This research aimed to improve the interpretation of electrical resistivity (ER) results in concrete bridge decks by utilizing results from multiple nondestructive evaluations (NDE) techniques in machine learning algorithms. To achieve this, a parametric study was first conducted using numerical simulations to investigate the effect of various parameters on ER measurements, such as the degree of saturation, corrosion length, delamination depth, concrete cover, and the moisture condition of delamination. A data set from this study was used to build a machine-learning algorithm based on the Random Forest methodology. This algorithm was then implemented on data collected from a bridge deck in the BEAST® facility. The presented results demonstrate an improvement in the interpretation of ER measurements using data from other NDE technologies.

One of the critical problems in multiclass classification tasks is the imbalance of the dataset. This is especially true when using contemporary pre-trained neural networks, where, in fact, the last layers of the neural network are retrained. Therefore, the large datasets with highly unbalanced classes are not good for models’ training since the use of such a dataset leads to overfitting and, accordingly, poor metrics on test and validation datasets. In this paper the sensitivity to a dataset imbalance of Xception, ViT-384, ViT-224, VGG19, ResNet34, ResNet50, ResNet101, Inception_v3, DenseNet201, DenseNet161, DeIT was studied using a highly imbalanced dataset of 20,971 images sorted into 7 classes. It is shown that the best metrics were obtained when using a cropped dataset with augmentation of missing images in classes up to 15% of the initial number. So, the metrics can be increased by 2-6% compared to the metrics of the models on the initial unbalanced data set. Moreover, the metrics of the rare classes' classification also improved significantly – the TruePositive value can be increased by 0.3 and more. As result, the best approach to train considered networks on an initially unbalanced dataset was formulated.

Electroencephalography (EEG) signals are the primary source for discriminating the preictal from the interictal stage, enabling early warnings before the seizure onset. The epileptic seizure prediction models face significant challenges due to data scarcity, diversity, and privacy. This paper proposes a three-tier architecture for epileptic seizure prediction associated with the Federated Learning (FL) model that enhances the capability by utilizing the significant amount of seizure patterns from globally distributed patients with data privacy. The determination of the preictal state is influenced by global and local model-assisted decision-making by modeling the two-level edge layer. Integrating the Spiking Encoder (SE) with Graph Convolutional Neural Network (Spiking-GCNN) works as the local model trained using the bi-timescale approach. Each local model utilizes the aggregated seizure knowledge from the different medical centers through FL and determines the preictal probability in the coarse-grained personalization. The Adaptive Neuro-Fuzzy Inference System (ANFIS) is utilized in fine-grained personalization to recognize epileptic seizure patients by examining the outcomes of the FL model, heart rate variability features, and patient-specific clinical features. The proposed seizure prediction is evaluated using benchmark datasets by comparing them with the existing works to demonstrate the potential results.

A morphological feature estimation method is presented, that can be used to monitor fish from low contrast underwater images and videos. The fish orientation is classified in order to apply a shape alignment technique that is based on the Ensemble of Regression Trees machine learning method. Shape alignment allows the estimation of fish dimensions (length, height, mass) and the location of fish body parts of particular interest such as the eyes and gills. The developed system can be exploited both for fish monitoring in open sea as well as aquacultures where non-invasive, low cost morphological feature extraction is essential. Fish health can be assessed from malformations in body shape, the color of the eyes or the gills as well as the fish behavior. The proposed method can estimate the position of 18 landmarks with an accuracy of about 95% from low resolution and low contrast underwater images where the fish can be hardly distinguished from its background. Hardware acceleration can be applied at various stages of the proposed method for real time video processing. As a case study, the developed system has been trained and tested with several Mediterranean fish species in the category of seabream or similar: diplodous sargus annularis (white seabream), diplodus annularis seabream (spawn), oblada melanura (saddled seabream), pagrus pagrus (common seabream), etc. A large dataset with low resolution underwater videos and images has been created in the context of this work.

Advancements in technology have revolutionized communication on social media platforms, where reviews and comments greatly influence product selection. Current opinion mining methods predominantly focus on textual content, overlooking the rich information within customer-posted images, termed here as Multus-Medium. This research introduces an innovative deep learning approach, Multus Medium Opinion Mining (MMOM), capitalizing on both text and image data for comprehensive product review analysis. MMOM employs an integrated model of Bidirectional Long Short-Term Memory (BiLSTM) and embedded Convolutional Neural Network (CNN), incorporating architectures of GoogleNet and VGGNet, thus enabling efficient extraction and fusion of textual and visual features. This synergistic approach enables data collection, preprocessing, feature extraction, fusion strategy-based feature vector generation, and subsequent product recommendation. Performance evaluation on two diverse real-world datasets name as “flicker8k” and “t4sa”. These datasets show substantial improvement over existing methods. MMOM outperforms standard benchmark models, achieving an accuracy, F1 score and ROC over fliker8k are 90.38%, 88.75% and 93.08%, whereas for twitter dataset are 88.54%, 86.34%, and 92.26% respectively, the accuracy of purposed model is 7.34% and 9.54% higher than the other two mentioned techniques. These statistics highlight the robustness and applicability of MMOM across various domains. The compelling results underscore the potential of MMOM, providing a more holistic and precise approach to opinion mining in the era of social media product reviews. This research, product recommendation helps the customer to make purchasing decision. Last but not the least, the purposed scheme can further be expanded in any other sentiment task like hospital recommendation system, crop farming recommendation and medical diagnostic system etc.

Radiotherapy commonly utilizes CBCT for patient positioning and treatment monitoring. CBCT is deemed to be secure for patients, making it suitable for the delivery of fractional doses. However, limitations such as a narrow field of view, beam hardening, scattered radiation artifacts, and variability in pixel intensity hinder the direct use of raw CBCT for dose recalculation during treatment. To address this issue, reliable correction techniques are necessary to remove artifacts and remap pixel intensity into HU values. This study proposes a deep-learning framework for calibrating CBCT images acquired with narrow FOV systems and demonstrates its potential use in proton treatment planning updates. Cycle-consistent GAN processes raw CBCT to reduce scatter and remap HU. Monte Carlo simulation is used to generate CBCT scans, enabling the possibility to focus solely on the algorithm’s ability to reduce artifacts and cupping effects without considering intra-patient longitudinal variability and producing a fair comparison between planning CT and calibrated CBCT dosimetry. To showcase the viability of the approach using real-world data, experiments were also conducted using real CBCT. Tests were performed on a publicly available dataset of 40 patients who received ablative radiation therapy for pancreatic cancer. The simulated CBCT calibration led to a difference in proton dosimetry of less than 2%, compared to the planning CT. The potential toxicity effect on the organs at risk decreased from about 50% (uncalibrated) up the 2% (calibrated). The gamma pass rate at 3%/2mm produced an improvement of about 37% in replicating the prescribed dose before and after calibration (53.78% vs 90.26%). Real data also confirmed this with slightly inferior performances for the same criteria (65.36% vs 87.20%). These results may confirm that generative artificial intelligence brings the use of narrow FOV CBCT scans incrementally closer to clinical translation in proton therapy planning updates.

Malicious apps specifically aimed at the Android platform have increased in tandem with the proliferation of mobile devices. Malware is now so carefully written that it is difficult to detect. Due to the exponential growth in malware, manual methods of malware are increasingly ineffec-tive. Although prior writers have proposed numerous high-quality approaches, static and dy-namic assessments inherently necessitate intricate procedures. The obfuscation methods used by modern malware are incredibly complex and clever. As a result, it cannot be detected using only static malware analysis. As a result, this work presents a hybrid analysis approach, partially tai-lored for multiple-feature data, for identifying Android malware and classifying malware families to improve Android malware detection and classification. This paper offers a hybrid method that combines static and dynamic malware analysis to give a full view of the threat. Three distinct phases make up the framework proposed in this research. Normalization and feature extraction procedures are used in the first phase of pre-processing. Both static and dynamic features undergo feature selection in the second phase. Two feature selection strategies are proposed to choose the best subset of features to use for both static and dynamic features. The third phase involves ap-plying a newly proposed detection model to classify android apps; this model uses a neural net-work optimized with an improved version of HHO. Application of binary and multi-class classi-fication is used, with binary classification for benign and malware apps and multi-class classifica-tion for detecting malware categories and families. By utilizing the features gleaned from static and dynamic malware analysis, several machine-learning methods are used for malware classifi-cation. According to the results of the experiments, the hybrid approach improves the accuracy of detection and classification of Android malware compared to the scenario when considering static and dynamic information separately.

Analysing and understanding donor behaviour in Non-profit Organisations (NPOs) is challenging due to the lack of human and technical resources. Machine learning (ML) techniques can analyse and understand donor behaviour at a certain level; however, it remains to be seen how to build and design an Artificial Intelligence enabled Decision Support System (AI-enabled DSS) to analyse donor behaviour. Thus, this paper proposes an AI-enabled DSS conceptual design to analyse donor behaviour in NPOs. A conceptual design is created following a Design Science Research approach to evaluate an AI-enabled DSS's initial DPs and features to analyse donor behaviour in NPOs. The evaluation process of the conceptual design applied formative assessment through conducting interviews with stakeholders from NPOs. The interviews were conducted using the Appreciative Inquiry framework to facilitate the process of interviews. The results of analysis based on the interviews provide insightful information not only about the proposed conceptual design for an AI-enabled DSS, but also about what is required to analyse donor behaviour NPOs using DSS. Evaluating the conceptual design results recommend efficiency, effectiveness, flexibility, and useability in the requirements of the AI-enabled DSS. This research contributes to the design knowledge base of AI-enabled DSS for analysing donor behaviour in NPOs. Future research will combine theoretical components to introduce a practical AI-enabled DSS for analysing donor behaviour in NPOs. This research is limited to such analysis on donors who donate money or volunteer time for NPOs.

Highly-skilled migrants and refugees finding employment in low-skill vocations, despite professional qualifications and educational background, has become a global tendency, mainly due to the language barrier. Employment prospects for displaced communities are mostly decided by their knowledge of the sublanguage of the vocational domain they are interested in working. Common vocational domains include agriculture, cooking, crafting, construction, and hospitality. The increasing amount of user-generated content in wikis and social networks provides a valuable source of data for data mining, Natural Language Processing and machine learning applications. This paper extends the contribution of the authors’ previous research on automatic vocational domain identification by further analyzing the results of the machine learning experiments with the domain-specific textual data set, considering 2 research directions: a. predictions analysis and b. data balancing. Wrong predictions analysis and the features that contributed to misclassification, along with correct predictions analysis and the features that were the most dominant, contributed to the identification of a primary set of terms for the vocational domains. Data balancing techniques were applied on the data set to observe their impact on the performance of the classification model. A novel 4-step methodology is proposed in this paper for the first time, consisting of successive applications of SMOTE oversampling on imbalanced data. Data oversampling obtains better results than data undersampling in imbalanced data sets, while hybrid approaches perform reasonably well.

With the proliferating of video surveillance system deployment and related applications, real-time video analysis is very critical to achieve intelligent monitoring, autonomous driving, etc. It is non-trivial to achieve high accuracy and low latency video stream analysis through the traditional cloud computing. In this paper, we propose a non-orthogonal multiple access (NOMA) based edge real-time video analysis framework with one edge server (ES) and multiple user equipments (UEs). A cost minimization problem composed of delay, energy and accuracy is formulated to improve the QoE of UEs. In order to efficiently solve this problem, we propose the joint video frame resolution scaling, task offloading, and resource allocation algorithm based on the Deep Q-Learning Network (JVFRS-TO-RA-DQN), which effectively overcomes the sparsity of the single-layer reward function and accelerates the training convergence speed. JVFRS-TO-RA-DQN consists of two DQN networks to reduce the curse of dimension, which respectively select the offloading and resource allocation action, the resolution scaling action. Experimental results show that JVFRS-TO-RA-DQN can effectively reduce the cost of transmission and computation, and have better performance in convergence compared to other baseline.

As one of the fastest-growing new energy sources, wind power technology has attracted widespread attention from all over the world. In order to improve the quality of wind power generation, wind speed prediction is an indispensable task. In this paper, an error correction based Variational Mode Decomposition and Broad Learning System (VMD-BLS) hybrid model is proposed for wind speed prediction. First, the wind speed is decomposed into multiple components by the VMD algorithm, and then an ARMA model is established for each component to find the optimal number of sequence divisions. Second, the BLS model is used to predict each component, and the prediction results are summed to obtain the wind speed forecast value. However, in some traditional methods, there is always time lag, which will reduce the forecast accuracy. To deal with this, a novel error correction technique is developed by utilizing BLS. Through verification experiment with actual data, it proves that the proposed method can reduce the phenomenon of prediction lag, and can achieve higher prediction accuracy than traditional approaches, which shows our method’s effectiveness in practice.

Many problems in the fields of finance and actuarial science can be transformed into the problem of solving backward stochastic differential equations (BSDE) and partial differential equations (PDE) with jumps, which are often difficult to solve in high-dimensional cases. To solve this problem, this paper applies the deep learning algorithm to solve a class of high-dimensional nonlinear partial differential equations with jump terms and their corresponding backward stochastic differential equations (BSDE) with jump terms. Using the nonlinear Feynman-Kac formula, the problem of solving this kind of PDE is transformed into the problem of solving the corresponding backward stochastic differential equations with jump terms, and the numerical solution problem is turned into a stochastic control problem. At the same time, the gradient and jump process of the unknown solution are separately regarded as the strategy function and they are approximated respectively by using two multilayer neural networks as function approximators. Thus, deep learning-based method is used to overcome the “curse of dimensionality” caused by high-dimensional PDE with jump, and the numerical solution is obtained. In addition, this paper proposes a new optimization algorithm based on the existing neural network random optimization algorithm, and compares the results with the traditional optimization algorithm, and achieves good results. Finally, the proposed method is applied to three practical high-dimensional problems: Hamilton-Jacobi-Bellman equation, bond pricing under the jump Vasicek model and high-dimensional option pricing model with default risk. The proposed numerical method has obtained satisfactory accuracy and efficiency. The method has important application value and practical significance in investment decision-making, option pricing, insurance and other fields.

Education is one of the most important tools available to policymakers and non-governmental bodies to promote a change in the behavior of society and to address the climate crisis, in line with the 4^th and 13^th Sustainable Development Goals of the United Nations 2030 Agenda. Project-based learning (PBL) addresses real and global challenges and allows the academic and professional formation of students. As part of the reflection stage of the educational action research method using the Business Canvas Model (BMC), pedagogic deficiencies were identified in the PBL and a didactic proposal was elaborated to emulate the interaction of students with the ecosystems of society. A prototype for improving the management of organic manures as soil amendments was initially developed, to provide the students with a quick start on the first steps of the proposed project. In the 10 sessions designed for the PBL (Make it happen!), the students elaborate a more sophisticated artifact in response to the demands of potential clients, as per the outcomes of the primary market research (5^th session). Active teaching methods and tools, such as a modified template of the BMC with the Rumsfeld’s matrix, aid the metacognition of students and their competences development. In a double session of the PBL, the primary market research is organized with key stakeholders of the agroindustry to enquire about the feasibility of the implementation of the technological solution and the logistics at farm level. Finally, the evaluation relies on the suitability of the upgraded prototype to respond customers’ demands.

Based on a reflection on the tensions between play, education, and learning in early childhood, this article aims to identify and analyze the factors that limit or negatively condition the possibilities for play at school during the transition between Early Childhood Education and Primary Education in Chile. The study was conducted in four Chilean schools, with the Transition Levels of Chilean Early Childhood Education (children aged 4 and 5) and the first two levels of Primary Education (children aged 6 and 7). Based on an ethnographic approach, we combined 22 ethnographic observation days spread over two consecutive years and 59 interviews of various types with children, educators, and parents. The results show structural-material limitations on school play that mainly affect children in Primary Education. Beyond, factors associated with routines, indications, and statements governing functioning and participation in this level tend to limit or prevent play, often considered a "non-legitimate" activity. Conclusions highlight the potentialities that children's restricted or resisted play can present in terms of learning.

Landslide risk mitigation is limited by data scarcity. This could be improved using continuous landslide detection systems. In order to investigate which image types and machine learning (ML) models are most useful for landslide detection in a Norwegian setting, we compared the performance of five different ML models, for the Jølster case study (30-July-2019), in Western Norway. These included three globally pre-trained models; i) the Continuous Change Detection and Classification (CCDC) algorithm, ii) a combined k-means clustering and Random Forest classification model, and iii) a convolutional neural network (CNN), and two locally-trained models, including; iv) Classification and Regression Trees and v) a U-net CNN model. Images used included Sentinel-1, Sentinel-2, digital elevation model (DEM) and slope. The globally-trained models performed poorly in shadowed areas, and were all outperformed by the locally-trained models. A maximum Matthew’s correlation coefficient (MCC) score of 89% was achieved with model v, using combined Sentinel-1 and -2 images as input. This is one of the first attempts to apply deep-learning to detect landslides with both Sentinel-1 and -2 images. Using Sentinel-1 images only, the locally-trained deep-learning model significantly outperformed the conventional ML model. These findings contribute towards developing a national continuous monitoring system for landslides.

Background: MR image classification in datasets collected from multiple sources is complicated by inconsistent and missing DICOM metadata. Therefore, we aimed to establish a method for the efficient automatic classification of MR brain sequences. Methods: Deep convolutional neural networks (DCNN) were trained as one-vs-all classifiers to differentiate between six classes, T1 weighted (w), contrast-enhanced T1w, T2w, T2w-FLAIR, ADC, and SWI. Each classifier yields a probability, allowing threshold-based and relative probability assignment while excluding images with low probability (label: unknown, open-set recognition problem). Data from three high-grade glioma (HGG) cohorts was assessed; C1 (320 patients, 20101 MRI images) was used for training, while C2 (197, 11333) and C3 (256, 3522) were for testing. Two raters manually checked images through an interactive labeling tool. Finally, MR-Class' added value was evaluated via radiomics models' performance for progression-free survival (PFS) prediction in C2, utilizing the concordance index (C-I). Results: Approximately 10% of annotation errors were observed in each cohort between the DICOM series descriptions and the derived labels. MR-Class accuracy was 96.7% [95%-Cl: 95.8, 97.3] for C2 and 94.4% [93.6, 96.1] for C3. 620 images were misclassified; Manual assessment of those frequently showed motion artifacts or alterations of anatomy by large tumors. Implementation of MR-Class increased on average the PFS model C-I by 14.6% compared to a model trained without MR-Class. Conclusions: We provide a DCNN-based method for sequence classification of brain MR images and demonstrate its usability in two independent HGG datasets.

In recent times, voice assistants have become a part of our day-to-day lives, allowing information retrieval by voice synthesis, voice recognition, and natural language processing. These voice assistants can be found in many modern-day devices such as Apple, Amazon, Google, and Samsung. This project is primarily focused on Virtual Assistance in Natural Language Processing. Natural Language Processing is a form of AI that helps machines understand people and create feedback loops. This project will use deep learning to create a Voice Recognizer and use Commonvoice and data collected from the local community for model training using Google Colaboratory. After recognizing a command, the AI assistant will be able to perform the most suitable actions and then give a response. The motivation for this project comes from the race and gender bias that exists in many virtual assistants. The computer industry is primarily dominated by the male gender, and because of this, many of the products produced do not regard women. This bias has an impact on natural language processing. This project will be utilizing various open-source projects to implement machine learning algorithms and train the assistant algorithm to recognize different types of voices, accents, and dialects. Through this project, the goal to use voice data from underrepresented groups to build a voice assistant that can recognize voices regardless of gender, race, or accent. Increasing the representation of women in the computer industry is important for the future of the industry. By representing women in the initial study of voice assistants, it can be shown that females play a vital role in the development of this technology. In line with related work, this project will use first-hand data from the college population and middle-aged adults to train voice assistants to combat gender bias.

Lung cancer is the leading cause of cancer mortality worldwide, and it is urgently necessary to diagnose it as early as possible. Usually, the diagnostic process begins with a radiological examination which, when a possible tumour is present, is followed by a biopsy to extract tissue samples from the patient's lungs. Therefore, the purpose of this study is the development of an artificial intelligence algorithm that will analyse the Whole Slide Image (WSI) generated by the digitisation of the glass slides obtained from the extracted samples and detect if there is a tumour. The developed learning algorithms as well as the tested neural networks (NNs) were trained on a dataset composed of previously annotated WSI tiles, classified as Tumour or Non-Tumour. From these, four developed convolutional neural networks stood out and were selected to be compared with each other and with the tested NNs. When the best result of each of the developed architectures was compared to the highest result of the tested NNs, it was possible to denote that version 4 of CancerDetecNN achieved an average accuracy of 89.749 \% and an average loss of 0.220. Furthermore, the results for the four selected versions are in agreement with the results reported in the literature, however, the limited size of the given dataset must be considered. Given the results obtained, the fourth version has the potential to optimise the lung cancer diagnosis process.

Ever-increasing need for improving the livability of a city and improve outcomes for its residents, over the last decade, the adoption of technology to develop urbanised societies around the world has given rise to the need for developing smart cities. The speed at which the world population is growing, the use of Internet of Things in smart cities have really advanced the quality of life. One significant area of concern within the smart city framework is waste management. If the waste within a city is not adequately managed, then it leads to issues in the health of the citizens. Additionally, the waste management has such a high impact on the environmental footprint, hence the need to have a smart way of managing waste is of critical importance. Through our research, we analyse the challenges of waste management within a city to understand the impact of the problem on to the citizens and overall city operations. We then investigate ways in which we can solve these problems using the emerging technologies, such as the Internet of Things, to collect valuable data of large volumes arriving at an astronomical rate, then apply multi-agent deep reinforcement learning algorithms to harness the power of big data to extract meaningful information and actionable insights. We ingest data generated by our Internet of Things into our algorithm for three main purposes including providing the notifications to an external system, for example, a map navigation engine out of the scope for this project but a future extension for route optimisation and waste vehicle tracking; extracting and reporting the actionable insights from the underlying data; and consuming the extracted data for predictive forecasting to draw out the unknown patterns of waste fill levels within various geographical locations and again send out triggers and notification to external systems for example a waste collection authority who can efficiently schedule the waste collection vehicles and optimise the route. To achieve the above mentioned outcomes, we propose a framework that is agnostic of the hardware that it connects to and can effectively interface with a wide variety of hardware keeping a level of abstraction in the architecture.

Directed movement towards a target requires spatial working memory, including processing of sensory inputs and motivational drive. In a stimulus-driven, operant conditioning paradigm designed to train zebrafish, we present a pulse of light via LED’s and/or sounds via an underwater transducer. A webcam placed below a glass tank records fish swimming behavior. During operant conditioning, a fish must interrupt an infrared beam at one location to obtain a small food reward at the same or different location. A timing-gated interrupt activates robotic-arm and feeder stepper motors via custom software controlling a microprocessor (Arduino). “Ardulink”, a JAVA facility, implements Arduino-computer communication protocols. In this way, full automation of stimulus-conditioned directional swimming is achieved. Precise multi­day scheduling of training, including timing, location and intensity of stimulus parameters, and feeder control is accomplished via a user-friendly interface. Our training paradigm permits tracking of learning by monitoring, turning, location, response times and directional swimming of individual fish. This facilitates comparison of performance within and across a cohort of animals. We demonstrate the ability to train and test zebrafish using visual and auditory stimuli. Current methods used for associative conditioning often involve human intervention, which is labor intensive, stressful to animals, and introduces noise in the data. Our relatively simple yet flexible paradigm requires a simple apparatus and minimal human intervention. Our scheduling and control software and apparatus (NemoTrainer) can be used to screen neurologic drugs and test the effects of CRISPR­-based and optogenetic modification of neural circuits on sensation, locomotion, learning and memory.

Globally, seagrass meadows provide critical ecosystem services. However, seagrasses are globally degraded at an accelerated rate. The lack of information on seagrass spatial distribution and seagrass health status seriously hinders seagrass conservation and management. Therefore, this study proposes to combine remote sensing big data with a new hybrid machine learning model (RF-SWOA) to predict potential seagrass habitats. The multivariate remote sensing data is used to train the machine learning model, which can improve the prediction accuracy of the model. This study shows that a hybrid machine learning model (RF-SWOA) can predict potential seagrass habitats more accurately and effectively than traditional models. At the same time, it has been shown that the most important factors influencing the potential habitat of seagrass in the Hainan region were the distance from land (38.2%) and the depth of the ocean (25.9%). This paper provides a more accurate machine learning model approach for predicting the distribution of marine species, which can help develop seagrass conservation strategies to restore healthy seagrass ecosystems.

G protein-coupled receptors (GPCRs) are amongst the most pharmaceutically relevant and well-studied protein targets, yet unanswered questions in the field leave significant gaps in our understanding of their nuanced structure and function. 3D pharmacophore models are powerful computational tools in silico drug discovery, presenting myriad opportunities for the integration of GPCR structural biology and cheminformatics. This review highlights success stories in the application of 3D pharmacophore modeling to de novo drug design, discovery of biased and allosteric ligands, scaffold hopping, QSAR analysis, hit-to-lead optimization, GPCR de-orphanization, mechanistic understanding of GPCR pharmacology and elucidation of ligand-receptor interactions. Furthermore, advances in the incorporation of dynamics and machine learning will be highlighted. The review will analyze challenges in the field of GPCR drug discovery, detailing how 3D pharmacophore modeling can be used to address them. Finally, we will present opportunities afforded by 3D pharmacophore modeling in the advancement of our understanding and targeting of GPCRs.

Portable Document Format (PDF) files are one of the most universally used file types. This has fascinated hackers to develop methods to use these normally innocent PDF files to create security threats via infection vectors PDF files. This is usually realized by hiding embedded malicious code in the victims’ PDF documents to infect their machines. This, of course, results in PDF Malware and requires techniques to identify benign files from malicious files. Research studies indicated that machine-learning methods provide efficient detection techniques against such malware. In this paper, we present a new detection system that can analyze PDF documents in order to identify benign PFD files from malware PFD files. The proposed system makes use of the AdaBoost decision tree with optimal hyperparameters, which is trained and evaluated on a modern-inclusive dataset, viz. Evasive-PDFMal2022. The investigational assessment demonstrates a lightweight-accurate PDF detection system, achieving a 98.84% prediction accuracy with a short prediction interval of 2.174 μSec. To this end, the proposed model outperforms other state-of-the-art models in the same study area. Hence, the proposed system can be effectively utilized to uncover PDF malware at high detection performance and low detection overhead.

The steep rise in reinforcement learning (RL) in various applications in energy as well as the penetration of home automation in recent years are the motivation for this article. It surveys the use of RL in various home energy management system (HEMS) applications. There is a focus on deep neural network (DNN) models in RL. The article provides an overview of reinforcement learning. This is followed with discussions on state-of-the-art methods for value, policy, and actor–critic methods in deep reinforcement learning (DRL). In order to make the published literature in reinforcement learning more accessible to the HEMS community, verbal descriptions are accompanied with explanatory figures as well as mathematical expressions using standard machine learning terminology. Next, a detailed survey of how reinforcement learning is used in different HEMS domains is described. The survey also considers what kind of reinforcement learning algorithms are used in each HEMS application. It suggests that research in this direction is still in its infancy. Lastly, the article proposes four performance metrics to evaluate RL methods.

While thunderstorms can pose severe risks to property and life, forecasting remains challenging, even at short lead times, as these often arise in meta-stable atmospheric conditions. In this paper, we examine the question of how well we could perform short-term (up to 180min) forecasts using exclusively multi-spectral satellite images and past lighting events as data. We employ representation learning based on deep convolutional neural networks in an “end-to-end” fashion. Here, a crucial problem is handling the imbalance of the positive and negative classes appropriately in order to be able to obtain predictive results (which is not addressed by many previous machine-learning-based approaches). The resulting network outperforms previous methods based on physically-based features and optical flow methods (similar to operational prediction models) and generalizes across different years. A closer examination of the classifier performance over time and under masking of input data indicates that the learned model actually draws most information from structures in the visible spectrum, with infrared imaging sustaining some classification performance during the night.

The following article presents an analysis of the determinants of diabetes using a dataset containing the surveys of 2000 patients from the Frankfurt Hospital in Germany. The data were analyzed using the following models, namely: Tobit, Probit, Logit, Multinomial Logit, OLS, WLS with heteroskedasticity. The results show that the presence of diabetes is positively associated with "Pregnancies", "Glucose", "BMI", "Diabetes Pedigree Function", "Age" and negatively associated with "Blood Pressure". A cluster analysis is realized using the fuzzy c-Means algorithm optimized with the Elbow method and three clusters were found. Finally a confrontation among eight different machine learning algorithms is realized to select the best performing algorithm to predict the probability of patients to develop diabetes.

Objective: Radiomics and deep transfer learning are two popular technologies used to develop computer-aided detection and diadnosis (CAD) schemes of medical images. This study aims to investigate and compare advantages and potential limitations of applying these two technologies in developing CAD schemes. Methods: A relatively large and diverse retrospective dataset including 3,000 digital mammograms is assembled in which 1,496 images depict malignant lesions and 1,054 images depict benign lesions. Two CAD schemes are developed to classify breast lesions. The first scheme is developed using four steps namely, applying an adaptive multi-layer topographic region growing algorithm to segment lesions, computing initial radiomics features, applying a principal component algorithm to generate an optimal feature vector, and building a support vector machine classifier. The second CAD scheme is built based a pre-trained residual net architecture (ResNet50) as a transfer learning model to classify breast lesions. Both CAD schemes are trained and tested using a 10-fold cross-validation method. Several score fusion methods are also investigated to classify breast lesions. CAD classification performance is evaluated by the area under ROC curve (AUC). Results: ResNet50 model-based CAD scheme yields AUC = 0.85±0.02, which is significantly higher than radiomics feature-based CAD scheme with AUC = 0.77±0.02 (p < 0.01). Additionally, fusion of classification scores generated by two CAD schemes does not further improve classification performance. Conclusion: This study indicates that using deep transfer learning is more efficient to develop CAD schemes and enables to yield higher lesion classification performance than CAD schemes developed using radiomics-based technology.

A correct system design can be systematically obtained from a specification model of a real-time system that integrates hybrid measurements in a realistic industrial environment, this has been carried out through complete Matlab / Simulink / Stateflow models. However, there is a widespread interest in carrying out that modeling by resorting to Machine Learning models, which can be understood as Automated Machine Learning for Real-time systems that present some degree of hybridization. An induction motor controller which must be able to maintain a constant air flow through a filter is one of these systems and it is discussed in the paper as a study case of closed-loop control system. The article discusses a practical application of ML methods that demonstrates how to replace such closed loop in industrial control systems with a Simulink block generated from neural networks to show how the proposed procedure can be applied to derive complete hybrid system designs with artificial neural networks (ANN). In the proposed ANN-based method to design a real-time hybrid system with continuous and discrete components, we use a typical design of a neural network, in which we define the usual phases: training, validation, and testing. The generated output of the model is made up of reference variables values of the cyber-physical system, which represent the functional and dynamic aspects of model. They are used to feed Simulink/Stateflow blocks in the real target system.

Place-based education (PBE) and active learning are effective strategies for geoscience education. However, traditional PBE via field trips requires significant resources, time, physical abilities, and expertise of teachers. We provide an alternative PBE experience by showing how different kinds of geoscience videos can be spatially organized into one digital interactive virtual environment. Here, we present the Google Earth Geoscience Video Library (GEGVL) which uses Google Earth and location specific videos about Earth events to create a virtual PBE experience. Using Google Earth, GEGVL organizes place-based videos by locations and links pertinent non-place-based videos and allows users to roam the globe in search of geoscientific videos that are pertinent to them or their students. Currently GEGVL contains 150 videos organized into ten different geoscience disciplines: Plate Tectonics, Minerals, Structural Geology, Metamorphism, Magmatism, Hydrology, Environmental Science, Sedimentology, Paleontology, and Paleomagnetism. Despite stability challenges with Google Earth integration, results of user surveys among lower division undergraduates show that the design logic of GEGVL is promising virtual PBE organizer for interesting students in and helping them learn about Earth sciences.

Abstract: Ambulatory cancer centers face fluctuating patient demand and deploy specialized personnel who have variable availability. This undermines operational stability through misa-lignment of resources to patient needs, resulting in overscheduled clinics, budget deficits, and wait times exceeding provincial targets. We describe deployment of a Learning Health System framework for operational improvements within the entire ambulatory center. Known methods of value stream mapping, operations research and statistical process control were applied to achieve organizational high performance that is data-informed, agile and adaptive. We transitioned from a fixed template model by individual physician to a caseload management by disease site model that is realigned quarterly. We adapted a block schedule model for the ambulatory oncology clinic to align the regional demand for specialized services with optimized human and physical resources. We demonstrated improved utilization of clinical space, increased weekly consistency and im-proved distribution of activity across the workweek. Increased value, represented as the ratio of monthly encounters per nursing worked hours, and increased percentage of services delivered by full-time nurses were benefits realized in our cancer system. The creation of a data-informed demand capacity model enables application of predictive analytics and business intelligence tools that will further enhance clinical responsiveness..

We live in a complex world characterised by complex people, complex times, and complex social, technological, and ecological environments. There is clear evidence that governments are failing at most public matters. The recent COVID-19 pandemic is a high example of global governance failure both at preventing such pandemics and managing the COVID-19 pandemic. It is time that all of us take responsibility and look into ways of collaboratively improving the governance of public matters, our matters. While there are many reasons for government failures, we believe the lack of information availability is a fundamental reason that limits the government’s ability to act smartly and allows the lack of transparency to creep into policy and action leading to corruption and failure. To this end, this paper introduces the concept of deep journalism, a data-driven deep learning-based approach for discovering multi-perspective parameters related to a topic of interest. We build three datasets (a newspaper, a technology magazine, and a Web of Science dataset) and discover the academic, industrial, public, governance, and political parameters for the transportation sector as a case study to introduce deep journalism and our tool DeepJournal (Version 1.0) that implements our proposed approach. We elaborate on 89 transportation parameters and hundreds of dimensions reviewing 400 technical, academic, and news articles. The findings related to the multi-perspective view of transportation reported in this paper show that there are many important problems seen by the public that industry and academia seem to not place their focus on. On the other hand, academia produces much broader and deeper knowledge on the subject such as a wide range of pollutions affecting the people and planet do not get to reach the public eye. Our deep journalism approach could find the gaps and highlight them to the public and other stakeholders.

This research introduces Genus-Physiognomy-Ecosystem (GPE) mapping at a prefecture level through machine learning of multi-spectral and multi-temporal satellite images at 10m spatial resolution, and later integration of prefecture wise maps into country scale for dealing with 88 GPE types to be classified from a large size of training data involved in the research effectively. This research was made possible by harnessing entire archives of Level-2A product, Bottom of Atmosphere reflectance images collected by MultiSpectral Instruments onboard a constellation of two polar-orbiting Sentinel-2 mission satellites. The satellite images were pre-processed for cloud masking and monthly median composite images consisting of 10 multi-spectral bands and 7 spectral indexes were generated. The ground truth labels were extracted from extant vegetation survey maps by implementing systematic stratified sampling approach and noisy labels were dropped out for preparing a reliable ground truth database. Graphics Processing Unit (GPU) implementation of Gradient Boosting Decision Trees (GBDT) classifier was employed for classification of 88 GPE types from 204 satellite features. The classification accuracy computed with 25% test data varied from 65-81% in terms of F1-score across 48 prefectural regions. This research produced seamless maps of 88 GPE types first time at a country scale with an average 72% F1-score. In addition, mapping of solar panels and vegetation disturbance are added.

Classification and mapping of plant communities is an essential step for conservation and management of ecosystems and biodiversity. We adopt the Genus-Physiognomy-Ecosystem (GPE) system developed in previous study for satellite-based classification of plant communities. This paper assesses the potential of multi-spectral and multi-temporal images collected by Sentinel-2 satellites. This research was conducted in five representative study sites in a temperate region. It consists of 44 types of plant communities including a few land cover types as well. The plant community types were enumerated in the study sites and ground truth data were prepared with reference to extant vegetation surveys, visual interpretation of high-resolution images, and onsite field observations. We acquired all Sentinel-2 Level-1C product images available for the study sites between 2017-2019 and generated monthly median composite images consisting of ten spectral and twelve spectral-indices. Gradient Boosting Decision Trees (GBDT) classifier was employed as an efficient and distributed gradient boosting technique for the supervised classification of big datasets involved in the research. The cross-validation accuracy in terms of kappa coefficient varied from 87% in Oze site with 41 land cover and plant community types to 95% in Hakkoda site with 19 land cover and plant community types; with average performance of 91% across all sites. In addition, the resulting maps demonstrated a clear distribution of plant community types involved in all sites, highlighting the potential of Sentinel-2 multi-spectral and multi-temporal images with GPE classification system for operational and broad-scale mapping of land cover and plant communities.

Deep reinforcement learning (DRL) has achieved significant results in many Machine Learning (ML) benchmarks. In this short survey we provide an overview of DRL applied to trading on financial markets, including a short meta-analysis using Google Scholar, with an emphasis on using hierarchy for dividing the problem space as well as using model-based RL to learn a world model of the trading environment which can be used for prediction. In addition, multiple risk measures are defined and discussed, which not only provide a way of quantifying the performance of various algorithms, but they can also act as (dense) reward-shaping mechanisms for the agent. We discuss in detail the various state representations used for financial markets, which we consider critical for the success and efficiency of such DRL agents. The market in focus for this survey is the cryptocurrency market.

We investigate the power of time series analysis based on a variety of information-theoretic approaches from statistics (AIC, BIC) and machine learning (Minimum Message Length) - and we then compare their efficacy with traditional time series model and with hybrids involving deep learning. More specifically, we develop AIC, BIC and Minimum Message Length (MML) ARMA (autoregressive moving average) time series models - with this Bayesian information-theoretic MML ARMA modelling already being new work. We then study deep learning based algorithms in time series forecasting, using Long Short Term Memory (LSTM), and we then combine this with the ARMA modelling to produce a hybrid ARMA-LSTM prediction. Part of the purpose of the use of LSTM is to seek capture any hidden information in the residuals left from the traditional ARMA model. We show that MML not only outperforms earlier statistical approaches to ARMA modelling, but we further show that the hybrid MML ARMA-LSTM models outperform both ARMA models and LSTM models.

Apathy in patients with Parkinson's disease (PD) is one of the least studied manifestations of a wide range of neuropsychiatric disorders (PND). The frequency of apathy in PD, according to various researchers, is 17–80%. Structural and neurochemical changes associated with PD are considered as the leading pathophysiological factors of apathy. Possible general pathophysiological mechanisms of apathy and hypokinesia, depression, executive (frontal) cognitive functions, sleep disorders in PD are discussed. The basis of the pathophysiological commonality of apathy, hypokinesia, and executive functions is probably bilateral disturbances in the functional connections of the stratum and dorsolateral, medial parts of the prefrontal cortex. The combination of apathy and depression in PD may be due to dysfunction of the structures of the limbic system and the medial orbital prefrontal cortex responsible for motivational determined behavior. The variability of the relationship between apathy and hypokinesia, depression, cognitive impairments, sleep disorders at different stages of PD may be associated with the phenomenological heterogeneity of apathy.Apathy worsens the quality of life, makes a significant contribution to disorders of both household and social adaptation of PD patients. It is promising to study the possibility of correcting apathy using dopaminergic therapy. Against the background of the appointment of pramipexole (1.5-3.0 mg / day) to 20 patients with PD (middle stage, according to Hen-Yar-2.5) to correct movement disorders after 4-6 weeks of therapy, a statistically significant positive dynamics of apathy were noted. According to the total assessment of the scale of apathy SE Starkstein (AS). As a result of the study, no statistically significant correlation was found between the dynamics of the total apathy indicator and the dynamics of motor symptoms of PD according to the unified rating scale for assessing PD (“Motor functions”), which, we believe, indicates an independent effect of pramipexole therapy in relation to motivational disorders.

In order to be able to face competition, thriving corporations have to be compelled to maintain an awfully smart relationship with their existing customers and additionally to be able to anticipate their future wants. Thus, corporations do not target customers as teams, however they’re attempting to focus on them as individuals. However, to be able to use this information, corporations have to be compelled to use promoting automation tools. Marketing Automation was an idea first introduced in 2001 by John D.C. Little in his presentation at the 5th Invitational Choice Symposium UC Berkeley 2001. This survey paper assesses prominent research on Marketing Automation and suggests how it can be modified to adapt to the current marketing scenario.

One of the critical tools for early detection and subsequent evaluation of the incidence of lung diseases is chest radiography. At a time when the speed and reliability of results, especially for COVID-19 positive patients, is important, the development of applications that would facilitate the work of untrained staff involved in the evaluation is also crucial. Our model takes the form of a simple and intuitive application, into which you only need to upload X-rays: tens or hundreds at once. In just a few seconds, the physician will determine the patient's diagnosis, including the percentage accuracy of the estimate. While the original idea was a mere binary classifier that could tell if a patient was suffering from pneumonia or not, in this paper we present a model that distinguishes between a bacterial disease, a viral infection, or a finding caused by COVID-19. The aim of this research is to demonstrate whether pneumonia can be detected or even spatially localized using a uniform, supervised classification.

Aim. The purpose of the work was the development of a machine learning model for diagnosing the stage of liver fibrosis in patients with chronic viral hepatitis C according to the data of routine clinical examination. Materials and methods. A total of 1240 patients with chronic viral hepatitis C was examined. A set of data obtained from 689 patients balancing by the stage of liver fibrosis was used for developing and testing machine learning models. 9 routine clinical parameters were selected as the most important predictors for determining the likelihood of liver fibrosis the 3–4 stages presence: age, height, weight and body mass index of the patient, the number of platelets in the clinical blood test, levels of alanine transaminase, aspartate transaminase, gamma-glutamyltransferase, and total bilirubin in a biochemical blood test. Results. The accuracy of the developed method for determining the 3–4 stages of liver fibrosis in patients with chronic viral hepatitis C in comparison with the «gold standard» of diagnosis (liver biopsy) was 80.56% (95% CI: 69.53–88.94%), sensitivity — 66.67%, specificity — 94.44%. Conclusion. The developed method is an alternative to more expensive and geographically inaccessible studies. The method does not require the purchase of additional equipment or software, as well as additional laboratory tests, when used in real clinical practice. The introduction of the method into clinical practice can help to solve the problem of low material and territorial availability of diagnostic tests and allow determining the stage of liver fibrosis in patients with chronic viral hepatitis C.

This paper presents ensemble learning of multi-source satellite sensors dataset to obtain better predictive performance of the forest biomass. Spectral, spectral-indices, and spectral-textural features were generated from two optical satellite sensors, Landsat 8 Operational Land Imager (OLI) and Sentinel-2 Multispectral Instrument (MSI). In addition, two radar satellite sensors, Sentinel-1 C-band Synthetic Aperture Radar (CSAR), and Advanced Land Observing Satellite (ALOS-2) Phased Array type L-band Synthetic Aperture Radar (PALSAR-2) were utilized to generate backscattering and backscattering-textural features. The plot-wise above ground biomass data available from five forests in New England region were utilized. Ensemble learning of multi-source satellite sensors dataset was carried out by employing four machine learning regressors namely, Support Vector Machines (SVM), Random Forests (RF), Gradient Boosting (GB), and Multilayer Perceptron (MLP). A five-fold cross-validation method was used to evaluate predictive performance of the multi-source satellite sensors. The integration of multi-source satellite features, comprising of spectral, spectral-indices, backscattering, spectral-textural, and backscattering-textural information, through ensemble learning and cross-validation approach implemented in the research showed promising results (R² = 0.81, RMSE = 46.2 Mg/ha) for the estimation of plots-level forest biomass in New England region.

Mapping forest extent and forest cover classification are important for the assessment of forest resources in socio-economic as well as ecological terms. Novel developments in the availability of remotely sensed data, computational resources, and advances in areas of statistical learning have enabled fusion of multi-sensor data, often yielding superior classification results. Most former studies of nemoral forests fusing multi-sensor and multi-temporal data have been limited in spatial extent and typically to a simple classification of landscapes into major land cover classes. We hypothesize that multi-temporal, multi-censor data will have a specific strength in further classification of nemoral forest landscapes owing to the distinct seasonal patterns of the phenology of broadleaves. This study aimed to classify the Danish landscape into forest/non-forest and further into forest types (broadleaved/coniferous) and species groups, using a cloud-based approach based on multi-temporal Sentinel 1 and 2 data and machine learning (random forest) trained with National Forest Inventory (NFI) data. Mapping of non-forest and forest resulted in producer accuracies of 99% and 90 %, respectively. The mapping of forest types (broadleaf and conifer) within the forested area resulted in producer accuracies of 95% for conifer and 96% for broadleaf forest. Tree species groups were classified with producer accuracies ranging 34-74%. Species groups with coniferous species were the least confused whereas the broadleaf groups, especially Oak, had higher error rates. The results are applied in Danish National accounting of greenhouse gas emissions from forests, resource assessment and assessment of forest biodiversity potentials.

The progressive impairment analysis in gait from neurological diseases patients such as Hereditary Ataxias (HA) has been carried out using gait data collected with movement sensors. This research is focused on finding the minimum amount required of gait features to recognize efficiently and less intrusive way, HA patients based on data collected with iPhone movement sensors placed on the ankles from 14 HA patients and 14 healthy people. A twofold proposal is made , first a local minimum prominent peak criterion to find out the starting point of each stride, to get 10-stride window about which 56 spatial-temporal features are derived; second a search strategy based on Hill Climbing algorithm to reduce the number of gait features and sensors. The main results were the findings that with two gait patterns a 96% of classification accuracy was achieved by using K-Nearest Neighbors (KNN) and Multi-Layer Perceptron (MLP) algorithms, but in addition, MLP only right ankle sensor patterns were required which also allows to reduce the intrusion.

An accurate outbreak prediction of COVID-19 can successfully help to get insight into the spread and consequences of infectious diseases. Recently, machine learning (ML) based prediction models have been successfully employed for the prediction of the disease outbreak. The present study aimed to engage an artificial neural network-integrated by grey wolf optimizer for COVID-19 outbreak predictions by employing the Global dataset. Training and testing processes have been performed by time-series data related to January 22 to September 15, 2020 and validation has been performed by time-series data related to September 16 to October 15, 2020. Results have been evaluated by employing mean absolute percentage error (MAPE) and correlation coefficient (r) values. ANN-GWO provided a MAPE of 6.23, 13.15 and 11.4% for training, testing and validating phases, respectively. According to the results, the developed model could successfully cope with the prediction task.

The main purpose of this paper is to propose a novel optimization model with a new machine learning approach in the first section to achieve the best results in financial institutions in the second section. Since the constancy of efficacy derived from parametric and non-parametric is not significant, this paper provides a scientific assessment at the optimization section and proposes a novel combined parametric and non-parametric model which will be a new experiment in literature perception. A scientific assessment of banks based on a combination of the efficiency measurement method of CCR(Charnes, Cooper and Rhodes model) or CRS(Constant Return to Scale) BCC(Banker, Charnes, and Cooper model) or VRS (Variable Return to Scale) in Data Envelopment Analysis (DEA), as well as Stochastic Frontier Approach (SFA) for 65 banks during Feb to July 2020, are introduced. For analyzing the performance of the parametric and non-parametric approaches we have considered the linear regression and Unreplicated Linear Functional Relationship (ULFR). At the machine learning section, a novel four-layers data mining filtering pre-processes for selected supervised classification as well as unsupervised clustering algorithms to increase the accuracy and to remove unrelated attributes and data are applied. For the four kinds of preprocessing approaches of unsupervised attributes, supervised attributes, supervised instances, and unsupervised instances, we have chosen discretization, attribute selection, stratified remove folds, and resample filters respectively. Based on the nature of the suggested financial institution's dataset and attributes, the most appropriate preprocessing filter in each layer to achieve the highest performance is suggested. Finally, the superior bank, best performance model, and the most accurate algorithm are introduced. The results indicate that the bank number 56 is the superior bank. Among the proposed techniques, the novel recommended CVS compared with CCR-BCC and SFA models, has a more positive correlation with profit risk, and show a higher coefficient of determination values. Sequential Minimal Optimization(SMO) algorithm receives the highest accuracy in all four suggested filtering layers.

Due to the substantial growth of internet users and its spontaneous access via electronic devices, the amount of electronic contents is growing enormously in recent years through instant messaging, social networking posts, blogs, online portals, and other digital platforms. Unfortunately, the misapplication of technologies has boosted with this rapid growth of online content which leads to the rise in suspicious activities. People misuse the web media to disseminate malicious activity, perform the illegal movement, abuse other people, and publicize suspicious contents on the web. The suspicious contents usually available in the form of text, audio or video, whereas text contents have been used in most of the cases to perform suspicious activities. Thus, one of the most challenging issues for NLP researchers is to develop a system that can identify suspicious text efficiently from the specific contents. In this paper, a Machine Learning (ML)-based classification model is proposed (hereafter called STD) to classify Bengali text into non-suspicious and suspicious categories based on its original contents. A set of ML classifiers with various features has been used on our developed corpus, consisting of 7000 Bengali text documents where 5600 documents used for training and 1400 documents used for testing. The performance of the proposed system is compared with the human baseline and existing ML techniques. The SGD classifier `tf-idf’ with the combination of unigram and bigram features are used to achieve the highest accuracy of 84.57%.

IoT system becomes hot topic nowadays for smart home, IoT helps devices to communicate together without human intervention inside home, so it is offering many challenges. A new smart home IoT platform powered using electromagnetic energy harvesting is proposed in this paper. It contains a high gain transmitted antenna array and efficient circular polarized array rectenna system to harvest enough power from any direction to increase life time of the batteries used in IoT system. Optimized energy consumption, the software with adopting the Zigbee protocol of the sensor node and low power microcontroller are used to operate in lower power modes. The proposed system has an 84.6 days lifetime which is approximately 10 times the lifetime for similar system. On the other hand, the proposed power management circuit operated at 0.3 V DC to boost the voltage to ~3.7V from radio frequency energy harvesting and manage battery level to increase the batteries lifetime. A predictive indoor environment monitoring system is designed based on a novel hybrid system to provide a non-static plan, approve energy consumption and avoiding failure of sensor nodes in smart home.

The use of Hyperspectral (HS) and LiDAR acquisitions has a great potential to enhance mapping and monitoring practices of endangered grasslands habitats, beyond conventional botanical field surveys. In this study we assess the potentiality of Recursive Feature Elimination (RFE) in combination with Random Forest (RF) classification in extracting the main HS and LiDAR features needed to map selected Natura 2000 grasslands along Polish lowland river valleys, in particular alluvial meadows 6440, lowland hay meadows 6510 and xeric and calcareous grasslands 6120. We developed an automated RFE-RF system capable to combine the potentials of both techniques and applied it to multiple acquisitions. Several LiDAR-based products and different Spectral Indexes (SI) were computed and used as input in the system, with the aim of shedding light on the best-to-use features. Results showed a remarkable increase in classification accuracy when LiDAR and SI products are added to the HS dataset, strengthening in particular the importance of employing LiDAR in combination with HS. Using only the 24 optimal features selection generalized over the three study areas, strongly linked to the highly heterogeneous characteristics of the habitats and landscapes investigated, it was possible to achieve rather high classification results (K around 0.7-0.77 and habitats F1 accuracy around 0.8-0.85), indicating that the selected Natura 2000 meadows and dry grasslands habitats can be automatically mapped by airborne HS and LiDAR data. Similar approaches might be considered for future monitoring activities in the context of habitats protection and conservation

Breast cancer is a significant health issue across the world. Breast cancer is the most widely-diagnosed cancer in women; early-stage diagnosis of disease and therapies increase patient safety. This paper proposes a synthetic model set of features focused on the optimization of the genetic algorithm (CHFS-BOGA) to forecast breast cancer. This hybrid feature selection approach combines the advantages of three filter feature selection approaches with an optimize Genetic Algorithm (OGA) to select the best features to improve the performance of the classification process and scalability. We propose OGA by improving the initial population generating and genetic operators using the results of filter approaches as some prior information with using the C4.5 decision tree classifier as a fitness function instead of probability and random selection. The authors collected available updated data from Wisconsin UCI machine learning with a total of 569 rows and 32 columns. The dataset evaluated using an explorer set of weka data mining open-source software for the analysis purpose. The results show that the proposed hybrid feature selection approach significantly outperforms the single filter approaches and principal component analysis (PCA) for optimum feature selection. These characteristics are good indicators for the return prediction. The highest accuracy achieved with the proposed system before (CHFS-BOGA) using the support vector machine (SVM) classifiers was 97.3%. The highest accuracy after (CHFS-BOGA-SVM) was 98.25% on split 70.0% train, remainder test, and 100% on the full training set. Moreover, the receiver operating characteristic (ROC) curve was equal to 1.0. The results showed that the proposed (CHFS-BOGA-SVM) system was able to accurately classify the type of breast tumor, whether malignant or benign.

Feature Selection (FS) in data mining is one of the most challenging and most important activities in pattern recognition. The problem of choosing a feature is to find the most important subset of the main attributes in a specific domain, and its main purpose is removing additional or unrelated features, and ultimately improving the accuracy of the classification algorithms. As a result, the problem of FS can be considered as an optimization problem, and use metaheuristic algorithms to solve it. In this paper, a new hybrid model combining whale optimization algorithm (WOA) and flower pollination algorithm (FPA) is presented for the problem of FS based on the concept of Opposition based Learning (OBL) which name is HWOAFPA. In our proposed method, using natural processes of WOA and FPA, we tried to solve the problem of optimization of FS; and on the other hand, we used an OBL method to ensure the convergence rate and accuracy of the proposed algorithm. In fact, in the proposed method, WOA create solutions in their search space using the prey siege and encircling process, bubble invasion and search for prey methods, and try to improve the solutions for the FS problem; along with this algorithm, FPA improves the solution of the FS problem with two global and local search processes in an opposite space with the solutions of the WOA. In fact, we used all of the possible solutions to the FS problem from both the solution search space and the opposite of solution search space. To evaluate the performance of the proposed algorithm, experiments were carried out in two steps. In the first stage, the experiments were performed on 10 FS datasets from the UCI data repository. In the second step, we tried to test the performance of the proposed algorithm in terms of spam e-mails detection. The results obtained from the first step showed that the proposed algorithm, performed on 10 UCI datasets, was more successful in terms of the average size of selection and classification accuracy than other basic metaheuristic algorithms. Also, the results from the second step showed that the proposed algorithm which was run on the spam e-mail dataset, performed much more accurately than other similar algorithms in terms of accuracy of detecting spam e-mails.

Recent advancements in Software Defined Networking (SDN) makes it possible to overcome the management challenges of traditional network by logically centralizing control plane and decoupling it from forwarding plane. Through centralized controllers, SDN can prevent security breach, but it also brings in new threats and vulnerabilities. Central controller can be a single point of failure. Hence, flow-based anomaly detection system in OpenFlow Controller can secure SDN to a great extent. In this paper, we investigated two different approaches of flow-based intrusion detection system in OpenFlow Controller. The first of which is based on machine-learning algorithm where NSL-KDD dataset with feature selection ensures the accuracy of 82% with Random Forest classifier using Gain Ratio feature selection evaluator. In the later phase, the second approach is combined with Gated Recurrent Unit Long Short-Term Memory based intrusion detection model based on Deep Neural Network (DNN) where we applied an appropriate ANOVA F-Test and Recursive Feature Elimination feature selection method to improve the classifier performance and achieved an accuracy of 88%. Substantial experiments with comparative analysis clearly show that, deep learning would be a better choice for intrusion detection in OpenFlow Controller.

The classical approach to non-linear regression in physics, is to take a mathematical model describing the functional dependence of the dependent variable from a set of independent variables, and then, using non-linear fitting algorithms, extract the parameters used in the modeling. Particularly challenging are real systems, characterised by several additional influencing factors related to specific components, like electronics or optical parts. In such cases, to make the model reproduce the data, empirically determined terms are built-in the models to compensate for the impossibility of modeling things that are, by construction, impossible to model. A new approach to solve this issue is to use neural networks, particularly feed-forward architectures with a sufficient number of hidden layers and an appropriate number of output neurons, each responsible for predicting the desired variables. Unfortunately, feed-forward neural networks (FFNNs) usually perform less efficiently when applied to multi-dimensional regression problems, that is when they are required to predict simultaneously multiple variables that depend from the input dataset in fundamentally different ways. To address this problem, we propose multi-task learning (MTL) architectures. These are characterized by multiple branches of task-specific layers, which have as input the output of a common set of layers. To demonstrate the power of this approach for multi-dimensional regression, the method is applied to luminescence sensing. Here the MTL architecture allows predicting multiple parameters, the oxygen concentration and the temperature, from a single set of measurements.

Primary importance is devoted to Fault Detection and Diagnosis (FDI) of electrical machine and drive systems in modern industrial automation. The widespread use of Machine Learning techniques has made it possible to replace traditional motor fault detection techniques with more efficient solutions that are capable of early fault recognition by using large amounts of sensory data. However, the detection of concurrent failures is still a challenge in the presence of disturbing noises or when the multiple faults cause overlapping features. The contribution of this work is to propose a novel methodology using multi-label classification method for simultaneously diagnosing multiple faults and evaluating the fault severity under noisy conditions. Performance of various multi-label classification models are compared. Current and vibration signals are acquired under normal and fault conditions. The applicability of the proposed method is experimentally validated under diverse fault conditions such as unbalance and misalignment.

Evaporation is one of the main processes in the hydrological cycle, and it is one of the most critical factors in agricultural, hydrological, and meteorological studies. Due to the interactions of multiple climatic factors, the evaporation is a complex and nonlinear phenomenon; therefore, the data-based methods can be used to have precise estimations of it. In this regard, in the present study, Gaussian Process Regression (GPR), Nearest-Neighbor (IBK), Random Forest (RF) and Support Vector Regression (SVR) were used to estimate the pan evaporation (PE) in the meteorological stations of Golestan Province, Iran. For this purpose, meteorological data including PE, temperature (T), relative humidity (RH), wind speed (W) and sunny hours (S) collected from the Gonbad-e Kavus, Gorgan and Bandar Torkman stations from 2011 through 2017. The accuracy of the studied methods was determined using the statistical indices of Root Mean Squared Error (RMSE), correlation coefficient (R) and Mean Absolute Error (MAE). Furthermore, the Taylor charts utilized for evaluating the accuracy of the mentioned models. The outcome indicates that the optimum state of Gonbad-e Kavus, Gorgan and Bandar Torkman stations, Gaussian Process Regression (GPR) with the error values of 1.521, 1.244, and 1.254, the Nearest-Neighbor (IBK) with error values of 1.991, 1.775, and 1.577, Random Forest (RF) with error values of 1.614, 1.337, and 1.316, and Support Vector Regression (SVR) with error values of 1.55, 1.262, and 1.275, respectively, have more appropriate performances in estimating PE. It found that GPR for Gonbad-e Kavus Station with input parameters of T, W and S and GPR for Gorgan and Bandar Torkmen stations with input parameters of T, RH, W, and S had the most accurate performances and proposed for precise estimation of PE. Due to the high rate of evaporation in Iran and the lack of measurement instruments, the findings of the current study indicated that the PE values might be estimated with few easily measured meteorological parameters accurately.

It is difficult to capture the real-time online measurement data for biochemical oxygen demand (BOD) in wastewater treatment processes. An optimized extreme learning machine (ELM) based on an improved cuckoo search algorithm (ICS) is proposed in this paper for the design of soft BOD measurement model. In ICS-ELM, the input weights matrices of the extreme learning machine (ELM) and the threshold of the hidden layer are encoded as the cuckoo's nest locations. The best input weights matrices and threshold are obtained by using the strong global search ability of improved cuckoo search (ICS) algorithm. The optimal results can be used to improve the precision of forecasting based on less number of neurons of the hidden layer in ELM. Simulation results show that the soft sensor model has good real-time performance, high prediction accuracy and stronger generalization performance for BOD measurement of the effluent quality compared to other modeling methods such as back propagation (BP) network in most cases.

The aim of this article has been to evaluate the impact of a physical-sport education programme, based on the pedagogical model of Sport Education within the framework of quality Physical Education and approached from the field of social and emotional learning, on a set of psychological variables: subjective well-being (quality of life related to health, positive affect and negative affect); trait emotional intelligence and social anxiety. A total number of 113 Compulsory Secondary Education students were involved, aged 12 to 15 years old, 44 of whom belonged to the control group (CG) and 69 to the experimental group (EG). A quasiexperimental design of repeated pretest and posttest measures with the CG was used. The results obtained in this investigation revealed that the intervention programme caused significant improvements in the subjective well-being and the trait emotional intelligence for the EG. These findings reinforce the pedagogical efficiency of the programme with regards to the aim that has been set. Likewise, the findings also highlight the suitability and appropriateness in terms of innovative teaching proposals. In the same way, the results showed relevant empirical contributions in this given school context due to its psychological benefits and the encouragement of healthy living.

Reservoir computers (RCs) are a biology inspired computational framework for signal processing typically implemented using recurrent neural networks. Recent work has shown that Boolean networks (BN) can also be used as reservoirs. We analyze the performance of BN RCs, measuring their flexibility and identifying factors that determine effective approximation of Boolean functions that are applied in a sliding-window fashion over a binary signal, either non-recursively or recursively. We train and test BN RCs of different sizes, signal connectivity, and in-degree to approximate 3-bit, 5-bit and 3-bit recursive binary functions. We analyze how BN RC parameters and function average sensitivity, a measure of function smoothness, affect approximation accuracy as well as the spread of accuracies for a single reservoir. We found that approximation accuracy and reservoir flexibility are highly dependent on RC parameters. Overall, our results indicate that not all reservoirs are equally flexible and RC instantiation and training can be more efficient if this is taken into account. The optimum range of RC parameters opens up an angle of exploration for understanding how biological systems might be tuned to balance system restraints with processing capacity.

In recent years, online social networks have received important consideration in spatial modelling fields given the critical information that can be extracted from them for events in real time; one of the most latent issues is that regarding various natural disasters such as earthquakes. Although it is possible to retrieve data from these social networks with embedded geographic information provided by GPS, in many cases this is not possible. An alternative solution is to reconstruct specific locations using probabilistic language models, more specifically those based on Name Entity Recognition (NER), which extracts names from a user’s description about an event occurring in a specific place (e.g., a collapsed building on a specific avenue). In this work, we present a methodology to use twitter as a social sensor system for disasters. The methodology scores NER locations with a kernel density estimation function for different subtopics originating from a natural disaster and that maps them into a geographic space is proposed. The proposed methodology is evaluated with tweets related to the 2017 earthquake in Mexico.

Automatic garments design class identification for recommending the fashion trends is important nowadays because of the rapid growth of online shopping. By learning the properties of images efficiently, a machine can give better accuracy of classification. Several methods, based on Hand-Engineered feature coding exist for identifying garments design classes. But, most of the time, those methods do not help to achieve better results. Recently, Deep Convolutional Neural Networks (CNNs) have shown better performances for different object recognition. Deep CNN uses multiple levels of representation and abstraction that helps a machine to understand the types of data (images, sound, and text) more accurately. In this paper, we have applied deep CNN for identifying garments design classes. To evaluate the performances, we used two well-known CNN models AlexNet and VGGNet on two different datasets. We also propose a new CNN model based on AlexNet and found better results than existing state-of-the-art by a significant margin.

BackgroundThe present review summarizes the state-of-the-art of in silico methods and techniques that are the most useful in drug discovery, their relationship with data science, as well as the successful application of data science, machine learning (ML) and artificial intelligence (AI) applications. A meta-analysis of the various technologies available is furthermore proposed as a guideline for the non-expert, reader relative to the several subject areas is also discussed in this article. The scope of this meta-analysis is to rank the enlisted technologies by their field of applications and to depict the latter according to knowledge accessibility, from students to experts.Method The search strategy utilized for this review first produced a general collection of 900 papers without duplications, which were subsequently streamlined and divided into two independent collections: the top 300 most-cited papers of all time (since 2000) and the papers with the highest interest for a systematic review analysis (high-impact exciting papers). Results In Part 1, we discuss the most cited and quality 97 articles in these top 300 papers most relevant to the field of in silico drug discovery. The different disciplines are listed according to their industrial and economic incurred to society, independently from the “metric” results of how many new drug approvals (NDAs) each discipline has generated to date.ConclusionBig data, the ensemble of known items stored in publicly available databases, has improved our understanding of the many fates of a potential drug candidate during its development and even after its commercialization. Moreover, the combination of new screening techniques and “omics” with old drugs has led to a new paradigm in which the unknown knowledge of any biological molecule and its cellular structure, now plays an important role as a target for a series of yet-to-be-developed drugs: the chemical space. Furthermore, leveraging big data, data science, ML, and AI can revolutionize drug discovery by swiftly analyzing massive datasets, predicting efficacy and safety profiles, streamlining development, cutting costs, and boosting success rates for new drugs. AI also speeds up the search for promising drug candidates, advancing innovative therapies.

Decision sciences (DSC) involve studying complex dynamic systems and processes to aid informed choices subject to constraints in uncertain conditions. It integrates multidisciplinary methods, techniques, and strategies to evaluate decision engineering processes, identifying alternatives and providing insights towards enhancing prudent decision-making. This study analyzes the evolutionary trends and innovation in DSC education and research to uncover the transformations over the years. We employ the science mapping method, text analytics, and metadata from bibliographic databases to evaluate thematic and social structures. The results highlight data science methods, including data mining and business/learning analytics as essential components. The evolutionary trends in DSC education and research mirror the development in practice, including technological transformation, computer science advances, and engineering processes. Sustainable education through virtual/online learning also constitutes a significant component of scientific production. The evolutionary trends in DSC education and research highlight innovative pedagogical approaches and strategies, including computer simulation and games ('play and learn'). The current era witnessed generative artificial intelligence (GenAI) adoption (e.g., ChatGPT) in teaching, learning, and scholarly activities amidst challenges (academic integrity, plagiarism, intellectual property violations, and other ethical and legal issues). Future research will implement and integrate AI automatic detection systems to address some GenAI adoption challenges.

The unprecedented progress in Artificial Intelligence (AI), particularly in deep learning algorithms with ubiquitous internet connected smart devices, has created a high demand for AI computing on the edge devices. This review studied commercially available edge processors, and the processors that are still in industrial research stages. We categorized state-of-the-art edge processors based on the underlying architecture, such as dataflow, neuromorphic, and Processing in-Memory (PIM) architecture. The processors are analyzed based on their performance, chip area, energy efficiency, and application domains. The supported programming frameworks, model compression, data precision, and the CMOS fabrication process technology are discussed. Currently, most of the commercial edge processors utilize dataflow architectures. However, emerging non-von Neumann computing architectures have attracted the industry in recent years. Neuromorphic processors are highly efficient for performing computation with fewer synaptic operations, and several neuromorphic processors offer online training for secured and personalized AI applications. This review found that the PIM processors show significant energy efficiency and consume less power compared to dataflow and neuromorphic processors. The future direction of the industry would be to implement state-of-the-art deep learning algorithms in emerging non-Von Neumann computing paradigms for low power computing on the edge devices.

Digital recruitment systems have revolutionized the hiring paradigm, imparting exceptional efficiencies and extending the reach for both employers and job seekers. This investigation scrutinizes the efficacy of classical machine learning methodologies alongside advanced large language models (LLMs) in aligning resumes with job categories. Traditional matching techniques, such as Logistic Regression, Decision Trees, Naïve Bayes, and Support Vector Machines, are constrained by the necessity of manual feature extraction, limited feature representation, and performance degradation, particularly as dataset size escalates, rendering them less suitable for large-scale applications. Conversely, LLMs like GPT-4, GPT-3, and LLAMA, adeptly process unstructured textual content, capturing nuanced language and context with greater precision. We evaluate these methodologies utilizing two datasets comprising resumes and job descriptions to ascertain accuracy, efficiency, and scalability. Our results reveal that while conventional models excel with structured data, LLMs significantly enhance the interpretation and matching of intricate textual information. This study highlights the transformative potential of LLMs in recruitment, offering insights into their application and future research avenues.

Stress has various impacts on the health of human beings. Recent success in wearable sensor development, combined with advancements in deep learning to automatically detect features from raw data, opens several interesting applications related to detecting emotional states. Being able to accurately detect stress-related emotional arousal in an acute setting can positively impact the imminent health status of humans, i.e., through avoiding dangerous locations in an urban traffic setting. This work proposes an explainable deep learning methodology for the automatic detection of stress in physiological sensor data, recorded through a non-invasive wearable sensor device, the Empatica E4 wristband. We propose an Long-Short Term-Memory (LSTM) network, extended through a Deep Generative Ensemble of conditional GANs (LSTM DGE) , to deal with the low data regime of sparsely labeled sensor measurements. As explainability is often a main concern of deep learning models, we leverage Integrated Gradients (IG) to highlight the most essential features used by the model for prediction and to compare the results to state-of-the-art expert-based stress detection methodologies in terms of precision, recall and interpretability. Results show that our LSTM DGE outperforms the state-of-the-art algorithm by 3 percentage points in terms of recall, and 7.18 percentage points in terms of precision. More importantly, through the use of Integrated Gradients as a layer of explainability, we show that there is a strong overlap between model-derived stress features for electrodermal activity, and existing literature, which current state-of-the-art stress detection systems in medical research and psychology are based on.

Brain-to-brain communication (B2B-C) is rapidly expanding, integrating communication technology and neuroscience to enable direct neural data transfer between people. Nonetheless, because neural data is susceptible to noise, interference, and hostile attacks, guaranteeing the security and resilience of B2B-C systems continues to be difficult. This work aims to use Adversarial Neural Network Training (ANNT) to improve the security of B2B-C systems by using Steady-State Visually Evoked Potentials (SSVEP) EEG data. We use two large SSVEP datasets for a thorough analysis: Lee2019_SSVEP and Nakanishi2015. We use the Fast Gradient Sign Method (FGSM) to create adversarial instances and ANNT to train the model on clean and adversarially perturbed data. The system's accuracy and resilience are significantly improved by ANNT, as seen by the up to 17% increase in adversarial accuracy and the average 0.03 point improvement in the Area Under the Curve (AUC). This work demonstrates how ANNT may strengthen B2B-C systems against advanced cyberattacks, opening the door for dependable and safe neural communication technologies.

The integration of deep learning models into financial risk prediction and analysis has significantly transformed traditional approaches. While conventional quantitative methods often rely on simplistic metrics like maximum drawdown, the advent of deep learning necessitates a more nuanced evaluation, emphasizing the model's generalization ability, especially during market crises such as stock market crashes. This paper explores the critical aspects of evaluating deep learning models' risk control capabilities in finance, underscoring the importance of understanding both statistical metrics and generalization abilities, particularly in adverse market conditions. By examining deep learning models' performance in scenarios like stock market crashes and highlighting the significance of cross-validation techniques, this study aims to offer practitioners insights into constructing robust risk management systems. It advocates for a comprehensive approach integrating quantitative analysis with macroeconomic factors to enhance financial risk prediction and analysis in volatile markets. The experimentation reveals that different deep generative models excel in various aspects of financial time series analysis, with generative adversarial networks (GANs) demonstrating superior performance in predicting Value at Risk (VaR) and variational autoencoders (VAEs) excelling in return rate prediction. Moreover, integrating multiple models further enhances predictive performance, leveraging the strengths of each model to compensate for individual weaknesses. Overall, this paper underscores the potential and significance of deep generative models in financial time series analysis, offering a roadmap for improved risk management and decision-making in financial markets.

In an era marked by digitization and automation, extracting relevant information from business documents, like electricity invoices, remains a major challenge. To address this, we need to use machine-learning techniques to automate the process, reduce manual labor, and minimize errors. This work introduces a new method for extracting key values from this type of invoice, including customer personal data, bill breakdown, electricity consumption, or marketer data. We evaluate several machine learning techniques, such as Naive Bayes, Logistic Regression, Random Forests, or Support Vector Machines. Our approach uses a bag-of-words strategy and custom-designed features specifically tailored for electricity data. We tested the method on the IDSEM dataset, which includes 75.000 electricity invoices with eighty-six different fields. The method converts PDF invoices into text and processes each word separately using a context of eleven words. The results of our experiments indicate that Support Vector Machines and Random Forests perform exceptionally well in capturing numerous values with high precision. The study also explores the advantages of our custom features and evaluates the performance of the model on unseen documents. The precision obtained with Support Vector Machines is 91,86%, peaking at 98,47% for one document template. These results demonstrate the effectiveness of our method in accurately extracting key values from invoices.

Remote sensing technology is crucial for accurate rooftop detection, benefiting urban planning, disaster management, and solar resource estimation. This study employs Efficient Interactive Segmentation (EISEG) to enhance the efficiency of remote sensing image labeling, with a particular focus on rooftop detection. It is necessary to use modern technology because traditional manual labelling methods are labor-intensive and complicated. The study introduces a novel framework on deep learning semantic segmentation models, facilitating an efficient approach to rooftop identification using high-resolution UAV remote sensing datasets. Large dataset of labeled UAV rooftop building images, in which each superpixel region is assigned a binary label indicating rooftop presence. Advanced methods including Asymmetric Neural Network (ANN), Dual At-tention Network (DANet), PP-LiteSeg, and Deeplab3 are implemented for automatic rooftop detection due to their higher performance and advanced architectures. These models are executed on the Baidu deep learning platform PaddlePaddle, generating initial rooftop segmentation maps crucial for estimating photovoltaic resources. The ANN model emerges with the highest accuracy at 96%, followed by DANet at 95.09%, PP-LiteSeg at 94.54%, and Deeplab3 at 81.61%. The outcomes presenting efficient models for automated rooftop identification, and demonstrating the continuous need for improving deep learning techniques in smart and sustainable cities.

In recent years, advancements in brain science and neuroscience have significantly influenced the field of computer science, particularly in the domain of reinforcement learning (RL). Drawing insights from neurobiology and neuropsychology, researchers have leveraged these findings to develop novel mechanisms for understanding intelligent decision-making processes in the brain. Concurrently, the emergence of quantum computing has opened new frontiers in artificial intelligence, leading to the development of quantum machine learning (QML). This study introduces a novel model that integrates Quantum Spiking Neural Networks (QSNN) and Quantum Long Short-Term Memory (QLSTM) architectures, inspired by the complex workings of the human brain. Specifically designed for reinforcement learning tasks in energy-efficient environments, our approach progresses through two distinct stages mirroring sensory and memory systems. In the initial stage, analogous to the brain’s hypothalamus, low-level information is extracted to emulate sensory data processing patterns. Subsequently, resembling the hippocampus, this information is processed at a higher level, capturing and memorizing correlated patterns. We conduct a comparative analysis of our model against existing quantum models such as Quantum Neural Networks and their classical counterparts, elucidating its unique contributions. Through empirical results, we aim to underscore the effectiveness of our approach in optimizing energy consumption in practical scenarios.

The objectives of this paper are to investigate the tradeoffs between a physically constrained neural network and a deep, convolutional neural network and to design a combined ML approach ("VarioCNN"). Our solution is provided in the framework of a cyberinfrastructure that includes a newly designed ML software, GEOCLASS-image, modern high-resolution satellite image data sets (Maxar WorldView data) and instructions/descriptions that may facilitate solving similar spatial classification problems. Combining the advantages of the physically-driven connectionist-geostatistical classification method with those of an efficient CNN, VarioCNN provides a means for rapid and efficient extraction of complex geophysical information from submeter resolution satellite imagery. A retraining loop overcomes the difficulties of creating a labeled training data set. Computational analyses and developments are centered on a specific, but generalizable, geophysical problem: The classification of crevasse types that form during the surge of a glacier system. A surge is a glacial catastrophe, an acceleration of a glacier to typically 100-200 times its normal velocity. GEOCLASS-image is applied to study the current (2016-2024) surge in the Negribreen Glacier System, Svalbard. The geophysical result is a description of the structural evolution and expansion of the surge, based on crevasse types that capture ice deformation in six simplified classes.

Byers Peninsula is considered one of the largest ice-free areas in Maritime Antarctica. Since 2006, the Spanish Polar Program has taken part in a large number of environmental studies involving effects of climate changes in lives cycles, limnology and microbiology. Soils from maritime Antarctica are generally weakly developed and have chemical, physical and morphological characteristics strongly influenced by the parent material. However, biological activity during the short Antarctic summer promotes intense transference of nutrients and organic matter in areas occupied by different species of birds and marine mammals. To mapping and monitoring those areas with high biological occupation, could be very useful to have models of edaphic properties prepared from satellite images. In this approach, Deep Learning and Linear Regression models of soil properties and spectral indexes as explicative variables were performed. We training models of soil properties closely related to biological activity such as Dissolved Organic Carbon (DOC) and the iron fraction associated with organic matter (Fe). We tested the best approach to model the spatial distribution of DOC, Fe and pH by training models of Linear Regression and Deep Learning over Sentinel2 and WorldView2 images. The most robust models were used to track possible areas with ornithogenic soils as well as areas of the Byers Peninsula that could support the highest biological development.

Conventional cancer clinical trials can be time-consuming and expensive, often yielding results with limited applicability to real-world scenarios and presenting challenges for patient participation. Real-world data (RWD) studies offer a promising solution to address evidence gaps and provide essential information about the effects of cancer treatments in real-world settings. Defining RWD based on its original intent, which is the collection of data at the point of care for clinical purposes, can distinguish it from conventional clinical trial data. RWD can be generated using experimental designs that resemble those used in conventional clinical trials, but with several advantages, such as improved efficiency and a better balance between internal and external validity. RWD can support pharmacovigilance, insights into disease progression, and the development of external control groups. Prospective RWD collection enables evidence generation based on pragmatic clinical trials (PCTs) that support randomized study designs and expand clinical research to the point of care. To ensure the quality of real-world studies, it is crucial to implement auditable data abstraction methods and develop new incentives to capture clinically relevant data electronically at the point of care. The treatment landscape is constantly evolving, with the integration of front-line immune checkpoint inhibitors (ICIs), either alone or in combination with chemotherapy, affecting subsequent treatment lines. Real-world effectiveness and safety in underrepresented populations, such as the elderly, patients with poor performance status (PS), hepatitis, or human immunodeficiency virus-infected patients, are still largely unexplored. Similarly, the cost-effectiveness and sustainability of these innovative agents are important considerations in the real world.

Background: Renal cancers are among the top ten causes of cancer-specific mortality, of which the ccRCC subtype is responsible for most cases. The grading of ccRCC is important in determining tumour aggressiveness and clinical management. Objectives: The objectives of this research were to predict the WHO/ISUP grade of ccRCC pre-operatively and characterise the heterogeneity of tumour sub-regions using radiomics and ML models, including comparison with pre-operative biopsy-determined grading in a sub-group. Methods: Data were obtained from multiple institutions across two countries, including 391 patients with pathologically proven ccRCC. For analysis, the data were separated into four cohorts. Cohorts 1 and 2 included data from the respective institutions from the two countries, cohort 3 was the combined data from both cohort 1 and 2, and cohort 4 was a subset of cohort 1, for which both the biopsy and subsequent histology from resection (partial or total nephrectomy) were available. 3D image segmentation was carried out to derive a voxel of interest (VOI) mask. Radiomics features were then extracted from the contrast-enhanced images, and the data were normalised. The Pearson correlation coefficient and the XGBoost model were used to reduce the dimensionality of the features. Thereafter, 11 ML algorithms were implemented for the purpose of predicting the ccRCC grade and characterising the heterogeneity of sub-regions in the tumours. Results: For cohort 1, the 50% tumour core and 25% tumour periphery exhibited the best performance, with an average AUC of 77.9% and 78.6%, respectively. The 50% tumour core presented the highest performance in cohorts 2 and 3, with average AUC values of 87.6% and 76.9%, respectively. With the 25% periphery, cohort 4 showed AUC values of 95.0% and 80.0% for grade prediction when using internal and external validation, respectively, while biopsy histology had an AUC of 31.0% for the classification with the final grade of resection histology as a reference standard. The CatBoost classifier was the best for each of the four cohorts with an average AUC of 80.0%, 86.5%, 77.0% and 90.3% for cohorts 1, 2, 3 and 4 respectively. Conclusion: Radiomics signatures combined with ML have the potential to predict the WHO/ISUP grade of ccRCC with superior performance, when compared to pre-operative biopsy. Moreover, tumour sub-regions contain useful information that should be analysed independently when determining the tumour grade. Therefore, it is possible to distinguish the grade of ccRCC pre-operatively to improve patient care and management.

Machine learning models are increasingly being used in critical domains, but their complexity, lack of transparency, and poor interpretability remain problematic. Decision trees (DTs) and rule-based approaches are well-known examples of interpretable models, and numerous studies have investigated techniques for approximating tree ensembles using DTs or rule sets; however, tree ensemble approximators do not consider interpretability. These methods are known to generate three main types of rule sets: DT-based, unordered-based, and decision list-based. However, no known metric has been devised to distinguish and compare these rule sets. Therefore, the present study proposes an interpretability metric to allow comparisons of interpretability between different rule sets, such as decision list- and DT-based rule sets, and investigates the interpretability of the rules generated by the tree ensemble approximators. To provide new insights into the reasons why decision list-based and inspired classifiers do not work well for categorical datasets consisting of mainly nominal attributes, we compare objective metrics and rule sets generated by the tree ensemble approximators and the \textit{Recursive-Rule eXtraction algorithm (Re-RX) with J48graft}. The results indicated that \textit{Re-RX with J48graft} can handle categorical and numerical attributes separately, has simple rules, and achieves high interpretability, even when the number of rules is large.

Buildings are rapidly becoming more digitized, to a large extent due to developments in IoT. This will provide many opportunities but also a number of challenges. One of the central challenges in the process of digitizing buildings is the ability to monitor the building’s status effectively. This monitoring is essential for various services that rely on information about the presence and activities of individuals within different areas of the building. Occupancy information, including people counting, occupancy detection, location tracking, and activity detection, plays a vital role in the management of smart buildings. In this article, our primary focus is on the use of Passive Infrared (PIR) sensors for gathering occupancy information. PIR sensors are among the most widely used sensors for this purpose due to their consideration of privacy concerns, cost-effectiveness, and low processing complexity compared to many others. Despite numerous literature review articles in the field of occupancy information, there currently isn’t a specialized literature review dedicated to occupancy information derived specifically from PIR sensors.Therefore, this study analyzes articles that specifically explore the application of PIR sensors for occupancy information. This article provides a comprehensive literature review of PIR sensor technology from 2015 to 2023, with a focus on applications in people counting, activity detection, and localization (traking and location). It consolidates findings from a number of articles that have explored and enhanced the capabilities of PIR sensors in these interconnected domains. This review thoroughly examines the application of various techniques, machine learning algorithms, and configurations for PIR sensors in indoor building environments, emphasizing not only the data processing aspects but also their advantages, limitations, and efficacy in producing accurate occupancy information.These developments are crucial for improving building management systems in terms of energy efficiency, security, and user comfort, among other operational aspects.These developments are crucial for improving building management systems in terms of energy efficiency, security, and user comfort, among other operational aspects. The paper seeks to offer a thorough analysis of the present state and potential future advancements of PIR sensor technology in efficiently monitoring and understanding occupancy information by classifying and analyzing improvements in these domains.

Small peptides are an important component of the vertebrate immune system. They are important molecules for distinguishing proteins that originate in the host from proteins derived of a pathogenic organism, such as a virus or bacterium. Consequently, these peptides are central for the vertebrate host response to intracellular and extracellular pathogens. Computational models for prediction of these peptides have been based on a narrow sample of data with an emphasis on the position and chemical properties of the amino acids. In past literature, this approach has resulted in higher predictability than models that rely on the geometrical arrangement of atoms. However, protein structure data from experiment and theory are a source for building models at scale, and, therefore, knowledge on the role of small peptides and their immunogenicity in the vertebrate immune system. The following sections introduce procedures that contribute to theoretical prediction of peptides and role in immunogenicity. Lastly, deep learning is discussed as it applies to immunogenetics and the acceleration of knowledge by a capability for modeling the complexity of natural phenomena.

One of the needs of the teaching and learning processes is the lack of information during the process, such as the emotions of students. Emotions influence learning, the ability to process information and accurately understand what we are dealing with. They profoundly affect students’ academic engagement and performance. One new way of getting such information is monitoring students' emotions. This research aims to expose 6 groups of secondary school students to video recordings for further analysis and categorization of their emotions. A model of emotional recognition (ER) during classroom learning was designed, with a custom-made code, from recorded videos to images to identify faces, action units (AUs) and consequently the emotions of each of the students shown on the screen. In addition, the ER model was optimized, from detecting few students to many students during a class. Emotions were then analysed according to the academic year, subject, and comparing the emotions at the beginning and at the end of the class. The results indicate the presence of a variety of emotions in the classroom and we found significant differences in the presence of some emotions depending on the time of class, subject and academic year, although there are no clear patterns. We discussed how emotions influence students' academic performance, and we suggest future research focus on teachers utilizing tools like this to improve student well-being and performance.

Metabolic Syndrome (MetS) is a serious condition that significantly increases the risk of cardiovascular diseases and the severity of type 2 diabetes, also impacting on the development and evolution of other chronic diseases. Predicting metabolic syndrome is a complex task due to the multifactorial nature of this condition, which involves a combination of various risk factors such as abdominal obesity, insulin resistance, dyslipidemia, and hypertension. The complex interplay of these factors makes it challenging to predict the syndrome. Both genetic predisposition and environmental factors also contribute to the development of metabolic syndrome. Metabolic syndrome affects diverse populations with different ethnicities, lifestyles, and socioeconomic backgrounds. Prediction models, in addition, need to account for population heterogeneity and consider variations in risk factors across different groups. The present study analyzed data from participants in a cohort from Mexico City to identify key risk factors in men and women, addressing the presence of unbalanced data. In order to tackle the issues posed by data imbalance data, SMOTE and ADASYN were applied to assess significant differences in the selection of risk factors for MetS prediction. Random Forest and RPART models using ADASYN and SMOTE demonstrated better performance, achieving a balanced accuracy of approximately 87%. In women, they highlighted sleep quality, anxiety factors, tobacco consumption, and nutritional components. In the case of men, stronger associations were identified with the social development index and factors related to gout in parents.

This article explores the crucial task of estimating State of Charge (SOC) in Hybrid Electric Vehicles (HEVs) and examines the applicability of various regression models for this purpose. We delve into the strengths and limitations of Linear Regression, Support Vector Regression (SVR), and Neural Network Regression (NNR) in the context of SOC estimation. Linear regression provides a simple and interpretable baseline, SVR extends this to nonlinear relationships, while NNR emerges as a powerful tool with adaptive capabilities. The choice of model depends on factors such as data characteristics, interpretability, and computational resources. As the field evolves, the article advocates for a nuanced approach, possibly incorporating hybrid models, to achieve robust and accurate SOC estimation, contributing to the ongoing enhancement of HEV efficiency and sustainability.

The Centers for Disease Control and Prevention (CDC) indicates that individuals with prediabetes are significantly less likely to develop type 2 diabetes if they participate in a lifestyle change program that results in at least 5% weight loss and 150 minutes of physical activity per week. The CDC recognizes distance learning as an effective delivery mode for lifestyle change programs to prevent type 2 diabetes. The purpose of this study was to assess enrollment, engagement, and effectiveness of a type 2 diabetes prevention program (DPP) using synchronous distance technology. Eat Smart, Move More, Prevent Diabetes (ESMMPD) is an intensive 12-month DPP delivered using synchronous distance technology. Throughout 26 lessons, participants focused on healthy eating, physical activity, and mindfulness behaviors. Study findings showed a significant decrease in A1C (-0.24 p<.0001). Weight loss averaged 5.66% for those who completed the program. Based on the Wilcoxon signed-rank test, participants demonstrated statistically significant changes in self-reported confidence in their ability to perform all 18 health-promoting behaviors assessed (p<.0001). Participation in the program also resulted in the adoption of health promoting behaviors. A DPP using synchronous distance technology is an effective delivery mode to help participants adopt healthy behaviors, increase physical activity, and achieve the weight loss necessary to prevent or delay the onset of type 2 diabetes.

Accurate estimation of body fat percentage is essential for various health and fitness applications. Traditional methods for measuring body fat, such as underwater weighing, can be costly and inconvenient. In this study, we apply machine learning techniques to predict body fat percentage using easily accessible body measurements and data. The results highlight the effectiveness of regression models in estimating body fat, with Linear Regression, Ridge Regression, and Bayesian Ridge models achieving R-squared scores of approximately 74%, 73%, and 73%, respectively. These models provide a practical and cost-effective solution for individuals and professionals seeking reliable body fat estimates.

The work presented in this paper presents several novel findings from a comprehensive analysis of about 50,000 Tweets about online learning during COVID-19, posted on Twitter between November 9, 2021, and July 13, 2022. First, the results of sentiment analysis from VADER, Afinn, and TextBlob show that a higher percentage of these tweets were positive. The results of gender-specific sentiment analysis indicate that for positive tweets, negative tweets, and neutral tweets, between males and females, males posted a higher percentage of the tweets. Second, the results from subjectivity analysis show that the percentage of least opinionated, neutral opinionated, and highly opinionated tweets were 56.568%, 30.898%, and 12.534%, respectively. The gender-specific results for subjectivity analysis indicate that for each subjectivity class, males posted a higher percentage of tweets as compared to females. Third, toxicity detection was performed on the tweets to detect different categories of toxic content - toxicity, obscene, identity attack, insult, threat, and sexually explicit. The gender-specific analysis of the percentage of tweets posted by each gender in each of these categories revealed several novel insights. For instance, for the sexually explicit category, females posted a higher percentage of tweets as compared to males. Fourth, gender-specific tweeting patterns for each of these categories of toxic content were analyzed to understand the trends of the same. The results unraveled multiple paradigms of tweeting behavior, for instance, the intensity of obscene content in tweets about online learning by males and females has decreased since May 2022. Fifth, the average activity of males and females per month was calculated. The findings indicate that the average activity of females has been higher in all months as compared to males other than March 2022. Finally, country-specific tweeting patterns of males and females were also performed which presented multiple novel insights, for instance, in India a higher percentage of the tweets about online learning during COVID-19 were posted by males as compared to females.

In water scarcity regions, using data-driven approaches to predict groundwater level is challenging due to limited data availability. However, these regions have substantial water needs and require cost-effective groundwater utilization strategies. In this study, we use artificial intelligence to predict groundwater levels to provide guidance for drilling shallow boreholes for subsistence irrigation. The Bilate watershed, which is located in southern Ethiopia, was selected as the study area. This is typical of areas in Africa with high demand for water and limited availability of well data. Using a non-time-series database of 75 boreholes, machine learning models including multiple linear regression, multivariate adaptive regression spline, artificial neural networks, random forest regression, and gradient boosting regression (GBR) were constructed to predict the depth to the water table. 20 independent variables were considered in the models. GBR performed the best of the approaches with an average 0.77 R-squared value on testing data. Finally, a map of predicted water levels in the Bilate watershed was created based on the best model with water levels ranging from 1.6 to 245.9 meters. With the limited set of borehole data, the results show a clear signal that can provide guidance for borehole drilling decisions for sustainable irrigation with additional implications for drinking water.

The Internet of Things (IoT) was born from the fusion of virtual and physical space and became the initiator of many scientific fields. Economic sustainability is the key to further development and progress. Today, the need for electronic commerce has become an economic priority in the transition period between Industry 4.0 and Industry 5.0. Unlike mass production in Industry 4.0, customized production in Industry 5.0 should reach its true potential in vertically organized management and decision-making systems. The authors focused their research on e-commerce based on the three-level vertical IoT environment and the edge, fog, and cloud computing. The paper presents hands-on machine learning (ML) algorithms to facilitate the transition from a flat to a vertical e-commerce concept. The authors also propose practical ML algorithms for a few e-commerce types: consumer-consumer relationships and consumer-company-consumer relationships. These algorithms are mainly composed of convolution neural networks (CNN), natural language understanding (NLU) and sequential pattern mining (SPM), reinforcement learning (RL for agent training), algorithms for clicking on the item prediction, consumer behavior learning, etc. All presented concepts, algorithms, and models are described in detail.

In this study, deep neural network (DNN) and transfer learning (TL) techniques were employed to predict the viscous resistance and wake distribution based on the positions of flow control fins (FCFs) applied to containerships of various sizes. Both methods utilized data collected through Computational Fluid Dynamics (CFD) analysis. The position of the flow control fin (FCF) and hull-form information were utilized as input data, and the output data included viscous resistance coefficients and components of propeller axial velocity. The base DNN model was trained and validated using a source dataset from a 1000 TEU containership. Grid search cross-validation technique was employed to optimize the hyperparameters of the base DNN model. Then, transfer learning was applied to predict the viscous resistance and wake distribution for containerships of varying sizes. To enhance the accuracy of feature prediction with a limited amount of dataset, learning rate optimization was conducted. Transfer learning involves retraining and reconfiguring the base DNN model, and the accuracy was verified based on the fine-tuning method of the learning model. The results of this study can provide hull designers for containerships with performance evaluation information by predicting wake distribution, without relying on CFD analysis.

Hate Speech Detection in Arabic presents a multifaceted challenge due to the broad and diverse linguistic terrain. With its multiple dialects and rich cultural subtleties, Arabic requires particular measures to address hate speech online successfully. To address this issue, academics and developers have used natural language processing (NLP) methods and machine learning algorithms adapted to the complexities of Arabic text. However, many proposed methods were hampered by a lack of a comprehensive dataset/corpus of Arabic hate speech. In this research, we propose a novel multi-class public Arabic dataset comprised of 403,688 annotated tweets categorized as extremely positive, positive, neutral, or negative based on the presence of hate speech. Using our developed dataset, we additionally characterize the performance of multiple machine learning models for Hate speech identification in Arabic Jordanian dialect tweets. Specifically, the Word2Vec, TF-IDF, and AraBert text representation models have been applied to produce word vectors. With the help of these models, we can provide classification models with vectors representing text. After that, seven Machine learning classifiers have been evaluated: Support Vector Machine (SVM), Logistic Regression (LR), Naive Bays (NB), Random Forest (RF), AdaBoost (Ada), XGBoost (XGB), and CatBoost (CatB). In light of this, the experimental evaluation revealed that, in this challenging and unstructured setting, our gathered and annotated datasets were rather efficient and generated encouraging assessment outcomes. This will enable academics to delve further into this crucial field of study.

Continuous-variable quantum key distribution (CV-QKD) shows potential for the rapid development of an information-theoretic secure global communications network; however, the complexities of CV-QKD implementation remain a restrictive factor. Machine learning (ML) has recently shown promise in alleviating these complexities. ML has been applied to almost every stage of CV-QKD protocols, including ML-assisted phase error estimation, excess noise estimation, state discrimination, parameter estimation and optimization, key sifting, information reconciliation, and key rate estimation. This survey provides a comprehensive analysis of the current literature on ML-assisted CV-QKD. In addition, the survey compares the ML algorithms assisting CV-QKD with the traditional algorithms they aim to augment, as well as providing recommendations for future directions for ML-assisted CV-QKD research.

We describe a machine learning (ML) approach to process the signals collected from Covid-19 optical-based detector. Multilayer Perceptron (MLP) and Support Vector Machine (SVM) were used to process both raw data and feature engineering data, and high performances for qualitative detection of the SARS-CoV-2 virus with concentration down to 1 TCID50/ml has been achieved. Valid detection experiments contain 486 negative and 108 positive samples; and control experiments, in which biosensors without antibody functionalization were used to detect SARS-CoV-2, contains 36 negative samples and 732 positive samples. Data distribution patterns of the valid and control detection dataset, based on T-distributed Stochastic Neighbor Embedding (t-SNE), was used to study the distinguishability between positive and negative samples, and explain the ML prediction performances. This work demonstrates that ML can be a generalized effective approach to process signals and dataset of biosensors dependent on resonant modes as biosensing mechanism.

Detecting suicidal ideation in adults with major depression is crucial for timely intervention and prevention of self-harm. As suicide is influenced by various biological, socio-cultural and psychological factors, traditional screening methods have accuracy and efficiency limitations. In certain cultures, societal stigma and marginalization can compel individuals with depression to conceal their suffering. Such individuals often turn to online social media platforms and share their experiences with peers under the protection of anonymity. Our research explored the potential of machine learning detection of suicidal ideation among Romanian adults with major depression that contributed to a web-based depression support forum. A trained algorithm (C4.5 decision tree) analyzed 125 posts fed to on a free access online support forum over 5 years (2014 – 2018) and classified them based on suicidal ideation content. 32 texts (25%) were identified as having a high probability of suicidal ideation content. 65% of the authors were male, with a mean age of 36.7±10.3 years and an average duration of illness of 3.4±1.4 years. Texts indicating positive suicidal ideation were generally shorter and elicited more general responses but fewer professional responses compared to those without suicidal ideation content. The study's main limitations include the relatively small number of classified texts, the absence of prospective information and the lack of qualitative evaluation of the excerpts' content. As socio-demographic and linguistic actuarial results were comparable to data reported by real life studies, we may consider basic text mining techniques as a screening tool that is able to detect suicidal ideation in texts written in unstructured Romanian language.

We report on the use of quartz-enhanced photoacoustic spectroscopy (QEPAS) for multi-gas detection. Photo-acoustic (PA) spectra of mixtures of water (H2O), ammonia (NH3) and methane (CH4) were measured in the mid-infrared (MIR) wavelength range using a MIR (mid-infrared) optical parametric oscillator (OPO) light source. Highly overlapping absorption spectra is a common challenge for gas spectroscopy. To mitigate this, we use a partial least-squares regression (PLS) method to estimate the mixing ratio and concentrations of the individual gasses. The concentration range explored in the analysis varies from a few parts-per-million (ppm) to thousands of ppm. Spectra obtained from HITRAN and experimental single-molecule reference spectra of each of the molecular species were acquired and used as training data sets. These spectra were used to generate simulated spectra of the gas mixtures (linear combinations of the reference spectra). Here in this proof-of-concept experiment we demonstrate that after an absolute calibration of the QEPAS cell, the PLS analyses could be used to determine concentrations of single molecular species with a relative accuracy within a few % for mixtures of H2O, NH3 and CH4 and with an absolute sensitivity of approximately 300(±50) ppm/V, 50(±5) ppm/V and 5(±2) ppm/V for water, ammonia and methane, respectively. Thus, demonstrating that QEPAS assisted by PLS is a powerful approach to estimate concentrations of individual gas components with considerable spectral overlap, which is a typical scenario for real-life adoptions and applications.

The correct classification of defects originating from partial discharges (PD) in medium-voltage (MV) switchgears with air insulation (AIS) remains a challenging research topic for scientists worldwide. In this article, the authors simulated four possible defects occurring in the power industry, including one that is a simultaneous combination of two commonly ones. In addition, the correctness of the algorithm was checked by adding a classification class without any fault. The measurement signals were recorded with TEV sensors. The effectiveness of various hy-brid-connected neural networks was tested and discussed: GoogleNet and SqueezeNet based on spectrograms, SAE with FNN, 2D-CNN with LSTM, and hybrid AE combined with CNN and LSTM. The highest effectiveness – approximately 97% – was demonstrated by the GoogleNet and SqueezeNet networks. The research results are expected to form the basis for the development of a universal and wireless capacitive sensor for monitoring the level of PD in switchgears.

Automatic milking systems (AMSs) are among the earliest Precision Livestock Farming developments that have transformed dairy farming worldwide. This review aims to gather, evaluate, and summarize papers that focus on the use of modeling approaches in the context of AMS. We provided a review of 60 articles with a specific focus on cows’ health, production, and behavior/management. The most used modeling approach was Machine Learning (ML, present in 63% of the studies), followed by statistical analysis (14%), fuzzy algorithms (9%), deterministic mod-els (7%), and detection algorithms (7%). Most of the reviewed studies (82%) focused on the detection of cows' health, specifically mastitis, while only 11% were concerned with milk production. Accurate forecasting of dairy cow milk yield and knowledge on the deviation between expected and observed milk yields of individual cows would be beneficial in dairy cow management. Likewise, the study of cows’ behavior and the herd management in AMSs is under-explored (7%). Despite the increasing use of ML techniques in this field there is still a lack of a robust methodology for their application. In particular, we identified a significant gap in the systematic balancing of positive and negative classes for health prediction models.

Intelligent systems are increasingly present in various areas of society, gaining special relevance in healthcare environments. In this work, grounded on previous developments proposed by the authors, the evolution and improvement of a novel intelligent system focused on the diagnosis of obstructive sleep apnea (OSA) is addressed. To do this, starting from two packages of information of a heterogeneous nature, and deploying a set of Machine Learning classification algorithms, focused each of them on different levels of the apnea-hypopnea index (AHI), as well as a set of cascaded expert systems, it is possible to obtain a series of risk metric pairs (Statistical Risk, Symbolic Risk) for each AHI level, understood as a warning forecast associated with the early detection of the pathology. The risk indicators of each pair are subsequently aggregated by means of a symbolic inference system, whose knowledge base was determined using the automatic rule generation approach proposed by Wang and Mendel. At the output of each inference system, a risk indicator is obtained for each AHI level, the Apnea Risk, whose interpretation makes it possible to discriminate between patients who could suffer OSA and those who do not, as well as to generate the appropriate recommendations. For the initial tests of the system, the design and development of a specific software artifact was carried out using data from 4,400 patients from the Álvaro Cunqueiro Hospital in Vigo, obtaining when applied to the test set AUC values within the range 0.74–0.88, which invites optimism and points to the benefits expected from the architecture of the proposed intelligent system.

The timely diagnosis of defects at their incipient stage of formation is crucial to extend the life-cycle of technical appliances. This is the case of mechanical-related stress, either due to long aging degradation processes (e.g., corrosion) or in-operation forces (e.g., impact events), which might provoke detrimental damages, such as cracks, disbonding or delaminations, most commonly followed by the release of acoustic energy. The localization of these sources can be successfully fulfilled via adoption of Acoustic Emission (AE)-based inspection techniques through the computation of the Time of Arrival (ToA), namely the time at which the induced mechanical wave released at the occurrence of the acoustic event arrives to the acquisition unit. However, the accurate estimation of the ToA may be hampered by poor Signal-to-Noise ratios (SNRs). In these conditions, standard statistical methods typically fail. In this work, two alternative Deep Learning methods are proposed for ToA retrieval, namely a Dilated Convolutional Neural Network (DilCNN) and a Capsule Neural Network for ToA (CapsToA). These methods have the additional benefit of being portable on resource-constrained microprocessors. Their performance has been extensively studied on both synthetic and experimental data, focusing on the problem of ToA identification for the case of a metallic plate. Results show that the two novel methods can achieve localization errors which are up to 70% more precise than those yielded by conventional strategies, even when the SNR is severely compromised (i.e., down to 2 dB). Moreover, DilCNN and CapsNet have been implemented in a tiny machine learning environment and then deployed on microcontroller units, showing a negligible loss of performance with respect to offline realizations.

The nursing home (NH) population becomes increasingly frail, suffering several chronic ill-nesses, high symptom severity, and short remaining lifespan after admission; all this requires skilled, well-organized professional care. Little is known about how NH managers influence the caring and learning environment (CLE) to ensure competencies in meeting NH patients’ needs. The aim of this study is to explore how NH managers influence the CLE to provide basic nursing education for students and apprentices, in order to improve it. This study applies a qualitative design, using multiple methods and focusing on NHs as a context involving complex adaptive systems and on basic nursing as a complex issue. NH managers express a constant struggle to keep workloads manageable, and NHs come across as exhausted organizations with little surplus. Both managers and staff look for ways to execute the work with as little effort as pos-sible and mainly stick to well-established routines. Not participating directly in either daily caring or placement learning, NH managers influence the CLE indirectly through taming and coping strategies, largely using taming strategies that lead to serious unintended outcomes. Coping strategies involve leading collaborative processes in holding environments that are feasible with their workload and roles as managers.

In a complex working environment, the fault signal of the gearbox is greatly affected by the outside world, and fault feature recognition is difficult, so the fault diagnosis accuracy is difficult to meet the expected requirements. To solve this problem, this paper proposes a gearbox fault diagnosis method based on an optimized stacked denoising auto encoder (SDAE) and kernel extreme learning machine (KELM). Firstly, the Particle Swarm Optimization algorithm in Adaptive Weight (SAPSO) was adopted to optimize the SDAE network structure, and the number of hidden layer nodes, learning rate, noise addition ratio and iteration times were adaptively obtained to make SDAE obtain the best network structure. Then, the best SDAE network structure was used to extract the deep feature information of weak faults in the original signal. Finally, the extracted fault features are fed into KELM for fault classification. Experimental results show that, compared with existing commonly used methods of fault diagnosis, the fault diagnosis model proposed in this paper can reduce the influence of noise in the original signal can better learn the deep-level features in the original signal and has higher diagnosis accuracy, faster diagnosis speed and good generalization in fault diagnosis.

This paper presents a proposal for a non-isolated bidirectional converter (NIBC) controlled by a deep neural network (DNN) to enable vehicle-to-vehicle (V2V) and vehicle-to-grid (V2G) charging, which contributes to the development of more efficient and sustainable transportation and energy systems. The DNN controller manages power flow in both directions, making it possible to charge electric vehicles (EVs) and discharge power from EVs to the grid with improved efficiency and performance compared to traditional control methods. The non-isolated topology used in this proposal offers several benefits, including reduced cost, smaller size, and higher efficiency. To train the DNN controller, a large dataset of simulations was used, and the results were validated with a hardware setup. The real-time performance of the DNN controller was compared to a proportional-integral (PI) based controller through simulated results. The findings of the study show that the DNN controller outperforms traditional PI controllers.

United Nations Framework Convention on Climate Change (UNFCCC) has recently established the Reducing Emissions from Deforestation and forest Degradation (REDD+) program that requires countries to report their carbon emissions and sink estimates through national greenhouse gas inventories (NGHGI). Thus, developing automatic systems capable of estimating the carbon absorbed by forests without in-situ observation becomes essential. To support this important need, in this work we introduce ReUse, a simple but effective deep-learning approach to estimate the carbon absorbed by forest areas based on remote sensing. The novelty of the proposed method is in the use of the public above-ground biomass (AGB) data from the European Space Agency's Climate Change Initiative Biomass project as ground truth to estimate the carbon sequestration capacity of any portion of land on Earth using Sentinel-2 images and a pixel-wise Regressive UNet. The approach has been compared to two literature proposals, using a private dataset and human-engineered features. The results show a greater generalization ability of the proposed approach, with a decrease in Mean Absolute Error and Root Mean Squared Error, respectively, of 16.9 and 14.3 in the area of Vietnam and 4.7 and 5.1 in the area of Myanmar over the runner-up. Finally, as a case study, we reported an analysis made for the Astroni area, a nature reserve located near the metropolitan area of Naples in southern Italy, struck by a large fire, producing predictions consistent with values found by experts in the field. These results further support the use of such an approach for the early detection of AGB variations, both in urban and rural areas.

Prostate cancer (PC) is the most frequently diagnosed non-skin cancer in the world. Previous studies showed that genomic alterations represent the most common mechanism for molecular alterations that cause the development and progression of PC. Great efforts have been done to identify common protein-coding genetic variations; however, the impact of non-coding variations including regulatory genetic variants is not still well understood. To gain an understanding of the functional impact of genetic variants, particularly, regulatory variants in PC, we developed an integrative pipeline (AGV) that used whole genome/exome sequences, GWAS SNPs, chromosome conformation capture data, and ChIP-Seq signals to investigate the potential impact of genomic variants on the underlying target genes in PC. We identified 646 putative regulatory variants, of which 30 of them significantly altered the expression of at least one protein-coding gene. Our analysis of chromatin interactions data (Hi-C) revealed that the 30 putative regulatory variants may affect 131 coding and non-coding genes. Interestingly, our study showed the 131 protein-coding genes are involved in disease-related pathways including Reactome and MSigDB in which for most of them targeted treatment options are currently available. Together, our results provide a comprehensive map of genomic variants in PC and revealed their potential contribution to prostate cancer progression and development.

In this paper, we consider a reconfigurable intelligent surface (RIS)-assisted integrated satellite-high altitude platform-terrestrial networks (IS-HAP-TNs) that can improve network performance by exploiting HAP's stability and RIS's reflection. Specifically, the reflector RIS is installed on the side of HAP to reflect signals from the multiple ground user equipments (UEs) to the satellite. To aim at maximising system sum rate, we jointly optimize the transmit beamforming matrix at the ground UEs and RIS phase shift matrix. Due to the limitation of the unit modulus of the RIS reflective elements constraint, the combinatorial optimization problem is difficult to tackle it effectively by traditional solving methods. Based on this, this paper studies deep reinforcement learning (DRL) algorithm to achieve online decision making for this joint optimization problem. In addition, it is verified through simulation experiments that the proposed DRL algorithm outperforms the standard scheme in terms of system performance and execution time, and higher computing speed, making real-time decision making truly feasible。

An adaptive deep neural network is used in an inverse system identification setting to approximate the inverse of a nonlinear plant with the aim of constituting the plant controller by copying to the latter the weights and architecture of the converging deep neural network. This deep learning (DL) approach to the adaptive inverse control (AIC) problem is shown to outperform adaptive filtering techniques and algorithms normally used in adaptive control, especially when the plant is nonlinear. The deeper the controller the better the inverse function approximation, provided that the nonlinear plant have an inverse and that this inverse can be approximated. Simulation results prove the feasibility of this DL-based adaptive inverse control scheme. The DL-based AIC system is robust to parameter change of the nonlinear plant in that, under such change, the plant output reassumes the value of the reference signal considerably faster than with the adaptive filter counterpart of the deep neural network. Settling times and rise times of the step response are shown to improve in the DL-based AIC system.