Search

• A model to explore the multiphysics characteristic of semiconductors is presented. • The model determines the thermal and mechanical properties of complex patterns. • Results show a strong correlation between thermal and mechanical properties. • Dielectric bands asymmetrically affect thermal and mechanical behavior. • Machine learning can predict one property from another. As semiconductor performance improves through advanced package designs, it becomes important to consider both thermal and mechanical properties. Better understanding their relationship enhances system design and optimization. This study has introduced a numerical method that takes into account both thermal and mechanical fluxes to construct thermal and mechanical property maps for practical application in semiconductor engineering. Furthermore, this paper investigated the relationship between the two properties using the constructed property maps in commercially available semiconductor packages. Owing to the complexity of packaging design patterns, a coupled isoparametric mapping and machine learning (ML) method was introduced to investigate their effects. The model then determines and investigates the anisotropic equivalent thermal and mechanical properties of the commercialized semiconductor packages with complex pattern designs, according to the package materials, volume fractions of each material, and design patterns. This approach pursues more sophistication and practicality compared to simplified composite structure property evaluation models. Additionally, all processes in the algorithm are automated based on ML methods, making them practically applicable in the semiconductor industry. The study shows that there is a strong correlation between the thermal and mechanical characteristics in the complex package patterns. This relationship was able to form a fairly clear category based on the shape of the dielectric band because the dielectric band had significantly different effects on the thermal and mechanical fluxes. The study discussed the physical implications of the similarities and differences between the two behaviors and validated the results of the equivalent properties through finite element (FE) analysis. Finally, the study cross-validates the relationship by showing that information from one flux behavior can be used to predict the other based on the ML method. Based on the results, this paper can provide a better understanding of thermal and mechanical fluxes in semiconductor package patterns for package design and optimization. [ABSTRACT FROM AUTHOR]

Machine learning performs well in many problems. However, the tendency to generate predictions that violate theoretical knowledge makes it difficult to apply to practical processing. To resolve this situation, this paper combines domain knowledge with a data-driven model, proposes a theory-guided machine learning framework based on a parameter transfer strategy, and applies it to the width prediction of plates after multiple passes of hot rolling. The framework applies a swarm optimization algorithm to the original theoretical model and generates numerous highly-physical consistent samples. The established deep neural network (DNN) model is trained with simulated data, and the parameters are fine-tuned using a parameter transfer strategy combined with actual data to ensure excellent adaptation to the actual environment based on adequate learning of theoretical knowledge. In tests, the proposed model had the best overall prediction performance in this paper. Meanwhile, the developed model is consistent with the existing perception of rolling theory. This allows for the quick and reliable application of machine learning models in production. [Display omitted] • A novel theory-guided machine learning framework for width prediction of rolled plates. • Pre-training of the model using the data generated by the optimized theoretical model. • The proposed model has the best accuracy in both sufficient and less actual samples. • The variable influence of the proposed model is consistent with theoretical perceptions. [ABSTRACT FROM AUTHOR]

This paper reports the prediction results of the ionospheric irregularities represented by the ROTI index close to the equatorial ionization anomaly's Northern peak. A feedforward backpropagation Neural Network (NN) approach is implemented using a time series Nonlinear Autoregressive approach with Exogenous inputs (NARX). We used the data from a dual frequency GPS-SCINDA station located at Helwan (geographic coordinates of 29.86°N, 31.32°E, and MLAT of 29.94°N) in Egypt. To allow the model to be independently tested during varying levels of solar activities, we collected a 5-minute resolution of ROTI data for the solar cycle 24 from 2009 to 2017. The factors that influence the development of ionospheric irregularities are involved in the established model representing the diurnal and seasonal variations as well as solar and geomagnetic activity parameters. To support learning, we included IRI-foF2 and IRI-hmF2 parameters in the input layer neurons to improve the model learning about the behavior of the ionospheric F layer. The results show that the NN-ROTI values precisely match the GPS-ROTI values with an RMSE of 0.106 TECU/min and a prediction efficiency of 95%. The predicted values are highly correlated with the originals, with a regression of 0.89. Furthermore, the irregularities were more prevalent during the equinox months than during the solstice months. It is also observed that predicted NN-ROTI values in all seasons have RMSEs less than 0.03 and 0.05 TECU/min for the low and high solar activity, respectively. The results also showed a clear correlation between solar activity and the occurrence percentage of ionospheric irregularities indicating a solar cycle dependency. The prediction values of the NN-ROTI occurrence % demonstrated a remarkable correlation with the observed GPS-ROTI occurrence % across SC24. [ABSTRACT FROM AUTHOR]

IoT technologies are becoming more and more common in our daily activities because the networks they create are capable of collecting information, monitoring and controlling remotely. However, these devices are not exempt from security attacks, as they become vulnerable entry points to data networks. The use of traditional methods to secure networks (e.g., Next Generation Firewalls (NGFW), encryption, etc.) is not recommended because the devices used in this type of network are limited in terms of computing power and storage availability (e.g., nodeMCU). In this paper, we propose to design two intrusion detection systems in embedded systems using machine learning (ML) algorithms, Artificial Neural Networks and K-means. In a distributed architecture Wireless Sensor Network scenario (WSN), we evaluate their performance in terms of connection and response times, detection accuracy and intruder detection time. Simulation results show that both models are able to find irregularities in network traffic within milliseconds. [ABSTRACT FROM AUTHOR]

In this paper, we consider the evolution of a new probability distribution called the exponential flexible Weibull distribution. The proposed exponential flexible Weibull distribution is obtained by combining the flexible Weibull extension with the exponential T- X strategy. For the exponential flexible Weibull, the estimators of the model parameters are derived mathematically. The appraisal of these parameters is accomplished through a simulation study. The applicability and virtuoso of the exponential flexible Weibull distribution are exemplified via two data sets. Furthermore, we implement the state-of-the-art deep learning algorithms, specifically Artificial Neural Networks and Extreme Gradient Boosting, which are widely employed in real-world applications. A comprehensive comparative analysis is conducted to assess the relative performance of these methodologies. [ABSTRACT FROM AUTHOR]

This research paper focuses on comparing two Machine Learning (ML) approaches—Time Series Analysis and a Feature-Based Prediction—for predicting traffic accident counts. Spanning the years 2005 to 2016 in Paris, the study leverages a comprehensive dataset that includes attributes such as weather conditions. Following dataset preprocessing and partitioning into training and test sets, the research systematically develops and evaluates these two contrasting ML modeling approaches. Furthermore, the study extends its comparison by evaluating the performance of various ML models, emphasizing the power of the proposed Neural Network (NN) model. Metrics such as Mean Absolute Percentage Error (MAPE) are employed to assess and contrast the predictive capabilities of each model. The results not only showcase the effectiveness of the neural network model but also elucidate its superiority over alternative ML approaches, particularly in the context of traffic accident prediction. [ABSTRACT FROM AUTHOR]

Multi-view learning (MVL) is a rapidly evolving direction in the field of machine learning. Despite the positive results, most algorithms that combine multi-view learning with twin support vector machines (TSVM) focus on the traditional machine learning domain. No method has been accomplished for combining MVL, TSVM, and deep learning. In this paper, we propose two novel multi-view deep models to solve the multiclass classification problem, namely deep multi-view twin support vector machines (DMvTSVM) based on deep neural network (DNN) and auto-encoder (AE) network. They find two non-parallel hyperplanes such that each hyperplane is as close to its own class as possible while being as far away from the other class as possible. Meanwhile, we apply similarity regularization to the output of the Deep TSVM classifier for each view to learn consensus information between views, and use this to refine the joint weights of the deep model and TSVM. Finally, the novel models employ the o n e − v s − r e s t strategy to allow the DMvTSVM classifier to solve the multiclass classification problems. In the experiments, the proposed methods are compared with existing state-of-the-art algorithms to prove their effectiveness. • The first combination of twin support vector machines (TSVM) and deep neural networks. • Nesting of more advanced auto encoder networks. • Incorporating multi-view learning capabilities. • Mutual negotiation and simultaneous learning between deep neural networks and TSVM. • The experiments prove the effectiveness of the algorithm in this paper. [ABSTRACT FROM AUTHOR]

In recent years, predictive analysis has attracted a lot of interest due to advances in technology, particularly in the large data and machine learning fields. The advancement in technology has also scored the cases of cybercrimes. The majority of the time, a mathematical model that captures important trends is built using data that is historical. The predictive model is used to analyze data to forecast certain parameters or trends or to advise actions to achieve the best results. Artificial neural network (ANN) is an effective technique for such predictions. In this paper, ANN is used for prediction from a survey-based dataset that has been created from the students of universities of J&K Union Territory. The dataset that is used has been created with a dire need to understand the level of students in terms of their knowledge and understanding of cybercrimes. A very imperative way to prevent cyber against people is to make people aware of crimes and by training them for the same. For such a problem, a model is proposed to predict the need for cyber training among students using ANN. In this paper, ANN with back-propagation is proposed as a tool to predict whether there is a need for cyber training for individuals. Numerous cases have been reported in the cyber cell of J&K where cybercrimes have been registered by individuals. It is the need of the hour to train the student community on cybercrime schemes and behavior. [ABSTRACT FROM AUTHOR]

Researchers are putting in a lot of time and energy into developing methods to use machine learning algorithms, a subfield of AI, to ‎diagnose disease in an individual patient. Extensive studies have been conducted on the potential benefits of using machine learning ‎techniques in the treatment of cardiovascular disease. For this preliminary study, the study have zeroed down on heart illness to get ‎as specific as possible about our methodology. In this paper, the authors investigate the differences in accuracy between different ‎machine learning approaches specifically, (SVM), (KNN), and a(ANN) when applied to the categorization of cardiovascular ‎illness. Our research makes use of approximately seventy thousand patient records from the Kaggle dataset, which focuses on ‎cardiovascular disease The Kaggle dataset comprises a limited number of variables per patient record, encompassing serum ‎cholesterol, diastolic and systolic blood pressure, relative blood glucose levels, and the presence or absence of angina.‎ The present study examines the Kaggle dataset and employs the (KNN), (SVM), and (ANN) methodologies. The results indicate ‎that the K-nearest neighbors (KNN) algorithm, specifically with a value of 9 for the number of neighbors, achieved an accuracy of ‎‎0.997. The SVM model using default hyperparameters achieved an accuracy of 0.9997. The Support Vector Machine (SVM) model ‎utilizing a Radial Basis Function (RBF) kernel and a C value of 100.0 exhibited an accuracy of 0.9998. Conversely, the SVM model ‎employing a linear kernel and a C value of 1000.0 achieved a perfect accuracy of 1.000. The Feedforward neural network achieved a ‎perfect accuracy of 1.000 using the Adam optimization algorithm after 10 epochs and 50 batches..In future research, the authors ‎intend to employ a deep neural network hypermodel in order to enhance the accuracy of their findings. [ABSTRACT FROM AUTHOR]

Software-Defined Networking (SDN) simplifies network administration as well as reduces the need for manual configuration on individual devices. SDN is expected to remain a crucial technology in shaping the future of network infrastructure. However due to key vulnerabilities like Open Flow Protocol Weaknesses, Flow Table Poisoning, Weak authentication and authorization mechanisms, it is prone to intrusion attacks. In this paper, authors aim to build framework based on various machine learning models (ML) to capture anomaly packets. Four models Decision tree, Support Vector Classifier, Naïve Bayes Classifier and artificial neural networks are designed and trained to capture anomaly packets. While SVC achieved an impressive accuracy of 99%, Artificial Neural Networks (ANN) demonstrated satisfactory speed and efficiency, despite their accuracy being slightly lower than SVM's. ANN is then deployed in SDN simulated using Mininet. The model is able to detect all DOS traffic. Other types of attacks SQL Injection, U2R Attack, Buffer Overflow Attack, Probe Attack, Brute Force Attack could not be tested as there is provision to simulated these using Mininet. [ABSTRACT FROM AUTHOR]

The image-based automatic plant disease identification has emerged as a prominent research area, driven by recent advancements in machine learning algorithms. Conventional disease detection methods rely on manual feature extraction from acquired images, involving extensive expertise from experts and pathologists. This labor-intensive practice is often time-consuming and impractical. With the recent advancements in digital technologies and computer vision, Deep neural networks address these challenges by learning the features automatically. This paper focuses on the EfficientNet B0 architecture-based deep neural network model integrated with a convolutional block attention mechanism module for identifying major wheat crop diseases. The attention module in the EfficientNet B0 model improves its performance by emphasizing the disease-infected regions in leaf images. To evaluate the proposed methodology, experiments were conducted on the WheatRust21 image dataset, comprising 6556 images of three major fungal diseases, namely, stripe rust, leaf rust, and stem rust, collected in natural field conditions from 2019 to 2021. Our developed EfficientNet B0-CBAM model performed well with a testing accuracy of 98.70% and an impressive F1 score of 98% on the dataset. The Grad-CAM visualization demonstrates that the attention module focuses more on the infected region and plays a crucial role in wheat disease identification. The results are quantitatively substantial, with the model achieving high accuracy and other evaluation metrics scores with an average of 98.5 %. These findings hold promise for practical applications in agriculture and sustainable crop management. [ABSTRACT FROM AUTHOR]

Mushrooms are fungi that play significant roles in ecosystems, food, and medicine. However, distinguishing toxic mushrooms from non-toxic ones is challenging, as their visual characteristics can be misleading. Deep learning, a subset of artificial intelligence, offers a promising approach to detecting and classifying mushrooms based on their toxicity. By training deep neural networks on datasets of labelled mushroom images, it becomes possible to create models capable of accurately differentiating between toxic and non-toxic mushrooms. Mushrooms are fungi that play significant roles in ecosystems, food, and medicine. However, manually distinguishing toxic mushrooms from non-toxic ones is a challenging and time-consuming task. This research work is to help the local farmers and exporters to identify the difference between the toxic and the edible mushroom which will eventually boost production and will directly have an impact on the economic growth in India. This paper compared different deep learning algorithms such as Support Vector Machine (SVM), Resnet50, YOLO V5 and Alexnet, which have been found to be the most useful in classifying the mushrooms effectively as toxic and non-toxic respectively. The patterns in the images of the mushrooms have been predicted through the above classifiers. The validation techniques show SVM to be the most effective with an accuracy of 83%. [ABSTRACT FROM AUTHOR]

Cybersecurity threats, particularly spam SMS, are increasingly sophisticated, demanding more advanced detection systems. Traditional spam detection methods fall short due to their ineffectiveness against novel threats and lack of transparency. This paper investigates the role of Explainable Artificial Intelligence (XAI) in spam detection, emphasizing the interpretability of AI-driven systems through SHapley Additive explanations (SHAP). We propose a hybrid model combining BERT with Random Forest (RF) and Artificial Neural Networks (ANN) for spam detection, and employ SHAP values to elucidate the decision-making process. The study demonstrates that our XAI approach not only improves the accuracy of spam detection but also enhances the transparency and trustworthiness of the predictions. These findings suggest that the incorporation of XAI into spam detection models is not only beneficial but necessary for future cybersecurity measures. Our research invites further exploration into other XAI techniques and their applications in real-world scenarios. [ABSTRACT FROM AUTHOR]

Federated learning has emerged as a robust framework for distributed machine learning, enabling model training across decentralized data sources while preserving data privacy. Despite its advantages, a persistent challenge remains: the high communication overhead during the model update process results in a high energy consumption on the client devices. This paper introduces a new approach that combines (1) weights sparsification technique with (2) single layer update of the shared neural network model. Our proposal serves dual purposes: it significantly reduces the volume of data transmitted during each training round while lessening the computational burden on resource-limited devices. Through empirical evaluations, we witness an impressive reduction—up to 98.3%—in data exchange during the aggregation phase without much compromising the model's performance. Moreover, we find that the communication cost savings scale with the size of the model, making our approach particularly advantageous for large, complex models. This work opens the door to for more energy-efficient and scalable federated learning implementations, especially in resource-constrained environments like IoT and mobile devices. [ABSTRACT FROM AUTHOR]

The stock market is a very important part of the financial field, and the prediction of the stock market has a great relationship with the returns and risk safety of the entire financial field. With the continuous mature application of machine learning and deep learning in other fields, such as image processing and text analysis, people begin to focus on the use of different models so as to predict stock volatility. However, in view of the unique multi-source and heterogeneous characteristics of stock information, the artificial neural network relying on deep learning cannot make a good prediction on it. At this time, the graph neural network that can well analyze the graph structure data is gradually favored by scholars at home and abroad, and the research thinking is also expanding. This dissertation examines the purpose of deeply analyzing the methods of different graph neural network models on stock prediction through an inductive study of amount of relevant literature. In this paper, we not only classify the literature by various graph neural network models, but also describe objectively the models and ideas presented in each paper. By referring to literature, this paper summarizes the previous research results, analyzes the applicability and results of different methods, and lays a foundation for better stock prediction in the future. [ABSTRACT FROM AUTHOR]

This paper employs a deep reinforcement learning algorithm named Twin Delayed Deep Deterministic algorithm into autonomous navigation in intelligent transportation systems. It trains a fully connected neural network model in a simulation environment, which outputs the expected linear and angular velocity of the vehicle based on real-time data measured by embedded sensors. Through continuous epochs of training, the model gradually navigates the vehicle to reach a provided destination by making rational motion decisions at each discrete time instant without knowing global environment information. Especially, to improve the model's generalization ability across various scenes, an input preprocessing function is proposed to eliminate the singularity and uniformity of raw input data. A large number of simulation tests are carried out, where the proportion that the vehicle moves from a start position to a destination without collision within a specified limited time exceeds 90%. The remaining failures are mainly due to the vehicle's inability to approach the destination immediately adjacent to obstacles for its safety. Furthermore, traditional mapless navigation algorithms suffer from locally optimal solutions in the face of U-shaped obstacles. This paper introduces a virtual obstacle mechanism designed to prevent the vehicle from entering the U-shaped region, effectively addressing the aforementioned issue. Finally, the model trained from the simulation environment can be directly loaded onto a physical vehicle without considering the different processor architectures. Large quantities of experiments show that the model improves the autonomous navigation capability of vehicles when global environment information cannot be obtained by the system, which optimizes the functions of the navigation module in intelligent transportation systems. • The TD3 navigation algorithm's custom parameters achieve superior performance. • A preprocessing function enhances the navigation model's generalization capability. • A virtual obstacle mechanism effectively addresses the issue of U-shaped obstacles. • The model trained in simulation can be directly deployed on physical vehicles. [ABSTRACT FROM AUTHOR]

The objective of this paper is to optimize the energy consumption and performance of fuel cell electric bicycles (FCEBs) under specific key input parameters. The paper applied an integrated method that includes an artificial neural network (ANN) and genetic algorithm (GA) to forecast and identify an optimal performance and energy consumption of FCEBs. The simulation model of FCEBs is established and simulated in MATLAB-Simulink environment to generate 1000 data points, that are used for training, validating, testing artificial neural network, the ANN architecture containing five input neurons, two hidden neurons and two output neurons, respectively. Furthermore, the GA is integrated to find the maximum performance and energy consumption once the ANN has exactly been trained. The study found that the FCEB configuration can achieve an effective performance at 30.3 km/h with required power of 210.4 W under speed level_5, radius of wheel 0.39 m, frontal area 0.423 m2, slope grade 0%. In order to validate and verify the simulated results, the experimental approach method was conducted in the same condition. The experimental results fit well with the simulated results in the same initial input parameters. • A method integrating the artificial neural network with genetic algorithm is applied. • The consumed power and fuel cell voltage are optimized by combining artificial neural network and genetic algorithm (ANN-GA). • The effective performance area of fuel cell electric bicycle under various a structure and operating parameters is identified. • Deep-learning results reflect major physical mechanism of fuel cell electric bicycle operation. [ABSTRACT FROM AUTHOR]

The paper describes three lossy data compression techniques based on the principal component analysis (PCA), which are compared using the image compression task. The presented approach uses both classical PCA method based on the eigen-decomposition of the image data covariance matrix and two different neural network structures. The first neural structure is a two-layer feed-forward network with supervised learning acting as the so-called autoencoder, and the second one is a single-layered network with an unsupervised learning method commonly known as the generalized Hebbian algorithm. For each compression method mentioned above, the influence of the number of image segments (frames) and the number of eigenvalues/eigenvectors on the compression ratio and the image quality are examined using three different gray-scale test images. The paper also addresses a vital implementation issue regarding selecting appropriate data types to represent the compressed data. The paper's main conclusion is that the classical PCA method outperforms its neural counterparts, both in terms of the decompressed image quality and the time required to perform the compression procedure. The positive aspect of using neural networks as a tool for PCA-based lossy data compression is that they do not require calculating the correlation matrix explicitly and thus can be used in online data acquisition schemes. [Display omitted] • Classical PCA compression outweighs neural nets in image quality and operation time. • Appropriate learning algorithm is essential for the neural PCA compression. • Neural PCA compression can have an advantage in online data acquisition schemes. • Appropriate data types are important for compression ratio and image quality. [ABSTRACT FROM AUTHOR]

This paper proposes a novel algorithm for incremental learning over streaming data in a non-stationary environment. The idea refers to the applicability of Probabilistic Neural Networks (PNNs), commonly used as a fast and robust method for solving classification problems in a stationary scenario. It is well known that PNNs have solid mathematical foundations but they fail in the non-stationary scenario and are not able to deal with concept drift. In this paper, the method based on the orthogonal series expansions of unknown probability densities is proposed. This approach significantly extends the applicability of the PNNs. The nonparametric procedures called Incremental Probabilistic Neural Networks (IPNNs) for tracking drifting probability densities or conditional class densities, in the case of classification, are presented. We prove their convergence as the stream data size is growing to infinity. More precisely, we show convergence in probability and with probability one as the sample size tends to infinity. Compared to the existing literature, almost exclusively based on various heuristics, the proposed method is mathematically justified and has solid theoretical foundations. Simulations performed on synthetic and air pollution data confirm the effectiveness of the algorithm. • The incremental version of the Probabilistic Neural Network (IPNN) based on the orthogonal series, able to work in non-stationary environments. • Mathematical proofs of the convergence of the proposed estimators for different types of concept drift. • Extension to the classification task, using estimated density functions as discriminant functions. • Application of the proposed IPNN to air pollution monitoring. [ABSTRACT FROM AUTHOR]

Two participants with competing objectives are considered in one-to-one orbital pursuit-evasion problem, one of which attempts to satisfy some certain terminal conditions with a minimum cost through its own control while the other player attempts to maximize the specified payoff and avoids entering this terminal range. This paper treats the problem of minimax time to a given final distance, within which the interception between pursuer and evader is defined to occur. To achieve the successful interception with an evader that adopts any unknown maneuvers, a near-optimal interception strategy for the orbital pursuit-evasion is presented in this paper. The pursuit-evasion problem is formulated as a differential game first, and a closed-form barrier solution is provided next. A near-optimal guidance law using deep learning is proposed to intercept the evader inside the capture zone. For the games that start outside the barrier, a learning algorithm for the capture zone embedding strategy is presented based on deep reinforcement learning to help the game state cross the barrier surfaces. The simulation cases of intercepting the evaders that adopt different maneuvering strategies are provided, and the results demonstrate the effectiveness and onboard feasibility of the proposed strategy in solving the orbital interception problem. • The closed-form barrier solution for a planar orbital pursuit-evasion game is provided. • A deep neural network is trained on a dataset consisting of plenty of barrier trajectories generated through the closed-form barrier formula. • The near-optimal guidance law inside capture zone is proposed using trained neural network. • A capture zone embedding strategy is presented based on deep reinforcement learning. • The closed loop interception strategy is proposed combining the strategies outside and inside capture zone. [ABSTRACT FROM AUTHOR]

This paper studies the application of two machine learning methods to model precipitable water vapor (PWV) using observations of 23 GPS stations from the local GPS network of north-west of Iran in 2011. In a first step, the zenith tropospheric delay (ZTD) and zenith hydrostatic delay (ZHD) is calculated with the Bernese GNSS software and Saastamoinen model as revised by Davis, respectively. Then, by subtracting the ZHD from the ZTD, the zenith wet delay (ZWD) is obtained at each GPS station, for all times. In a second step, ZWD is modeled by two different machine learning methods, based on the latitude, longitude, DOY, time, relative humidity, temperature and pressure. After training a Support Vector Machine (SVM) and an Artificial Neural Network (ANN), ZWD temporal and spatial variations are estimated. Using the formula by Bevis, the ZWD can be converted to PWV at any time and space, for each machine learning method. The accuracy of the two new models is evaluated using control stations, exterior and radiosonde station, whose observations were not used in the training step. Also, all the results of the SVM and ANN are compared with a voxel-based tomography (VBT) model. In the control and exterior stations, ZWD estimated by the SVM (ZWD SVM) and ANN (ZWD ANN) is compared with the ZWD obtained from the GPS (ZWD GPS). Also, in the control and exterior stations, precise point positioning (PPP) is used to evaluate the accuracy of the new models. In the radiosonde station, the PWV of the new models (PWV SVM , PWV ANN) is compared with the radiosonde PWV (PWV radiosonde) and voxel-based PWV (PWV VBT). The averaged relative error of the SVM, ANN and VBT models in the control stations is 10.50%, 12.71% and 12.91%, respectively. For SVM, ANN and VBT models, the averaged RMSE at the control stations is 1.87 (mm), 2.22 (mm) and 2.29 (mm), respectively. Analysis of the results of PWV estimated by the SVM, ANN and VBT, as well as the surface precipitation obtained from meteorological stations, indicate the high accuracy of the SVM in comparison with the ANN and VBT model. In the results shown in this paper, the SVM has the best ability to accurately estimate ZWD and PWV, using local GPS network observations. [ABSTRACT FROM AUTHOR]

• The proposed AP-GAN-DNN method is able to predict creep fracture life more accurately in the case of small samples, which solves the complex nonlinear problem and the problem of test data dispersion. • Compared with traditional physical methods and machine learning models, the AP-GAN-DNN model has better generalization and robustness for creep fracture life prediction. • AP-GAN data enhancement method can significantly reduce the "pattern collapse" effect of GAN and improve the performance of prediction algorithms. 7050 aluminum alloy has high strength and excellent fracture toughness. However, damage can be caused to the 7050 aluminum alloy by creep at elevated temperatures. The accuracy of conventional creep life prediction methods may fall short of meeting the desired standards. And the application of machine learning (ML) methods is limited due to the scarcity and dispersion of creep sample data. Generative Adversarial Networks (GAN) are often used for data enhancement, but suffer from "pattern collapse" under small sample conditions. To solve the above problems, this paper proposes a creep fracture life prediction method, which combines the affinity propagation (AP) clustering algorithm, GAN, and deep neural networks (DNN) for accurate creep fracture life prediction. The AP clustering algorithm for adaptive clustering was utilized to better reflect the creep sample distribution. Independent GAN models were trained for each cluster to better capture distribution characteristics of the data and generate synthetic data that was highly similar to the real data. The DNN models were trained using the synthetic data and then predicted using real creep fracture life data. The presented method was compared with traditional physical and machine learning methods, and the method combining K-Means, GAN, and DNN. The experimental results show that the method proposed in this paper has better prediction accuracy in a small sample creep fracture life dataset. [ABSTRACT FROM AUTHOR]

Deep neural networks have played an important role in the automatic classification of sleep stages due to their strong representation and in-model feature transformation abilities. However, class imbalance and individual heterogeneity which typically exist in raw EEG signals of sleep data can significantly affect the classification performance of any machine learning algorithms. To solve these two problems, this paper develops a generative adversarial network (GAN)-powered ensemble deep learning model, named SleepEGAN, for the imbalanced classification of sleep stages. To alleviate class imbalance, we propose a new GAN (called EGAN) architecture adapted to the features of EEG signals for data augmentation. The generated samples for minority classes are used in the training process. In addition, we design a cost-free ensemble learning strategy to reduce the model estimation variance caused by the heterogeneity between the validation and test sets, to enhance the accuracy and robustness of prediction performance. We show that the proposed method improves classification accuracy compared to several existing state-of-the-art methods. The overall classification accuracy and macro F1-score obtained by our SleepEGAN method on three public sleep datasets are: Sleep-EDF-39: 86.8% and 81.9%; Sleep-EDF-153: 83.8% and 78.7%; SHHS: 88.0% and 82.1%. • This paper develops a new GAN-enhanced ensemble deep learning model, called SleepEGAN, for the imbalanced classification of sleep stages. • It targets to solve two problems commonly existing in sleep or EEG signal-related data — the class imbalance and individual heterogeneity of EEG signals. • It proposes a new EGAN model that can effectively and efficiently generate EEG signals for small classes of sleep stages, and it develops a cost-free ensemble algorithm that can solve the problem of individual heterogeneity of EEG signals. • The proposed method meets the immediate needs of practitioners for seeking an automatic toolbox to classify the sleep stages in the sleep data which are imbalanced and heterogeneous. • It can be conveniently used for automated sleep monitoring and promotes modern wearable technologies. [ABSTRACT FROM AUTHOR]

A multi-layer neural network is used to extract the value of a superconductor's T c of cuprate from two models. The first model extracts T c from the structure's chemical composition whereas the second model extracts T c from the structure's chemical composition and the lattice parameters. The back-propagation algorithm is used to find the empirical equation of T c. It can calculate error signals and redistribute backward propagation signals. This paper studies four systems of cuprate superconductors: Y Ba Cu O, Bi Sr Ca Cu O, Tl Ba Ca Cu O, and Hg Ba Ca Cu O. In the first model, the T c of four high-temperature oxide superconductors are calculated as a function of eight parameters and one output, which is T c. Although the same output is produced in the second model, it is produced as a function of eleven parameters. The eight parameters are superconductor type number (Bi2212, Bi2223, Hg1201, Hg1212, Hg1223, Y123, Y124, Y247, Tl1223, Tl2212, Tl2223), first component composition, second component composition, third component composition, fourth component composition, atomic number of doping type, doping composition, and oxygen composition of the first model. The previous parameters with the three lattice parameters a , b and c are used in the second model. The trained deep learning models have shown a high degree of performance in matching the trained distributions. After analysing the results, we deduce electronegativity plays an important role in increasing T c of cuprate superconductors. Using the obtained T c prediction model, the scope is expanded to include the eleven unexplored multi-element materials. Candidates for superconductors with a higher T c that can be synthesized are proposed. By comparison with other models of machine learning, the suggested models in this paper give the highest T c for predicting new cuprate superconductors. [ABSTRACT FROM AUTHOR]

Livestock producer's profits are generally linked to the weight of their animals. This will allow them to better plan their supply of the worldwide increasing demand on meat An interesting approach to address the issue of final performance prediction is to use machine learning techniques. In this paper, we will review a number of papers that have attempted to address this issue using machine learning algorithms such as multiple regressions, partial least squares regression, random forests, naive Bayes, support vector machines and artificial neural networks. Based on previously collected datasets of animals at different stages of growth, these algorithms attempt to predict the final performance of new animals. The quality of the predictions is measured using different parameters such as accuracy, sensitivity, mean absolute error percentage and root mean square error. [ABSTRACT FROM AUTHOR]

Cardiotocogram (CTG) is one of the monitoring tools to estimate the fetus health in womb. CTG mainly yields two results fetal health rate (FHR) and uterine contractions (UC). In total, there are 21 attributes in the measurement of FHR and UC on CTG. These attributes can help obstreticians to clasify whether the fetus health is normal, suspected, or pathological. This paper compares 7 algorithms to predict the fetus health: Artificial Neural Network (ANN), Long-short Term Memory (LSTM), XG Boost (XGB), Support Vector Machine (SVM), K-Nearest Neighbour (KNN), Light GBM (LGBM), and Random Forest (RF). By employing three scenarios, this paper reports the performance measurements among those algorithms. The results show that 5 out of 7 algorithms perform very well (89-99% accurate). Those five algorithms are XGB, SVM, KNN, LGBM, RF. Furthermore, only one from five algorithm that always performs well through three scenarios: LGBM. [ABSTRACT FROM AUTHOR]

Over the years, Machine Learning models have been successfully employed on neuroimaging data for accurately predicting brain age. Deviations from the healthy brain aging pattern are associated with the accelerated brain aging and brain abnormalities. Hence, efficient and accurate diagnosis techniques are required to elicit accurate brain age estimations. Several contributions have been reported in the past for this purpose, resorting to different data-driven modeling methods. Recently, deep neural networks (also referred to as deep learning) have become prevalent in manifold neuroimaging studies, including brain age estimation. In this review, we offer a comprehensive analysis of the literature related to the adoption of deep learning for brain age estimation with neuroimaging data. We detail and analyze different deep learning architectures used for this application, pausing at research works published to date quantitatively exploring their application. We also examine different brain age estimation frameworks, comparatively exposing their advantages and weaknesses. Finally, the review concludes with an outlook towards future directions that should be followed by prospective studies. The ultimate goal of this paper is to establish a common and informed reference for newcomers and experienced researchers willing to approach brain age estimation by using deep learning models. • We categorize brain age estimation models based on the deep learning architectures. • We classify deep learning architectures based on the slice/voxel-based input data. • We examine the modalities, size of data, performance and the datasets used. • We enumerate several challenges and trace directions that can be explored further. [ABSTRACT FROM AUTHOR]

Machine learning algorithms especially deep neural networks have seen tremendous growth in their real-world deployment. While these algorithms have to yield high performances for the task at hand, it is of equal importance that they are robust against the different kinds of singularities or adversarial anomalies. Researchers have generally addressed singularity detection independently for each anomaly, however, for the algorithms to be effective in the real world, the singularity detection algorithm must be able to handle a wide variety of attacks whether trained individually on them or not seen at the time of training. With this objective, in this paper, we propose a unique end-to-end transformation domain network to detect a variety of well-known attacks. The proposed architecture utilizes a combination of two different wavelet transformations to simultaneously learn low-level and high-level image features in a deep stacked layer fashion. The proposed method is generalized to handle a broad set of singularities of several computer vision algorithms whether operating in the object recognition domain or biometrics recognition. We showcase the results on a wide range of singularity points including (i) adversarial perturbations which are learned using deep learning networks, (ii) physical presentation attacks on face recognition which aim to produce fake data for the sensor for acquisition, and identification, (iii) synthetic images, and (iv) digital retouching of the images. Even with a zero-day or open-world attack setting, the results of the proposed algorithm show improvement over state-of-the-art results. The proposed architecture is agnostic to parameters, computationally efficient to provide a sustainable detector to resource-constrained institutions, provides robustness to attacks, and supports green computing. • A novel parameter-agnostic architecture is proposed to defend anomalies. • The proposed algorithm can handle adversaries in seen, unseen, and open-set settings. • The proposed algorithm is domain agnostic i.e., can handle vision and face datasets. • Our unified algorithm surpasses the SOTA works developed to handle specific attacks. • Bring a computationally feasible algorithm, it can be deployed on mobile devices. [ABSTRACT FROM AUTHOR]

The paper devotes to a new conception "Machine learning control". The mathematical formulation of this term is presented. It is shown, that a numerical method for solution of the control general synthesis problem belongs to the machine learning control. In common case the machine learning control is a search some control function. There are two approaches to this problem. First approach consists of definition of the function with accuracy to some unknown parameters. A search of these parameters is a machine learning. Artificial neural network technology belongs to the first approach. The second approach consists of search mathematical expression of control function by computer. This is a search of function structure and parameters together. Now so far there is only one way to realize this approach. It is symbolic regression. The paper describes symbolic regression technology in common case and some examples of symbolic regression applications for the control synthesis problem are presented. [ABSTRACT FROM AUTHOR]

The purpose of current paper is to create a smart and effective tool for telemedicine to early detect and diagnose COVID-19 disease and therefore help to manage Pandemic Crisis (MCPC) in Sultanate of Oman, as a tool for future pandemic containment. In this paper, we used tools to create robust models in real-time to support Telemedicine, it is Machine Learning (ML), Deep Learning (DL), Convolutional Neural Networks using Tensorflow (CNN-TF), and CNN Deployment. These models will assist telemedicine, 1) developing Automated Medical Immediate Diagnosis service (AMID). 2) Analysis of Chest X-rays image (CXRs). 3) Simplifying Classification of confirmed cases according to its severity. 4) Overcoming the lack of experience, by improving the performance of medical diagnostics and providing recommendations to the medical staff. The results show that the best Regression among the five Regression models is Random Forest Regression. while the best classification among the eight classification models and Recurrent Neural Network using Tensorflow (RNNTF) is Random Forest classification, and the best Clustering model among two Clustering models is K-Means++. Furthermore, CNN-TF model was able to discriminate between those with positive cases Covid-19 and those with negative cases. [ABSTRACT FROM AUTHOR]

Cardiovascular diseases are currently the major causes of death globally. Among the strategies to prevent cardiovascular issues, the automated classification of heart sound abnormalities is an efficient way to detect early signs of cardiac conditions leading to heart failure or other, even asymptomatic, complications, quite effective for timely interventions. Despite the significant improvements in this field, there are still limitations due to the lack of solutions, available data-sets and poor (mainly binary — normal vs abnormal) classification models and algorithms. This paper presents a Medical Cyber–Physical System (MCPS) for the automatic classification of heart valve diseases onsite, in a timely manner. The proposed MCPS, indeed, can be deployed into personal and mobile devices, addressing the limitations of existing solutions for patients, healthcare practitioners, and researchers, through an efficient and easy accessible tool. It combines different neural network models trained on a new Italian dataset of 132 adult patients covering 9 heart sound categories (1 normal and 8 abnormal), also validated against two main open-access (Physionet/CinC Challenge 2016 and Korean) datasets. The overall MCPS performance (time, processing and energy resource utilization) and the high accuracy of the models (up to 98%) demonstrated the feasibility of the proposed solution, even with few data. The dataset supporting the findings of this paper is available upon request to the authors. • DB of 132 heart sounds of Italian patients in 9 categories, available upon request. • MCPS for automated HVD classification via hierarchical ML model structures. • Compared six ML classifiers (RF, SVM, NB, LR, DNN, LSTM) for HVD and majority voting. • MCPS validated on two open access datasets (Physionet/CinC 2016 and Korean). • Time, processing and energy efficiency of MCPS validated, with usage guidelines. [ABSTRACT FROM AUTHOR]

Marine ecosystems and their fish habitats are becoming increasingly important due to their integral role in providing a valuable food source and conservation outcomes. Due to their remote and difficult to access nature, marine environments and fish habitats are often monitored using underwater cameras to record videos and images for understanding fish life and ecology, as well as for preserve the environment. There are currently many permanent underwater camera systems deployed at different places around the globe. In addition, there exists numerous studies that use temporary cameras to survey fish habitats. These cameras generate a massive volume of digital data, which cannot be efficiently analysed by current manual processing methods, which involve a human observer. Deep Learning (DL) is a cutting-edge Artificial Intelligence (AI) technology that has demonstrated unprecedented performance in analysing visual data. Despite its application to a myriad of domains, its use in underwater fish habitat monitoring remains under explored. In this paper, we provide a tutorial that covers the key concepts of DL, which help the reader grasp a high-level understanding of how DL works. The tutorial also explains a step-by-step procedure on how DL algorithms should be developed for challenging applications such as underwater fish monitoring. In addition, we provide a comprehensive survey of key deep learning techniques for fish habitat monitoring including classification, counting, localisation, and segmentation. Furthermore, we survey publicly available underwater fish datasets, and compare various DL techniques in the underwater fish monitoring domains. We also discuss some challenges and opportunities in the emerging field of deep learning for fish habitat processing. This paper is written to serve as a tutorial for marine scientists who would like to grasp a high-level understanding of DL, develop it for their applications by following our step-by-step tutorial, and see how it is evolving to facilitate their research efforts. At the same time, it is suitable for computer scientists who would like to survey state-of-the-art DL-based methodologies for fish habitat monitoring. • Marine environments and fish habitats are widely surveyed using underwater cameras. • Deep learning (DL) offers an effective solution for processing underwater videos. • We write a tutorial on the key concepts and steps of DL for underwater monitoring. • We provide a survey of key DL-based visual fish monitoring methods/datasets. • We shed light on challenges/opportunities of DL for underwater fish monitoring. [ABSTRACT FROM AUTHOR]

This paper proposes a data-driven model for predicting the code-based seismic vulnerability index calibrated on a dataset comprising almost 300 buildings. The vulnerability index, estimated following the Italian Seismic Code, involved rigorous investigations, including geometric surveys, experimental tests, and numerical modelling. Leveraging data from these investigations, encompassing approximately 15 categorical and numerical explanatory variables, the authors developed several regression and classification predictive models, such as Logistic Regression and Artificial Neural Networks (ANN). The optimal models perform binary classification to determine the categorization into two macro-classes, defined by an arbitrary vulnerability threshold. The ANN model stands out as the best performer. When adjusting the vulnerability threshold to obtain a balanced dataset, such a model achieves an accuracy higher than 85%. The paper also discusses the importance of each feature by calculating the SHapley Additive exPlanations (SHAP) values. The proposed model can aid decision-makers in allocating resources effectively to mitigate seismic risks of built environments. • Data-driven model for code-based seismic vulnerability assessment. • 15 explanatory variables are considered. • Regression models perform poorly. • Binary classification is the only reliable approach. • The ANN model has an 85% accuracy on binary classification with balanced dataset. [ABSTRACT FROM AUTHOR]

Automatic decision support systems focused on credit risk assessment based on scoring or similar methods are often used by financial institutions. Default prediction is a very important issue. This problem is often analyzed by researchers, but products offered by banks are mainly considered. However, additional attributes of fixed assets should be used for developing the method for default prediction of leasing contracts. The aim of this paper was to develop and compare machine learning methods to increase the level of default prediction in leasing companies. We focused mainly on Random Forest Classifier, AdaBoostClassifier, GradientBoostingClassifier, and Deep Neural Networks. The main contribution is the comparison of different developed machine-learning methods using data acquired from leasing companies. The results of the experiments show the precision of the prediction of defaults was from 72,8% to 75%, and the recall of the prediction of defaults was from 76,3% to 81,6%. The precision of non-default prediction, in turn, was from 71,9% to 79,1%, and the recall of prediction of defaults from 69,7% to 71,9%. The conclusion is that the models proposed in this research may be a helpful tool in the current operations of various financial institutions. Although the functionality of the models was presented in the example of a selected leasing company, due to their flexible and universal nature, they can be successfully used in the activities of other financial institutions. [ABSTRACT FROM AUTHOR]

Explainable Artificial Intelligence (XAI) is an emerging research field bringing transparency to highly complex and opaque machine learning (ML) models. Despite the development of a multitude of methods to explain the decisions of black-box classifiers in recent years, these tools are seldomly used beyond visualization purposes. Only recently, researchers have started to employ explanations in practice to actually improve models. This paper offers a comprehensive overview over techniques that apply XAI practically to obtain better ML models, and systematically categorizes these approaches, comparing their respective strengths and weaknesses. We provide a theoretical perspective on these methods, and show empirically through experiments on toy and realistic settings how explanations can help improve properties such as model generalization ability or reasoning, among others. We further discuss potential caveats and drawbacks of these methods. We conclude that while model improvement based on XAI can have significant beneficial effects even on complex and not easily quantifiable model properties, these methods need to be applied carefully, since their success can vary depending on a number of factors, such as the model and dataset used, or the employed explanation method. [Display omitted] • We show how and why XAI improves several model properties in toy experiments. • We develop a unifying theoretical framework for XAI-based model improvement. • We extensively review and discuss existing approaches that use XAI to improve models. • We provide experiment-supported practical recommendations for XAI-based augmentation. [ABSTRACT FROM AUTHOR]

In the domain of process planning, operation sequencing is one of the most essential tasks. Operation sequences determine the optimal order of different manufacturing processes for a product and therefore influence cost, quality, and production time of the manufactured product. Current approaches predicting operation sequences formulate the task as a mathematical optimization problem or rule-based system and therefore require a formulation of knowledge, for example as precedence constraints. Such a formulation is tedious and complex, because a lot of different relationships have to be considered. Moreover, due to individual machining equipment of companies the knowledge formulation can vary and consequently needs to be adopted to the manufacturing systems specifics. Therefore, this paper presents a deep artificial neural networks (ANN) approach for which a mathematical formulation for the operation sequencing task is not required and the system can quickly be adopted to different manufacturing systems through training processes. The presented approach captures knowledge from historic process plans through training. The deep ANN is constructed combining a convolutional neural network (CNN) with a long short-term memory network (LSTM) to predict operation sequences. The ANN is trained using business data including a wide range of machining operations. [ABSTRACT FROM AUTHOR]

Wildfires have caused devastating consequences to property and human and animal lives, which has become a global problem. Consequently, advanced wildfire prediction models are required to treat complex features and climate conditions. As a result, Machine Learning and Deep Learning models are becoming popular. However, creating a balanced true and false labeled dataset in the wild-fire domain is often challenging. Hence, One-class classification models are a promising approach to overcome this concern. In this paper, several One-class classification models are investigated; linear models (Principal Component Analysis and One-Class Support Vector Machines), outlier ensemble models (Lightweight On-line Detector of Anomalies and Locally Selective Combination of Parallel Outlier Ensembles), proximity-based models (Histogram-based Outlier Score and Rotation-based Outlier Detection), probabilistic models (Unsupervised Outlier Detection Using Empirical Cumulative Distribution Functions and Copula-Based Outlier Detection), neural network-based models (Deep One-class Classification and Adversarially Learned Anomaly Detection) is used in two case studies for California and Western Australian states. In conclusion, it was found that Deep learning-based One-class classification models outperform other models in terms of performance and feature importance of showcasing the effectiveness of deep neural network models in the wildfire prediction domain. [ABSTRACT FROM AUTHOR]

Since their development at the end of the 50s, panel methods were widely used for the fast simulation of aerospace objects reentry. Although improvements were proposed for the continuum regime formulations, the bridging functions usually employed in the transitional regime did not go through major changes since then. With the current interest in designing Very Low Earth Orbit satellites and more efficient reentry vehicles, a greater level of preciseness is now required for the fast computation of the aerodynamic and aerothermodynamic wall quantities in rarefied regime. In this context, this paper presents a new approach to build Machine Learning based surrogates going from the choice of the design variables and the Design of Experiments, to the models training and evaluation. Hence, kriging and Artificial Neural Networks are respectively trained to predict the pressure and heat flux stagnation coefficients, and the pressure, friction and heat flux coefficient distributions in the rarefied portion of any aerodynamic shape's reentry. • New reduced models for the wall quantities in hypersonic rarefied conditions. • Kriging models for the stagnation heat flux and pressure coefficients. • Neural networks for the friction, heat flux and pressure coefficient distributions. • A thorough and challenging validation of the models has been carried out. • A more precise and generic alternative to classic panel methods. [ABSTRACT FROM AUTHOR]

Signals used for Earth observation, when travelling through the atmosphere, are sensitive to refractivity; especially high spatio-temporal variations of water vapor are difficult to model and correct. Remaining unmodeled tropospheric delays deteriorate the positioning solution and therefore limit the accuracy of sensing and navigation applications. These delays are usually computed with empirical models based on ground meteorological parameters (pressure, temperature and water vapor partial pressure). However, existing models are not accurate enough for high-precision applications such as GNSS, where in consequence the so-called zenith total delay (ZTD) has to be estimated together with other unknown parameters (coordinates etc.). For decades, the Institute of Geodesy and Photogrammetry at ETH Zurich has been studying collocation methods for the modeling of tropospheric delays using meteorological parameters, successfully interpolating pointwise or integral atmospheric observations. Meanwhile, machine learning has become a widely used and valuable alternative, when big datasets are available for the training process. Indeed, we have already successfully predicted ZTDs based on meteorological parameters with an accuracy of 1–2 cm for locations (GNSS stations) already used in the training phase. However, difficulties arise to predict delays at new locations. In this work, we take a step forward in investigating the combination of machine learning algorithms and physical models used in a collocation approach to derive atmospheric delay fields at a very high resolution. Thus, without processing any GNSS data we can predict tropospheric delay fields everywhere in the area of investigation. In this paper, we firstly describe the designed architecture of the neural network, secondly, the combination of least-squares collocation and artificial neural networks for high-resolution prediction of tropospheric delays. We benefit from the complementary characteristics of these algorithms. While machine learning is capable of successfully predicting the variation of time series for given points, empirical models based on collocation are well suited for describing spatial variations within the area of investigation. Finally, we report the achieved performance for the entire territory of Switzerland (1–2 cm in terms of RMS), showing that the synergic combination of these algorithms can overcome the individual drawbacks of each method and provide more accurate delay estimates than either method individually. Datasets of 11 years, covering the territory of Switzerland, consisting of GNSS ZTDs from 72 permanent AGNES/COGEAR (swisstopo, ETHZ) stations and meteorological data from MeteoSwiss were used for this research. • Machine learning to predict time series of GNSS tropospheric delays. • The prediction of tropospheric delays at new locations is difficult. • Least-squares collocation can successfully interpolate in space tropospheric delays. • Combination of machine learning and collocation (physical models) methods. • High-resolutions spatio-temporal tropospheric fields. [ABSTRACT FROM AUTHOR]

Interpretability and explainability of machine learning systems have received ever-increasing attention, especially for deep neural networks. In the case of convolutional neural networks (CNNs), their properties are usually explained by generating local explanation maps (e.g., visualizing the contribution of individual pixels to a given prediction). In this paper, we propose a new framework that analyzes the inner workings of CNNs in terms of neural activations. To be precise, we consider a forward-pass as sequential activations of neurons and develop its inverse process, so that the inverse preserves the physical meaning of neuron activations. Our inverse process is formulated as a constrained optimization problem, and we solve the problem with the gradient projection algorithm. The proposed approach can provide equivalent visualization results to several conventional methods, and thus can be a reference tool for CNN visualization. Also, the attributions generated by our inverse method yield the state-of-the-art deletion scores and visualize the contribution of colors as well as shape features. [ABSTRACT FROM AUTHOR]

This paper investigates and discusses the current and future role of machine learning (ML) within the hydropower sector. An overview of the main applications of ML in the field of hydropower operations is presented to show the most common topics that have been addressed in the scientific literature in the last years. The objective is to provide recommendations for novel research directions that can be taken in the near future to cover those areas that have not been studied so far. The key contribution of this paper lies in a critical investigation of the state of the art of ML applications in hydropower scheduling. In light of the established literature available in the last years, this study identifies and discusses new roles that can be covered by ML, coupled with cyber-physical systems (CPSs), with a particular focus on short-term hydropower scheduling (STHS) challenges. [ABSTRACT FROM AUTHOR]

Buckling Restrained Braces (BRBs) play an essential role in seismic protection due to their remarkable energy dissipation capacity, ductility, and stiffness. This paper represents the first thorough evaluation of the reliability and uncertainty of BRBs, accounting for various sources of uncertainty and varied conditions, such as different gap sizes, friction coefficients between the encasing and the steel core, and other geometric and mechanical properties of the connecting parts. This paper introduces an innovative application of an integrated probabilistic approach that combined Finite Element (FE) modeling, Artificial Neural Networks (ANN), and Monte Carlo simulation to characterize the seismic behavior of BRBs. Experimental results from literature is used to validate the FE model constructed using ABAQUS. This validated model is then integrated into a Low-rank Tensor Approximation process to yield variance-based sensitivity measures for the considered variables. The most influential variables identified in this process along with the calibrated FE model is utilized to conduct a reliability assessment through an ANN-assisted Monte Carlo simulation. This analysis is conducted to quantify the reliability level of the investigated BRBs as a function of the gap size and establish the resistance factors necessary to maintain the reliability level above prescribed thresholds. It was found that the highest reliability can be achieved at a small gap size equal to half the radius of gyration of the main steel core, requiring a resistance factor of 0.9. For gap sizes higher than this value, a resistance factor ranging between 0.70 and 0.85 is needed. • Comprehensive approach for evaluating reliability of Buckling Restrained Braces (BRBs) • Uncertainties in material properties and geometrical parameters are considered • Effect of changing the gap size and contact interaction are considered • A FE model is developed to predict hysteresis behavior • Monte Carlo simulation is used to quantify BRBs failure probability [ABSTRACT FROM AUTHOR]

Alzheimer's is a dangerous disease prevalent in human societies, and unfortunately, its incidence is increasing daily. The number of patients is on the rise, while the availability of physical doctors has become limited and their schedules are packed. Consequently, the adoption of digital healthcare systems for Alzheimer's disease (AD) has become more common, aiming to alleviate the burden on both AD patients and doctors. AD digital healthcare is a highly complex domain that incorporates various technologies, including fog computing, cloud computing, and deep learning algorithms. However, the implementation of these fog, cloud, and deep learning technologies has encountered challenges related to high computational time during AD detection processes. To address these challenges, this paper focuses on the convex optimization problem, which aims to optimize computation time and accuracy constraints in digital healthcare applications for AD. Convex optimization necessitates the use of an evolutionary algorithm that can enhance different AD constraints in distinct phases. The paper introduces a novel scheme called Evolutionary Deep Convolutional Neural Network Scheme (EDCNNS), designed to minimize computation time and achieve the highest prediction accuracy criteria for AD. EDCNNS comprises several phases, including feature extraction, selection, execution, and scheduling on the fog cloud nodes. The simulation results demonstrate that EDCNNS optimized security by 38%, reduced the deadline failure ratio by 29%, and improved selection accuracy by 50% across different Alzheimer's classes compared to existing studies. • An evolutionary deep neural network scheme (EDNNS) is proposed. • The EDNNS is applied to detect Alzheimer's disease using different modalities. • Federated deep learning is used to minimize computational load. • Evolutionary algorithm is used for local search and global search. [ABSTRACT FROM AUTHOR]

This paper attempts to present an Internet of Things (IoT) based Home Energy Management System (HEMS) to accommodate Artificial Intelligence (AI) based Distributed Generation (DG) Integration in Smart Micro Grid environment. This work presents the feasibility of load and weather Big Data acquisition, online load forecasting /prediction, online load priority assignment, online peak clipping estimation on the cloud (Thingspeak). Load priority and peak clipping Demand Side Management (DSM) Techniques are used to run Load Management Algorithm (LMA) on the cloud which ultimately executes AI-based DG Integration at the load center. Based on the real time load and weather Big Data Load Priority Table (LPT) is generated on the cloud in order to assign the priority to the loads of the load center and online forecasting is also carried out on the cloud to estimate Total Power P T using Artificial Neural Network (ANN) and five different ML algorithms which are later utilized to estimate Threshold /Peak Clipping Power P Th. Using these LPT and P Th values LMA executes AI-based DG Integration. To that end, a novel IoT-based HEMS is designed and fabricated to run cloud-based LMA in order to accommodate proposed DG Integration. Amongst all the prediction algorithms trained on the cloud to estimate P Th , Linear Regression (LR) ML algorithm is witnessed to have lowest RMSE of 4.44e−13, MSE of 1.97e−25 and MAE of 2.11e−13. MATLAB 2018b licensed version is used to run ANN and ML algorithms based forecasting/prediction on the cloud. [ABSTRACT FROM AUTHOR]

In some illegal businesses, spammers are hired to post fake reviews on social media platforms, causing spammers to appear among normal reviewers. Studies have used graph neural networks (GNNs) to detect spammers based on community characteristics and correlations. A common problem with graph neural network construction is the failure to filter out noisy neighbors of the center node. Due to the aggregation of graph neural network message transmission, the information carried by these noisy neighbors will influence the detection process. We propose a method based on Label-aware cosine similarity for filtering camouflaged and noisy nodes from the center node in order to retain potentially similar nodes of the same type for message passing. Several studies have used multi-relational graphs to detect spammers who implement behavior features and relation camouflage. Despite improvements in the detection effect, there are still shortcomings in the design of intra-relation aggregation and inter-relation aggregation. In this paper, multi-relational graphs are examined to enhance the detection of spammers using intra-relation aggregation and interrelation aggregation. Extensive experimental results show that the proposed model outperforms the state-of-the-art GNN-based spam detection on the Yelp and Amazon datasets. [ABSTRACT FROM AUTHOR]

Multi-target missions are an attractive solution to visit multiple bodies, increasing the scientific return and reducing the cost, compared to multiple missions to individual targets. Examples of multi-target missions are multiple active debris removals (MADR) and multiple near-Earth asteroids rendezvous (MNR) missions. MADR missions allow for the disposal of inactive satellites, preventing the build-up of space junk, while MNR missions allow to reduce the expenses of each asteroid observation. Since those missions are long and highly demanding in terms of energy, it is paramount to select the most convenient propulsion system so that the propellant mass and the duration of the mission are minimized. To this end, this paper proposes the use of a multi-objective optimization and artificial neural networks. The methodology is assessed by optimizing trajectories for MADR and MNR sequences with off-the-shelf thrusters. Multiple Pareto-optimal solutions can be identified depending on the propulsion system characteristics, enabling mission designers to trade-off the different options quickly and reliably. [ABSTRACT FROM AUTHOR]

Wireless Body Area Networks (WBAN) can provide continuous monitoring of patients' health. Such monitoring can be a decisive factor in health and death situations. Fault management in WBANs is a key reliability component to make it socially acceptable and to overcome pertained challenges such as unpredicted faults, massive data streaming, and detection accuracy. Failures in fault detection due to hardware, software, and network issues may put human lives at risk. This paper focuses on detecting and predicting faults in sensors in the context of a WBAN. A framework is proposed to manage AI-based prediction models and fault detection using thresholds where four Machine learning techniques: Artificial Neural Networks (ANN), Deep Neural Networks (DNN), Support Vector Machines (SVM), and Decision Trees (DT), are used. The framework also provides alarm notifications, prediction model deployment, version control, and sensing node profiling. As a proof of concept, a fault management prototype is implemented and validated. The prototype classifies faults, manages automation of sensing node profiling, training, and validation of new models. The obtained experimental results show an accuracy greater than 96% for detecting faults with an inferior false alarm rate. [ABSTRACT FROM AUTHOR]

This paper outlines a study of various approaches to the task of detecting and removing personal data from text documents in Russian. To solve the problem regular expressions, various supervised learning models, artificial neural networks and Markov models were used. To train and validate the models, a labeled dataset with named entities was used. For each approach, suitable preprocessing was performed on the data. To measure the performance of the models, 3 metrics were evaluated, precision, recall, and f1-score. The best result was obtained using bidirectional LSTM with conditional random field layer (BiLSTM CRF). Options for integrating the developed tool into the software solution, as well as ways to further improve the quality of models are proposed. The software tool can be used by government agencies, judicial institutions, or legal entities. [ABSTRACT FROM AUTHOR]

The data from thermal simulation plays a significant role in understanding the deformation behavior and deformation mechanisms of materials, and provides guidance for the design of hot deformation processes. In this paper, thermal simulation experiments were performed on an Al-6.3Zn-2.5Mg-2.6Cu-0.11Zr alloy, and the microstructure after hot deformation were characterized by Electron Backscatter Diffraction (EBSD) technique. The thermal simulation data and microstructural characteristics were analyzed and studied using machine learning technique: the Backpropagation Artificial Neural Network (BP-ANN) method, correlation analysis and K-means clustering analysis. A model for predicting not only flow stress but also dislocation density was established using the BP-ANN method, which exhibits good prediction accuracy. The R² and AARE values are 90.19 % and 6.87 % for the prediction of dislocation density, and are 98.67 % and 6.96 % for the prediction of flow stress. Subsequently, correlation analysis was performed to investigate the relationship between energy dissipation efficiency η and deformation parameters as well as microstructural characteristics, revealing that energy dissipation rate is correlated positively with the content of dynamical recrystallization (DRX) and high angle grain boundary (coefficients of 0.90 and 0.82) and negatively with the dislocation density and the Zener-Hollomon parameter (coefficients of −0.98 and −0.97). Additionally, K-means clustering analysis was applied to study the relationship between the energy dissipation efficiency and softening mechanisms, it was found that the softening mechanisms changed with the variation of η value, dynamic recovery (DV), geometric DRX (GDRX) and continuous DRX (CDRX) dominated when η >0.38; DV, CDRX and discontinuous DRX(DDRX) dominated when 0.28< η <0.38; DV dominated when η <0.28. The results show that machine learning techniques are useful tools in mining thermal simulation data, and more information can be obtained than traditional data mining methods. • Flow stress and dislocation density of an AlZnMgCu alloy during hot deformation were accurately predicted by a neural network model. • The correlation analysis showed that the energy dissipation efficiency is related with the proportion of DRX. • Relationship between the η value and the deformation softening mechanism was established based on K-means clustering method. [ABSTRACT FROM AUTHOR]

This paper aims to propose a new hybrid Machine Learning (ML) with Egret Swarm Optimization Algorithm (ESOA) and Weighted Relevance-based Combination Strategy (WERCS) methods for predicting the patch loading resistance (PLR) of both longitudinally unstiffened and stiffened plate girders. A dataset of both stiffened and unstiffened plate girders under patch loading are collected and used for training and testing to generate the proposed models. Firstly, the WERCS method is used to resample the training set to improve the performance of training data. After that, four ML models, including Gradient Boosted Tree (GTB), Extreme Gradient Boosting algorithm (XGB), Artificial neural network (ANN), and CATBoost regression (CAT) are employed. The hyperparameter of all above ML models are optimized by using ESOA algorithm to choose the best performance models. It was found that the WERCS influences considerably the performance of hybrid ML models, and the WERCS + ESOA + XGB model presents the best performance compared to others. The accuracy of the WERCS + ESOA + XGB model is validated by comparing its predictive results with the existing design codes and formulae. Additionally, the Local Interpretable Model-Agnostic Explanations (LIME) method is used to assess the importance and contributions of each input variable in the proposed model. This algorithm can explain the global and local effects of features with each range and create favourable foundations for practical designing. A Graphical User Interface (GUI) tool is developed to conveniently estimate both the patch loading resistance of longitudinally unstiffened and stiffened plate girders. A Python library has been developed and uploaded to PyPi for more convenient use without the need for accessing the source code. [ABSTRACT FROM AUTHOR]