This study optimizes the placement and farm layout of Vertical Axis Wind Turbines (VAWTs) using a neural fuzzy network, an advanced machine learning system, and meta-heuristic algorithms. The methodology introduces a novel approach to enhance turbine efficiency and overall farm performance. The objective is to determine the optimal configuration of vertical axis wind turbines using a neural-fuzzy system and meta-heuristic optimizers. Turbine efficiency and power generation rates are assessed through three-dimensional numerical simulations based on the Reynolds-averaged Navier-Stokes equations. This innovative design, featuring straight blades with bevel-angle vortex generators, represents a significant advancement over traditional straight-blade VAWTs. Comparative analyses demonstrate that the oblique configuration exhibits higher average output moment and power. A novel concept integrates the strengths of Darrieus VAWTs, enhancing efficiency through vortex generator integration. Simulation results are validated with empirical data, confirming the superior aerodynamic efficiency and increased power generation of the oblique configuration. Inspired by the optimal group movements of birds, this study recommends adopting the oblique arrangement for improved wind turbine performance.

This study presents an advanced defect detection approach for solar cells using the YOLOv10 deep learning model. Leveraging a comprehensive dataset of 10,500 solar cell images, annotated with 12 distinct defect types, our model integrates Compact Inverted Blocks (CIB) and Partial Self-Attention (PSA) modules to enhance feature extraction and classification accuracy. Training on the Viking cluster with state-of-the-art GPUs, our model achieved remarkable results, including a mean Average Precision ([email protected]) of 98.5%. Detailed analysis of the model's performance revealed exceptional precision and recall rates for most defect classes, notably achieving 100% accuracy in detecting black core, corner, fragment, scratch, and short circuit defects. Even for challenging defect types such as thick line and star crack, the model maintained high performance with accuracies of 94% and 96%, respectively. The recall-confidence and precision-recall curves further demonstrate the model's robustness and reliability across varying confidence thresholds. This research not only advances the state of automated defect detection in photovoltaic manufacturing but also underscores the potential of YOLOv10 for real-time applications. Our findings suggest significant implications for improving the quality control process in solar cell production.

Antimicrobial resistance (AMR) poses a global public health threat, with rates directly linked with consumption. The World Health Organization (WHO) AWaRе-classification aims to guide antibiotic use, which is influenced by drug availability, affordability, and economic policies. In Jordan, a high proportion of consumed antibiotics belong to the 'Watch' category. Data from the WHO-AWaRе classification, the Essential Medicines List, and the Jordan Food and Drug Administration were analyzed. Antibiotics for adults were classified and their cost per Defined Daily Dose (DDD) was determined, then affordability was assessed. In 2023, 43 injectable and 43 oral antibiotics for adults were registered in Jordan. 'Watch' antibiotics were the most common. 'Access' antibiotics had the lowest cost/DDD. 'Rеsеrvе' antibiotics were the most expensive with few generics. Injectable antibiotics had a negative correlation between cost and the number of alternatives. Affordability was higher for oral antibiotics compared to injectable ones. 'Rеsеrvе' antibiotics were generally unaffordable. This study highlights the need to promote 'Access' antibiotics over other categories by encouraging registration of missing ‘Access’ antibiotics and adjusting 'Watch' and 'Rеsеrvе' antibiotic prices. Competition among generics can lead to lower prices, increasing affordability and accessibility. We emphasize the importance of the AWaRе-classification in guiding antibiotic use in Jordan.

The existence of low-cost and accurate tools that can equip the First Responders (FRs) to detect trapped victims and provide insights about their health condition in the aftermath of a disaster, is imperative. To address the problem of detecting trapped victims behind walls or debris, we have developed a tool that exploits an Ultra-Wide Band (UWB) radar sensor for data collection and Machine Learning (ML) algorithms for data analysis. To evaluate the efficacy of our approach, we collected data from nine humans, both in standing and lying down positions. Next, we applied various ML algorithms to the collected dataset for two discrete sub-tasks that are of interest from an FR’s perspective. The first task is the detection of the victim’s presence, where the algorithms attained more than 95% accuracy and F1-Score. The second task is the estimation of the distance between the radar sensor and the victim, where the tool showed an average error of less than 40 cm.

The climate crisis necessitates a global shift to achieve a secure, sustainable, and affordable energy system toward a green energy transition reaching climate neutrality by 2050. Because of this, renewable energy sources have come to the forefront and the research interest in microgrids which rely on distributed generation and storage systems has exploded. Furthermore, many new markets for energy trading, ancillary services, and frequency reserve markets have provided attractive investment opportunities in exchange for balancing the supply and demand of electricity. Artificial intelligence can be utilized to locally optimize energy consumption, trade energy with the main grid, and participate in these markets. Reinforcement learning (RL) is one of the most promising approaches to achieve this goal because it enables an agent to learn optimal behavior in a microgrid by executing specific actions that maximize the long-term reward signal/function. The study focuses on testing two optimization algorithms: logic-based optimization and reinforcement learning. This paper proposes an optimization algorithm based on reinforcement learning in an industrial microgrid that is capable of trading energy with the main grid, providing significant cost savings. The RL-based approach is implemented in Python based on real data from the site and in combination with MATLAB-Simulink to validate its results. The application of the RL algorithm achieved an average monthly cost saving of 20% compared to logic-based optimization and 86% savings compared to not using any optimization. These findings contribute to digitalization and decarbonization of energy technology and support fundamental goals and policies of the European Green Deal.

Infrared thermography has already been proven to be a significant method in non-destructive evaluation since it gives information with immediacy, rapidity and low cost. However, the thorniest issue for wider application of IRT is the quantification. In this work, we proposed a specific depth quantifying technique by employing the Gated Recurrent Units (GRU) in composite material samples via pulsed thermography (PT). Carbon Fiber Reinforced Polymer(CFRP) embedded with flat bottom holes were designed via Finite Element Method (FEM) modeling in order to precisely control the depth and geometrics of the defects. The GRU model automatically quantified the depth of defects presented in the CFRP material. The proposed method evaluated the accuracy and performance of synthetic CFRP data from FEM for defect depth predictions.

This paper addresses the evolving landscape of electricity markets in Europe, with a focus on the integration of Renewable Energy Communities as introduced by the Renewable Energy Directive 2018/2001. Residents within a postal code area are highly incentivized to join a community, which enables them to exchange energy among themselves at lower procurement costs. Thereby, energy management systems optimize the operation of respective energy systems, with electrical load forecasting playing a key role. Given that prosumers may switch between communities on a daily basis, electricity demands within these groups will vary, leading to data that is non-stationary, discontinuous as well as non-identical and independently distributed. To encounter this issue, we propose a sophisticated forecasting model that applies federated learning, using informations from various distributed communities to learn domain-invariant features. To achieve this, we initially utilize synthetic electrical load time series at district level and aggregate them to profiles of Renewable Energy Communities with dynamic portfolios. Subsequently, we develop a forecasting model that accounts for the composition of residents of a Renewable Energy Community, adapt data pre-processing in accordance with the time series process, and detail a federated learning algorithm that incorporates weight averaging and data sharing. Following the training of various experimental setups, we ultimately evaluate their effectiveness. The findings suggest that our proposed framework is capable of effectively forecast non-stationary and discontinuous time series and that it can be applied to new, unseen data through the integration of knowledge from multiple sources.

In this paper, a seamless connection between sensor technology and machine learning (ML) has been presented which has wide applicability in rehabilitation and physical medicine. The intent is to identify an ML algorithm which has a better performance, easy to deploy, and has less training time and consumes less computational resources. In short, we propose an algorithm which maximizes the synergy between a sensor and ML by maximizing classification performance and easy to do implementation, which is robust in computational power and lower in resource consumption. The premise of the work is to show the important considerations for evaluating ML algorithms for Upper-limb activity recognition for Physical medicine and rehabilitation field.

The purpose of this study was to analyze the cross-linguistic influence of previously learned languages and working memory capacities on the vocabulary performance of two different typological languages. The objectives of this study were (1) to compare the working memory capacities of bilingual adults in relation to the vocabulary performance of two different languages never learned by the participants, and (2) to analyze to what extent the typology of previously learned languages influences working memory capaci-ties in relation to the vocabulary performance of French and Nahuatl. A group of 43 Mexican-Spanish college students participated in this experimental study. The participants completed a series of working memory tasks in Nahuatl and French. The results showed that working memory capacities were lower in Nahuatl than in French. Thus, a correlation was found between their first and second language and vo-cabulary performance in French. We can consider the influence of previously learned languages as a significant factor in vocabulary acquisition in accordance with the participants' working memory capacities.

The mathematical structure underlying a sentence is made of two independent processing units in series. The conditional probability density function of sentence length (measured in words) recordable in the extended short–term memory (E–STM) buffer made of CF cells is Gaussian. The number of sentences that authors of Italian and English Literatures have written is compared to that theoretically available to them. The multiplicity factor α describes this comparison. α>1 is more likely than α<1 and often α≫1, therefore the same sentence pattern is reused many times. These texts are easier to read. Very few novels show α<1. In these cases, there are enough diverse sentence patters to convey meaning, but most of them are not used. Texts are more difficult to read, as measured by a universal readability index GU. A mismatch index IM synthetically describes the process. α, GU. and IM increase with year of publication. Future work will concern other literatures – including ancient ones as Greek and Latin – to confirm what, in our opinion, is general feature of human mind.

Unlike animals, persistent dynamic environmental perturbations threaten plants, as they are sessile. Plants keep an inbuilt database of all epigenetic episodes during their lifetime. Present knowledge for exploiting information about how the gene network of plants contributes to epigenetic memory needs to be improved, and extensive in-depth studies are needed. Data from epigenetic memories imparts intelligent behaviour to plants, and these memories can be decoded further to investigate how these plants respond when the same abiotic stress recurs. The epigenetic phenomenon refers to gene expression patterns, including vital factors such as nucleic acids (small ribonucleic acids), histones modelling and methylation of DNA. These changes are cell cycle-associated events that may be transmitted to successive generations. Epigenetic memories due to abiotic stress are necessary for maintaining healthy ecophysiological behaviour of plants and impart the tendency to resist and adapt to challenging environmental conditions. These intelligent memories can be stored and interpreted to prepare for future challenges.

This study estimates the effects of double long memory and structural breaks on the persistence level of six major cryptocurrency markets. We apply the Bai and Perron’s structural break test, Inclán and Tiao’s iterated cumulative sum of squares (ICSS) algorithm, and the fractionally integrated generalized autoregressive conditional heteroscedasticity (FIGARCH) model with different distributions. The results show that long memory and structural breaks characterize the conditional volatility of cryptocurrency markets and confirm our hypothesis that ignoring structural breaks leads to an underestimation of the persistence of volatility modelling. The ARFIMA-FIGARCH model with structural breaks and a skewed Student–t distribution fits the cryptocurrency market’s price dynamics well.

Memristors were proposed in the early ’70s of the XXth century by Leon Chua as a new electrical element linking the charge and the flux. Since that first introduction, these devices have positioned themselves to be considered as possibly fundamental for the new generations of electronic devices. It has to be mentioned that actual memristors have only been recognized to exist as physical elements. In this paper, we apply a modeling framework to generate a model describing experimental measurements performed on a ReRAM. We show how to apply the Dynamic Route Map technique in the general case to obtain an approximation to the differential equation that determines the behaviour of the device.

We investigated the role of the human medio-temporal complex (hMT+) in the memory encoding and storage of a sequence of four coherently moving RDKs by applying repetitive transcranial magnetic stimulation (rTMS) during an early or late phase of the retention interval. Moreover, in a second experiment we also tested whether disrupting the functional integrity of hMT+ during the early phase impaired the precision of the encoded motion directions. Overall, results showed that both recognition accuracy and precision were worse in middle serial positions, suggesting the occurrence of primacy and recency effects. We found that rTMS delivered during the early (but not the late) phase of the retention interval was able to impair not only recognition of RDKs, but also the precision of the retained motion direction. However, such impairment occurred only for RDKs presented in middle positions along the presented sequence, where performance was already closer to chance level. Altogether these findings suggest an involvement of hMT+ in the memory encoding of visual motion direction. Given that both position sequence and rTMS modulated not only recognition but also precision of the stored information, these findings are in support of a model of visual short-term memory with a variable resolution of each stored item, consistent with the assigned amount of memory resources, and that such item-specific memory resolution is supported by the functional integrity of area hMT+.

With the availability of wearable health monitoring sensor modules like 3-Lead Electrocardiogram (ECG), Pulse Oximeter (SpO2), Galvanic Skin Response (GSR), Hall effect sensor (for measuring Respiratory Rate), Blood Pressure and Temperature measuring and sensing elements, it has now become possible to device a composite health status monitoring kit that can measure vital signs and other physiological parameters pertaining to human health in real time. Traditionally, the physiological parameters along with vital signs related examination was possible only in a hospitalized or ambulatory environment, however due to advances in sensing and embedded system technology and miniaturization of data acquisition and processing elements health monitoring has become possible even when individuals remain engaged in their day to day activities at the convenience of space and location. The patients or individuals subject to monitoring may suffer from a traumatic experience due to their medical condition and may need emergent incidence response and the critical care team may have to prepare for the treatment only after the patient arrives, which often is too late, as in case of cardiac arrests or severe injuries. The research focused on real-time health status monitoring and trauma scoring using standard physiological parameters along with standard telemetry protocols to make the critical care team aware of an emergent situation and prepare for a medical emergency. Vital signs and physiological parameters (heart rate, temperature, respiratory rate, and blood pressure, SpO2) were measured in real time from human subjects non-invasively. In order to enable monitoring of the patients engaged in day to day activities, errors due to the motion were removed using stationary wavelet transform correction (correlation coefficient of 0.9 after correction) and signals from various sensors were denoised, filtered and were encoded in a format suitable for further data analysis. A composite sensor kit capable of monitoring vital signs and physiological parameters can be very useful in incident response when an individual undergoes a traumatic experience related to stroke, cardiac arrest, fits or even injury, as along with monitoring information the kit can calculate scores related to trauma like the Injury Severity Score (ISS), National Early Warning Signs (NEWS), Revised Trauma Score (RTS). Trauma Injury Severity Score (TRISS), Probability of Survival (Ps) score. An open access database of vital signs and physiological parameters from Physionet, MIMIC 2 Numerics (mimicdb/numerics) database was used to calculate NEWS and RTS and to generate correlation and regression models using the vital signs/physiological parameters for a clinical class of patients with respiratory failure and admitted to Intensive Care Unit (ICU). NEWS and RTS scores showed no significant correlation (r = 0.25, p<0.001) amongst themselves, however together NEWS and RTS showed significant correlation with Ps (blunt) (r = 0.70, p<0.001). RTS and Ps (blunt) scores showed some correlation (r = 0.63, p<0.001) and NEWS score showed significant correlation (r = 0.79, p<0.001) with Ps (blunt) scores. Furthermore, since individuals have to be monitored regardless of location, these kits have to have a built-in capability to locate the individual so that the incident response team can locate the individual based on Global Positioning System coordinates (GPS). A Quantum GIS (Geographical Information System) application using real-time GPS coordinates (OpenStreetMap coordinates) was used to calculate the shortest path using QGIS Network Analysis tool to demonstrate the calculation of shortest path and direction to locate the nearest service provider in shortest time. Along with locating the nearest healthcare service provider, it would help if the critical care team could be made aware of the physiological parameters and trauma scores using standard protocols accepted across the globe. The physiological parameters from the sensors along with the calculated trauma scores were encoded according to a standard Systematized Nomenclature of Medicine-Clinical Terms (SNOMED-CT) coding system and International Code of Diseases (ICD) codes and the trauma information was logged to Electronic Health Records (EHR) using Fast Health Interoperability Resources (FHIR) servers. FHIR servers provided interoperable web services to log the event information in real time. It could be concluded that analytical models trained on existing datasets can help in analyzing a traumatic experience or an injury and the information can be logged using a standard telemetry protocol as a telemedicine initiative. These scores enable the healthcare service providers to estimate the extent of trauma and prepare for medical emergency procedures and find applications in general and military healthcare.

Partial Differential Equations (PDEs) constitute a fundamental framework for modeling various physical phenomena across diverse fields such as physics, engineering, and finance. Solving PDEs accurately and efficiently remains a significant challenge, particularly when dealing with complex systems or high-dimensional data. In this paper, we present a novel approach based on deep learning techniques to investigate the effective factors in solving PDEs. Our methodology leverages the expressive power of deep neural networks to learn and represent the underlying relationships between input parameters and the solutions of PDEs. By incorporating domain knowledge into the network architecture and training process, our approach aims to provide insights into the key factors influencing the solution of PDEs. We demonstrate the effectiveness of our method through numerical experiments on various PDEs, showcasing its capability to identify important features and improve predictive accuracy. Our findings suggest that deep learning techniques offer a promising avenue for understanding and analyzing the complex dynamics inherent in PDEs, paving the way for enhanced computational methods in scientific and engineering applications.

Electricity load forecasting is a crucial undertaking within all the deregulated markets globally. In contemporary times, the transition from conventional electricity grids to Smart Grids constitutes an area where extensive research is conducted on a global scale. Among the research challenges, the investigation of Deep Transfer Learning (DTL) in the field of electricity load forecasting represents a fundamental effort that imparts generality to Artificial Intelligence applications, due to new capabilities, such as knowledge transfer and computational power reduction. In this paper a comprehensive study is conducted for day-ahead electricity load forecasting. For this purpose, three Sequence-to-Sequence (Seq2seq) Deep Learning (DL) models are used, namely the Multilayer Perceptron (MLP), the Convolutional Neural Network (CNN) and the Ensemble Learning Model (ELM), which is consisted of the weighted combination of the outputs of MLP and CNN models. Also, the study focuses on the development of different forecasting strategies based on DTL and emphasizing the way the datasets are trained and fine-tuning for higher forecasting accuracy. In order to implement the forecasting strategies using Deep Learning models, load datasets from three Greek islands, Rhodes, Lesvos, and Chios, are used. The main purpose is to apply DTL for day-ahead predictions (1-24 hours) for each month of the year for Chios dataset after training and fine-tuning the models using the datasets of the three islands in various combinations. After several trials, four DTL strategies are illustrated. In the first strategy (DTL Case 1), each of the three DL models is trained using only Lesvos dataset, while fine-tuning is performed on the dataset of Chios island, in order to create day-ahead predictions for Chios load. In the second strategy (DTL Case 2), data from both Lesvos and Rhodes concurrently are used for the DL model training period, and fine-tuning is performed on the data from Chios. The third DTL strategy (DTL Case 3) contains the training of the DL models using Lesvos dataset, and the testing period performed directly on the Chios dataset without fine-tuning. The fourth strategy is a Multi-task Deep Learning (MTDL) approach, which has been extensively studied in recent years. In MTDL, the three DL models are trained simultaneously on all three datasets and the final predictions are made on the unknown part of the dataset of Chios. In this paper, we explore the performance of DTL and compare the results with those produced with MTDL. The results demonstrated that DTL can be applied with high efficiency for day-ahead load forecasting. Specifically, the two cases with fine-tuning (DTL Case 1 and 2) outperformed MTDL in terms of load prediction accuracy. Regarding the DL models, all three exhibit very high prediction accuracy, especially in the two cases with fine-tuning. The ELM excels compared to the single models. More specifically, for conducting day-ahead predictions, it has been concluded that the MLP model presents best monthly forecasts with a MAPE of 6.24% and 6.01% for the first two cases, the CNN model presents best monthly forecasts with a MAPE of 5.57% and 5.60% respectively and the ELM model achieves best monthly forecasts with a MAPE of 5.29% and 5.31%, respectively, indicating the very high accuracy it can achieve.

Epilepsy is a common neurological condition, typically diagnosed using Electroencephalogram (EEG). Large scale EEG datasets have recently been made publicly available, allowing the use of advanced Machine Learning (ML) algorithms to analyze EEG patterns associated with epilepsy. While most existing studies focus on identifying seizures in the EEG, few have tried to identify preictal EEG segments. Identifying preictal EEG segments are not only useful in developing early warning systems but also helps inform the course of treatment for the patient. In this study, we propose to represent EEG segments as images, instead of time-series data, and identify preictal EEG segments using a preexisting ML algorithm (YOLOv8) designed for image processing. Multiplexed images (containing the original EEG signal represented on a 2D grid, kurtosis, and spectral entropy) achieve the best accuracy of 95.75% on the dataset while images just containing the EEG signal result in an accuracy of 91.25%. Using only spectrograms, generated from the original EEG signal, results in an accuracy of 90.15%.

Fractional calculus gained a lot of attention in the last couple of years. Researchers discovered that processes in various fields follow rather fractional dynamics than ordinary integer-ordered dynamics, meaning the corresponding differential equations feature non-integer valued derivatives. There are several arguments for why this is the case, one of them being that fractional derivatives’ inherit spatiotemporal memory and/or the ability to express complex naturally occurring phenomena. Another popular topic nowadays is machine learning, i.e., learning behavior and patterns from historical data. In our ever-changing world with ever-increasing amounts of data, machine learning is a powerful tool for data analysis, problem-solving, modeling, and prediction. It further provides many insights and discoveries in various scientific disciplines. As these two modern-day topics provide a lot of potential for combined approaches to describe complex dynamics, this article reviews combined approaches of fractional derivatives and machine learning from the past, puts them into context, and thus provides a list of possible combined approaches and the corresponding techniques. Note, however, that this article does not deal with neural networks, as there already is profound literature on neural networks and fractional calculus. We sorted past combined approaches from the literature into three categories, i.e., preprocessing, machine learning &amp; fractional dynamics, and optimization. The contributions of fractional derivatives to machine learning are manifold as they provide powerful preprocessing and feature augmentation techniques, can improve physically informed machine learning, and are capable of improving hyperparameter optimization. Thus, this article serves to motivate researchers dealing with data-based problems, to be specific machine learning practitioners, to adopt new tools and enhance their existing approaches.

This study introduces session-aware recommendation models, leveraging GRU (Gated Recurrent Unit) and attention mechanisms for advanced latent interaction data integration. A primary ad-vancement is enhancing latent context, a critical factor for boosting recommendation accuracy. We address existing models' rigidity by dynamically blending short-term (most recent) and long-term (historical) preferences, moving beyond static period definitions. Our approaches, pre-combination (LCII-Pre) and post-combination (LCII-Post) with fixed (Fix) and flexible learning (LP) weight configurations, are thoroughly evaluated. We conducted extensive experiments to as-sess our models' performance on public datasets such as Amazon and MovieLens 1M. Notably, on the MovieLens 1M dataset, LCII-PreFix achieved a 1.85% and 2.54% higher Recall@20 than II-RNN and BERT4Rec+st+TSA, respectively. On the Steam dataset, LCII-PostLP outperformed these models by 18.66% and 5.5%. Furthermore, on the Amazon dataset, LCII showed a 2.59% and 1.89% improvement in Recall@20 over II-RNN and CAII. These results affirm the significant enhancement our models bring to session-aware recommendation systems, showcasing their po-tential for both academic and practical applications in the field.

Deep learning has been introduced to single-image super-resolution (SISR) in the last decade. These techniques have taken over the benchmarks of SISR tasks. Nevertheless, most architectural designs necessitate substantial computational resources, leading to a prolonged inference time on embedded systems or rendering them infeasible for deployment. This paper presents a comprehensive survey of plausible solutions and optimization methods to address this problem. Then, we propose a pipeline that aggregates the latter in order to enhance the inference time without significantly compromising the perceptual quality. We investigate the effectiveness of the proposed method on a lightweight GAN-based perceptual-oriented model as a case study. The experimental results show that our proposed method leads to significant improvement in the inference time on both Desktop and Jetson Xavier NX, especially for higher resolution input sizes on the latter, thereby making it deployable in practice.

This paper investigates the cooperative anti-jamming distributed channel selection problem in UAV communication networks. Considering the existence of malicious jamming and co-channel interference, a location-aware cooperative anti-jamming scheme is designed for the purpose of maximizing the users' utilities. Users in the UAV group cooperate with each other via location information sharing. When the received interference energy is lower than mutual interference threshold, users conduct channel selection strategies independently. Otherwise, users take joint actions with a cooperative anti-jamming pattern under the impact of mutual interference. Aimed at the independent anti-jamming channel selection problem under no mutual interference, a Markov Decision Process framework is introduced, whereas for the cooperative anti-jamming channel selection case under the influence of co-channel mutual interference, a Markov game framework is employed. Furthermore, motivated by reinforcement learning with a ``Cooperation-Decision-Feedback-Adjustment" idea, we design a location-aware cooperative anti-jamming distributed channel selection algorithm (LCADCSA) to obtain the optimal anti-jamming channel strategies for the users with a distributed way. In addition, the channel switching cost and cooperation cost, which have great impact on the users' utilities, are introduced. Finally, simulation results show that the proposed algorithm converges to a stable solution with which the UAV group can avoid the malicious jamming as well as co-channel interference effectively.

This paper presents a comprehensive study on applying machine learning (ML) techniques for real-time credit card fraud detection. With the increasing prevalence of credit card fraud, financial institutions face the challenge of detecting fraudulent transactions promptly and accurately. This research evaluates various ML models, including Logistic Regression, Decision Trees, Random Forests, XGBoost, and Deep Convolutional Neural Networks, for their effectiveness in identifying fraudulent activities. Utilizing PySpark for processing large-scale transaction data, the study highlights the importance of real-time analysis, adaptive learning, and handling imbalanced datasets. Key findings reveal that XgBoost, with its balance of accuracy and complexity, emerged as the most promising model, achieving an accuracy rate of 98% in detecting fraudulent transactions. The paper further discusses the potential of ensemble methods, graph-powered systems, and intelligent sampling in enhancing fraud detection capabilities. Challenges such as overfitting, data access, and the need for real-time analysis are addressed. Future research directions include implementing models in live transaction environments, expanding model applicability across financial platforms, and developing advanced anomaly detection methodologies. This study underscores the pivotal role of machine learning in safeguarding financial transactions against fraud, offering significant implications for consumers, financial institutions, and the broader financial ecosystem.

This research delves into librarians' perceptions of artificial intelligence (AI) support in learning experiences, lifelong learning, and digital literacy within the library context, undertaking a comparative analysis between Malaysia and Indonesia. Employing a survey methodology, a self-developed questionnaire was administered to 59 librarians in Malaysia and 85 in Indonesia. The questionnaire, utilizing a Likert scale, systematically explored subjective judgments on AI's impact across various dimensions. A noteworthy finding is the consistent and harmonized perception among librarians in both countries, underscoring a universal recognition of AI's perceived support for learning experiences, lifelong learning, and digital literacy. Of particular interest is the emphasis on sustainability in librarians' perspectives, as they recognize the enduring value of AI in fostering educational growth. Despite the limitations inherent in perceptual measures and a relatively modest sample size, the empirical and practical contributions of this study are significant. It offers a nuanced exploration of librarians' viewpoints, providing valuable insights for future research endeavors. Moreover, the study's findings have immediate practical implications for the integration of AI tools in library services, policy-making, and professional development, with a focus on ensuring sustainable implementation for long-term benefits.

This paper reviews the multiple roles of machine learning in improving the resilience of power grids, especially in applying new energy storage technologies. Energy storage technologies, such as compressed air energy storage, flywheel energy storage, and superconducting coil energy storage, significantly improve the power grid's ability to respond to load fluctuations and emergencies through intelligent control and optimisation of machine learning algorithms. This not only helps to optimise energy dispatch and improve the operational efficiency and flexibility of the grid but also significantly improves the stability and reliability of the grid so that it is better able to meet future challenges and needs.

This paper presents MADS (Multi-Agents for Data Science), an innovative and simple open-source multi-agent framework designed for systemic pipeline execution in applied supervised machine learning. By leveraging the capabilities of multi-agent systems (MAS), we introduce a universal approach to optimize and streamline machine learning pipelines. Our framework highlights the differences between various types of agents, such as reinforcement learning (RL) agents and large language model (LLM) agents, and their distinct contributions to the process. While we currently employ LLM agents to automate and enhance machine learning tasks, we acknowledge the potential of incorporating RL agents in future iterations to further improve performance and adaptability. The primary objective is to enhance the efficiency, scalability, and adaptability of supervised learning applications across various domains. This integration addresses the complexity and manual effort typically associated with machine learning workflows, paving the way for more automated, robust, and scalable solutions. Our approach demonstrates significant improvements in task automation, reduced human intervention, and enhanced model performance. The MADS framework, which will soon be available as an open-source implementation, represents a pivotal contribution to the field of machine learning, promising to facilitate broader adoption and collaborative advancement.

This paper presents a methodology based on deep learning models and metaheuristic algorithms for the optimization of airfoils for the design of aircraft wings with large endurance. The use of AZTLI-NN (a neural network with an architecture composed of a multilayer perceptron and a variational autoencoder) is implemented for the prediction of graphs of the aerodynamic coefficients of the airfoil as a function of the angle of attack. This neural network presents good predictions of the aerodynamic coefficients, similar to the coefficients obtained with computational fluid dynamics simulations. AZTLI-NN in combination of metaheuristic algorithms and the CST profile parameterization method show excellent performance in single-objective and multi-objective profile optimization tasks.

Student-centered active learning (SCAL) shifts the focus from the teacher to the student. Implementing SCAL requires the development of new forms of assessment beyond memorization and comprehension. This paper aims to demonstrate the effectiveness of SCAL by analyzing student performance at different cognitive levels. In flipped classrooms, students completed tasks with varying cognitive demands. The tests measured knowledge (level 1), comprehension (level 2), application (level 3) and analysis (level 4). This approach to assessment assesses not only the acquisition of content, but also skills that are critical to a health science student's future career. The results of expository learning were compared with student-centered collaborative learning in the Anatomy and Embryology I course over three academic years. Student opinions were collected through 326 anonymous Wooclap® surveys. No differences in performance were found for low cognitive level questions. However, SCAL significantly improved performance on higher cognitive level questions that required problem solving and application of knowledge. Despite the benefits of SCAL, it requires more effort from both teachers and students. The current assessment system, which measures the quality of teaching, penalizes this effort and requires teachers to believe strongly in the effectiveness of SCAL.

The Na+/K+ ATPase is a protein involved in the active transport of ions across the cellular membrane. Ouabain is a cardiotonic glycoside that, by inhibiting the Na+/K+ pump, interferes with cell processes mediated directly by the pump, but also indirectly influences other cellular processes, such as cellular cycle and proliferation, growth, cell differentiation, angiogenesis, migration, adhesion and invasion. We used the SK-BR-3 breast cancer cell line, mesenchymal stem cells (MSCs), and tumor-associated fibroblasts (TAFs) in vitro for determining the changes induced by Ouabain in concentration of 10-5 M, 10-6 M, 10-8 M, 10-9 M on these cellular types, employing specific methods: SEM for morphological evaluation; immunocytochemistry, flowcytometry to assess immunophenotypical markers expression, cell cycle and Annexin V/PI assay for cellular proliferation and viability testing; flowchamber assay to evaluate functional adhesion behavior; RT-PCR for Na+/K+ ATPase subunits molecular expression. Being indicative of the pro-apoptotic and inhibitory effect of Ouabain on tumor invasion and metastasis, the results support the addition of Ouabain to the oncological therapeutic arsenal, trailing the “repurposing drugs” approach.

Amid escalating urbanization, devising rational commercial space layouts is a critical challenge. Leveraging machine learning, this study uses a Back-propagation (BP) neural network to optimize commercial spaces in Weinan City's central urban area. The results indicate an increased number of commercial facilities with a trend of multi-centered agglomeration and outward expansion. Based on these findings, we propose a strategic framework for rational commercial space development emphasizing aggregation centers, development axes, and spatial guidelines. This strategy provides valuable insights for urban planners in small and medium-sized cities in the Yellow River Basin and metropolitan areas, ultimately showcasing the power of machine learning in enhancing urban planning.

Every subset S of a Cartesian spaces Rd, endowed with differen- tial structure C∞(S) generated by restrictions to S of functions in C∞(Rd), has a canonical partition M(S) by manifolds, which are or- bits of the family X(S) of all derivations of C∞(S) that generate local one-parameter groups of local diffeomorphisms of S. This partition satisfies the frontier condition, Whitney’s conditions A and B. If M(S) is locally finite, then it satisfies all definitions of stratification of S. This result extends to Hausdorff locally Euclidean differential spaces.

The review aims to assess fifteen (15) academic literature sources, highlighting the application of machine learning algorithms in the maintenance operations of optical fiber networks. It exhibits the collection of data using PRISMA methodology—Preferred Reporting Item for Systems Review and Meta-Analyses. The application, results, and performance metrics are discussed based on the collected observations, computations, and statistics in the studies, which revealed records of high accuracy degrees ranging from 86% to 98% on average and quality ML models including Neural Networks (NNs), Support Vector Machines (SVMs), and LSTM, as well as deep learning models that disclosed effective results of determining challenges and problems within the optical fiber lines. The review mainly centralized on superior machine learning technologies that surpass traditional techniques in fault detection and localization for improved optical fiber networks’ operations while providing insights into the limitations and challenges encountered in real-world applications of these models, offering a comprehensive perspective on the optical fiber network’s domain.

Keywords: Innovation ecosystems, Economic sustainability, Hydrocarbon-based economies, Economic diversification, Qualitative approach

Inspired by works of W. H. Zurek and others, a mathematical, physical theory, entirely within a quantum mechanical formalism, is proposed for cognitive processes in terms of an abstract Hilbert-space for the conscious state that is an exact replica of the Hilbert-space for the neuronic physical state. Thus, any actual state of consciousness arises by its formal alignment (identification) with some-one in the set of the neuronic states, with the latter undergoing perpetual changes in the wake of life-long experiences. It is posited that these changes become expressed by an increase in the number of ordered, coherent neuronic states at the expense of the pre-ordinal random neuronic states. Changes, transitions between states are induced by a Gorini-Kossakowski-Sudarshan-Lindblad formalism, which is also instrumental in the effect of the conscious state on bodily actions. The paradigmatic findings of R.N. Shepard (1958 - 2011) and of S. Sternberg (1966 - 2016) for long- and short-term recalls are interpreted within the model.

The COVID-19 pandemic has triggered seismic shifts in how we work, and organizations behave. It has caused many organizations to transition from an office-centric culture to more flexible ways of working. This shift is necessitated by health conditions and the need for controls. It is also driven by the assumption that remote work or working from home offer a certain assurance of safety for employees against the threat of infection in highly vulnerable office conditions. The shift to remote work has so far been mainly experimental as most businesses continue to learn about what works and what doesn’t. There is also the assumption that all that matters for the efficient operability of a remote work regime is the availability and effectiveness of computing technologies and internet connectivity. Thus, once those supplies are in place remote work is expected to be fully functional and without problems. As learning continues about what works and what doesn’t, it has also become increasingly clear that beyond the threat of covid-19 and the relative safety that individual homes may offer, there are other vulnerabilities which are ignored or underestimated in the process. In most instances, the home environment of the employee, the conditions under which employees operate from home and the health and safety such environments provide (or not) are either ignored or underestimated in discussions around remote work practices. This paper highlights remote work as an emergent practice while exploring associated, but ignored, health and safety issues in employee homes.

Based on the detailed exploration of AI techniques for the early identification of learning difficulties in education, this study underscores the pivotal role of educational data analysis in enhancing student outcomes. Educators can proactively identify and address learning challenges through systematic data collection and analysis, thereby minimizing long-term academic obstacles and emotional stress. The integration of AI, particularly through natural language processing and computer vision technologies, facilitates personalized learning paths and real-time interventions, offering tailored support that maximizes each student's learning potential. These advancements optimize educational resource allocation and foster a more inclusive and effective learning environment, paving the way for future advancements in personalized education and intelligent teaching practices.

Pig farms management is involved in multiple factors such as environmental conditions, animal behavior, weight gaining and others. In all those scenarios, it is fundamental to detect each individual and its development as it grows to reach the shipment phase. Therefore, the objective of this study was to apply an automatic individual pig detection algorithm using Deep Learning Techniques, in frames taken from videos recorded during the weaning phase in real production conditions of small and medium producers in tropical conditions in Colombia. The weaning phase was selected because individual detection in each cage is more difficult due to environmental adaptations that piglets undergo after nursing. Piglets tend to cluster together during this phase, making image processing more challenging compared to the fattening phase, where animals are more isolated. The You Only Look Once (YOLOv7) algorithm and VGG Image Annotator were used to detect individuals in two pens separated by gender. All animal postures, lighting conditions were considered. The Precision, Recall and mAP metrics were used to assess the model performance with different confidence values. A precision of 98.3% in a threshold of 0.9 was reached, Recall of 98.5% in a threshold of 0.85. Data augmentation techniques were important to increase the dataset and to have a more realistic model for individuals’ detection. The method used allowed us to identify all the complete pigs’ bodies under different posture and lighting situations.

Background We investigated to determine the effectiveness of verbal feedback in learning the round-off back somersault on the balance beam with stable landing. Methods: The research material consisted of female gymnasts (n = 16). They were randomly assigned to one of two groups: FKE group (n = 8) with feedback on key elements, or FAE group (n = 8) with 100% feedback on all errors made in the phase structure of the task. Results: Based on research, it was established that key elements could be identified in the preparatory, main and final phases. Mixed ANOVA showed that significant differences (p &lt; 0.05) were noted due to the teaching method used (Group x Time factor) when performing the gymnastic routine of round-off back somersault with stable landing on the balance beam. Based on the Welch t test for independent data it was revealed that the group with feedback on the key elements obtained significantly higher mean scores from judges at the end of the experiment. Conclusions: The findings of the present study point to a possibility of offering coaches teaching methods that increase the effectiveness of learning complex motor skills and indicate a possibility of applying such solutions in groups of female gymnasts both in training and during competitions.

Objectives: Aim to assess the perceptions of virtual learning among dental residents and faculty and employ Regulatory Focus Theory (RFT) to understand the impact of motivational orientations on virtual learning during COVID pandemic. Methods: 46 dental residents and 10 faculty in Upstate New York participated in the study (June -August 2021). Questionnaires were used to collect demographics, perceptions of virtual learning, burnout, and RFT types (promotion and prevention focus). Multiple regression analyses were used to examine factors associated with perceptions of virtual learning and burnout. Results: Overall, 70% of residents and 44% of faculty found virtual learning effective. Younger residents with less experience preferred virtual learning more than their older, experienced peers. Residents trained outside the U.S. and Canada favored in-person learning more than those trained within. Furthermore, residents with a higher promotion focus score found virtual learning more interactive for didactic courses. Additionally, 52% of residents experienced burnout, with a higher incidence among females (p=0.044). Conclusions: Virtual learning is well-received by dental residents and faculty, with potential for continued use post-pandemic. Future efforts should focus on creating an inclusive and supportive educational environment that meets the motivational and well-being needs of dental residents and faculty.

Introduction: It may be feasible to detect episodic memory change in preclinical Alzheimer’s disease (AD) to indicate navigational risks and AD prior to mild cognitive impairment. The establishment of episodic memory signatures may allow for biomarker mapping to inform diagnostic research and practiceMethods: Retrospective longitudinal mixed methods and cross-sectional effect size, to compare group differences, are applied to the Craft-21 memory scores from the preclinical years of persons who later developed AD (pre-AD) dementia , n = 175 with 112 females and 63 males. Their scores are compared to cognitively normal controls (non-AD) n = 6,814 with 4,232 females and 2,582 males. Pre-AD and non-AD groups are further analyzed by biological sex. The dataset is from the National Alzheimer’s Coordinating Center funded by NIA/NIH Grant U24 AG072122. Results: The pre-AD episodic memory scores decreased an average of -.510, p < .001 versus (vs.) the non-AD annual increase by .127, p < .001. The first Cohen’s d = .482 and last Cohen’s d = 976, p < .001. The pre-AD females had an average annual decreased of -.762, p < .001 vs. non-AD females increase of .117, p < .001. The first Cohen’s d = .576 and last Cohen’s d = 1.133, p <.001. The pre-AD males increased every year by .185, p = .996 vs. the non-AD males annual increase of .185, p < .001. The first Cohen’s d = 1.054 decreased by the last year to Cohen’s d = .680, p <.001Discussion: Distinct decline in episodic memory occurs for pre-AD females, but there is not a significant change in pre-AD males. However, the effect size difference between both pre-AD and non-AD groups suggests biomarker mapping in conjunction with memory trajectories may be feasible to determine potential navigational risks as well as biological and cognitive preclinical AD.

Virtual Reality (VR) can be useful in efforts that aim to improve wellbeing of older members of the society. Within this context, the work presented in this paper aims to provide to elderly a user-friendly and enjoyable Virtual Reality (VR) application incorporating memory recalling and storytelling activities that can promote mental awareness, so that negative side effects related to brain inactivity are prevented. An important aspect of the proposed VR application is the presence of a virtual audience that listens to the stories presented by elderly users, and interacts with the user. In an effort to maximize the impact of the VR application, research was conducted to study whether the elderly are willing to use the VR application and whether they believe it can help to improve well-being and reduce the effects of loneliness and social isolation. The results show that elderly users are positive towards the use of such an application in everyday life, as a means of improving their overall well-being.

We study in this work a dilute granular gas immersed in a thermal bath made of smaller particles with nonnegligible masses as compared with the granular ones. The kinetic theory for this system is developed and described by an Enskog--Fokker--Planck equation for the one-particle velocity distribution function. Granular particles are assumed to have inelastic and hard interactions, losing energy in collisions as accounted by a constant coefficient of normal restitution. The interaction with the thermal bath is based on a nonlinear drag force plus a white-noise stochastic force. To get explicit results of the temperature aging and steady states, Maxwellian and first Sonine approximations are developed. The latter takes into account the coupling of the excess kurtosis with the temperature. Theoretical predictions are compared with direct simulation Monte Carlo and event-driven molecular dynamics simulations. While good results for the granular temperature are obtained from the Maxwellian approximation, a much better agreement, especially as inelasticity and drag nonlinearity increase, is found when using the first Sonine approximation. The latter approximation is, additionally, crucial to account for memory effects like Mpemba and Kovacs-like ones.

Equiatomic CuZr alloy undergoes a martensitic transformation from the B2 parent phase to martensitic phases (P21/m and Cm) below 150 °C. We clarified the effect of the thermal cycling on the morphology and crystallography of martensite in equiatomic CuZr alloy using a transmission electron microscopy. The 10th cycled specimens consisted of different multiple structures at the maximum temperature of DSC measurement: 400 °C and 500°C, respectively. At the maximum temperature 400 °C of DSC measurement, it is composed of the fine plate-like variants, and a lamellar eutectoid structure consisting of Cu10Zr7 and CuZr2 phases on the martensitic variant. Concerning the maximum temperature 500 °C of DSC measurement, it is observed the martensitic structure and the lamellar structure in which the martensitic phase was completely eutectoid transformed. The formation of this lamellar eutectoid structure due to thermal cycling leads to the shift of forward and reverse transformation peaks to low and high temperature side. In addition, new forward and reverse transformation peaks indicating a new transformation appeared by thermal cycling, and the peaks remained around -20 °C. This new martensitic transformation behavior is also discussed.

Long memory plays an important role in many fields by determining the behaviour and predictability of systems; for instance, climate, hydrology, finance, networks and DNA sequencing. In particular, it is important to test if a process is exhibiting long memory since that impacts the accuracy and confidence with which one may predict future events on the basis of a small amount of historical data. A major force in the development and study of long memory was the late Benoit B. Mandelbrot. Here we discuss the original motivation of the development of long memory and Mandelbrot's influence on this fascinating field. We will also elucidate the sometimes contrasting approaches to long memory in different scientific communities

Abstract This study delved into the application of various machine learning (ML) models for the classification of lung cancer levels. Through meticulous monitoring of parameters such as minimum child weight and learning rate, efforts were made to mitigate overfitting while optimizing model performance. The Deep Neural Network (DNN) emerged as a standout performer, showcasing robust performance across training, validation, and testing stages. Ensemble methods like voting and bagging also demonstrated promising results. However, Support Vector Machine (SVM) models with the Sigmoid kernel faced challenges in achieving satisfactory performance. Overall, the investigation sheds light on the efficacy of different ML models in lung cancer level classification and underscores the importance of parameter tuning to address overfitting concerns.

Accurate diagnosis for the 400 million people with rare diseases is critical for healthcare decisions, prognosis, understanding disease mechanisms, and identification of treatments. Despite advances in genome sequencing, barriers such as high interpretation costs, diagnostic expertise, throughput associated delays, and uncertain variant classifications persist, with demand exceeding capacity. Many variant classification methods focus narrowly on specific consequences, leading to the use of complex integrative pipelines that often overlook transcript variability and lack prediction transparency. To overcome these limitations, we introduce DITTO. This transparent, transcript-aware machine-learning method demonstrates superior overall performance in accuracy, recall, and precision when compared to existing tools. DITTO is publicly available at https://github.com/uab-cgds-worthey/DITTO

Photovoltaic (PV) systems, which are renewable energy sources, are increasingly being utilized in distributed generation. To maintain a stable energy balance, energy storage systems such as batteries (BAT) play a vital role. Electric vehicles (EVs) offer a promising solution with rechargeable battery systems for operation. The BATs must maintain their state of charge within design boundaries, despite intermittent PV and load power fluctuations, and advanced power control and management techniques are essential for their effective operation. The article evaluates an intelligent controller that uses a Sliding Mode Control adaptive deep learning algorithm Convolutional Neural Networks (SMC-CNN) and a unique Strategy for managing supervisory power. (SPMS) for photovoltaic systems with battery energy storage for better regulation of DC bus voltage. SMC-CNN offers exceptional resilience and seamless functionality, minimizing fluctuations in DC bus voltage in the control strategy design requirements. The primary goals are maintaining a consistent power supply and ensuring continuous service by preventing system components from exceeding capacity. This study aims to enhance the control of DC bus voltage in the PV and battery system, with the primary significance focusing on the following aspects. The advanced SPMS has been created, incorporating control system constraints to enhance SOC balancing speed and reduce fluctuations in DC bus voltage. Power flow management involves optimizing energy flow between the PV system, battery system, and load while minimizing battery capacity requirements. The proposed SMC-CNN and SPMS are demonstrated through real-time simulation using Matlab/Simulink, as demonstrated in comprehensive case studies.

The increasing prevalence of Metabolic Syndrome (MetS), a serious condition associated with elevated risks of cardiovascular diseases, stroke, and type 2 diabetes, underscores the urgent need for effective diagnostic tools. This research carefully examines the effectiveness of 16 diverse machine learning (ML) models in predicting MetS, a multifaceted health condition linked to increased risks of heart disease and other serious health complications. Utilizing a comprehensive, unpublished dataset of imbalanced blood test results, spanning from 2017 to 2022, from the Laboratory Information System of the General Hospital of Amfissa, Greece, our study embarks on a novel approach to enhance MetS diagnosis. By harnessing the power of advanced ML techniques, we aim to predict MetS with greater accuracy using non-invasive blood test data, thereby reducing the reliance on more invasive diagnostic methods. Central to our methodology is the application of the Borda count method, an innovative technique employed to refine the dataset. This process prioritizes the most relevant variables, as determined by the performance of the leading ML models, ensuring a more focused and effective analysis. Our selection of models, encompassing a wide array of ML techniques, allows for a comprehensive comparison of their individual predictive capabilities in identifying MetS. This study not only illuminates the unique strengths of each ML model in predicting MetS but also reveals the expansive potential of these methods in the broader landscape of health diagnostics. The insights gleaned from our analysis are pivotal in shaping more efficient strategies for the management and prevention of Metabolic Syndrome, thereby addressing a significant concern in public health.

Ice formation on aircraft surfaces poses significant safety risks, and current detection systems often struggle to provide accurate, real-time predictions. This paper presents the development and comprehensive evaluation of a smart ice control system using a suite of machine learning models. The system utilizes various sensors to detect temperature anomalies and signal potential ice formation. We trained and tested supervised learning models (Logistic Regression, Support Vector Machine, Random Forest), unsupervised learning models (K-means clustering), and neural networks (Multi-Layer Perceptron) to predict and identify ice formation patterns. Experimental results demonstrate that our smart system, driven by machine learning, accurately predicts ice formation in real-time, optimizes de-icing processes, and enhances safety while reducing power consumption. This solution holds the potential for improving ice detection accuracy in aviation and other critical industries requiring robust predictive maintenance.

Utilizing deep learning for semantic segmentation of cropland from remote sensing imagery has become a crucial technique in land surveys. Cropland illustrates diverse morphologies and degrees of fragmentation on the Earth’s surface, underscoring the importance of accurately perceiving the complex boundaries of cropland which are crucial for effective segmentation. This paper introduces a UNet-like boundary-aware compensation model BAFormer. Cropland boundaries typically exhibit rapid transformations in pixel values and texture features, often appearing as high-frequency features in remote-sensing images. To enhance the recognition of these high-frequency features as represented by cropland boundaries, the proposed BAFormer integrates a Feature Adaptive Mixer (FAM) and develops a Deep Wide Large Kernel Multi-Layer Perceptron (DWLK-MLP) to enrich the global and local cropland boundaries features separately. Specifically, FAM adaptively mixes high-frequency and low-frequency features through the advantages of convolution and self-attention; DWLK-MLP expands the convolutional receptive field by deeply decomposing large kernel convolutions. The efficacy of BAFormer has been evaluated on the Vaihingen, Potsdam, and LoveDA public datasets, as well as the Mapcup dataset. It has demonstrated advanced performance, achieving mIoU scores of 84.5%, 87.3%, 53.5%, and 83.1% on these datasets respectively. Notably, BAFormer-T, the lightweight iteration of the model, surpasses other lightweight models on the Vaihingen dataset with scores of 91.3% F1 and 84.1% mIoU. The source code is available at https://github.com/WangYouM1999/BAFormer.

Energy communities are key actors in the energy transition since they optimally interconnect renewable energy capacities with the consumers. Despite versatile objectives, they usually aim at improving the self-consumption of renewable electricity within low voltage grids to maximize revenues. In addition, energy communities are an excellent opportunity to supply renewable electricity to regional and national energy systems. However, effective price signals have to be designed to coordinate the needs of the energy infrastructure with the interests of these local stakeholders. The aim of this paper is to demonstrate the integration of energy communities at the national level with a bottom-up approach. District energy systems with a building scale resolution are modelled in a mixed integer linear programming problem. The Dantzig-Wolfe decomposition is applied to reduce the computational time. The methodology lies within the framework of renewable energy hub, characterized by a high share of photovoltaic capacities. Both investments into equipment and its operation are considered. The model is applied on a set of five typical districts and weather locations representative of the Swiss building stock. The extrapolation to the national scale revealed a heterogeneous photovoltaic potential throughout the country. Present electricity tariffs promote a maximal investment into photovoltaic panels in every region, reaching an installed capacity of 67.2 GW and generating 80 TWh per year. Since the national PV capacity needed is forecast at 15.4 GW peak, coordinated investments between local and national actors are needed to prevent dispensable expenses. An uncoordinated design is expected to increase the total costs for residential energy systems by 43.2% and curtails 48.2% of local renewable electricity.

The increased deployment of IoT devices in specific areas results in an interference among them and the quality of communications can be severely degraded. To deal with this interference issue, the IEEE 802.11ax standard has been established in hyper-densely wireless networking systems. The 802.11ax adopts a new candidate technology that is called multiple network allocation vector in order to mitigate the interference problem. In this paper, we point out potential problem in multiple network allocation vector which can cause delays to the communication among IoT devices in hyper-dense wireless networks. Furthermore, this paper introduces an adaptive beam alignment algorithm for interference issue resolution. In addition, we analyze potential delays of communications among IoT devices under interference conditions. Lastly, we simulate our proposed algorithm in densely deployed environment and show that the interference issue can be mitigated and the IEEE 802.11ax-based IoT devices can utilize the air interface more fairly compared to conventional IEEE 802.11 distributed coordination function.

Background/Aim: Performing emergency surgery for bowel obstruction continues to place a significant strain on the healthcare system. Conventional assessment methods for outcomes in bowel obstruction cases often concentrate on isolated factors, and the evaluation of results for individuals with bowel obstruction remains poorly studied. This study aimed to examine the risk factors associated with major postoperative complications. Methods: We retrospectively analyzed 99 patients undergoing surgery from 2015 to 2022. We divided the patients into two groups: 1) benign related obstruction (n=68), 2) cancer related obstruction (n=31). We used logistic regression, KNN and XGBOOST. We calculated the receiver operating characteristic curve, and accuracy of the model. Results: Colon obstructions were more frequent in the cancer group (p=0.005). Operative time, intestinal resection and stoma were significantly more frequent in the cancer group. Major complications were 41% for the cancer group vs. 20 in the benign group (p=0.03). Uni-and multivariate analysis shows that significant risk factors for major complication were cancer related obstruction and CRP. The best model was KNN with an accuracy of 0.82. Conclusion. Colonic obstruction is associated with a tumor-related blockage. Malignant cancer and an increase in C-reactive protein (CRP) are significant risk factors for patients who have undergone emergency surgery due to major complications. KNN could improve the process of counseling and the perioperative management of patients with intestinal obstruction in emergency settings.

This paper presents a novel approach to designing beam codebooks for downlink multiuser hybrid multiple input multiple output (MIMO) wireless communication systems, leveraging multi-agent reinforcement learning (MARL). The primary objective is to develop an environment-specific beam codebook composed of non-interfering beams, learned by cooperative agents within the MARL framework. Machine learning (ML) based beam codebook design for downlink communications have been based on channel state information (CSI) feedback or only reference signal received power (RSRP) consisting of an offline training and user clustering phase. In massive MIMO, the full CSI feedback data is of large size and is resource-intensive to process, making it challenging to implement efficiently. RSRP alone for a stand-alone base station is not a good marker of the position of a receiver. Hence, in this work, uplink CSI estimated at the base station along with feedback of RSRP and binary acknowledgment of the accuracy of received data is utilized to design the beamforming codebook at the base station. Simulations using sub-array antenna and ray-tracing channel demonstrate the proposed system’s ability to learn topography-aware beam codebook for arbitrary beams serving multiple user groups simultaneously. The proposed method extends beyond mono-lobe and fixed beam architectures by dynamically adapting arbitrary shaped beams to avoid inter-beam interference, enhancing overall system performance. This work leverages MARL’s potential in creating efficient beam codebooks for hybrid MIMO systems, paving the way for enhanced multiuser communication in future wireless networks.

In higher education, the cultivation of research competency is pivotal for students’ critical thinking development and their subsequent transition into the professional workforce. While statistics plays a fundamental role in supporting the completion of a research project, it is often perceived as challenging, particularly by students in majors outside mathematics or statistics. The connection between students’ statistical proficiency and their research competency remains unexplored despite its significance. To address this gap, we utilized the supervised machine learning approach to predict students’ research competency, as represented by their performance in a research methods class, with predictors of students’ proficiency in statistical topics. Predictors relating to students’ learning behavior in a statistics course such as assignment completion and academic dishonesty are also included as auxiliary variables. Results indicate that the three primary categories of statistical skills—namely, understanding of statistical concepts, proficiency in selecting appropriate statistical methods, and statistics interpretation skills— can be used to predict students’ research competency, as demonstrated by their final course scores and letter grades. This study advocates for strategic emphasis on the identified influential topics to enhance efficiency in developing students’ research competency. Findings could inform instructors in adopting a strategic approach to teaching the statistical component of research for enhanced efficiency.

Analysis of land use/land cover (LULC) in the catchment areas is the first action toward safeguarding the freshwater resources. The LULC information in the watershed has gained popularity in the natural science field as it helps water resource managers and environmental health specialists develop natural resource conservation strategies based on available quantitative information. Thus, remote sensing is the cornerstone in addressing environmental-related issues at the catchment level. In this study, the performance of four machine learning algorithms (MLAs), such as Random Forests (RF), Support Vector Machine (SVM), Artificial Neural Networks (ANN), and Naïve Bayes (NB) was investigated to classify the catchment into nine relevant classes of the undulating watershed landscape using Landsat 8 Operational Land Imager (L8-OLI) imagery. The assessment of the MLAs were based on the visual inspection of the analyst and the commonly used assessment metrics, such as user’s accuracy (UA), producers’ accuracy (PA), overall accuracy (OA), and kappa coefficient. The MLAs produced good results, where RF (OA= 97.02%, Kappa= 0.96), SVM (OA= 89.74 %, Kappa= 0.88), ANN (OA= 87%, Kappa= 0.86), and NB (OA= 68.64 Kappa= 0.58). The results show the outstanding performance of the RF model over SVM and ANN with a small margin. While NB yielded satisfactory results, which could be primarily influenced by its sensitivity to limited training samples. In contrast, the robust performance of RF could be due to an ability to classify high-dimensional data with limited training data.

Significant Wave Height(SWH) is a crucial parameter in oceanographic research, essential for understanding various marine and atmospheric processes. Traditional methods for obtaining SWH, such as ship-based and buoy measurements, face limitations like limited spatial coverage and high operational costs. With the advancement of Global Navigation Satellite Systems reflectometry(GNSS-R) technology, a new method for retrieving SWH has emerged, demonstrating promising results. This study utilizes Radio occultation sounder(GNOS) data from the FY-3E satellite and incorporates the latest Vision Transformer(ViT) technology to investigate GNSS-R-based SWH retrieval. We designed and evaluated various deep learning models, including ANN-Wave, CNN-Wave, Hybrid-Wave, Trans-Wave, and ViT-Wave. Through comparative training using ERA5 data, the ViT-Wave model was identified as the optimal retrieval model. The ViT-Wave model achieved an Root Mean Square Error(RMSE) accuracy of 0.4052 meters and Mean Absolute Error(MAE) accuracy of 0.2700 meters, significantly outperforming both traditional methods and newer deep learning approaches utilizing Cyclone Global Navigation Satellite Systems(CYGNSS) data. These results underscore the potential of integrating GNSS-R technology with advanced deep learning models to enhance SWH retrieval accuracy and reliability in oceanographic research.

The present era of the Internet of Things (IoT) having intelligent functionalities in solving problems pertaining to realtime mission-critical systems has brought an immense revolution in diverse fields including healthcare and navigation systems. However, to the best of our knowledge, the potential of IoT has not been fully exploited yet in the field of the energy sector. We argue that there is an immense need to shift the traditional mission-critical electric power system architecture to IoT-based fully orchestrated architecture in order to increase efficiency, as billions of investment is reserved for the energy sector globally. Since network orchestration deals with auomating the interaction between multiple components involved to execute a particular service, therefore, scheduling the relevant processes within strict deadlines becomes the core pillar of the architecture. The mission-critical systems with urgent task execution often suffer from issues of missing task deadlines. In this study, we present a novel IoT task orchestration architecture for efficient energy management of a nanogrid system that focuses on minimizing the use of nonrenewable energy resources and maximizing the use of renewable energy resources. Moreover, major components of IoT task orchestration such as task mapping and task scheduling are also enhanced using NLP and PSO optimization modules. The proposed task scheduling algorithm incorporates the optimized surplus time, and efficiently executes the energy management-related tasks contemplating to their types. The study utilizes sensors to obtain data from physical IoT devices, including photovoltaic (PV), Energy Storage System (ESS), and diesel generator (DG). The performance of the proposed model is evaluated using data set of nanogrid houses. The outcomes revealed that IoT-task orchestration has played a pivotal role in efficient energy management for nanogrid mission-critical system. Furthermore, the comparison with state-of-the-art scheduling algorithms showed that the task starvation rate is reduced to 16% and 12% when compared with RR and FEF algorithms, respectively.

Presence detection is essential in many applications, including smart homes, office automation, and public space management. Traditional technologies like infrared sensors and cameras frequently encounter obstacles due to privacy concerns, high costs, and complexity. The study provides a novel way to detect presence based on Wi-Fi signals and machine learning algorithms, utilizing the ESP8266 microcontroller. The suggested system attempts to reliably detect the presence of people in a given place by evaluating fluctuations in Wi-Fi signal strength and patterns. The theoretical basis of this strategy is investigated, including the ESP8266’s capabilities for Wi-Fi data gathering and the use of machine learning methods for data analysis. The methodology includes data collecting with the ESP8266, preprocessing, feature extraction, and training and evaluating machine learning models. This system’s potential uses include smart home automation, office occupancy tracking, and crowd management in public settings. The paper also discusses potential issues such as signal interference, data privacy concerns, and the limitations of Wi-Fi detection. Future work is also mentioned, including the suggested system’s installation and testing and enhancement proposals to improve accuracy and scalability. This research aims to provide a cost-effective, non-intrusive, and scalable presence detection system by harnessing the power of Wi-Fi signals and machine learning, enhancing intelligent environments

Alginate-silver nanocomposites in the form of spherical beads and films were prepared using a green approach by using the aqueous extract of Ajwa dates seeds. The nanocomposites were fabricated by in situ reduction and gelation method by ionotropic crosslinking using calcium ions in solution. The rich phytochemicals of the dates seeds extract played a dual role as reducing and stabilizing agent in the synthesis of silver nanoparticles. The formation of silver nanoparticles was studied using UV-Vis absorption spectroscopy and a distinct surface plasmon resonance (SPR) peak at 421 nm characteristic of silver nanoparticles confirmed the green synthesis of silver nanoparticles. The morphology of the nanocomposite beads and film was compact with even distribution of silver nanoclusters. The catalytic property of the nanocomposite beads was evaluated for the degradation of 2-nitrophenol in the presence of sodium borohydride. The degradation followed pseudo-first order kinetics with a rate constant of 1.40 ´ 10^-3 s^-1 at 23 °C with an activation energy of 18.45 kJ mol^-1. The thermodynamic parameters such as changes in enthalpy and entropy were evaluated to be 15.22 kJ mol^-1 and -197.50 J mol^-1 K^-1, respectively. The nanocomposite exhibited properties against three clinically important pathogens (Gram-positive and Gram-negative bacteria)

Biological systems have a unique ability inherited through their genome. It allows them to build, operate, and manage a society of cells with complex organizational structures where autonomous components execute specific tasks and collaborate in groups to fulfill systemic goals with shared knowledge. The system receives information from various senses, makes sense of what is being observed, and acts using its experience, while the observations are still in progress. We use the General Theory of Information (GTI) to implement a digital genome, specifying the operational processes that design, deploy, operate, and manage a cloud-agnostic distributed application that is independent of IaaS and PaaS infrastructure, which provides the resources required to execute the software components. The digital genome specifies the functional and non-functional requirements that define the goals and best-practice policies to evolve the system using associative memory and event-driven interaction history to maintain stability and safety while achieving the system’s objectives. We demonstrate a structural machine, cognizing oracles, and knowledge structures derived from GTI used for designing, deploying, operating, and managing a distributed video streaming application with autopoietic self-regulation that maintains structural stability and communication among distributed components with shared knowledge while maintaining expected behaviors dictated by functional requirements.

Alzheimer’s disease (AD) and type 2 diabetes mellitus (T2DM) are comorbidities that result from the sharing of common genes. The molecular background of comorbidities can provide clues for the development of treatment and management strategies. Here, the common genes involved in the development of the two diseases and in memory and cognitive function are reviewed. Network clustering based on protein-protein interaction networks identified tightly connected gene clusters that have an impact on memory and cognition among the comorbidity genes of AD and T2DM. Genes with functional implications were intensively reviewed, and relevant evidence was summarized. Gene information will be useful in the discovery of biomarkers and the identification of therapeutic targets for AD.

We study the short−term memory capacity of ancient readers of the original New Testament written in Greek, of its translations to Latin and modern languages. To model the short–term capacity, we have considered the number of words per interpunctions, the “word interval” , because this parameter can model how the human mind memorizes “chunks” of information. Since can be calculated for any alphabetical text, we can perform experiments − otherwise impossible − with ancient readers by studying the literary works they used to read. The “experiments” compare the of texts of a language/translation to those of another language/translation by measuring the minimum average probability of finding joint readers (those who can read both texts because of their similar short–-term memory capacity) and by defining an “overlap index”. We also define a population of universal readers who can read any the New Testament written in alphabetical language. More than 50% of the readers of specific languages overlap with the universal readers with probability . Future work is vast, with many research tracks, because alphabetical literatures are very large and allow many experiments, such as comparing authors, translations or even texts written by artificial intelligence tools.

Purpose of the study was to explore the association of cognition with hazardous drinking, binge drinking and alcohol use disorder in schizophrenia and schizoaffective disorder. Cognitive deficits are common in schizophrenia. Alcohol might be associated with additional cognitive impairment in schizophrenia patients. The study population included 3362 schizophrenia and schizoaffective disorder patients in Finland. Hazardous drinking was screened with the AUDIT-C (Alcohol Use Disorders Identification Test for Consumption) screening tool. Binge drinking was obtained from the AUDIT-C. Alcohol use disorder (AUD) diagnoses were obtained from the national registrar data. Participants performed two computerized tasks from the Cambridge automated neuropsychological test battery (CANTAB) on tablet computer: the 5-choice serial reaction time task (5-CSRTT), or, reaction time (RT) test and the Paired Associative Learning (PAL) test. Association of alcohol use with RT test and PAL test was analyzed with log-linear regression and logistic regression, respectively. After adjustment for age, education and age at first psychotic episode, hazardous drinking in females was associated with lower median RT. Compared to never binge drinkers, male and female participants drinking 6 or more doses of alcohol monthly or less had lower median RT. In the PAL test both first trial memory score (FTMS) and total errors adjusted score (TEAS) were associated with better performance in males drinking 6 or more doses of alcohol weekly or more and in females drinking 6 or more doses monthly or less. Higher PAL TEAS was associated with AUD in females Some positive associations between alcohol and cognition were found in male and female schizophrenia and schizoaffective disorder patients with hazardous drinking and binge drinking.

Federated learning is an effective approach for preserving data privacy and security, enabling machine learning to occur in a distributed environment and promoting its development. However, an urgent problem that needs to be addressed is how to encourage active client participation in federated learning. The Shapley Value, a classical concept in cooperative game theory, has been utilized for data valuation in machine learning services. Nevertheless, existing numerical evaluation schemes based on the Shapley Value are impractical as they necessitate additional model training, leading to increased communication overhead. Moreover, participants’ data may exhibit Non-IID characteristics, posing a significant challenge to evaluating participant contributions. Non-IID data weakens the marginal effects of participants, which in turn affects model accuracy and leads to underestimated contribution measurements. Current works often overlook the impact of heterogeneity on model aggregation. This paper presents a fair federated learning contribution measurement scheme that addresses the need for additional model computations. By introducing a noval aggregation weight, it enhances the accuracy of contribution measurement. Experiments on the MNIST dataset show that the proposed method can accurately compute the contributions of participants. Compared to existing baseline algorithms, the model accuracy is significantly improved, with a similar time cost.

The success of deep learning (DL) in offline brain-computer interfaces (BCIs) has not yet translated into efficient online applications. This is due to two limiting factors: the need for large amounts of training data in DL and the fact that current DL solutions are primarily developed for offline decoding. To enable real-time decoding, even across subjects without calibration data, we first introduce a novel method real-time adaptive pooling (RAP) to tune existing offline DL models towards online decoding by modifying the pooling layers. To reduce the amount of training data required, our approach leverages different levels of domain adaptation. We show how different settings enable different adaptation solutions. Our results demonstrate that our approach is both powerful and can be calibration-free, providing a robust and practical solution for real-time BCI applications. These findings pave the way for the development of co-adaptive and highly efficient DL-based BCI systems.

Abstract: Wildfires in forest ecosystems exert substantial ecological, economic, and social impacts. The effectiveness of fire management hinges on precise pre‐fire risk assessments to inform mitigation efforts. This study aims to investigate the relationship between predictions from pre‐fire risk assessments and outcomes observed through post‐fire burn severity analyses. In this study, forest fire risk was assessed with the Fuzzy Analytical Hierarchy Process, in which fire behavior factors were used as input. The degree of burn was determined using the Random Forest method using 11519 training points and 400 test points on Sentinel‐2 satellite images in three different classes. According to the results obtained from 266 selected test points located within the forest boundaries, all primary factors showed an increased effect in areas with high burn severity. Climate, in particular, emerged as the most influential factor, accounting for 52% of the overall impact. However, in cases of high fire severity, climate proved to be the most effective risk factor, ac‐counting for 67%. It followed by topography with 50% accuracy at high fire intensity. In the risk assessment is based on the FAHP method, climate was assigned the highest weight value among other factors with 32.2%. Topography emerged as the second most effective risk factor with 27 %. To evaluate the results more comprehensively both visually and statistically, two regions with different stand canopy characteristics were selected within the study area. While high burn severity had the highest accuracy in Case 1 area, moderate burn severity had the highest in Case 2 area. During the days when the fire continued, the direction of spread was obtained from MODIS images. In this way, the fire severity depending on the direction of fire progression was also interpreted. Through an analysis of various case studies and existing literature, the research underscores both the strengths and limitations inherent in predicting forest fire behavior‐based pre‐fire risk assessments. Furthermore, it emphasizes the necessity of continuous improvement to increase the success of forest fire management.

Globalization, knowledge economy, information technology advancements, and the rise of learning societies contribute to the concept of a learning city. The study examines the economic indicators of Yazd city, Iran, in the context of learning city development. A descriptive-analytical approach with a survey method and cluster sampling was employed. Data analysis involved Kolmogorov-Smirnov normality test, single-sample T-test, simple linear regression, and Kendall's W test. The normality test confirmed data normality. The T-test indicated that experts perceived the current state of most variables in Yazd as undesirable. Regression analysis revealed a significant positive association between the economic index and independent variables. Kendall's W test prioritized areas based on economic indicators, with the top 7 and bottom 5 areas identified for focused interventions. The study emphasizes the need to prioritize areas within Yazd based on their economic indicators. This prioritization informs strategies for enhancing social and legal aspects of Yazd's transformation into a learning city. Further research should explore effective methods to cultivate a full-fledged learning environment in the city.

This paper presents an innovative multi-agent, data-driven reinforcement learning (RL) approach to develop and utilize the thermal equivalent network model that represents the motor's thermal dynamics. A multi-agent reinforcement learning is designed and trained to adjust the model parameters using data from several motor driving cycles. To ensure the incoming driving cycle matches the historical data before employing the pre-trained RL agents, offline statistical analysis and clustering techniques are developed and used. Numerical simulations highlighted the RL agent's ability to develop strategies that effectively address the variability of driving cycles. The proposed RL framework showed its capability to accurately reflect the motor's thermal behavior under various driving conditions.

Detection of subsurface archaeological remains using a range of remote sensing methods, poses several challenges until today. Recent studies regarding the detection of archaeological proxies like those of cropmarks highlight the complexity of the phenomenon. In this work we present three different methods, and associated indices, for identifying stressed reflectance signatures indicating buried archaeological remains, based on a dataset of measured ground spectroradiometric reflectance. Several spectral profiles between the visible and near infrared part of the spectrum, were taken over a controlled environment in Cyprus during the 2011-2012 and are re-used in this study. The first two (spectral) methods are based on a suitable analysis of the spectral signatures in (1) the visible part of the spectrum, and in particular in the neighborhood of 570 nm, and (2) the red edge-near infrared part of the spectrum, in the neighborhood of 730 nm. Machine learning (decision trees) allows for the deduction of suitable wavelengths to focus on, in order to formulate the proposed indices and the associated classification criteria (decision boundaries) that can enhance the detection probability of stressed vegetation. Noise in the signal is taken into account by simulating reflectance signatures perturbed by white noise. Applying decision tree classification on the ensemble of simulations and basic statistical analysis we refine the formulation of the indices and criteria for the noisy signatures. The success rate of the proposed methods is over 90%. The third method rests on the estimation of vegetation/canopy reflectance parameters through inversion of the physical-based PROSAIL reflectance model and the associated classification through machine learning methods. The obtained results provide further insights into the formation of stress vegetation that occurred due to the presence of shallow buried archaeological remains, which are well aligned with physical-based models and existing empirical knowledge. To the best of the authors' knowledge, this is the first study demonstrating the usefulness of radiative transfer models such as PROSAIL for understanding the formation of cropmarks. Similar studies can support future research directions towards the development of regional remote sensing methods and algorithms if systematic observations are adequately dispersed in space and time.

This study delves into hospital mobility, understood as an indicator of perceived service quality, across the Italian regions of Apulia and Emilia Romagna, utilizing logistic regression among machine learning techniques. The focus is on how structural, operational, and clinical variables impact patient perceptions of service quality, influencing their healthcare choices. Through the analysis of mobility trends with machine learning, significant differences between regions were uncovered, highlighting the influence of regional context on perceived quality. The integration of SHAP (SHapley Additive exPlanations) values into our analysis provided deeper insights into the logistic regression model, elucidating the specific contribution of each variable to perceived healthcare quality. This incorporation of SHAP values underscores the study's commitment to employing advanced, explainable AI techniques to enhance the interpretability and fairness of healthcare service evaluations. The choice of logistic regression elucidated the impact of specific variables on quality perception, offering essential insights for optimizing healthcare resource distribution and underscoring the importance of data-driven strategies to foster more equitable, efficient, and patient-centred healthcare systems. Contributing to the understanding of perceived quality dynamics within the healthcare context, the research paves the way for further investigations into enhancing accessibility and service quality, leveraging machine learning as a tool for improving healthcare services efficiency in diverse regional settings.

Structures inevitably suffer damages after an earthquake, with their severity ranging from minimal damages to non-structural elements to partial or even total collapse, possibly with loss of human lives. Thus, it is essential for engineers to understand the crucial factors that drive a structure towards suffering higher degrees of damage, so that preventative measures can be taken. In the present study, we focus on three well-known damage thresholds, namely Collapse Limit State, Ultimate Limit State and Serviceability Limit State and analyze which of the features obtained via Rapid Visual Screening, determine whether or not a given structure will cross that threshold. To this end, we use Machine Learning to perform binary classification for each damage threshold, as well as Explainability via SHAP values (acronym for SHapley Additive exPlanations) to quantify the effect of each parameter. The quantitative results obtained demonstrate the potential applicability of ML methods to re-calibrate the computation of structural vulnerability indices using data from recent earthquakes.

Timely and accurate information on tree species is crucial for the sustainable management of natural resources, forest inventory, biodiversity detection, and carbon stock calculation. The advancement of remote sensing technology and artificial intelligence has facilitated the acquisition and analysis of remote sensing data, resulting in more precise and effective classification of tree species. Multimodal remote sensing data and deep learning seem to be the current tree species classification research mainstream, whether or not. The current review on the remote sensing data and deep learning tree species classification methods perspectives to analyze the unimodal and multimodal remote sensing data and classification methods in this realm is missing. To bridge the gap, we search for major trends in the remote sensing data and tree species classification methods, provide a detailed overview of classic deep learning-based methods for tree species classification, and discuss the limitations.

Dementia is a public health priority, in which memory impairments are prevalent and affects an individual’s daily activities. Research has tried to find ways to support memory problems of individuals with dementia. Self reference effect (SRE) has been shown to benefit memory in healthy, non-dementia group. The study aimed to investigate if SRE will improve memory performance of individuals with dementia. We used ecologically valid Ownership Procedure and the Remember/Know Paradigm to examine the Self-Reference Effect (SRE) on memory. It was hypothesised that participants living with dementia will perform differently in the recall of items that were self-referentially encoded compared to items other-referentially encoded and that the memory will be different in control participants than in those that live with dementia. The research found that self-referential processes did not have effect on memory in individuals with dementia. We suggest that impaired self-awareness may have contributed to the lack of this effect. However, we had a small sample size and these findings should be treated with caution.

Dialogue State Tracking is an essential component in multi-domain dialogue systems, aiming to accurately determine the current dialogue state based on the dialogue history. Existing research has addressed the issue of multiple mappings in dialogues by employing slot self-attention as a data-driven approach. However, learning the relationships between slots from a single sample has limitations and introduces noise. In this paper, we propose an External Slot Relation Memory-based Dialogue State Tracking model (ER-DST). By utilizing an external memory storage, we learn the relationships between slots as a dictionary of multi-domain slot relations. Additionally, we employ a small filter to discard slot information irrelevant to the current dialogue state. Experimental results on the MultiWOZ2.0 and MultiWOZ2.1 benchmarks demonstrate significant improvements while reducing the time complexity to O(n).

(1) Background: Many processes play a key role in how language functions, and these processes are strongly related to reading. The aim of our research was to explore the relationship between reading impairment associated with adult acquired cognitive-linguistic impairment (aphasia) and the components of verbal working memory involved in language functioning. (2) Methods: We measured the reading abilities of a total of twenty-two adults diagnosed with aphasia using the Adult Acquired Reading Assessment. To assess working memory, we applied the measurement procedures available in Hungarian for measuring verbal working memory. Correlation analyses were performed to investigate the relationship between reading and the components of working memory involved in processing verbal information. In order to explore this relationship as comprehensively as possible, the results were analysed quantitatively through group-level analyses and qualitatively through case studies. (3) Results: The results suggest that the functioning of phonological short-term memory and verbal working memory is crucial for the reading of vowels, for certain word reading sub-processes such as reading complex words and pseudowords, and for text comprehension tasks, in particular for the processing of implicit text-level infor-mation. (4) Conclusions: The data support a strong relationship between reading and working memory, but not all mechanisms are related with the same weighting. The data will contribute to the understanding of the relationship between reading and working memory, which is important in order to see which cognitive components are dominant in reading instruction and which other cognitive mechanisms are affected in poor readers.

Malware complexity is rapidly increasing, causing catastrophic impacts on computer systems. Memory dump malware is gaining increased attention due to its ability to expose plaintext passwords or key encryption files. This paper presents an enhanced classification model based on One class SVM (OCSVM) classifier that can identify any deviation from the normal memory dump file patterns and detect it as malware. The proposed model integrates OCSVM and Principal Component Analysis (PCA) for increased model sensitivity and efficiency. An up-to-date dataset known as “MALMEMANALYSIS-2022” was utilized during the evaluation phase of this study. The accuracy achieved by the traditional one-class classification (TOCC) model was 55%, compared to 99.4% in the one-class classification with PCA (OCC-PCA) model. Such results have confirmed the increased performance achieved by the proposed model.

Concussion, also known as mild traumatic brain injury (mTBI), commonly causes transient neurocognitive symptoms, but in some cases, it causes cognitive impairment, including working memory (WM) deficit, which can be long-lasting and impede a patient’s return to work. The predictors of long-term cognitive outcomes following mTBI remain unclear because abnormality is often absent in structural imaging findings. The purpose of the study was to determine whether machine learning-based models using functional magnetic resonance imaging (fMRI) biomarkers and demographic or neuropsychological measures at baseline could effectively predict 1-year cognitive outcomes of concussion. We conducted a prospective, observational study of patients with mTBI who were compared with demographically-matched healthy controls enrolled between September 2015 to August 2020. Baseline assessments were collected within the first week of injury, and follow-ups were conducted at 6 weeks, 3 months, 6 months, and 1 year. Potential demographic, neuropsychological, and fMRI features were selected according to the significance of correlation with the estimated changes in WM ability. The support vector machine classifier was trained using these potential features and estimated changes in WM between the predefined time periods. Patients demonstrated significant cognitive recovery at the third month, followed by worsened performance after 6 months, which persisted until 1 year after concussion. Approximately half of the patients experienced prolonged cognitive impairment at 1-year follow up. Satisfactory predictions were achieved for patients whose WM function did not recover at 3 months (accuracy=87.5%), 6 months (accuracy=83.3%), 1 year (accuracy=83.3%), and performed worse at 1-year follow-up compared to baseline assessment (accuracy=83.3%). This study demonstrated the feasibility of personalized prediction for long-term postconcussive WM outcomes based on baseline fMRI and demographic features, opening a new avenue for early rehabilitation intervention in selected individuals with possible poor long-term cognitive outcomes.

Shape-memory hydrogels (SMH) are as multifunctional, actively-moving polymers of interest in biomedicine. In loosely crosslinked polymer networks gelatin chains may form triple helices, which can act as temporary netpoints in SMH, depending on the presence of salts. Here, we show programming and initiation of the shape-memory effect of such networks based on a thermomechanical process compatible with the physiological environment. The SMH were synthesized by reaction of glycidylmethacrylated gelatin with OEG α,ω-dithiols of varying crosslinker length and amount. Triple helicalization of gelatin chains is shown directly by wide-angle X-ray scattering and indirectly via the mechanical behavior at different temperatures. The ability to form triple helices increased with the molar mass of the crosslinker. Hydrogels had storage moduli of 0.27-23 kPa and Young’s moduli of 215-360 kPa at 4 °C. The hydrogels were hydrolytically degradable, with full degradation to water soluble products within one week at 37 °C and pH = 7.4. A thermally-induced shape-memory effect is demonstrated in bending as well as in compression tests, in which shape recovery with excellent shape recovery rates Rr close to 100% were observed. In the future, the material presented here could be applied e.g. as self-anchoring devices mechanically resembling the extracellular matrix.

Heavy rains have created significant threats to human health and life. Floods and other natural disasters, which have a global impact annually, can be attributed to extended durations of intense precipitation. Accurate rainfall predictions are crucial in nations such as Bangladesh, where agriculture is the predominant occupation. The efficiency of machine learning (ML) methods is enhanced by the non-linearity of rainfall, surpassing the effectiveness of other alternative ways. Machine learning techniques show that individual classifiers exhibit worse accuracy than ensemble learning (EL) methodologies. Ensemble Learning techniques are utilized for rainfall prediction and estimating rainfall quantity and daily average temperature to enhance comprehension of the diverse Machine Learning algorithms. This research implements the machine learning techniques and ensemble-based classifier to predict the rainfall occurrence, along with the machine learning regressor models and ensemble-based regressor for the rainfall amount prediction and daily average temperature prediction, using Bangladesh Weather Dataset. The results of the machine learning and ensemble-based models are compared using the Accuracy and F1 score for rainfall occurrence prediction. In contrast, MAE and RMSE evaluation metrics are used for ensemble regressor and regression algorithms for the rainfall amount and daily average temperature prediction. With an accuracy of 83.41% and a recall of 78.17%, the Ensemble Classifier is the best at predicting when it will rain, but its precision of 51.16% stands in for the lowest. The Ensemble Regression model outperforms Linear Regression, Random Forest, and SVR in rainfall amount prediction, with the lowest MAE of 0.36 and RMSE of 0.90. The Ensemble Regression provides the most precise results for daily average temperature prediction with the lowest MAE 0.42 and RMSE 0.54 highlighting its superiority over the other regression models in forecasting temperature with less error. Ensemble approaches consistently lead task performance metrics.

In the era of mounting water scarcity, particularly in arid regions, the agricultural sector is striving to optimize the water resource management practices. Treated wastewater (TWW) has emerged as a viable alternative to freshwater for irrigation, offering a sustainable solution to water conservation. However, ensuring the safety and quality of TWW is paramount to safeguard for both crop health and environmental integrity. Electrical conductivity (EC), a critical factor in assessing TWW suitability for irrigation, can significantly impact crop yields and soil health since it is directly linked to the concentration of dissolved salts and ions. Therefore, this study delves into the development of advanced predictive models for EC assessment by employing supervised machine learning (ML) techniques like the Support Vector Regression (SVR), Adaptive Network-based Fuzzy Inference System (ANFIS), and Multiple Linear Regression (MLR). The TWW samples collected from Al-Qatif area, Saudi Arabia were assessed in the lab through a sensor-based real-time monitoring system integrated with Internet of Things (IoT) network and a multiprobe device. The key water quality parameters assessed involved, temperature (T), pH, Oxidation Reduction Potential (ORP), Resistivity (RES), Total Dissolved Solids (TDS), Salinity and Turbidity which served as the foundation for these models, given their profound influence on and their anticipated impact on EC levels. Following feature selection, two distinct model combinations were identified for the SVR, ANFIS and MLR models. Furthermore, to evaluate prediction performance, four statistical criteria, including coefficient of determination (R²), correlation coefficient (R), mean square error (MSE), and root mean square error (RMSE), were employed. Overall, the comparative performance results proved that ANFIS-M2 indicated the strongest predictive capability with the R² value of 0.99572 and 0.75145 and the RMSE values of 0.00965 and 0.01134, respectively in both calibration and verification stages.

This study addresses the importance of conducting mass movement susceptibility mapping and hazard assessment using quantitative techniques, including machine learning, in the Northern Lima Commonwealth (NLC). Previous exploration of the topographic variables revealed high correlation and multicollinearity among some of them, which led to dimensionality reduction through principal component analysis (PCA). Six susceptibility models were generated using weights of evidence, logistic regression, multilayer perceptron, support vector machine, random forest, and naive Bayes methods to produce quantitative susceptibility maps and assess the hazard associated with two scenarios: the first being an El Niño phenomenon and the second being an earthquake exceeding 8.8Mw. The main findings indicate that machine learning models exhibit excellent predictive performance for the presence and absence of mass movement events, as all models surpassed an AUC value of &gt;0.9, with the random forest model standing out. In terms of hazard levels, in the event of an El Niño phenomenon or an earthquake exceeding 8.8Mw, approximately 40% of the NLC area would be exposed to the highest hazard levels. It also highlights the importance of integrating methodologies to reduce model uncertainty, such as comprehensive analysis of variables supported by high quality data and organized workflows. The findings of this research are expected to serve as a supportive tool for land managers in formulating effective disaster prevention and risk reduction strategies.

Photovoltaic modules should pass series of tests and examinations, verifying the electrical and thermal characteristics of the module, before being released to the market, examining the properties of the modules should undergo appropriate durability and efficiency tests under real outdoor conditions with exposure to climatic conditions and under laboratory conditions. The performance of photovoltaic cells depends on many factors, such as solar irradiance, module operating temperature, installation location, weather conditions and module shading. In this paper, three selected photovoltaic modules were examined using a large-scale steady-state solar simulator. The current-voltage (I-V) characteristics of the photovoltaic modules were experimentally tested and analyzed. The next step was to implement a three-layer artificial neural network model (MLP). The experimental data obtained in the previous step coupled with output data from MLP were then used in global sensitivity analysis (GSA). Experiments carried out on a large-scale stationary solar simulator showed differences between the values declared by the manufacturer and the values obtained from measurements of PV modules. The first module tested achieved the maximum power point greater than that specified by the manufacturer, while the other two showed power drops; it was 85-87% for the second module, and 95-98% for the third, respectively. The performed global sensitivity analysis (GSA) for the MLP model showed that the parameters: eff (22.9) and Voc/V (14.19) have the largest effect on the power-voltage relationship, while U (7.29) has the smallest effect. The usefulness of machine learning (ML) methods in the comparative analysis of PV modules has been proved.

This paper explores the views of a group of young men aged 16–18, studying towards a Level 1 diploma in music in the North East area of England. It uses the conceptualization of “social haunting” to focus our discussions about how Level 1 learners articulated their experiences in the context of their learning journeys and perceived marginalization. The research took place at a large Further Education (FE) college and included a series of five “research encounters” with the group of Level 1 learners. These encounters included a range of activities, resulting in a variety of data being collected, including several activity worksheets, structured and unstructured focus group interviews, and questionnaires. This paper focusses on the outcomes of a single research activity that focused on exploring the topic of marginalization. We present a discussion on social haunting as one of the emerging findings from this research encounter, outlining how the reality of the social and cultural legacy of the UK’s industrial past can shape today’s youth and their futures. We will talk about the young men’s views of marginalization, their school-to-work transitions, the formation of masculinity in post-industrial communities and the role of Further Education in it. The paper concludes by discussing some insights for practice and future research.

Vertical Indoor Farming (VIF) with hydroponics offers a promising perspective for sustainable food production. Intelligent control of VIF system components plays a key role in reducing operating costs and increasing crop yields. Modern machine vision (MV) systems use Deep Learning (DL) in combination with camera systems for various tasks in agriculture, such as disease and nutrient deficiency detection, and flower and fruit identification and classification for pollination and harvesting. This study presents the applicability of MV technology with DL modelling to detect the growth stages of chilli plants using YOLOv8 networks. The influence of different bird’s eye and side view datasets and different YOLOv8 architectures was analysed. To generate the image data for training and testing the YOLO models, chilli plants were grown in a hydroponic environment and imaged throughout their life cycle using four camera systems. The growth stages were divided into growing, flowering and fruiting classes. All trained YOLOv8 models showed reliable identification of growth stages with high accuracy. The results indicate that models trained with data from both views show better generalisation. YOLO’s middle architecture achieved the best performance.

Shape-shifting polymers usually require not only reversible stimuli-responsive ability, but also strong mechanical properties. A novel shape-shifting photochromic hydrogel system was designed and fabricated through embedding hydrophobic spiropyran (SP) into double polymeric network (DN) by micellar copolymerization. Here, sodium alginate (Alg) and poly acrylate-co-methyl acrylate-co-spiropyran (P(SA-co-MA-co-SPMA)) were employed as the first network and the second network respectively to realize high mechanical strength. After soaked in the CaCl2 solution, the carboxyl groups in the system undergo metal complexation with Ca2+ to enhance the hydrogel. Moreover, after the hydrogel is exposed to UV-light, the closed isomer of spiropyran in the hydrogel network can be converted into an open zwitterionic isomer MC, which is considered to interact with Ca2+ ions. Interestingly, Ca2+ and UV-light responsive programmable shape of the copolymer hydrogel can recover to its original form by immersing in pure water. Since its excellent metal ion and UV-light stimuli-responsive and mechanical properties, the hydrogel has potential applications in the field of soft actuators.

Cu-Sn shape-memory microwires were fabricated by a glass-coated melt spinning method. Effects of Sn content on the microstructure and mechanical property of microwires were investigated. The phase transforms from martensite to austenite with Sn content increasing from 14.0 atomic percent (at.%) to 16.5 at.%, and highly ordered intermetallic phase, δ, formed with higher Sn content. The fracture stress, σf, and the critical stress for martensitic transformation, σMs, increases with Sn content increasing. The mechanical property as well as superelasticity were improved greatly by high cooling rate of the glass-coated melt spinning method.

The Study proposes possible solution to enhance Password Authentication using Association Technique based on the Ecological theory of memory and data at the Presbyterian university College Ghana. The study used a deductive research approach and employed two empirical Studies using the non-probability sampling technique where few respondents were selected in categories out of the populace by means of openness in other to get similar categories of respondents with different age groups and education background. The two Empirical study also used a quasi-experimental approach which structure incorporate observation, experimental treatment and timing. The First empirical study carried out an investigation to identify existing Password authentication Technique used by End Users, as well as their behavior in password utilization through a self-completed questionnaires which was analyzed using SPSS version 21 . The Second empirical study was an experiment to compared three kinds of password constructions that is own set, modified dictionary, and association against one another to see which of them would be best meet the ecological theory of memory and data which aims at creating a secured password that is easy to recall. The computation and evaluation of password construction was done using My1login Password meter whiles Levenshtein Distance String Edit Software was also used to compute the memorability of all given password. Across-tabulation was then employed out of the experiment using SPSS version 21. The result from the analysis revealed that the majority of the respondents do have weak passwords and also have few passwords which they even end up sharing with families and friends and reuse it. This confirms statements made by researchers that human being is the weakest connection in information system securities. To maintain Confidentiality, Availability and Integrity of data, the study therefore recommended the use of the Association Password technique which makes it easier to develop a much secured password that is difficult to crack but easy remember.

Precipitation downscaling is widely employed for enhancing the resolution and accuracy of precipitation products from general circulation models (GCMs). In this study, we propose a novel statistical downscaling method to foster GCMs’ precipitation prediction resolution and accuracy for monsoon region. We develop a deep neural network composed of convolution and Long Short Term Memory (LSTM) recurrent module to estimate precipitation based on well-resolved atmospheric dynamical fields. The proposed model is compared against GCM precipitation product and classical downscaling methods in the Xiangjiang River Basin in South China. Results show considerable improvement compared to the ECMWF-Interim reanalysis precipitation. Also, the model outperforms benchmark downscaling approaches, including 1) quantile mapping, 2) support vector machine, and 3) convolutional neural network. To test the robustness of the model and its applicability in practical forecast, we apply the trained network for precipitation prediction forced by retrospective forecasts from ECMWF model. Compared to ECMWF precipitation forecast, our model makes better use of the resolved dynamical field for more accurate precipitation prediction at lead time from 1 day up to 2 weeks. This superiority decreases along forecast lead time, as GCM’s skill in predicting atmospheric dynamics being diminished by the chaotic effect. At last, we build a distributed hydrological model and force it with different sources of precipitation inputs. Hydrological simulation forced with the neural network precipitation estimation shows significant advantage over simulation forced with the original ERA-Interim precipitation (with NSE value increases from 0.06 to 0.64), and the performance is just slightly worse than the observed precipitation forced simulation (NSE=0.82). This further proves the value of the proposed downscaling method, and suggests its potential for hydrological forecasts.

In modern Commercial Off-The-Shelf (COTS) multicore systems, cores can produce several simultaneous memory requests. The processing of such requests over the memory controller negatively impacts the interference delay triggered by running parallel tasks on the platform. In this paper, we propose a software-based testing approach for analyzing memory interference delay, when cores are exposed to extensive read/write requests that access in parallel their Cache Coherent Interconnect. The hardware targeted in this work is the well-known LayerScape QorIQ LS2085A, which can be approached as a potential successor to the Freescale QorIQ P4080. The test analysis was conducted based on a bare-metal operating system that we developed to guarantee a deterministic execution environment at all time points. Our testing was accomplished using a set of carefully designed synthetic benchmarks as well as TACLeBench benchmarks.

The period of the COVID-19 pandemic resulted in a rapid development of innovative education methods, in particular using e-learning and remote work tools. The effects of this development are also post-pandemic changes in formal teaching regulations, in particular in higher education, allowing classes and lectures to be carried out with Blended Learning or Flipped Classroom methods. This paper provides information about a case study of implementing ICT technologies with elements of the mentioned methods in one of the subjects at a technical university. The implemented tools and solutions in the field of e-learning and interactivity are presented, along with information regarding their perception by students during two academic years in the post-COVID-19 period. The analysis of results of these information and student evaluations indicates their generally positive approach to such innovations in the educational path, and at the same time shows significant challenges for teachers to increase the attractiveness and effectiveness of the teaching process and the development of practical, technical skills of students.

This study presents a groundbreaking approach in the field of gaming AI, focusing on the classic game” Pacman” through the lens of DRL integrated with advanced optimization techniques. The core of the research involves adapting DRL models for” Pacman”, utilizing the ESO for hyper- parameter tuning. These novel adaptations significantly enhance the AI agent’s performance, demonstrating a remarkable improvement in adaptability, responsiveness, and efficiency within the game environment. A pivotal aspect of this research is the innovative integration of metaheuristic optimization techniques into the DRL framework, a first in the domain of Atari gaming AI. This integration has proven essential in fine-tuning the DRL models, leading to a more effective and dynamic gaming experience. The study thoroughly evaluates and compares the performance of these algorithms, providing empirical support for their effectiveness and setting a new benchmark in AI-driven game development. The implications of this research extend beyond gaming AI, opening up possibilities for future exploration in several directions. Expanding DRL models to other complex gaming environments, continuous algorithmic enhancements, real-time learning adaptations, and applying these principles to robotics and autonomous vehicles are examples. The research also emphasizes ethical and responsible AI use in gaming to address fairness and addiction issues.

We will apply Pascal’s hydrostatic pressure law to black holes and also to the Hubble sphere. Haug has recently demonstrated how hydrostatic pressure in water can be utilized to determine the Planck length. One can conceptualize the energy in the Hubble sphere as a type of superfluid, and if this is correct, then Blaise Pascal’s hydrostatic pressure formula may also be applicable to such a superfluid, even within the Hubble sphere. By employing the same method on the Hubble sphere and considering it as a Schwarzschild black hole with the critical Friedmann mass, we can estimate the Planck length based on its hypothetical hydrostatic pressure.

This research presents the Cross-Cultural Intelligent Language Learning System (CILS), a novel approach integrating Artificial Intelligence (AI) into language education to enhance cross-cultural communication. CILS utilizes advanced AI technologies to provide adaptive, personalized learning experiences that cater to the unique linguistic and cultural backgrounds of each learner. By dynamically adjusting content and methodology, CILS significantly improves linguistic proficiency and cultural understanding, essential for effective global interactions. The implementation of CILS in platforms such as Busuu and HelloTalk has demonstrated marked improvements in engagement and communication skills among learners. Empirical studies validate the system's effectiveness in real-world settings, showing enhanced learner performance and increased intercultural competence. Additionally, the Technology Acceptance Model (TAM) applied confirms that the usability and perceived usefulness of AI-driven systems strongly influence learner acceptance and sustained use. This study not only underscores the potential of AI in transforming language education but also highlights the critical role of cultural sensitivity in designing educational technologies.

The joint extraction of entities and relations is a critical task in information extraction, and its performance directly affects the performance of downstream tasks. However, existing joint extraction models based on deep learning exhibit weak processing capabilities for the phenomenon of multiple pronunciations of one character and multiple characters of one pronunciation when processing Chinese texts, resulting in performance loss. To address these issues, this paper introduces part-of-speech (POS) and pinyin features to aid the model in learning semantic features that are more contextually appropriate. A Chinese Joint Entity and Relation Extraction Model based on Progressive Contrastive Learning and Heterogeneous Feature Fusion is proposed (CJE-PCHF). During model training, an interactive fusion network based on progressive contrastive learning is employed to learn the dependencies between pinyin, POS, and semantic features. This guides the model in heterogeneous feature fusion, capturing higher-order semantic associations between heterogeneous features. On the commonly used DuIE evaluation dataset for joint extraction, this model achieved a significant improvement, with the F1 score increasing by 5.4% compared to the benchmark model CasRel.

Dementia, primarily caused by neurodegenerative diseases like Alzheimer’s disease (AD), affects millions worldwide, making detection and monitoring crucial. To enable these tasks, we propose encoding in-text pauses and filler words (i.e., “uh” and “um”) in text-based language models, and thoroughly evaluate their effect in performance. Additionally, we suggest using contrastive learning to improve performance in a multi-task framework. Our results demonstrated the effectiveness of our approaches in enhancing the model’s performance, achieving 87% accuracy and an 86% F1-score. Compared to the state-of-the-art, our approach has similar performance despite having significantly fewer parameters. This highlights the importance of pause and filler word encoding on the detection of dementia.

The future of intelligent manufacturing machines involves autonomous selection of process parameters to maximize productivity while maintaining quality within specified constraints. To effectively optimize process parameters, these machines need to adapt to existing uncertainties in the physical system. This paper proposes a novel framework and methodology for feedrate optimization that is based on a physics-informed data-driven digital twin with quantified uncertainty. The servo dynamics are modeled using a digital twin, which incorporates the known uncertainty in the physics-based models and predicts the distribution of contour error using a data-driven model that learns the unknown uncertainty on-the-fly by sensor measurements. Using the quantified uncertainty, the proposed feedrate optimization maximizes productivity while maintaining quality under desired servo error constraints and stringency (i.e., the tolerance for constraint violation under uncertainty) using a model predictive control framework. Experimental results obtained using a 3-axis desktop CNC machine tool and a desktop 3D printer demonstrate significant cycle time reductions of up to 38% and 17% respectively, while staying close to the error tolerances compared to the existing methods.

Building a widely distributed hotspot network is a very tedious task due to its complexity. Providing security, fully distributed network services, and cost-conscious impact are the major challenges behind this goal. To overcome these issues, we have presented a novel distributed hotspot network architecture with five layers that can provide large-scale hotspot coverage as an assimilated result. Our contributions to this new architecture highlight important aspects. First, scalability can be increased by including many Internet-of-Things (IoT) devices with sensors and Wi-Fi and/or LoraWAN connectivity modules. Second, hotspot owners can rent out their hotspots to create a distributed hotspot network in which the hotspots can act as an ordinary data gateway, a full-fledged hotspot miner, and a lightweight hotspot miner to earn crypto tokens as rewards for certain activities. Third, the advantages of Wi-Fi and LoraWAN can be seamlessly leveraged to achieve optimal coverage, higher network security, and suitable data transmission rate for transferring sensor data from IoT devices to remote application servers and users. Fourth, blockchain is used to enhance the decentralized behavior of the architecture presented here by providing immutability and independence from a centralized regulator and making the network architecture more reliable and transparent. The main feature of our paper is the use of the tau-computing paradigm along with hotspots to improve availability, Internet backhaul-agnostic network coverage, and synchronous update capability, and tau-aware leasing to strengthen and improve coverage. We also discuss the key challenges and future roadmap that require further investment and deployment.

Wireless Sensor Networks (WSNs) continue to provide essential services for various applications such as surveillance, data gathering, and data transmission from the hazardous environments to safer destinations. This has been enhanced by the energy-efficient routing protocols that are mostly designed for such purposes. Gateway-based Energy-Aware Multi-hop Routing protocol (MGEAR) is one of the homogenous routing schemes that was recently designed to more efficiently reduce the energy consumption of distant nodes. However, it has been found that the protocol has a high energy consumption rate, lower stability period, less data transmission to the Base station (BS). In this paper, an enhanced Heterogeneous Gateway-based Energy-Aware multi-hop routing protocol ( HMGEAR) is proposed. The proposed routing scheme is based on the introduction of heterogeneous nodes in the existing scheme, selection of the head based on the residual energy, introduction of multi-hop communication strategy in all the regions of the network, and implementation of energy hole elimination technique. Results show that the proposed routing scheme outperforms two existing ones.

Cervical cancer is a worldwide public health problem with a high rate of illness and mortality among women. In this study, we proposed a novel framework based on Faster RCNN-FPN ar-chitecture for the detection of abnormal cervical cells in cytology images from cancer screening test. We extended the Faster RCNN-FPN model by infusing deformable convolution layers into the feature pyramid network (FPN) to improve scalability. Furthermore, we introduced a global contextual aware module alongside the Region Proposal Network (RPN) to enhance the spatial correlation between the background and the foreground. Extensive experimentations with the proposed deformable and global context aware (DGCA) RCNN were carried out using the cer-vical image dataset of “Digital Human Body" Vision Challenge from the Alibaba Cloud TianChi Company. Performance evaluation based on the mean average precision (mAP) and receiver operating characteristic (ROC) curve has demonstrated considerable advantages of the proposed framework. Particularly, when combined with tagging of the negative image samples using tra-ditional computer-vision techniques, 6-9% increase in mAP has been achieved. The proposed DGCA-RCNN model has potential to become a clinically useful AI tool for automated detection of cervical cancer cells in whole slide images of Pap smear.