direct mapping from the received pilots and dynamic network topology to the satellite and IRS’s beamforming, which is trained offline using the unsupervised learning approach. The simulation results corroborate that the proposed RBF-GAT can achieve approximate performance compared to the upper bound with low complexity.

The global spread of COVID-19 led the World Health Organization to declare a pandemic on 11 March 2020. To decelerate this spread, countries have taken strict measures that affected the lifestyle and economy. Various studies have been focused on the identification of COVID-19 impact to mental health of children and adolescents via traditional statistical approaches. However, a machine learning methodology must be developed to explain the main factors that contribute to the change of mood state of children and adolescents during the first lockdown. Therefore, to this study an explainable machine learning pipeline is presented focusing on children and adolescents in Greece, where a strict lockdown was imposed. The target group consists of children and adolescents, recruited from children and adolescent mental health services, who present mental health problems diagnosed before the pandemic. The proposed methodology imposes: (i) data collection via questionnaires; (ii) a clustering process to identify the groups of subjects with amelioration, deterioration and stability to their mood state; (iii) a feature selection process to identify the most informative features that contribute to mood state prediction; (iv) a decision-making process based on an experimental evaluation among classifiers; (v) calibration of the best performing model and (v) a post-hoc interpretation of the features’ impact on the best performing model. The results showed that a blend of heterogeneous features from almost all feature categories is necessary to increase our understanding regarding the effect of COVID-19 pandemic on the mood state of children and adolescents.

This paper provides a methodology for the production of synthetic images for training neural networks to recognise shapes and objects. There are many scenarios in which it is difficult, expensive and even dangerous to produce a set of images that is satisfactory for the training of a neural network. The development of 3D modelling software has nowadays reached such a level of realism and ease of use that it seemed natural to explore this innovative path and to give an answer regarding the reliability of this method that bases the training of the neural network on synthetic images. The results obtained in the two proposed use cases, that of the recognition of a pictorial style and that of the recognition of migrants at sea, leads us to support the validity of the approach, provided that the work is conducted in a very scrupulous and rigorous manner, exploiting the full potential of the modelling software. The code produced, which automatically generates the transformations necessary for the data augmentation of each image, and the generation of random environmental conditions in the case of Blender and Unity3D software, is available under the GPL licence on GitHub. The results obtained lead us to affirm that through the good practices presented in the article, we have defined a simple, reliable, economic and safe method to feed the training phase of a neural network dedicated to the recognition of objects and features, to be applied to various contexts.

Private vehicle travel is the most basic mode of transportation, and the effective control of the real-world fuel consumption rate of light-duty vehicles plays a vital role in promoting sustainable economic development as well as achieving a green low-carbon society. Therefore, the impact factors of individual carbon emission must be elucidated. This study builds five different models to estimate real-world fuel consumption rate of light-duty vehicles in China. The results reveal that the Light Gradient Boosting Machine (LightGBM) model performs better than the linear regression, Naïve Bayes regression, Neural Network regression, and Decision Tree regression models, with mean absolute error of 0.911 L/100 km, mean absolute percentage error of 10.4%, mean square error of 1.536, and R squared (R2) of 0.642. This study also assesses a large number of factors, from which three most important factors are extracted, namely, reference fuel consumption rate value, engine power and light-duty vehicle brand. Furthermore, a comparative analysis reveals that the vehicle factors with greater impact on real-world fuel consumption rate are vehicle brand, engine power, and engine displacement. Average air pressure, average temperature, and sunshine time are the three most important climate factors.

The load of power system changes with the development of economy, short-term load forecasting play a very important role in dispatching and management of power system. In this paper, the Ant Lion Optimizer (ALO) is introduced to improve the input weights and hidden-layer Matrix of extreme learning machine (ELM), after the parameters of ELM are optimized by ALO, then input nodes, hidden layer nodes and output nodes are determined, so a load forecasting model based on ALO-ELM combined algorithm is established. The proposed method is illustrated based on the historical load data of a city in China. The results show that the average absolute error of short-term load demand predicted by ALO-ELM model is 1.41, while that predicted by ELM is 4.34, the proposed ALO-ELM algorithm is superior to the ELM and meet the requirements of engineering accuracy, which proves the effectiveness of proposed method.

Egyptian cotton is one of the most important commodities to the Egyptian economy and is renowned globally for its quality, which is currently graded by manual inspection. This has several drawbacks including significant labour requirement, low inspection efficiency, and influence from inspection conditions such as light and human subjectivity. This current work uses a low-cost colour vision system, combined with machine learning to predict the cotton lint grade of the cultivars Giza 86, 97, 90, 94 and 96. Unsupervised and supervised machine learning approaches were explored and compared. Three different supervised learning algorithms were evaluated: linear discriminant analysis, decision trees and ensemble modelling. The highest accuracy models (77.3-98.2%) used an ensemble modelling technique to classify samples within the Egyptian cotton grades: Fully Good, Good, Fully Good Fair, Good Fair and Fully Fair. The unsupervised learning technique k-means showed that human error is more likely to occur when classifying lint belonging to the higher quality grades and underlined the need for an intelligent system to replace manual inspection.

Improving the acquisition and retention of a new motor skill is of great importance. The present study (i) investigated the effects of difficulty manipulation strategies (gradual difficulty), combined with different modalities of feedback (FB) frequency on performance accuracy and consistency when learning a novel fine motor coordination task, and (ii) examined relationships between novel fine motor task performance and executive function (EF), working memory (WM), and perceived difficulty (PD). Thirty-six, right-handed, novice physical education students volunteered to participate in this study. Participants were divided into three progressive difficulty groups (PDG), 100% visual FB (FB1), 50% FB (FB2), and 33% FB (FB3). Progressive difficulty was increased by the manipulation of the distance to the target; 2 m, 2.37 m, and 3.56 m. Three FB modalities were investigated (i.e.: 100% visual FB (100% FB), 50% reduced feedback condition (50% RFB), and 33% reduced feedback conditions (33% RFB)). Performance assessments were conducted following familiarization, acquisition, and retention learning phases. Two stress-conditions of dart throws were investigated (i.e.: free condition (FC) and time pressure condition (TPC)). After the learning intervention, data showed that, under the free condition, the 100% FB group had a significant improvement in accuracy during all learning phases. Under time pressure condition, for the 50% RFB and the 33% RFB group, the measured variable (accuracy and consistency) showed a significant linear improvement in performance. The association between the percentage of RFB frequencies and the task difficulty (50% group) may be a more appropriate and manageable cognitive load compared to the 33% RFB and the 100% FB group. The present findings could have practical implications for practitioners because, while strategies are clearly necessary for improving learning, the efficacy of the process appears to be essentially based on the characteristics of the learners.

A low-cost machine learning (ML) algorithm is proposed and discussed for spatial tracking of unknown, correlated signals in localized, ad-hoc wireless sensor networks. Each sensor is modeled as one neuron and a selected subset of these neurons are called to identify the spatial signal. The algorithm is implemented in two phases of spatial modeling and spatial tracking. The spatial signal is modeled using its M iso-contour lines at levels {ℓj}j=1M and those sensors that their sensor observations are in Δ margin of any of these levels report their sensor observations to the fusion center (FC) for spatial signal reconstruction. In spatial modeling phase, the number of these contour lines, their levels and a proper Δ are identified. In this phase, the algorithm may either use adaptive-weight stochastic gradient or scaled stochastic gradient method to select a proper Δ. Additive white Gaussian noise (AWGN) with zero mean is assumed along with the sensor observations. To reduce the observation noise’s effect, each sensor applies moving average filter on its observation to drastically reduce the effect of noise. The modeling performance, the cost and the convergence of the algorithm are discussed based on extensive computer simulations and reasoning. The algorithm is proposed for environmental monitoring. In this paper, the percentage of the communication attempts of wireless sensors is assumed as cost. Performance evaluation results show that the proposed spatial tracking approach is low cost and can model the spatial signal over time with the same performance as that of spatial modeling.

Diabetics or Diabetic Mellitus is a metabolic disorder of blood sugar levels in the human body. It is a major non-communicable disease and involved many serious health risk issues. This disease is rapidly increasing in India. It is a chronic condition and it occurs when a body doesn't produce enough insulin hormone to control the blood sugar level. In this study, different variables have been analyzed that cause the diabetics, and different machine learning algorithms are used to predict whether an unknown sample is diabetes or not. For this purpose, PIMA diabetic detection for Female patients was used. Here 10 different classification model is used for prediction. Finally, the detailed performance analysis of the different variables of the PIMA dataset and also the classification model are discussed.

Differentiated instruction has been implemented in classrooms where students who come from various backgrounds require appropriate lessons that are tailored to their varied learning preferences. As the spread of coronavirus 19 (Covid-19) is becoming more rampant, online learning has been lifted up as the main platform of teaching and learning, forcing the need to shift from the conventional face-to-face classroom to online, or virtual, mode of knowledge transfer. Having such global phenomenon affecting education, how does it affect the implementation of differentiated instruction that has been practised regularly by teachers before the wake of Covid-19? Previous studies have shown how it is done in the normal classroom setting, and that the practice of differentiated instruction contributes to students’ motivation as well as academic performance. However, there is a need to explore how do teachers go about with online differentiated instruction and how does it affect the students, since online learning poses various threads to both teachers and students; and thus, one might argue the effectiveness of not only the teaching approach but also the overall teaching and learning outcomes. Borg’s framework of teacher cognition, which has been extensively used in exploring how teachers teach, can be utilized to document the practice of online differentiated instruction. This study aimed to explore the practice of online differentiated instruction by teachers and examined its impact on students’ motivation and academic performance during the Covid-19 outbreak. The participants of this study consists of 247 gifted students from a public school in Malaysia. To meet these aims, this study employed a mixed method research design, utilizing the framework of teacher cognition to explore the teachers’ practice of online differentiated through interviews; and, utilizing a survey design using a questionnaire to determine the impact of online differentiated instruction towards students’ motivation and academic performance. The findings revealed that although online differentiated instruction is feasible, however, appropriate combination of differentiation constructs need to be applied in order to achieve higher motivation and better academic performance among the students.

The present study aims to develop a risk-based approach to find optimal solutions for life extension management for offshore wind farms based on Markowitz’s modern portfolio theory, adapted from finance. The developed risk-based approach assumes that the offshore wind turbines (OWT) can be considered as cash-producing tangible assets providing positive return from the initial investment (capital) with a given risk attaining the targeted (expected) return. In this regard, the present study performs a techno-economic life extension analysis within the scope of the multi-objective optimisation problem. The first objective is to maximise the return from the overall wind assets, while the latter aims to minimise the risk associated with obtaining the return. In formulating the multi-dimensional optimisation problem, the life-extension assessment considers the results of a detailed structural integrity analysis, free-cash-flow analysis, and probability of project failure, local and global economic constraints. Further, the risk is identified as the variance from the expected mean of return on investment. The risk-return diagram is utilised to classify the OWTs of different classes using an unsupervised machine learning algorithm. The optimal portfolios for the various required rate of return are recommended for different stages of life extension.

We propose a chemical language processing model to predict polymers’ glass transition temperature (Tg) through a polymer language (SMILES, Simplified Molecular Input Line Entry System) embedding and recurrent neural network. This model only receives the SMILES strings of polymer’s repeat units as inputs and considers the SMILES strings as sequential data at the character level. Using this method, there is no need to calculate any additional molecular descriptors or fingerprints of polymers, and thereby, being very computationally efficient and simple. More importantly, it avoids the difficulties to generate molecular descriptors for repeat units containing polymerization point `*’. Results show that the trained model demonstrates reasonable prediction accuracy on unseen polymer’s Tg. Besides, this model is further applied for high-throughput screening on an unlabeled polymer database to identify high-temperature polymers that are desired for applications in extreme environments. Our work demonstrates that the SMILES strings of polymer’s repeat units can be used as an effective feature representation to develop a chemical language processing model for predictions of Tg. The framework of this model is general and can be used to construct structure-property relationships for other polymer’s properties.