Search

The research groups in computer vision, graphics, and machine learning have dedicated a substantial amount of attention to the areas of 3D object reconstruction, augmentation, and registration. Deep learning is the predominant method used in artificial intelligence for addressing computer vision challenges. However, deep learning on three-dimensional data presents distinct obstacles and is now in its nascent phase. There have been significant advancements in deep learning specifically for three-dimensional data, offering a range of ways to address these issues. This study offers a comprehensive examination of the latest advancements in deep learning methodologies. We examine many benchmark models for the tasks of 3D object registration, augmentation, and reconstruction. We thoroughly analyse their architectures, advantages, and constraints. In summary, this report provides a comprehensive overview of recent advancements in three-dimensional deep learning and highlights unresolved research areas that will need to be addressed in the future. [ABSTRACT FROM AUTHOR]

To construct a nonlinear fractional-order neural network reflecting the complex environment of the real world, this paper considers the common factors such as uncertainties, perturbations, and delays that affect the stability of the network system. In particular, not only does the activation function include multiple time delays, but the memristive connection weights also consider transmission delays. Stemming from the characteristics of neural networks, two different types of discontinuous controllers with state information and sign functions are devised to effectuate network synchronization objectives. Combining the finite-time convergence criterion and the theory of fractional-order calculus, Mittag-Leffler synchronization conditions for fractional-order multi-delayed memristive neural networks (FMMNNs) are derived, and the upper bound of the setting time can be confirmed. Unlike previous jobs, this article focuses on applying different inequality techniques in the synchronous analysis process, rather than comparison principles to manage the multi-delay effects. In addition, this study removes the restrictive requirement that the activation function has a zero value at the switching jumps, and the discontinuous control protocol in this paper makes the networks achieve synchronization over a finite time, with some advantages in terms of the convergence speed. [ABSTRACT FROM AUTHOR]

De-mining operations are of critical importance for humanitarian efforts and safety in conflict-affected regions. In this paper, we address the challenge of enhancing the accuracy and efficiency of mine detection systems. We present an innovative Deep Learning architecture tailored for pulse induction-based Metallic Mine Detectors (MMD), so called DL-MMD. Our methodology leverages deep neural networks to distinguish amongst nine distinct materials with an exceptional validation accuracy of 93.5%. This high level of precision enables us not only to differentiate between anti-personnel mines, without metal plates but also to detect minuscule 0.2-g vertical paper pins in both mineralized soil and non-mineralized environments. Moreover, through comparative analysis, we demonstrate a substantial 3% and 7% improvement (approx.) in accuracy performance compared to the traditional K-Nearest Neighbors and Support Vector Machine classifiers, respectively. The fusion of deep neural networks with the pulse induction-based MMD not only presents a cost-effective solution but also significantly expedites decision-making processes in de-mining operations, ultimately contributing to improved safety and effectiveness in these critical endeavors. [ABSTRACT FROM AUTHOR]

To achieve high precision and robust control of switched reluctance machines (SRMs), this paper proposes a novel rotor position estimation method based on gain-optimized sliding mode observer (SMO) with neural networks and whale optimization algorithm. For the SMO, this paper uses the easily measured phase current to constitute the error function of the SMO, which requires less pre-stored data. Using the neural networks' powerful nonlinear mapping capability, the relationship between the sliding mode gains and speed estimation error and the position estimation error is obtained, and then the whale optimization algorithm is used to find the optimal sliding mode gains in the restricted range. The simulation and experiment results show that the accuracy of the SMO control system is significantly improved. [ABSTRACT FROM AUTHOR]

Image semantic segmentation technology is one of the core research contents in the field of computer vision. With the improvement of computer performance and the continuous development of deep learning technology, researchers have more and more enthusiasm to study the actual effect and performance of image semantic segmentation. The results of deep semantic segmentation allow computers to have a more detailed and accurate understanding of images, and have a wide range of application needs in the fields of autonomous driving, intelligent security, medical imaging, remote sensing images, etc. However, the existing image semantic segmentation algorithms have the disadvantages of easy discontinuous results and insufficient prediction accuracy. In this paper, we take deep learning-based image semantic segmentation technology as the research object to explore the improvement of the image semantic segmentation algorithm and its application in road scenarios. First, this paper proposes MCU-Net method based on residual fusion and multi-scale contextual information. MCU-Net uses residual fusion module to deepen the network structure and improve the ability of U-Net to acquire deeper features. Then a top-down and bottom-up path is constructed for feature information between different levels, and the spatial and semantic information contained in shallow and deep features in the network is fully utilized by fusing features from different levels. In addition, an enhanced void space pyramid pooling module is added for feature information between the same levels, which enables the output features to have a larger range of semantic information. Second, this paper proposes the DAMCU-Net method based on attention mechanism and edge detection based on MCU-Net. DAMCU-Net extracts global contextual information by the attention mechanism optimization module, while fusing features using dense jump connections to facilitate the network to recover more spatial detail information during upsampling, and uses the FReLU activation function to improve the segmentation capability of the network for complex targets. For the edge information lost in the feature extraction process, the edge detection branch is added to supplement the feature information of the main path by feature fusion to achieve the optimization of the edge information. [ABSTRACT FROM AUTHOR]

Context: With the union of machine learning (ML) and quantum chemistry, amid the debate between machine-learned functionals and human-designed functionals in density functional theory (DFT), this paper aims to demonstrate the generation of potential energy surfaces using computations with machine-learned density functional approximation (ML-DFA). A recent research trend is the application of ML in quantum sciences in the design of density functionals such as DeepMind's Deep Learning model (DeepMind21, DM21). Though science reported the state-of-the-art performance of DM21, the opportunity to utilize DeepMind's pretrained DM21 neural networks in computations in quantum chemistry has not yet been tapped. So far in the literature, the Deep Learning density functionals (DM21) have not been applied to generate potential energy surfaces. While the superior accuracy of DM21 has been reported, there is still a scarcity of publications that apply DM21 in calculations in the field. In this context, for the first time in literature, neural density functionals inferring 2D potential energy surfaces (ML-DFA-PES) based on machine-learned DFA-based computational method is contributed in this paper. This paper reports the ML-DFA-generated PES for C4H8, H2O, H2, and H2+ by employing a pretrained DM21m TensorFlow model with cc-pVDZ basis set. In addition, we also analyze the long-range behavior of DM21 based PES to investigate the ability to describe a system at long ranges. Furthermore, we compare PES diagrams from DM21 with popular DFT functionals (b3lyp/ PW6B95) and CCSD(T). Methods: In this method, 2D potential energy surfaces are obtained using a method that relies upon the neural network's ability to accurately learn the mapping between 3D electron density and exchange–correlation potential. By inserting Deep Learning inference in DFT with a pretrained neural network, self-consistent field (SCF) energy at different geometries along the coordinates of interest is computed, and then, potential energy surfaces are plotted. In this method, first, the electron density is computed mathematically, and this computed 3D electron density is used as a ML feature vector to predict the exchange correlation potential as a ML inference computed by a forward pass of pre-trained DM21 TensorFlow computational graph, followed by the computation of self-consistent field energy at multiple geometries, and then, SCF energies at different bond lengths/angles are plotted as 2D PES. We implement this in a python source code using frameworks such as PySCF and DM21. This paper contributes this implementation in open source. The source code and DM21-DFA-based PES are contributed at https://sites.google.com/view/MLfunctionals-DeepMind-PES. [ABSTRACT FROM AUTHOR]

Deep neural networks (DNN) have fundamentally revolutionized the artificial intelligence (AI) field. The transformer model is a type of DNN that was originally used for the natural language processing tasks and has since gained more and more attention for processing various kinds of sequential data, including biological sequences and structured electronic health records. Along with this development, transformer-based models such as BioBERT, MedBERT, and MassGenie have been trained and deployed by researchers to answer various scientific questions originating in the biomedical domain. In this paper, we review the development and application of transformer models for analyzing various biomedical-related datasets such as biomedical textual data, protein sequences, medical structured-longitudinal data, and biomedical images as well as graphs. Also, we look at explainable AI strategies that help to comprehend the predictions of transformer-based models. Finally, we discuss the limitations and challenges of current models, and point out emerging novel research directions. [ABSTRACT FROM AUTHOR]

CFRP hybrid bonded–bolted (HBB) joints combine the advantages of traditional joining methods, namely adhesive bonding, and bolting, to achieve optimal connection performance, making them the most favored connection method. The structural parameters of CFRP HBB joints, including overlap length, bolt-hole spacing, and fit clearance relationships, have a complex impact on connection performance. To enhance the connectivity performance of joint structures, this paper develops a multiscale finite element analysis model to investigate the impact of structural parameters on the strength of CFRP HBB joint structures. Coupled with experimental validation, the study reveals how changes in structural parameters affect the unidirectional tensile failure force of the joints. Building on this, an analytical approach and inverse design methodology for the mechanical properties of CFRP HBB joints based on deep supervised learning algorithms are developed. Neural networks accurately and efficiently predict the performance of joints with unprecedented combinations of parameters, thus expediting the inverse design process. This research combines experimentation and multiscale finite element analysis to explore the unknown relationships between the mechanical properties of CFRP HBB joints and their structural parameters. Furthermore, leveraging DNN neural networks, a rapid calculation method for the mechanical properties of hybrid joints is proposed. The findings lay the groundwork for the broader application and more intricate design of composite materials and their connection structures. [ABSTRACT FROM AUTHOR]

Generative adversarial networks (or GANs) are a specific deep learning architecture often used for different usages, such as data generation or image-to-image translation. In recent years, this structure has gained increased popularity and has been used in different fields. One area of expertise currently in vogue is the use of GANs to produce synthetic aperture radar (SAR) data, and especially expand training datasets for SAR automatic target recognition (ATR). In effect, the complex SAR image formation makes these kind of data rich in information, leading to the use of deep networks in deep learning-based methods. Yet, deep networks also require sufficient data for training. However, contrary to optical images, we generally do not have a substantial number of available SAR images because of their acquisition and labelling cost; GANs are then an interesting tool. Concurrently, how to improve explainability for SAR ATR deep neural networks and how to make their reasoning more transparent have been increasingly explored as model opacity deteriorates trust of users. This paper aims at reviewing how GANs are used with SAR images, but also giving perspectives on how GANs could be used to improve interpretability and explainability of SAR classifiers. [ABSTRACT FROM AUTHOR]

Intelligent control methodologies and artificial intelligence (AI) are essential components for the efficient management of energy storage modern systems, specifically those utilizing superconducting magnetic energy storage (SMES). Through the implementation of AI algorithms, SMES units are able to optimize their operations in real time, thereby maximizing energy efficiency. To have a more advanced understanding of this issue, DynamoMan is presented in this paper. For use with SMES systems, DynamoMan, an Artificial Neural Network (ANN)-tuned Fractional Order PID Brain Emotional Learning-Based Intelligent Controller (ANN-FOPID-BELBIC), has been developed. ANN tuning is employed to optimize the key settings of the reward/penalty generator of a BELBIC, which are important for its overall efficacy. Following this, DynamoMan is integrated into the SMES control system and compared to scenarios in which a BELBIC, PID, PI, and P are utilized. The findings indicate that DynamoMan performs considerably better than other models, demonstrating robust and control attributes alongside a considerably reduced period of settling time, especially when incorporated with the power grid. [ABSTRACT FROM AUTHOR]

The management of large enterprises influences their efficiency and profitability. One of the important aspects is the appropriate management of electricity consumption used for production and daily operation. The problem becomes more complicated when you need to manage not one but a large complex of buildings with heterogeneous purposes. In the paper, we examine real-time series data of electrical energy consumption in a complex of heterogeneous buildings, including offices and warehouses, using time series analysis methods such as the Holt–Winters model and ARIMA/SARIMA model, and neural networks (Deep Neural Network, Recurrent Neural Network, and Long Short-Term Memory). Experimental research was performed on a dataset obtained from an energy consumption meter placed in the building complex, built in different periods, and equipped with a variety of automation devices. The data were collected over a period of four years 2018–2021 in the form of time series. Results show that classic models are good at predicting energy consumption in the mentioned type of buildings. The ARIMA model gave the best results—for buildings characterized by seasonality and trends the forecasts were almost perfect with actual values. [ABSTRACT FROM AUTHOR]

This paper presents a novel crack size estimation method based on dilated convolution and time series fine tuning using in‐situ Lamb wave. The contributions of this proposed method are twofold: (1) a dilated convolution‐based neural network which is an effective representation learning methods with larger receptive fields for periodic signals and (2) a crack length adjustment approach based on previous estimations with a time series fine tuning method. The time series fine tuning method utilizes the monotonicity of the crack length with respect to time. A new evaluation metric has been adopted, which considers prediction errors, time errors, and monotonicity errors. The proposed method outperforms the previous feature extraction‐based methods with or without time series fine tuning in this new evaluation metric. Highlights: Crack estimation method using deep learning and time series fine tuning was proposed.The neural network using a combination of dilated convolution and long short‐term memory (LSTM) network was designed.The proposed method outperformed prior manual feature extraction‐based approaches. [ABSTRACT FROM AUTHOR]

This paper explores the application of multi-objective optimization techniques, including MOPSO, NSGA II, and SPEA2, to optimize the hyperparameters of artificial neural networks (ANNs) and support vector machines (SVMs) for predicting the physical properties of textile polymer composite materials (TPCMs). The optimization process utilizes data on the physical characteristics of the constituent fibers and fabrics used to manufacture these composites. By employing optimization algorithms, we aim to enhance the predictive accuracy of the ANN and SVM models, thereby facilitating the design and development of high-performance textile polymer composites. The effectiveness of the proposed approach is demonstrated through comparative analyses and validation experiments, highlighting its potential for optimizing complex material systems. [ABSTRACT FROM AUTHOR]

Introduction: Mpox (formerly monkeypox) is an infectious disease that spreads mostly through direct contact with infected animals or people's blood, bodily fluids, or cutaneous or mucosal lesions. In light of the global outbreak that occurred in 2022-2023, in this paper, we analyzed global Mpox univariate time series data and provided a comprehensive analysis of disease outbreaks across the world, including the USA with Brazil and three continents: North America, South America, and Europe. The novelty of this study is that it delved into the Mpox time series data by implementing the data-driven methods and a mathematical model concurrently--an aspect not typically addressed in the existing literature. The study is also important because implementing these models concurrently improved our predictions' reliability for infectious diseases. Methods: We proposed a traditional compartmental model and also implemented deep learning models (1D-convolutional neural network (CNN), long-short term memory (LSTM), bidirectional LSTM (BiLSTM), hybrid CNN-LSTM, and CNNBiLSTM) as well as statistical time series models: autoregressive integrated moving average (ARIMA) and exponential smoothing on the Mpox data. We also employed the least squares method fitting to estimate the essential epidemiological parameters in the proposed deterministic model. Results: The primary finding of the deterministic model is that vaccination rates can flatten the curve of infected dynamics and influence the basic reproduction number. Through the numerical simulations, we determined that increased vaccination among the susceptible human population is crucial to control disease transmission. Moreover, in case of an outbreak, our model showed the potential for epidemic control by adjusting the key epidemiological parameters, namely the baseline contact rate and the proportion of contacts within the human population. Next, we analyzed data-driven models that contribute to a comprehensive understanding of disease dynamics in different locations. Additionally, we trained models to provide short-term (eight-week) predictions across various geographical locations, and all eight models produced reliable results. Conclusion: This study utilized a comprehensive framework to investigate univariate time series data to understand the dynamics of Mpox transmission. The prediction showed that Mpox is in its die-out situation as of July 29, 2023. Moreover, the deterministic model showed the importance of the Mpox vaccination in mitigating the Mpox transmission and highlighted the significance of effectively adjusting key epidemiological parameters during outbreaks, particularly the contact rate in high-risk groups. [ABSTRACT FROM AUTHOR]

This paper explains about the determination of thermal conductivity, viscosity, density, and specific heat of water dispersed CoFe2O4 nanofluids experimentally. The obtained data was undergone with ANN-Levenberg-Marquardt algorithm. The utilized CoFe2O4 nanoparticles were synthesized through the chemical coprecipitation method. The obtained CoFe2O4 nanoparticles were characterized with different techniques. The properties were measured under 20°C to 60°C, and under 0.25% to 1.25% vol, respectively. The experimental results show, under the particle volume loading of 1.25%, the thermal conductivity value was raised by 27.56% at a temperature of 60°C, and the viscosity was increased by 49.36% at a temperature of 20°C, over the base fluid. Likewise, the density of nanofluids were increased and the specific heat of nanofluids were falls down over the base fluid. Results were also showing, the utilized ANN-Levenberg-Marquardt algorithm has good agreement with the obtained data. Based on Levenberg-Marquardt, the R2 coefficient of thermal conductivity, viscosity, density, and specific heat values are 0.99802, 0.99217, 0.98684, and 0.99948, respectively. [ABSTRACT FROM AUTHOR]

In this paper, a new command filter-based adaptive NN control strategy is developed to address the prescribed tracking performance issue for a class of nonstrict-feedback nonlinear systems. Compared with the existing performance functions, a new performance function, the fixed-time performance function, which does not depend on the accurate initial value of the error signal and has the ability of fixed-time convergence, is proposed for the first time. A radial basis function neural network is introduced to identify unknown nonlinear functions, and the characteristic of Gaussian basis functions is utilized to overcome the difficulties of the nonstrict-feedback structure. Moreover, in contrast to the traditional Backstepping technique, a command filter-based adaptive control algorithm is constructed, which solves the "explosion of complexity" problem and relaxes the assumption on the reference signal. Additionally, it is guaranteed that the tracking error falls within a prescribed small neighborhood by the designed performance functions in fixed time, and the closed-loop system is semi-globally uniformly ultimately bounded (SGUUB). The effectiveness of the proposed control scheme is verified by numerical simulation. [ABSTRACT FROM AUTHOR]

In the complex dynamics of modern information systems such as e-commerce and streaming services, managing uncertainty and leveraging information theory are crucial in enhancing session-aware recommender systems (SARSs). This paper presents an innovative approach to SARSs that combines static long-term and dynamic short-term preferences within a counterfactual causal framework. Our method addresses the shortcomings of current prediction models that tend to capture spurious correlations, leading to biased recommendations. By incorporating a counterfactual viewpoint, we aim to elucidate the causal influences of static long-term preferences on next-item selections and enhance the overall robustness of predictive models. We introduce a dual-tower architecture with a novel data augmentation process and a self-supervised training strategy, tailored to tackle inherent biases and unreliable correlations. Extensive experiments demonstrate the effectiveness of our approach, outperforming existing benchmarks and paving the way for more accurate and reliable session-based recommendations. [ABSTRACT FROM AUTHOR]

The applications of deep learning and artificial intelligence have permeated daily life, with time series prediction emerging as a focal area of research due to its significance in data analysis. The evolution of deep learning methods for time series prediction has progressed from the Convolutional Neural Network (CNN) and the Recurrent Neural Network (RNN) to the recently popularized Transformer network. However, each of these methods has encountered specific issues. Recent studies have questioned the effectiveness of the self-attention mechanism in Transformers for time series prediction, prompting a reevaluation of approaches to LTSF (Long Time Series Forecasting) problems. To circumvent the limitations present in current models, this paper introduces a novel hybrid network, Temporal Convolutional Network-Linear (TCN-Linear), which leverages the temporal prediction capabilities of the Temporal Convolutional Network (TCN) to enhance the capacity of LSTF-Linear. Time series from three classical chaotic systems (Lorenz, Mackey–Glass, and Rossler) and real-world stock data serve as experimental datasets. Numerical simulation results indicate that, compared to classical networks and novel hybrid models, our model achieves the lowest RMSE, MAE, and MSE with the fewest training parameters, and its R2 value is the closest to 1. [ABSTRACT FROM AUTHOR]

This paper presents a novel approach to automated music mixing, focusing on the optimization of loudness control in multi-track recordings. By taking into consideration the complexity and artistic nature of traditional mixing processes, we introduce a personalized multi-track leveling method using two types of approaches: a customized genetic algorithm and a neural network-based method. Our method tackles common challenges encountered by audio professionals during prolonged mixing sessions, where consistency can decrease as a result of fatigue. Our algorithm serves as a 'virtual assistant' to consistently uphold the initial mixing objectives, hence assuring consistent quality throughout the process. In addition, our system automates the repetitive elements of the mixing process, resulting in a substantial reduction in production time. This enables engineers to dedicate their attention to more innovative and intricate jobs. Our experimental framework involves 20 diverse songs and 10 sound engineers possessing a wide range of expertise, offering a useful perspective on the adaptability and effectiveness of our method in real-world scenarios. The results demonstrate the capacity of the algorithms to mimic decision-making, achieving an optimal balance in the mix that resonates with the emotional and technical aspects of music production. [ABSTRACT FROM AUTHOR]

Background: Calibrating material models to experimental measurements is crucial for realistic computational analysis of components. For complex material models, however, optimization-based identification procedures can become time-consuming, particularly if the optimization problem is ill-posed. Objective: The objective of this paper is to assess the feasibility of using machine learning to identify the parameters of a Chaboche-type material model that describes copper alloys. Specifically, we apply and analyze this identification approach using short-term uniaxial relaxation tests on a C19010 copper alloy. Methods: A genetic algorithm forms the basis for identifying the parameters of the Chaboche-type material model. The approach is accelerated by replacing the numerical simulation of the experimental setup by a neural network surrogate. The neural networks-based approach is compared against a classic approach using both, synthetic and experimental data. Results: The results show that on the one hand, a sufficiently accurate identification of the material model parameters can be achieved by a classic but time-consuming genetic algorithm. On the other hand, it is shown that machine learning enables a much more time-efficient identification procedure, however, suffering from the ill-posedness of the identification problem. Conclusion: Compared to classic parameter identification approaches, machine learning techniques can significantly accelerate the identification procedure for parameters of Chaboche-type material models with acceptable loss of accuracy. [ABSTRACT FROM AUTHOR]

The objectives of this paper are to investigate the trade-offs 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 (v1.0), 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. [ABSTRACT FROM AUTHOR]

In recent years, with the continuous development and popularization of unmanned aerial vehicle (UAVs) technology, the surge in the number of UAVs has led to an increasingly serious problem of illegal flights. Traditional acoustic-based UAV localization techniques have limited ability to extract short-time and long-time signal features, and have poor localization performance in low signal-to-noise ratio environments. For this reason, in this paper, we propose a deep learning-based UAV localization technique in low signal-to-noise ratio environments. Specifically, on the one hand, we propose a multiple signal classification (MUSIC) pseudo-spectral normalized mean processing technique to improve the direction of arrival (DOA) performance of a traditional broadband MUSIC algorithm. On the other hand, we design a DOA estimation algorithm for UAV sound sources based on a time delay estimation neural network, which solves the problem of limited DOA resolution and the poor performance of traditional time delay estimation algorithms under low signal-to-noise ratio conditions. We verify the feasibility of the proposed method through simulation experiments and experiments in real scenarios. The experimental results show that our proposed method can locate the approximate flight path of a UAV within 20 m in a real scenario with a signal-to-noise ratio of −8 dB. [ABSTRACT FROM AUTHOR]

This paper presents a novel forecasting methodology based on neural networks and second-generation wavelets, and an example of application of such methodology for forecasting the oil temperature of an actual power transformer. The proposed method consists on selecting the variables with the highest correlation concerning the magnitude to be predicted (in situations featuring multiple variables), selecting the most appropriate second-generation wavelet from a set of candidate lifting wavelet transforms to smooth each variable's data and using the values smoothed by the selected second-generation wavelet to train the considered neural network. The authors applied the proposed methodology to predict the oil temperature of an existing transformer for four days and for one month using field data collected during four years of equipment operation. The obtained results indicate that selecting the most appropriate second-generation wavelet considering different selection techniques and using them to smooth the input variables significantly reduce the forecasting errors. The application of the proposed approach to forecast the oil temperature from the field-collected data using a long short-term memory neural network considering different batch sizes, neuron numbers and second-generation wavelet selection techniques decreased the average forecasting errors presented by using just the considered long short-term memory network by up to eleven times. The innovations of this proposal about literature are the use of correlation-based variable selection techniques given improving neural network forecasting accuracy, which is unprecedented in transformer insulating oil temperature forecasting applications, and the employment of SGWs to smooth the network's inputs to increase the accuracy of the model significantly. For the application case study presented in this research, the minor average forecasting errors in percentage to predict the four-day and one-month future temperature were, respectively, 0.012 and 0.326%. Also, for one month of forecasting, the average error in degrees Celsius was less than 0.2. [ABSTRACT FROM AUTHOR]

This research paper aims to ensure the reliable and efficient operation of grid-connected solid-state transformers (SSTs) by detecting and evaluating various undesirable operating conditions. The study considers different types of faults, including internal faults like open switches and open capacitors, external faults such as symmetrical and asymmetrical faults occurring at various locations of the SST, and abnormalities on the grid side known as sympathetic inrush conditions. To analyze these operating conditions, the secondary current of the high-frequency transformer is normalized and decomposed using the discrete wavelet transform (DWT) and wavelet packet transform (WPT). From the DWT and WPT decomposition at multiple levels, several statistical parameters are calculated. These statistical parameters are carefully selected from different decomposition levels to enhance the effectiveness of the detection algorithm utilizing DWT and WPT. In order to quickly identify and classify all operating conditions that impact the performance of the grid-connected SST, a three-layer feedforward artificial neural network (ANN) is employed, using the selected statistical features. The accuracy and efficiency of the ANN-based classification approach are evaluated by assessing the effectiveness of the statistical features obtained from DWT and WPT. Simulation results have been altered by introducing various noise levels to systematically assess the performance of the proposed algorithms. The average accuracy of the DWT-ANN algorithm stands at 97.89%, while the WPT-ANN algorithm achieves a slightly elevated accuracy level of 98.01%. This notable similarity in accuracy curtails from the careful selection of the wavelet function, decomposition level, and feature sets. [ABSTRACT FROM AUTHOR]

This paper presents the results of a study on data preprocessing and modeling for predicting corrosion in water pipelines of a steel industrial plant. The use case is a cooling circuit consisting of both direct and indirect cooling. In the direct cooling circuit, water comes into direct contact with the product, whereas in the indirect one, it does not. In this study, advanced machine learning techniques, such as extreme gradient boosting and deep neural networks, have been employed for two distinct applications. Firstly, a virtual sensor was created to estimate the corrosion rate based on influencing process variables, such as pH and temperature. Secondly, a predictive tool was designed to foresee the future evolution of the corrosion rate, considering past values of both influencing variables and the corrosion rate. The results show that the most suitable algorithm for the virtual sensor approach is the dense neural network, with MAPE values of (25 ± 4)% and (11 ± 4)% for the direct and indirect circuits, respectively. In contrast, different results are obtained for the two circuits when following the predictive tool approach. For the primary circuit, the convolutional neural network yields the best results, with MAPE = 4% on the testing set, whereas for the secondary circuit, the LSTM recurrent network shows the highest prediction accuracy, with MAPE = 9%. In general, models employing temporal windows have emerged as more suitable for corrosion prediction, with model performance significantly improving with a larger dataset. [ABSTRACT FROM AUTHOR]

Image watermarking often involves the use of handheld devices under non-structured conditions for authentication purposes, particularly in the print-cam process where smartphone cameras are used to capture watermarked printed images. However, these images frequently suffer from perspective distortions, making them unsuitable for automated information detection. To address this issue, Cam-Unet, an end-to-end neural network architecture, is presented to predict the mapping from distorted images to rectified ones, specifically tailored for print-cam challenges applied to ID images. Given the limited availability of large-scale real datasets containing ground truth distortions, we created an extensive synthetic dataset by subjecting undistorted images to print-cam attacks. The proposed network is trained on this dataset, using various data augmentation techniques to improve its generalization capabilities. Accordingly, this paper presents an image watermarking system for the print-cam process. The approach combines Fourier transform-based watermarking with Cam-Unet as perspective distortion correction. Results show that the proposed method outperforms existing watermarking approaches typically employed to counter print-cam attacks and achieves an optimal balance between efficiency and cost-effectiveness. [ABSTRACT FROM AUTHOR]

One of the main lines of research in distributed learning in recent years is the one related to Federated Learning (FL). In this work, a decentralized Federated Learning algorithm based on consensus (CoL) is applied to Wireless Ad-hoc Networks (WANETs), where the agents communicate with other agents to share their learning model as they are available to the wireless connection range. When deploying a set of agents, it is essential to study whether all the WANET agents will be reachable before the deployment. The paper proposes to explore it by generating a simulation close to the real world using a framework (FIVE) that allows the easy development and modification of simulations based on Unity and SPADE agents. A fruit orchard with autonomous tractors is presented as a case study. The paper also presents how and why the concept of artifact has been included in the above-mentioned framework as a way to highlight the importance of some devices used in the environment that have to be located in specific places to ensure the full connection of the system. This inclusion is the first step to allow Digital Twins to be modeled with this framework, now allowing a Digital Shadow of those devices. [ABSTRACT FROM AUTHOR]

Recently, transfer learning has gained popularity in the machine learning community. Transfer Learning (TL) has emerged as a promising paradigm that leverages knowledge learned from one or more related domains to improve prediction accuracy in a target domain with limited data. However, for time series forecasting (TSF) applications, transfer learning is relatively new. This paper addresses the need for empirical studies as identified in recent reviews advocating the need for practical guidelines for Transfer Learning approaches and method designs for time series forecasting. The main contribution of this paper is the suggestion of a comprehensive framework for Transfer Learning Sensitivity Analysis (SA) for time series forecasting. We achieve this by identifying various parameters seen from various angles of transfer learning applied to time series, aiming to uncover factors and insights that influence the performance of transfer learning in time series forecasting. Undoubtedly, symmetry appears to be a core aspect in the consideration of these factors and insights. A further contribution is the introduction of four TL performance metrics encompassed in our framework. These TL performance metrics provide insight into the extent of the transferability between the source and the target domains. Analyzing whether the benefits of transferred knowledge are equally or unequally accessible and applicable across different domains or tasks speaks to the requirement of symmetry or asymmetry in transfer learning. Moreover, these TL performance metrics inform on the possibility of the occurrence of negative transfers and also provide insight into the possible vulnerability of the network to catastrophic forgetting. Finally, we discuss a sensitivity analysis of an Ensemble TL technique use case (with Multilayer Perceptron models) as a proof of concept to validate the suggested framework. While the results from the experiments offer empirical insights into various parameters that impact the transfer learning gain, they also raise the question of network dimensioning requirements when designing, specifically, a neural network for transfer learning. [ABSTRACT FROM AUTHOR]

This paper focuses on the modeling of automatic pricing and replenishment strategies for perishable products with time-varying deterioration rates based on an improved SVR-LSTM-ARIMA hybrid model. This research aims to support supermarkets in planning future strategies, optimizing category structure, reducing loss rates, and improving profit margins and service quality. Specifically, the paper selects perishable vegetables as the research category and calculates the cost-plus ratio for each vegetable category. Correlation analysis is conducted with total sales, and a non-parametric relationship curve is obtained using support vector regression for nonlinear fitting. The long and short memory recurrent neural network is then used to predict sales volume, and a pricing strategy is calculated based on the fitting curve. Additionally, the paper establishes a correlation between loss rate and shelf life, corrects the daily average sales volume index, and solves the problem of quantity and category of replenishment using a backpack problem approach. By considering multiple constraints, a quantitative category replenishment volume and pricing strategy is obtained. The mathematical model proposed in this paper addresses the replenishment and pricing challenges faced by supermarkets, aiming to improve revenue and reduce loss while meeting market requirements. [ABSTRACT FROM AUTHOR]

Operational load monitoring (OLM) is an industrial process related to structural health monitoring, where fatigue of the structure is tracked. Artificial intelligence methods, such as artificial neural networks (ANNs) or Gaussian processes, are utilized to improve efficiency of such processes. This paper focuses on moving such processes towards green computing by deploying and executing the algorithm on low-power consumption FPGA where high-throughput and truly parallel computations can be performed. In the following paper, the OLM process of typical aerostructure (hat-stiffened composite panel) is performed using ANN. The ANN was trained using numerically generated data, of every possible load case, to be working with sensor measurements as inputs. The trained ANN was deployed to Xilinx Artix-7 A100T FPGA of a real-time microcontroller. By executing the ANN on FPGA (where every neuron of a given layer can be processed at the same time, without limiting the number of parallel threads), computation time could be reduced by 70% as compared to standard CPU execution. Series of real-time experiments were performed that have proven the efficiency and high accuracy of the developed FPGA-based algorithm. Adjusting the ANN algorithm to FPGA requirements takes some effort, however it can lead to high performance increase. FPGA has the advantages of many more potential parallel threads than a standard CPU and much lower consumption than a GPU. This is particularly important taking into account potential embedded and remote applications, such as widely performed monitoring of airplane structures. [ABSTRACT FROM AUTHOR]

Short-term wind power forecasting has difficult problems due to the very large variety of speeds of the wind, which is a key factor in producing energy. From the point of view of the whole country, an important problem is predicting the total impact of wind power's contribution to the country's energy demands for succeeding days. Accordingly, efficient planning of classical power sources may be made for the next day. This paper will investigate this direction of research. Based on historical data, a few neural network predictors will be combined into an ensemble that is responsible for the next day's wind power generation. The problem is difficult since wind farms are distributed in large regions of the country, where different wind conditions exist. Moreover, the information on wind speed is not available. This paper proposes and compares different structures of an ensemble combined from three neural networks. The best accuracy has been obtained with the application of an MLP combiner. The results of numerical experiments have shown a significant reduction in prediction errors compared to the naïve approach. The improvement in results with this naïve solution is close to two in the one-day-ahead prediction task. [ABSTRACT FROM AUTHOR]

The surge in the intelligent information age has led to a growing need for enhanced computing power in smart mobile devices. However, the accompanying increase in computing power brings about a significant challenge — high power consumption. This poses a notable hurdle for mobile devices that prioritize sustainability performance. Effectively addressing power consumption estimation is crucial for overcoming this sustainability issue. In this paper, we propose using a branching parallel neural networks (BPNS) that consists of FCNN-LSTM and a attention mechanism to estimate the power consumption of a device. In addition, a data stabilization module is incorporated into the framework to improve the power estimation accuracy. We implement and assess the performance of BPNS for online estimation across diverse smart mobile devices, conducting a comparative analysis with commonly used neural networks. Notably, our approach achieves a deviation of 0.28W, 0.65W and 0.76W for online estimation on three smart mobile devices, and outperforms other methods in terms of estimation accuracy and computational cost. [ABSTRACT FROM AUTHOR]

Demand response management (DRM) plays a crucial role in the prospective development of smart grids. The precise estimation of electricity demand for individual houses is vital for optimizing the operation and planning of the power system. Accurate forecasting of the required components holds significance as it can substantially impact the final cost, mitigate risks, and support informed decision-making. In this paper, a forecasting approach employing neural networks for smart grid demand-side management is proposed. The study explores various enhanced artificial neural network (ANN) architectures for forecasting smart grid consumption. The performance of the ANN approach in predicting energy demands is evaluated through a comparison with three statistical models: a time series model, an auto-regressive model, and a hybrid model. Experimental results demonstrate the ability of the proposed neural network framework to deliver accurate and reliable energy demand forecasts. [ABSTRACT FROM AUTHOR]

Autonomous mobile robots are essential to the industry, and human–robot interactions are becoming more common nowadays. These interactions require that the robots navigate scenarios with static and dynamic obstacles in a safely manner, avoiding collisions. This paper presents a physical implementation of a method for dynamic obstacle avoidance using a long short-term memory (LSTM) neural network that obtains information from the mobile robot's LiDAR for it to be capable of navigating through scenarios with static and dynamic obstacles while avoiding collisions and reaching its goal. The model is implemented using a TurtleBot3 mobile robot within an OptiTrack motion capture (MoCap) system for obtaining its position at any given time. The user operates the robot through these scenarios, recording its LiDAR readings, target point, position inside the MoCap system, and its linear and angular velocities, all of which serve as the input for the LSTM network. The model is trained on data from multiple user-operated trajectories across five different scenarios, outputting the linear and angular velocities for the mobile robot. Physical experiments prove that the model is successful in allowing the mobile robot to reach the target point in each scenario while avoiding the dynamic obstacle, with a validation accuracy of 98.02%. [ABSTRACT FROM AUTHOR]

This paper shows solicitude for the generalized projective synchronization of Caputo fractional-order uncertain memristive neural networks (FOUMNNs) with multiple delays. By extending the constant scale factor to the time-varying function matrix, we establish an extraordinary synchronization mode called time-varying function matrix projection synchronization (TFMPS), which is a generalized version of traditional matrix projection synchronization, modified projection synchronization, complete synchronization, and anti-synchronization. To achieve the goal of TFMPS, we design a novel mixed controller including the open loop feedback control and impulsive control, which employs the state information in the time-delayed interval and the sampling information at the impulse instants. It has a prominent advantage that impulse intervals are not restricted by time delays. To establish the connection between the error system and the auxiliary system, a generalized fractional-order comparison theorem with time-varying coefficients and impulses is established. Applying the stability theory, the comparison theorem, and the Laplace transform, new synchronization criteria of FOUMNNs are acquired under the mixed impulsive control schemes, and the derived synchronization theorem and corollary can effectively expand the correlative synchronization achievements of fractional-order systems. [ABSTRACT FROM AUTHOR]

Obstructive sleep apnea/hypopnea syndrome (OSAHS) is a condition linked to severe cardiovascular and neuropsychological consequences, characterized by recurrent episodes of partial or complete upper airway obstruction during sleep, leading to compromised ventilation, hypoxemia, and micro-arousals. Polysomnography (PSG) serves as the gold standard for confirming OSAHS, yet its extended duration, high cost, and limited availability pose significant challenges. In this paper, we employ a range of machine learning techniques, including Neural Networks, Decision Trees, Random Forests, and Extra Trees, for OSAHS diagnosis. This approach aims to achieve a diagnostic process that is not only more accessible but also more efficient. The dataset utilized in this study consists of records from 601 adults assessed between 2014 and 2016 at a specialized sleep medical center in Colombia. This research underscores the efficacy of ensemble methods, specifically Random Forests and Extra Trees, achieving an area under the Receiver Operating Characteristic (ROC) curve of 89.2% and 89.6%, respectively. Additionally, a web application has been devised, integrating the optimal model, empowering qualified medical practitioners to make informed decisions through patient registration, an input of 18 variables, and the utilization of the Random Forests model for OSAHS screening. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI) has emerged as a powerful tool in healthcare significantly impacting practices from diagnostics to treatment delivery and patient management. This article examines the progress of AI in healthcare, starting from the field's inception in the 1960s to present-day innovative applications in areas such as precision medicine, robotic surgery, and drug development. In addition, the impact of the COVID-19 pandemic on the acceleration of the use of AI in technologies such as telemedicine and chatbots to enhance accessibility and improve medical education is also explored. Looking forward, the paper speculates on the promising future of AI in healthcare while critically addressing the ethical and societal considerations that accompany the integration of AI technologies. Furthermore, the potential to mitigate health disparities and the ethical implications surrounding data usage and patient privacy are discussed, emphasizing the need for evolving guidelines to govern AI's application in healthcare. [ABSTRACT FROM AUTHOR]

We apply supervised learning to a general problem in queueing theory: using a neural net, we develop a fast and accurate predictor of the stationary system-length distribution of a GI/GI/1 queue—a fundamental queueing model for which no analytical solutions are available. To this end, we must overcome three main challenges: (i) generating a large library of training instances that cover a wide range of arbitrary interarrival and service time distributions, (ii) labeling the training instances, and (iii) providing continuous arrival and service distributions as inputs to the neural net. To overcome (i), we develop an algorithm to sample phase-type interarrival and service time distributions with complex transition structures. We demonstrate that our distribution-generating algorithm indeed covers a wide range of possible positive-valued distributions. For (ii), we label our training instances via quasi-birth-and-death(QBD) that was used to approximate PH/PH/1 (with phase-type arrival and service process) as labels for the training data. For (iii), we find that using only the first five moments of both the interarrival and service times distribution as inputs is sufficient to train the neural net. Our empirical results show that our neural model can estimate the stationary behavior of the GI/GI/1—far exceeding other available methods in terms of both accuracy and runtimes. History: Ram Ramesh, Area Editor for Data Science and Machine Learning. Funding: O. Baron received financial support from the Natural Sciences and Engineering Research Council of Canada (NERC) [Grant 458051]. D. Krass received financial support from the NERC [Grant 458395]. Supplemental Material: The software that supports the findings of this study is available within the paper and its Supplemental Information (https://pubsonline.informs.org/doi/suppl/10.1287/ijoc.2022.0263) as well as from the IJOC GitHub software repository (https://github.com/INFORMSJoC/2022.0263). The complete IJOC Software and Data Repository is available at https://informsjoc.github.io/. [ABSTRACT FROM AUTHOR]

Solar wind modeling is classified into two main types: empirical models and physics-based models, each designed to forecast solar wind properties in various regions of the heliosphere. Empirical models, which are cost-effective, have demonstrated significant accuracy in predicting solar wind at the L1 Lagrange point. On the other hand, physics-based models rely on magnetohydrodynamics (MHD) principles and demand more computational resources. In this research paper, we build upon our recent novel approach that merges empirical and physics-based models. Our recent proposal involves the creation of a new physics-informed neural network that leverages time series data from solar wind predictors to enhance solar wind prediction. This innovative method aims to combine the strengths of both modeling approaches to achieve more accurate and efficient solar wind predictions. In this work, we show the variability of the proposed physics-informed loss across multiple deep learning models. We also study the effect of training the models on different solar cycles on the model's performance. This work represents the first effort to predict solar wind by integrating deep learning approaches with physics constraints and analyzing the results across three solar cycles. Our findings demonstrate the superiority of our physics-constrained model over other unconstrained deep learning predictive models. [ABSTRACT FROM AUTHOR]

Nowadays, trajectory control is a significant issue for unmanned micro aerial vehicles (MAVs) due to large disturbances such as wind and storms. Trajectory control is typically implemented using a proportional–integral–derivative (PID) controller. In order to achieve high accuracy in trajectory tracking, it is essential to set the PID gain parameters to optimum values. For this reason, separate gain values are set for roll, pitch and yaw movements before autonomous flight in quadrotor systems. Traditionally, this adjustment is performed manually or automatically in autotune mode. Given the constraints of narrow orchard corridors, the use of manual or autotune mode is neither practical nor effective, as the quadrotor system has to fly in narrow apple orchard corridors covered with hail nets. These reasons require the development of an innovative solution specific to quadrotor vehicles designed for constrained areas such as apple orchards. This paper recognizes the need for effective trajectory control in quadrotors and proposes a novel neural network-based approach to tuning the optimal PID control parameters. This new approach not only improves trajectory control efficiency but also addresses the unique challenges posed by environments with constrained locational characteristics. Flight simulations using the proposed neural network models have demonstrated successful trajectory tracking performance and highlighted the superiority of the feed-forward back propagation network (FFBPN), especially in latitude tracking within 7.52745 × 10−5 RMSE trajectory error. Simulation results support the high performance of the proposed approach for the development of automatic flight capabilities in challenging environments. [ABSTRACT FROM AUTHOR]

In this paper, the implementation of a new pupil detection system based on artificial intelligence techniques suitable for real-time and real-word applications is presented. The proposed AI-based pupil detection system uses a classifier implemented with slim-type neural networks, with its classes being defined according to the possible positions of the pupil within the eye image. In order to reduce the complexity of the neural network, a new parallel architecture is used in which two independent classifiers deliver the pupil center coordinates. The training, testing, and validation of the proposed system were performed using almost 40,000 eye images with a resolution of 320 × 240 pixels and coming from 20 different databases, with a high degree of generality. The experimental results show a detection rate of 96.29% at five pixels with a standard deviation of 3.38 pixels for all eye images from all databases and a processing speed of 100 frames/s. These results indicate both high accuracy and high processing speed, and they allow us to use the proposed solution for different real-time applications in variable and non-uniform lighting conditions, in fields such as assistive technology to communicate with neuromotor-disabled patients by using eye typing, in computer gaming, and in the automotive industry for increasing traffic safety by monitoring the driver's cognitive state. [ABSTRACT FROM AUTHOR]

Currently, Text-to-Speech (TTS) technology, aimed at reproducing a natural human voice from text, is gaining increasing demand in natural language processing. Key criteria for evaluating the quality of synthesized sound include its clarity and naturalness, which largely depend on the accurate modeling of intonations using the acoustic model in the speech generation system. This paper presents fundamental methods such as concatenative and parametric speech synthesis, speech synthesis based on hidden Markov models, and deep learning approaches like end-to-end models for building the acoustic model. The article discusses metrics for evaluating the quality of synthesized voice. Brief overviews of modern text-to-speech architectures, such as WaveNet, Tacotron, and Deep Voice, applying deep learning and demonstrating quality ratings close to professionally recorded speech, are also provided. [ABSTRACT FROM AUTHOR]

In recent years, the need for systems capable of achieving the dynamic learning and information storage efficiency of the biological brain has led to the emergence of neuromorphic research. In particular, neuromorphic optics was born with the idea of reproducing the functional and structural properties of the biological brain. In this context, solitonic neuromorphic research has demonstrated the ability to reproduce dynamic and plastic structures capable of learning and storing through conformational changes in the network. In this paper, we demonstrate that solitonic neural networks are capable of mimicking the functional behaviour of biological neural tissue, in terms of synaptic formation procedures and dynamic reinforcement. [ABSTRACT FROM AUTHOR]

During the development of the nervous system, neuronal cells extend axons and dendrites that form complex neuronal networks, which are essential for transmitting and processing information. Understanding the physical processes that underlie the formation of neuronal networks is essential for gaining a deeper insight into higher-order brain functions such as sensory processing, learning, and memory. In the process of creating networks, axons travel towards other recipient neurons, directed by a combination of internal and external cues that include genetic instructions, biochemical signals, as well as external mechanical and geometrical stimuli. Although there have been significant recent advances, the basic principles governing axonal growth, collective dynamics, and the development of neuronal networks remain poorly understood. In this paper, we present a detailed analysis of nonlinear dynamics for axonal growth on surfaces with periodic geometrical patterns. We show that axonal growth on these surfaces is described by nonlinear Langevin equations with speed-dependent deterministic terms and gaussian stochastic noise. This theoretical model yields a comprehensive description of axonal growth at both intermediate and long time scales (tens of hours after cell plating), and predicts key dynamical parameters, such as speed and angular correlation functions, axonal mean squared lengths, and diffusion (cell motility) coefficients. We use this model to perform simulations of axonal trajectories on the growth surfaces, in turn demonstrating very good agreement between simulated growth and the experimental results. These results provide important insights into the current understanding of the dynamical behavior of neurons, the self-wiring of the nervous system, as well as for designing innovative biomimetic neural network models. [ABSTRACT FROM AUTHOR]

It is often difficult to describe natural time series due to implicit dependences and correlated noise. During anomalous natural processes, anomalous features appear in data. They have a nonstationary structure and do not allow us to apply traditional methods for time series modeling. In order to solve these problems, new models, adequately describing natural data, are required. A new hybrid model of a time series (HMTS) with a nonstationary structure is proposed in this paper. The HMTS has regular and anomalous components. The HMTS regular component is determined on the basis of an autoencoder neural network. To describe the HMTS anomalous component, an adaptive nonlinear approximating scheme (ANAS) is used on a wavelet basis. HMTS is considered in this investigation for the problem of neutron monitor data modeling and anomaly detection. Anomalies in neutron monitor data indicate negative factors in space weather. The timely detection of these factors is critically important. This investigation showed that the developed HMTS adequately describes neutron monitor data and has satisfactory results from the point of view of numeric performance. The MSE model values are close to 0 and errors are white Gaussian noise. In order to optimize the estimate of the HMTS anomalous component, the likelihood ratio test was applied. Moreover, the wavelet basis, giving the least losses during ANAS construction, was determined. Statistical modeling results showed that HMTS provides a high accuracy of anomaly detection. When the signal/noise ratio is 1.3 and anomaly durations are more than 60 counts, the probability of their detection is close to 90%. This is a high rate in the problem domain under consideration and provides solution reliability of the problem of anomaly detection in neutron monitor data. Moreover, the processing of data from several neutron monitor stations showed the high sensitivity of the HMTS. This shows the possibility to minimize the number of engaged stations, maintaining anomaly detection accuracy compared to the global survey method widely used in this field. This result is important as the continuous operation of neutron monitor stations is not always provided. Thus, the results show that the developed HMTS has the potential to address the problem of anomaly detection in neutron monitor data even when the number of operating stations is small. The proposed HMTS can help us to decrease the risks of the negative impact of space weather anomalies on human health and modern infrastructure. [ABSTRACT FROM AUTHOR]

This paper tackles the challenge of time series forecasting in the presence of missing data. Traditional methods often struggle with such data, which leads to inaccurate predictions. We propose a novel framework that combines the strengths of Generative Adversarial Networks (GANs) and Bayesian inference. The framework utilizes a Conditional GAN (C-GAN) to realistically impute missing values in the time series data. Subsequently, Bayesian inference is employed to quantify the uncertainty associated with the forecasts due to the missing data. This combined approach improves the robustness and reliability of forecasting compared to traditional methods. The effectiveness of our proposed method is evaluated on a real-world dataset of air pollution data from Mexico City. The results demonstrate the framework's capability to handle missing data and achieve improved forecasting accuracy. [ABSTRACT FROM AUTHOR]

The advancement of unmanned aerial vehicles (UAVs) enables early detection of numerous disasters. Efforts have been made to automate the monitoring of data from UAVs, with machine learning methods recently attracting significant interest. These solutions often face challenges with high computational costs and energy usage. Conventionally, data from UAVs are processed using cloud computing, where they are sent to the cloud for analysis. However, this method might not meet the real-time needs of disaster relief scenarios. In contrast, edge computing provides real-time processing at the site but still struggles with computational and energy efficiency issues. To overcome these obstacles and enhance resource utilization, this paper presents a convolutional neural network (CNN) model with an early exit mechanism designed for fire detection in UAVs. This model is implemented using TSMC 40 nm CMOS technology, which aids in hardware acceleration. Notably, the neural network has a modest parameter count of 11.2 k. In the hardware computation part, the CNN circuit completes fire detection in approximately 230,000 cycles. Power-gating techniques are also used to turn off inactive memory, contributing to reduced power consumption. The experimental results show that this neural network reaches a maximum accuracy of 81.49% in the hardware implementation stage. After automatic layout and routing, the CNN hardware accelerator can operate at 300 MHz, consuming 117 mW of power. [ABSTRACT FROM AUTHOR]

Arc faults are the main cause of electrical fires according to national fire data statistics. Intensive studies of artificial intelligence-based arc fault detection methods have been carried out and achieved a high detection accuracy. However, the computational complexity of the artificial intelligence-based methods hinders their application for arc fault detection devices. This paper proposes a lightweight arc fault detection method based on the discrimination of a novel feature for lower current distortion conditions and the Adam-optimized BP neural network for higher distortion conditions. The novel feature is the pulse signal number per unit cycle, reflecting the zero-off phenomena of the arc current. Six features, containing the novel feature, are chosen as the inputs of the neural network, reducing the computational complexity. The model achieves a high detection accuracy of 99.27% under various load types recommended by the IEC 62606 standard. Finally, the proposed lightweight method is implemented on hardware based on the STM32 series microcontroller unit. The experimental results show that the average detection accuracy is 98.33%, while the average detection time is 45 ms and the average tripping time is 72–201 ms under six types of loads, which can fulfill the requirements of real-time detection for commercial arc fault detection devices. [ABSTRACT FROM AUTHOR]

This research delves into the cybersecurity implications of neural network training in cloud-based services. Despite their recognition for solving IT problems, the resource-intensive nature of neural network training poses challenges, leading to increased reliance on cloud services. However, this dependence introduces new cybersecurity risks. The study focuses on a novel attack method exploiting neural network weights to discreetly distribute hidden malware. It explores seven embedding methods and four trigger types for malware activation. Additionally, the paper introduces an open-source framework automating code injection into neural network weight parameters, allowing researchers to investigate and counteract this emerging attack vector. [ABSTRACT FROM AUTHOR]

Tsunami simulations require powerful computational resources to be performed efficiently. Although the modern graphics processing units (GPUs) allow the acceleration of this kind of simulations, they can still last many minutes or even hours for simulations which have to deal with very high spatial resolutions or simulation times. In this paper, we propose a method to predict the alert or inundation level of a tsunami generated by an earthquake using deep learning methods. In particular, we train multilayer perceptron (MLP) neural networks for predicting the alert level due to a tsunami at given coastal locations. Ensemble methods are used to improve the predictions of the neural networks. Tsunamis caused by ruptures of several fault segments at different time instants, application to real events, probabilistic forecasting and comparison with other machine learning algorithms are also addressed. Results on realistic scenarios confirm that good accuracies are obtained. The inference times of the trained networks and ensembles are also very low, lasting less than one second to predict the results of thousands of simulations. The proposed method could be used in a tsunami early warning system along with the application of scaling laws. Plain Language Summary: In tsunami early warning systems (TEWS) it is crucial to perform fast predictions of the risk of a tsunami in coastal areas in order to take appropriate measures before the arrival of the tsunami. Currently, tsunami simulations may take many minutes or even hours despite using modern computational resources. In this work we propose a method based on deep learning techniques to predict the alert level of a tsunami generated by an earthquake at given coastal locations in a fraction of a second. This method could be used in TEWS along with techniques to estimate the values of some parameters of the earthquake. Application to real events and probabilistic predictions are also addressed. Key Points: A deep learning method to predict different tsunami alert levels is proposedTsunamis caused by the rupture of multiple fault segments at different time instants are supportedApplication to real events with probabilistic predictions are addressed [ABSTRACT FROM AUTHOR]