Search

The purpose of this study is to investigate whether there are differences in handwritten Chinese signatures on different media including paper and electronic devices. Participants were asked to sign specified names on various types of media and the signatures were scanned or saved digitally for subsequent analysis. In this study, using convolutional neural networks and Siamese neural networks as classifiers and comparators, the performance plunge is revealed and thus considerable dissimilarity between the signatures on different media is implied. To further explore this, cubic Bézier curves are fitted to the signatures using the least square method for quantitative statistical analysis. By analyzing the visual changes in the morphology of strokes, several features of signatures are selected and computed, and the paired t‐test and the Wilcoxon signed‐rank test are implemented, which provides a deeper substantiation and explanation of the findings. [ABSTRACT FROM AUTHOR]

Avoiding financial losses requires preventing catastrophic oil‐filled power transformer breakdowns. Continuous online transformer monitoring is needed. The authors use paper insulation to evaluate transformer health for continuous online transformer monitoring. The study suggests a new artificial intelligence method for estimating paper insulation residual life in oil‐immersed power transformers. The four artificial intelligence models use backpropagation‐based neural networks to predict paper insulation lifespan. Four primary transformer insulating paper failure indices—degree of polymerisation, 2‐furfuraldehyde, carbon monoxide, and carbon dioxide—form the basis of these models. Each model, including the backpropagation‐based neural networks, estimates paper insulation life using one failure index, along with moisture and temperature data. Optimisation techniques enhance hidden layer neurons and epoch count for improved performance. Results are validated against literature‐based life models, establishing a precise input–output correlation. This method accurately predicts the remaining useable life of power transformer paper insulation, enabling utilities to take proactive measures for safe and efficient transformer operation. [ABSTRACT FROM AUTHOR]

The accurate estimation of the power number for closed clearance impellers holds significant importance in industries such as chemical, biochemical, paper and pulp, as well as paints, pigments, and polymers. Existing state‐of‐the‐art correlations for predicting power numbers, however, are inaccurate for impeller Reynolds number ReI>100. In this study, we compiled a dataset of 1470 data points from 15 research articles in the open literature, covering five types of impellers: (i) anchor; (ii) gate; (iii) single helical ribbon; (iv) double helical ribbon; and (v) helical ribbon with screw. Six machine learning models, namely artificial neural networks (ANN), CatBoost regressor, extra tree regressor, support vector regressor, random forest, and XGBoost regressor, were developed and compared. The results revealed that ANN emerged as the most efficient model, demonstrating the highest testing R2 value of 0.99 and the lowest testing MAPE of 7.3%. Further, we used the ANN model to develop a novel set of process correlations to estimate impeller power numbers for the industrially important anchor and double helical ribbon impellers: which significantly outperform the existing state‐of‐the‐art correlations available in literature. [ABSTRACT FROM AUTHOR]

Artificial intelligence is more present than ever, both in our society in general and in science. At the center of this development has been the concept of deep learning, the use of artificial neural networks that are many layers deep and can often reproduce human‐like behavior much better than other machine‐learning techniques. The articles in this collection are some recent examples of its application for X‐ray photon science and crystallography that have been published in Journal of Applied Crystallography. [ABSTRACT FROM AUTHOR]

A low‐temperature technology for fabricating thin‐film transistors (TFTs) is essential for the realization of electronic systems on flexible substrates. Presently reviewed are improved techniques for forming the source/drain regions and reducing the population of channel defects in a metal‐oxide TFT. These have been applied to the construction of different TFT structures, including ones with bottom gate, top gate, and dual gates. The utility of the improved 300‐°C technology has been demonstrated by the realization of a variety of electronic systems, such as a gate‐driver on array for active‐matrix displays, an analog front‐end for acquiring biopotential signals, and an artificial neural network for neuromorphic computing. [ABSTRACT FROM AUTHOR]

In this white paper, experts from the Digital Pathology Association (DPA) define terminology and concepts in the emerging field of computational pathology, with a focus on its application to histology images analyzed together with their associated patient data to extract information. This review offers a historical perspective and describes the potential clinical benefits from research and applications in this field, as well as significant obstacles to adoption. Best practices for implementing computational pathology workflows are presented. These include infrastructure considerations, acquisition of training data, quality assessments, as well as regulatory, ethical, and cyber‐security concerns. Recommendations are provided for regulators, vendors, and computational pathology practitioners in order to facilitate progress in the field. © 2019 The Authors. The Journal of Pathology published by John Wiley & Sons Ltd on behalf of Pathological Society of Great Britain and Ireland. [ABSTRACT FROM AUTHOR]

This document is a guest editorial from the journal IET Generation, Transmission & Distribution. It discusses the use of artificial intelligence (AI) in reliable forecasting for energy sectors. The editorial highlights the challenges of integrating renewable energy sources and fluctuating electricity demand, and emphasizes the importance of accurate forecasting for system operators. The document also provides summaries of several papers included in a special issue on AI-empowered forecasting in energy sectors, covering topics such as load forecasting, wind power prediction, and control parameter optimization. The editorial concludes by recommending further research and practical implementations of AI approaches in the energy sectors. [Extracted from the article]

This document is a guest editorial from the journal IET Radar, Sonar & Navigation. It discusses the advances in AI-assisted radar sensing applications and the challenges that hinder its adoption in this field. The special issue of the journal features nine papers that address these challenges and offer innovative ideas and experimental results. The papers cover a range of topics, including health monitoring, human activity recognition, voice identification, elderly care health monitoring, track-to-track association, signal pre-processing, traffic congestion alleviation, and target recognition. The authors express their gratitude to the contributors and reviewers and believe that the research presented will inspire further exploration and innovation in this field. [Extracted from the article]

Decoupling environment‐dependent response in sensing techniques is essential for the diverse practical applications. This work presents a novel thermal effect decoupling method for sponge pressure sensors based on a deep neural network (DNN) regression model, which is difficult to achieve owing to the material‐ and structure‐related complex effects of the sponge‐based pressure sensor. A poly(3,4‐ethylenedioxythiophene):poly(styrenesulfonate)‐based multifunctional device is fabricated with a both pressure and thermally responsive part and an only thermally responsive part; and a DNN model with two input features is adapted to implement the substantial pressure prediction system without thermal interference. Proposed model shows the robust decoupled pressure‐sensing capability with high accuracy of ≈96.23% using two input features. It also enables accurate pressure prediction under both the thermally steady and transition regions, which indicates significant potential for a precise measurement system. These results demonstrate the possibility of reliable pressure monitoring under varying thermal conditions, which is important for accurately measuring pressure in complex power plants, human–machine interfaces, and compact wearable platforms. [ABSTRACT FROM AUTHOR]

In this paper, we propose a binary feedback scheme for congestion control in computer networks using a gradient-based mechanism which employs neural network modelling of the system dynamics. The optimal direction for rate adjustment at the source is based on a single bit feedback signal which depends upon the sign of the sensitivity of the system performance index with respect to queue input rate. The paper presents the scheme and the analysis that went into the choice of the various decision mechanisms. Simulation results are presented to show the performance of the gradient based technique as compared to the conventional queue-based approach. Copyright © 2000 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

Power system operation and control are based on power flow calculations. In order to solve the uncertainty of the increasing penetration of renewable energy, the voltage fluctuation at the load point increases in the distribution network, and the inaccuracy of the power flow calculation due to the insufficient power flow data collection capability of the traditional power system. In this paper, a data‐driven power flow analysis model is proposed, a back propagation neural network combined with genetic algorithm (GA) and adaptive moment estimation (ADAM) optimization algorithm model is constructed to analyze the power flow calculation method of distribution networks under stochasticity. Firstly, the power flow initial value information, topology characteristics, and power factor index are introduced to construct a training set, and the mapping relationship between bus voltage and power is fully explored by training the regression model. Second, the GA‐ADAM algorithm is used to optimize the initial values and weight parameters of the model. Finally, it is verified based on IEEE‐33 bus distribution model, and the model is used for power flow calculation, and compared with other methods through each relevant error evaluation indicators. The results show that the model constructed in this paper has small error indicators and high accuracy, which improves the efficiency and accuracy of power flow calculation. [ABSTRACT FROM AUTHOR]

Recent advances in the field of computer vision can be attributed to the emergence of deep learning techniques, in particular convolutional neural networks. Neural networks, partially inspired by the brain’s visual cortex, enable a computer to “learn” the most important features of the images it is shown in relation to a specific, specified task. Given sufficient data and time, (deep) convolutional neural networks offer more easily designed, more generalizable, and significantly more accurate end‐to‐end systems than is possible with previously employed computer vision techniques. This review paper seeks to provide an overview of deep learning in the field of computer vision with an emphasis on recent progress in tasks involving 3D visual data. Through a backdrop of the mammalian visual processing system, we also hope to provide inspiration for future advances in automated visual processing. [ABSTRACT FROM AUTHOR]

This paper demonstrates an intelligent portable device, nGoggle, which combines brain monitoring with a virtual reality display. We proposed high‐frequency polychromatic composite stimuli with short repetitive sequences to elicit steady‐state visual evoked potentials (SSVEPs) at stimulus frequencies in 43–56 Hz for reducing the flickering. Additionally, a Generic Bootstrapping Model and classification using a Convolutional Neural Network (CNN) was implemented to improve the detection accuracy. [ABSTRACT FROM AUTHOR]

Multilevel inverters (MLIs) have a significant contribution in many industrial sectors due to their improved power quality and lesser voltage stress, over the conventional three‐level inverters. However, the implementation of MLIs with an increased device count creates the scope of development in MLIs topologies. In this regard, a hybrid MLI topology is studied in this paper whose architecture is based on conventional two‐level inverters. This topology has lesser device count characteristics when compared to conventional and most of the recently presented configurations for nine‐level output voltage generation. The major issue of capacitor voltage balancing is resolved by employing an appropriate switching strategy. However, the semiconductor switches are the most vulnerable components and causes the open circuit faults frequently that creates issues in real time operation. Hence, it is important to detect the open circuit fault in switches in the least possible time. A new approach to open circuit fault detection technique based on the analysis of load voltage waveform is proposed in this paper. The wavelet transform technique has been implemented for feature extraction of load voltage. Later, the classification of the fault has been achieved by training an artificial neural network (ANN). The proposed work has been studied in MATLAB/simulation and the obtained results are verified experimentally. [ABSTRACT FROM AUTHOR]

The cost for covering active power losses makes a significant item in transmission system operators (TSO) annual budgets, and still it received limited attention in the existing literature. The focus of accurate power loss forecasting and procurement is of high increase during the past 2 years due to spikes in electricity prices, making the cost of covering the active power losses a dominant factor of TSO operational costs. This paper presents practical aspects of the highly accurate models for transmission loss forecast in the day ahead time frame for the Croatian transmission system. The contributions are two‐fold: 1) Practical insights into usable TSO data are provided, filling a critical research gap and a foundational literature review is established on transmission loss forecasting. 2) A novel method utilizing only electricity transit data as input which outperforms existing practices is presented. For this, several algorithms such as gradient boosted decision tree model (XGB), support vector regressors, multiple linear regression and fully connected feedforward artificial neural networks are developed, and implemented and validated on data obtained from the Croatian TSO. The results show that the XGB model outperforms current TSO model by 32% for 4 months of comparison and TSCNET's commercial solution by 25% during a year‐long testing period. The developed XGB model is also implemented as a software tool and put into everyday operation with the Croatian TSO. [ABSTRACT FROM AUTHOR]

The significant risk associated with fault reactivation often necessitates slip tendency analyses for effective risk assessment. However, such analyses are challenging, particularly in large areas with limited or absent reliable stress measurements and where the cost of extensive geomechanical analyses or simulations is prohibitive. In this paper, we propose a novel approach using a physics‐informed neural network that integrates stress orientation and satellite displacement observations in a top‐down multi‐scale framework to estimate two‐dimensional slip tendency analyses even in regions lacking comprehensive stress data. Our study demonstrates that velocities derived from a continental scale analysis, combined with reliable stress orientation averages, can effectively guide models at smaller scales to generate qualitative slip tendency maps. By offering customizable data selection and stress resolution options, this method presents a robust solution to address data scarcity issues, as exemplified through a case study of the South Australian Eyre Peninsula. Plain Language Summary: Fault reactivation poses significant risks, often requiring slip tendency analyses for thorough risk assessment. Yet, such analyses face challenges, especially in large areas lacking reliable stress measurements or where extensive geomechanical analyses are too costly. Our paper suggests a new method using a physics‐based neural network. This approach combines compressive direction and satellite displacement observations to estimate slip tendencies in two dimensions, even where stress data is lacking. Our study shows that by using displacements from a continental scale analysis and reliable averages of compressive directions, we can guide models to create smaller‐scale maps indicating where faults are more likely to reactivate. This method allows for customizable data selection and stress resolution, offering a strong solution to data scarcity issues. We demonstrate its effectiveness through a case study of South Australia's Eyre Peninsula. Key Points: Physics‐based neural networks allow two‐dimensional slip tendency analyses without prior full‐stress informationA multi‐scale approach provides required displacement constraints when inferring full stresses from global navigation satellite system (GNSS) and stress orientation dataWe present a new application for GNSS data that would welcome more stations, even in seismically stable areas [ABSTRACT FROM AUTHOR]

Visual information is important in final approach and landing phases for an approaching aircraft, it presents supplementary source for navigation system, and provides backup guidance when radio navigation fails, or even supports a complete vision‐based landing. Relative position and attitude can be solved from the runway features in the image. Traditional runway detection methods have high latency and low accuracy, which is unable to satisfy the requirements for a safe landing. This paper proposes a real‐time runway detection model, efficient runway feature extractor (ERFE), based on deep convolutional neural network, generating semantic segmentation and feature lines output. In order to evaluate the model's effectiveness, a benchmark is proposed to calculate the actual error between predicted feature line and ground truth one. A novel runway dataset which is based on pictures from Microsoft Flight Simulator 2020 (FS2020), is also proposed in this paper to train and test the model. The dataset will be released at https://www.kaggle.com/datasets/relufrank/fs2020‐runway‐dataset. ERFE shows excellent performance in FS2020 dataset, it gives satisfactory results even for real runway images excluded from our dataset. [ABSTRACT FROM AUTHOR]

Introduction: Algorithms to predict short‐term changes in local weather modalities have been used in meteorology for many years. These algorithms predict the temporospatial change in the movement of weather patterns such as cloud cover or precipitation. This paper extends convolutional neural network models for weather prediction/nowcasting to predict evolution in the extrapolation of sequentially acquired count data seen with cardiac positron tomography (PET) data to expected value temporally rather than spatially. Methods: Six different algorithms used for nowcasting were modified and applied to confirm the approach. These algorithms were trained on an image data set of both simulated ellipsoids and simulated cardiac PET data. The peak signal‐to‐noise ratio (PSNR) and structural similarity (SSIM) were calculated for each of these trained models. They were compared to the BM3D denoising algorithm as a baseline comparison to a standard method of image denoising. Results: Most of the implemented algorithms showed a significant improvement in both PSNR and SSIM when compared with the baseline standard, especially when the algorithms were implemented in combination. The best results were obtained with a combination of the ConvLSTM and TrajGRU algorithms with a PSNR improvement over the standard of 5 and more than double the SSIM metric. Conclusion: This approach of using serially acquired count data to extrapolate a future expected representation through convolutional neural networks has been shown to produce accurate representations of the expected value when compared with a baseline analytic methodology. This paper confirms that algorithms such as these can be used to substantially improve image estimation and shows significant improvement over a baseline standard. [ABSTRACT FROM AUTHOR]

High-performance computing (HPC) offers the computing power to continuously support the world's most important discoveries in various scientific and business domains such as chemistry, physics, biology, material science, drug discovery, and financial investment risk analysis. Researchers from across the HPC community have been developing software systems, tools, libraries, frameworks, application packages, and methods that can fully exploit these extremely powerful computing resources. The eleventh paper titled "A large scale parallel fluid-structure interaction computing platform for simulating structural responses to a detonation shock" by Yang et al.[10] presents a partitioned fluid-structure interaction computing platform designed for parallel simulating structural responses to a detonation shock. [Extracted from the article]

Our goal is to be able to align objects in an RGB-D image with 3D models from a library. Our pipeline for this task involves detecting and segmenting objects and estimating coarse pose using a convolutional neural network, followed by inserting the rendered model in the scene. [ABSTRACT FROM AUTHOR]

The best-fit heuristic is a simple and powerful tool for solving the two-dimensional orthogonal strip packing problem. It is the most efficient constructive heuristic on a wide range of rectangular strip packing benchmark problems. In this paper, the results of the original best-fit heuristic are further improved by adding new item orderings and item placement strategies, resulting in the three-way best-fit heuristic. By applying these steps, significantly better results are obtained in comparable computation time. Furthermore, some data structures are implemented, which increase the scalability of the heuristic for large problem instances and a slightly altered heuristic with an optimal [ABSTRACT FROM AUTHOR]

In recent years, the object‐tracking algorithm based on Siamese network has gradually become the mainstream algorithm in the field of object tracking due to its characteristics of balancing speed and accuracy. The majority of Siamese‐based trackers only use the first frame extraction template for subsequent tracking in order to prevent the introduction of noise. However, merely with a single initial template employed, it is difficult to achieve the best performance of the tracker in the face of complex tracking environments such as occlusion, motion blur, and non‐rigid deformation. Therefore, the present paper proposes a new multi‐template fusion module based on graph attention network (G‐M module), which consists of two parts: a graph‐attention‐network‐based feature‐embedding module (G module) and a multi‐template fusion module (M module). It can greatly reduce the background noise introduced by template updating while improving the tracker's ability to adapt to changes in object appearance. In addition, in order to maximize the value of G‐M module, the present paper also puts forward a two‐stage template update threshold judgment mechanism. The Pearson correlation coefficient (PCCs) is introduced and combined with APCE and the maximum response value (F‐max) to filter out reliable templates for updating. In this paper, the proposed method is applied to the SiamFC and SiamFC++ trackers. Extensive experiments on mainstream data sets, such as OTB2015, VOT2016, and GOT‐10 k, show that the proposed method can effectively update the tracking template and improve the tracker performance. © 2022 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC. [ABSTRACT FROM AUTHOR]

This paper presents a multi‐input deep learning‐based joint pilot decontamination and symbol detection (SD) technique for 5G massive multiple‐input multiple‐output (MAMIMO) systems. It consists of a fully convolutional neural network (FCNN) that finds the 5G channel coefficients using pre‐known sounding reference signals (SRSs) under pilot contamination and a symbol detector derived from projected gradient descent iterations. The study considers pilot contamination caused by inter‐cell interferences between SRSs during channel estimation (CE). The proposed scheme accepts entire 5G orthogonal frequency modulated (OFDM) data and least square estimates and produces the transmitted OFDM signal. Simulation experiments demonstrated that the proposed technique has better CE and SD performance with reduced trainable parameters. Moreover, it is faster due to the lowest elapsed time during end‐to‐end OFDM symbol detection. This paper proposes a joint pilot decontamination and signal detection for 5G MAMIMO systems. It achieves better detection performance with the lowest number of trainable parameters and memory requirements. It is applicable in 5G OFDM symbol detection and channel estimation under pilot contamination. [ABSTRACT FROM AUTHOR]

The quality of scientific publications can be measured by quantitative indices such as the h‐index, Source Normalized Impact per Paper, or g‐index. However, these measures lack to explain the function or reasons for citations and the context of citations from citing publication to cited publication. We argue that citation context may be considered while calculating the impact of research work. However, mining citation context from unstructured full‐text publications is a challenging task. In this paper, we compiled a data set comprising 9,518 citations context. We developed a deep learning‐based architecture for citation context classification. Unlike feature‐based state‐of‐the‐art models, our proposed focal‐loss and class‐weight‐aware BiLSTM model with pretrained GloVe embedding vectors use citation context as input to outperform them in multiclass citation context classification tasks. Our model improves on the baseline state‐of‐the‐art by achieving an F1 score of 0.80 with an accuracy of 0.81 for citation context classification. Moreover, we delve into the effects of using different word embeddings on the performance of the classification model and draw a comparison between fastText, GloVe, and spaCy pretrained word embeddings. [ABSTRACT FROM AUTHOR]

With the rapid development of big data science, the research paradigm in the field of geosciences has also begun to shift to big data‐driven scientific discovery. Researchers need to read a huge amount of literature to locate, extract and aggregate relevant results and data that are published and stored in PDF format for building a scientific database to support the big data‐driven discovery. In this paper, based on the findings of a study about how geoscientists annotate literature and extract and aggregate data, we proposed GeoDeepShovel, a publicly available AI‐assisted data extraction system to support their needs. GeoDeepShovel leverages state‐of‐the‐art neural network models to support researcher(s) easily and accurately annotate papers (in the PDF format) and extract data from tables, figures, maps, etc., in a human–AI collaboration manner. As a part of the Deep‐Time Digital Earth (DDE) program, GeoDeepShovel has been deployed for 8 months, and there are already 400 users from 44 geoscience research teams within the DDE program using it to construct scientific databases on a daily basis, and more than 240 projects and 50,000 documents have been processed for building scientific databases. [ABSTRACT FROM AUTHOR]

Learning systems represent a particularly important class of practical data-driven systems that adapt to their environment based on the environment's response to the system's action. Despite the success of learning-based methods, finding suitable control frameworks for learning systems when there is uncertainty in the assumptions related to the system dynamics is still an open problem. They propose a novel constrained ILC design and further develop a decentralized implementation of the resulting ILC algorithm using the alternating direction method of multipliers, allowing the design to scale up to handle large-scale and varying system dynamics. [Extracted from the article]

Eye health has become a global health concern and attracted broad attention. Over the years, researchers have proposed many state‐of‐the‐art convolutional neural networks (CNNs) to assist ophthalmologists in diagnosing ocular diseases efficiently and precisely. However, most existing methods were dedicated to constructing sophisticated CNNs, inevitably ignoring the trade‐off between performance and model complexity. To alleviate this paradox, this paper proposes a lightweight yet efficient network architecture, mixed‐decomposed convolutional network (MDNet), to recognise ocular diseases. In MDNet, we introduce a novel mixed‐decomposed depthwise convolution method, which takes advantage of depthwise convolution and depthwise dilated convolution operations to capture low‐resolution and high‐resolution patterns by using fewer computations and fewer parameters. We conduct extensive experiments on the clinical anterior segment optical coherence tomography (AS‐OCT), LAG, University of California San Diego, and CIFAR‐100 datasets. The results show our MDNet achieves a better trade‐off between the performance and model complexity than efficient CNNs including MobileNets and MixNets. Specifically, our MDNet outperforms MobileNets by 2.5% of accuracy by using 22% fewer parameters and 30% fewer computations on the AS‐OCT dataset. [ABSTRACT FROM AUTHOR]

The optical time domain reflectometer (OTDR) curve features of communication fibers exhibit subtle differences among their normal, subhealthy, and faulty operating states, making it challenging for existing machine learning-based fault diagnosis algorithms to extract these minute features. In addition, the OTDR curve field fault data are scarce, and data-driven deep neural network that needs a lot of data training cannot meet the requirements. In response to this issue, this paper proposes a communication fiber state diagnosis model based on fuzzy clustering and an improved ResNet. First, the pretrained residual network (ResNet) is modified by removing the classification layer and retaining the feature extraction layers. A global average pooling (GAP) layer is designed as a replacement for the fully connected layer. Second, fuzzy clustering, instead of the softmax classification layer, is employed in ResNet for its characteristic of requiring no subsequent data training. The improved model requires only a small amount of sample training to optimize the parameters of the GAP layer, thereby accommodating state diagnosis in scenarios with limited data availability. During the diagnosis process, the OTDR curves are input into the network, resulting in 512 features outputted in the GAP layer. These features are used to construct a feature vector matrix, and a dynamic clustering graph is formed using fuzzy clustering to realize the fiber state diagnosis. Through on-site data detection and validation, it has been demonstrated that the improved ResNet can effectively identify the full cycle of fiber states. [ABSTRACT FROM AUTHOR]

The Sun continuously affects the interplanetary environment through a host of interconnected and dynamic physical processes. Solar flares, Coronal Mass Ejections (CMEs), and Solar Energetic Particles (SEPs) are among the key drivers of space weather in the near‐Earth environment and beyond. While some CMEs and flares are associated with intense SEPs, some show little to no SEP association. To date, robust long‐term (hours‐days) forecasting of SEP occurrence and associated properties (e.g., onset, peak intensities) does not effectively exist and the search for such development continues. Through an Operations‐2‐Research support, we developed a self‐contained model that utilizes a comprehensive data set and provides a probabilistic forecast for SEP event occurrence and its properties. The model is named Multivariate Ensemble of Models for Probabilistic Forecast of Solar Energetic Particles (MEMPSEP). MEMPSEP workhorse is an ensemble of Convolutional Neural Networks that ingests a comprehensive data set (MEMPSEP‐III by Moreland et al. (2024, https://doi.org/10.1029/2023SW003765)) of full‐disc magnetogram‐sequences and in situ data from different sources to forecast the occurrence (MEMPSEP‐I—this work) and properties (MEMPSEP‐II by Dayeh et al. (2024, https://doi.org/10.1029/2023SW003697)) of a SEP event. This work focuses on estimating true SEP occurrence probabilities achieving a 2.5% improvement in reliability and a Brier score of 0.14. The outcome provides flexibility for the end‐users to determine their own acceptable level of risk, rather than imposing a detection threshold that optimizes an arbitrary binary classification metric. Furthermore, the model‐ensemble, trained to utilize the large class‐imbalance between events and non‐events, provides a clear measure of uncertainty in our forecast. Plain Language Summary: Solar Energetic Particles (SEPs) play an important role in modulating near‐Earth space weather environments affecting communication satellites and posing radiation hazards to astronauts. Because of the complex processes involved reliable early forecast of SEP events still remains a challenge. In this paper, we present an ensemble of models that ingest both solar images and parameters measured by in situ instruments to reliably forecast the chance of SEP event occurrence. Our approach transforms a "yes"/"no" forecast to the probability of event occurrence and provides the users additional flexibility in prioritizing their forecasting goals. Our ensemble of models utilizes the fact that SEP events are much rarer than non‐events and generate uncertainties on predicted probabilities. These uncertainties add value in providing a measure of trust to users in forecasting outcomes. Key Points: End‐to‐End Deep Neural Network model‐ensemble trained on remote sensing + in situ data set for forecast of SEP occurrenceUsage of model ensemble maximizes the use of an imbalanced data set and brings forecasting confidence with uncertainty estimatesCalibration of model outcome to true probability optimizes the forecast reliability acting as a means to step away from the binary forecast [ABSTRACT FROM AUTHOR]

Solar Energetic Particles (SEPs) form a critical component of Space Weather. The complex, intertwined dynamics of SEP sources, acceleration, and transport make their forecasting very challenging. Yet, information about SEP arrival and their properties (e.g., peak flux) is crucial for space exploration on many fronts. We have recently introduced a novel probabilistic ensemble model called the Multivariate Ensemble of Models for Probabilistic Forecast of Solar Energetic Particles (MEMPSEP). Its primary aim is to forecast the occurrence and physical properties of SEPs. The occurrence forecasting, thoroughly discussed in a preceding paper (MEMPSEP‐I by Chatterjee et al., 2024a, https://doi.org/10.1029/2023sw003568), is complemented by the work presented here, which focuses on forecasting the physical properties of SEPs. The MEMPSEP model relies on an ensemble of Convolutional Neural Networks, which leverage a multi‐variate data set comprising full‐disc magnetogram sequences and numerous derived and in‐situ data from various sources (MEMPSEP‐III by Moreland et al., 2024, https://doi.org/10.1029/2023SW003765). Skill scores demonstrate that MEMPSEP exhibits improved predictions on SEP properties for the test set data with SEP occurrence probability above 50%, compared to those with a probability below 50%. Results present a promising approach to address the challenging task of forecasting SEP physical properties, thus improving our forecasting capabilities and advancing our understanding of the dominant parameters and processes that govern SEP production. Plain Language Summary: Solar Energetic Particles (SEPs) are important for understanding space weather. SEPs are hard to predict because they come from various sources and go through complicated processes. However, knowing when and how intense SEPs are in space is crucial for things like space exploration. In this work, we created a new model called MEMPSEP to help predict when and what the properties of these SEPs will be when they are detected. We used data from different sources to train the model on how to make these predictions. The results show that MEMPSEP is better at predicting the properties of SEPs when the chances of them happening are more than 50%. This is a significant step forward in improving our ability to forecast SEPs and understanding the factors that influence them in space. Key Points: An end‐to‐end deep neural network model ensemble, trained on remote sensing and in situ data sets, is used to forecast SEP propertiesModel ensemble maximizes the utilization of an imbalanced data set and enhances forecasting confidence with uncertainty estimatesSolar energetic particle occurrence probabilities are utilized as weights in the loss function to enhance regression performance for events [ABSTRACT FROM AUTHOR]

This paper proposes a hybrid data‐driven and physics‐based simulation technique for seismic response evaluation of steel Buckling‐Restrained Braced Frames (BRBFs) considering brace fracture. Buckling‐Restrained Brace (BRB) fracture is represented by cumulative plastic deformation capacity. A dataset, consisting of 95 past BRB laboratory tests and 120 simulated BRB responses generated using the finite element method, is first developed. An Artificial Neural Network‐based (ANN) predictive model is then trained using the training dataset to estimate the cumulative plastic deformation of BRBs. The prediction capability of the ANN‐based predictive model is validated using the training dataset and an existing regression‐based predictive model. In the second part of the paper, an hybrid simulation technique combining the data‐driven model and physics‐based numerical modeling is presented to conduct the nonlinear time history analysis, followed by 1) validation against a full‐scale BRBF testing and 2) demonstration of the proposed simulation technique using a six‐story BRBF. The results confirm that the proposed predictive model can predict the BRB fracture with sufficient accuracy. Furthermore, the hybrid data‐driven physics‐based simulation technique can be used as a powerful tool for dynamic analysis of BRBFs considering BRB fracture. [ABSTRACT FROM AUTHOR]

This paper presents a comprehensive review of the most recent papers and research trends in the fields of wind energy and artificial intelligence. Our study aims to guide future research by identifying the potential application and research areas of artificial intelligence and machine learning techniques in the wind energy sector and the knowledge gaps in this field. Artificial intelligence techniques offer significant benefits and advantages in many sub‐areas, such as increasing the efficiency of wind energy facilities, estimating energy production, optimizing operation and maintenance, providing security and control, data analysis, and management. Our research focuses on studies indexed in the Web of Science library on wind energy between 2000 and 2023 using sub‐branches of artificial intelligence techniques such as artificial neural networks, other machine learning methods, data mining, fuzzy logic, meta‐heuristics, and statistical methods. In this way, current methods and techniques in the literature are examined to produce more efficient, sustainable, and reliable wind energy, and the findings are discussed for future studies. This comprehensive evaluation is designed to be helpful to academics and specialists interested in acquiring a current and broad perspective on the types of uses of artificial intelligence in wind energy and seeking what research subjects are needed in this field. [ABSTRACT FROM AUTHOR]

Medical image colouring techniques enable to colourize grey‐scale medical images for assisting doctors in diagnosis. Benefiting from the non‐linear fitting ability of deep neural network, deep medical image colouring techniques have achieved remarkable results. However, existing methods are still facing content and structure feature leakage, unrealistic colouring and poor scale invariability. Thus, this paper, proposes a Transformer‐based medical image colouring algorithm with long‐term dependency to avoid feature leakage of coloured images. To be specific, this method employs two different Transformer encoders to generate and encode feature sequences for grey‐scale medical images and real human colour slice images, respectively. Then, a novel multi‐layer Transformer decoder is used to stylize grey‐scale map image features based on the real physical colour feature sequences. For colouring images at different scales, we implement content‐ aware positional encoding with scale invariance and propose style‐aware positional encoding strategy to take realistic and physical colour prior into account. Extensive experimental results indicate our method has achieved better colourization effects than recent state‐of‐the‐art medical image colourization methods. [ABSTRACT FROM AUTHOR]

Deep learning‐based models have become ubiquitous across a wide range of applications, including computer vision, natural language processing, and robotics. Despite their efficacy, one of the significant challenges associated with deep neural network (DNN) models is the potential risk of copyright leakage due to the inherent vulnerability of the entire model architecture and the communication burden of the large models during publishing. So far, it is still challenging for us to safeguard the intellectual property rights of these DNN models while reducing the communication time during model publishing. To this end, this paper introduces a novel approach using knowledge distillation techniques aimed at training a surrogate model to stand in for the original DNN model. To be specific, a knowledge distillation generative adversarial network (KDGAN) model is proposed to train a student model capable of achieving remarkable performance levels while simultaneously safeguarding the copyright integrity of the original large teacher model and improving communication efficiency during model publishing. Herein, comprehensive experiments are conducted to showcase the efficacy of model copyright protection, communication‐efficient model publishing, and the superiority of the proposed KDGAN model over other copyright protection mechanisms. [ABSTRACT FROM AUTHOR]

In this paper, a Hopfield‐type neural network system with Caputo–Hadamard fractional derivative is discussed. The importance of the existence of the equilibrium point in the analysis of artificial neural networks is well known. Another important investigation is the stability properties. So, the stability of a neural network system is dealt with in the present paper. First, a theorem that asserts the existence and uniqueness of the equilibrium point of the system is proven. Later, the conditions that ensure the Mittag‐Leffler stability of the equilibrium point is obtained by using the Lyapunov's direct method. In addition, an example is given with numerical simulations to show the effectiveness of our theoretical results. [ABSTRACT FROM AUTHOR]

The present review paper addresses the increasing interest in the application of machine learning (ML) algorithms in the assessment of the fatigue response of additively manufactured (AM) metal alloys. This review aims to systematically collect, categorize, and analyze relevant research papers in this domain. The most commonly used ML algorithms are presented, discussing their specific relevance to the fatigue modeling of AM metal alloys. A detailed analysis of the most relevant input features used in the literature to predict the main parameters related to the fatigue response is provided. Each work has been analyzed to highlight its strengths and peculiarities, thereby offering insights into novel methodologies and approaches for addressing critical challenges within this field. Particular attention is dedicated to the role of defects and the related size‐effect, as they strongly influence the fatigue response. In conclusion, this review not only synthesizes existing knowledge but also offers forward‐looking recommendations for future research directions, providing a valuable resource for researchers in the domain of ML‐assisted fatigue assessment for AM metal alloys. [ABSTRACT FROM AUTHOR]

Microgrids play a pivotal role in modern power distribution systems, necessitating precise control methodologies to tackle challenges such as performance instability, especially during islanding operations. This paper introduces an advanced control strategy that employs artificial intelligence, specifically deep neural network (DNN) predictions, to enhance microgrid performance, particularly in an islanding mode where voltage and frequency (VaF) deviations are critical concerns. By utilizing real‐time data and historical trends, the proposed controller accurately forecasts power demand and generation patterns, enabling proactive planning and optimization of efficiency, reliability, and sustainability in microgrid management. One significant aspect of this approach is to establish an intelligent distributed control system that minimizes reliance on communication devices while ensuring that VaF remains within acceptable limits. Moreover, it consolidates the roles of primary and secondary controllers within the microgrid and facilitates the prediction of load changes and load injection processes. This capability significantly reduces microgrid VaF deviations, enhancing system performance through precise power distribution and balanced coordination among distributed generators. Consequently, it ensures the stability and reliability of the system. In summary, the integration of DNN‐based predictive control represents a significant advancement in microgrid management, providing a solution to address performance challenges and optimize operational efficiency, reliability, and sustainability. [ABSTRACT FROM AUTHOR]

Abduallah et al. (2024b, https://doi.org/10.1029/2023sw003824) proposed a novel approach using a deep neural network model, which includes a graph neural network and a bidirectional LSTM layer, named SYMHnet, to forecast the SYM‐H index one and 2 hr in advance. Additionally, the network also provides an uncertainty quantification of the predictions. While the approach is innovative, there are some areas where the model's design and implementation may not align with best practices in uncertainty quantification and predictive modeling. We focus on discrepancies in the input and output of the model, which can limit the applicability in real‐world forecasting scenarios. This comment aims to clarify these issues, offering detailed insights into how such discrepancies could compromise the model's interpretability and reliability, thereby contributing to the advancement of predictive modeling in space weather research. Plain Language Summary: The use of Machine learning to predict geomagnetic storms is becoming a trend. A recent study by Abduallah et al. (2024b, https://doi.org/10.1029/2023sw003824) introduces a novel approach to forecast the SYM‐H index, which measures geomagnetic activity on a global scale, while also quantifying the uncertainty of these predictions. However, this commentary highlights methodological concerns with their approach, such as data selection issues and the reliability of uncertainty calculations. These factors could significantly affect the model's accuracy and applicability in real‐time forecasting scenarios. Key Points: Examination of the model input and output reveals oversights that could undermine the model's predictive accuracy and applicabilityThe process to estimate uncertainty has limited applicability for use in real timeThere are no coverage metrics regarding the uncertainty intervals [ABSTRACT FROM AUTHOR]

The increase in the volume of structured and unstructured data related to more than just sport events leads to the development and increased use of techniques that extract information and employ machine‐learning algorithms in predicting process outcomes based on input but not necessarily output data. Taking sports into consideration, predicting outcomes, and extracting valuable information has become appealing not only to sports workers but also to the wider audience, particularly in the areas of team management and sports betting. The aim of this article is to review the existing machine learning (ML) algorithms in predicting sport outcomes. Over 100 papers were analyzed and only some of these papers were taken into consideration. Almost all of the analyzed papers use some sort of feature selection and feature extraction, most often prior to using the machine‐learning algorithm. As an evaluation method of ML algorithms, researchers, in most cases, use data segmentation with data being chronologically distributed. In addition to data segmentation, researchers also use the k‐cross‐evaluation method. Sport predictions are usually treated as a classification problem with one class being predicted and rare cases being predicted as numerical values. Mostly used ML models are neural networks using data segmentation. This article is categorized under:Technologies > Machine LearningTechnologies > Prediction [ABSTRACT FROM AUTHOR]

A timescale is the estimate of phase and frequency of the "perfect" clock derived from the phase and frequency of the clocks which participate in the ensemble. An ensemble of clocks is the first step towards the realization of a timescale. In the past, several methodologies have been developed to solve the timescale problem such as KAS‐2, Multi‐scale Ensemble Timescale (METS), ALGOS (BIPM), AT1 (NIST) and algorithm for UTC (CRL). An adaptive ensemble algorithm based on Artificial Neural Network (ANN) has been developed which shows improvements in terms of betterment of frequency stability of the ensemble. The Neural Network in the ensemble algorithm learns differently for different sample spaces of the input phase data that is provided. The weights of the participating clocks are derived from their respective Allan deviations. The weights formulated for the ensemble undergo a regressive iteration to obtain the training data set for parameterization of weights. A single‐layer perceptron feedback Neural Network that is proposed in this paper, dynamically adapts the weights assigned to the participating clocks based on the paper clock performance. This paper dwells on the comparison of performances between the ANN‐based algorithms with that of two other algorithms, namely Reduced Kalman filter based algorithm and METS. Results of ANN‐based algorithm for different clock combinations are also presented. The behavior of this algorithm in the event of measurement data outage has also been presented in the paper. [ABSTRACT FROM AUTHOR]

Performance assessment is ubiquitous and crucial in people analytics. Scientific impact, particularly, plays a significant role in the academia. This paper attempts to understand researchers' career trajectories by considering the research community as a social network, where individuals build ties with each other via coauthorship. The resulting linkage facilitates information flow and affects researchers' future impact. Consequently, we systematically investigate the career trajectories of researchers with respect to research impact using the social capital theory as our theoretical foundation. Specifically, for early‐stage and mid‐career academics, we find that connections with prominent researchers associate with greater impact. Brokerage positions, in addition, are beneficial to a researcher's research impact in the long run. For senior researchers, however, the only social network feature that significantly affects their future impact is the reputation of their recently built ties. Finally, we build predictive models on future research impact which can be leveraged by both organizations and individuals. This paper provides empirical evidence for how social networks provide signals on researchers' career dynamics guided by social capital theory. Our findings have implications for individual researchers to strategically plan and promote their careers and for research institutions to better evaluate current as well as prospective employees. [ABSTRACT FROM AUTHOR]

At present, in the age of computers and automation of services, deep learning (DL) technology, mainly the subset of machine learning (ML) and artificial intelligence (AI), is expressively used in innumerable domains of computer vision such as data analysis, image recognition, classification, natural language processing, and many more. It has become the foremost choice of researchers as of its effectiveness in producing decent results. This paper presents detailed and analytical literature starting from the very elementary level to the recent trends of this trending technology while focusing on the most used DL model, that is, convolutional neural network and its pretrained models for image classification and object detection. It also reviews diverse existing current literature based on this. Further, a brief introduction of AI, ML, and DL has also been presented, making the foundation for the readers. As pretrained models continuously give an upper edge to DL over ML and other technologies, 23 most popular pretrained models with their architectural diagrams have also been presented. This paper aims to summarize and analyze all the concepts used to formulate DL and its models. Also, we have emphasized more on the GoogleNet models and the entire Inception modules in detail. Finally, the fascinating applications and discussion on integral components of DL have been presented. This paper will definitely draw the attention of the students and researchers working in the area of DL and its models. [ABSTRACT FROM AUTHOR]

Summary: Multimodal sentiment analysis is a popular research direction in the field of affective computing. It extends unimodal‐based sentiment analysis to the environment based on multimodal information exchange. Face retrieval is the most critical technology in the current multimodal sentiment analysis field. Traditional methods for face retrieval rely on large amounts of data to train the matching relationship between text and face images. This approach suffers from several issues, including high data acquisition costs, insufficient or poor quality training data, and high computational costs for training models. To address the aforementioned issues, this paper proposes a face retrieval technique that merges a large language model with a visual base model. This technique explores the use of zero samples for training, eliminating the need to collect data and train the model to achieve face retrieval. As a result, it significantly reduces the cost requirements of data and computational power. First, an accurate natural text of face description is generated using a large language model based on cue engineering based on face‐independent features. Second, the text and images are encoded using a visual base model and mapped into the same multidimensional space for matching. The experimental results indicate that this method performs well on the CelebA dataset. Extracting 31 different sets of face feature descriptions from the CelebA dataset for retrieval achieves 72% on top1 accuracy and 93% on top3 accuracy. Compared to traditional methods, the method proposed in this paper achieves considerable face retrieval accuracy without collecting text image pairs of data and without training the model. [ABSTRACT FROM AUTHOR]

High‐precision observation of significant wave height (SWH) is crucial for marine research. The Surface Waves Investigation and Monitoring (SWIM) aboard the China France Oceanography Satellite (CFOSAT) provides the ocean wave spectrum that allows for the calculation of the off‐nadir SWH parameters, but there exists a certain bias with the in‐situ SWH values. To improve the accuracy of the SWH calculation bias from the off‐nadir 6°, 8°, 10° wave spectra and the whole combined spectrum, this paper establishes a spatio‐temporal hybrid model that combines convolutional neural network (CNN) and long short‐term memory network (LSTM). Additionally, to further correct bias exhibited under high sea state, we introduce a bias correction module based on deep neural network (DNN) to adjust the SWIM off‐nadir SWH greater than 4 m. The experimental results demonstrate a significant enhancement in the accuracy of corrected SWIM off‐nadir SWH, and the best calibration result is 10° with 0.267 m root mean square error (RMSE), and 0.979 correlation coefficient (R) compared with the ERA5 value. We conducted a comprehensive study and analysis on the performance of the proposed model under different wave heights, extreme sea states, and wind and swell regions. Meanwhile, the buoy and altimeters are leveraged to render further evaluation the RMSE of the corrected SWH is less than 0.5 m. Plain Language Summary: The Surface Waves Investigation and Monitoring (SWIM) on the China France Oceanography Satellite (CFOSAT) provides wave data support for ocean research. However, the significant wave height (SWH) parameter calculated from the SWIM off‐nadir spectra has a certain bias from the real value due to the influence of speckle noise. In order to improve the accuracy of the SWIM off‐nadir SWH parameter, we developed a CNN‐LSTM model and introduced a high sea state bias correction network to improve the accuracy of SWH and achieve the purpose of correction. The analysis evaluated the correction performance across various sea conditions, comparing the corrected SWH data with measurements from altimeters and buoys. The findings demonstrated that the root mean square error of the corrected SWH was consistently below 0.5 m, with a correlation coefficient exceeding 0.940. This underscores the effectiveness of our model in enhancing the precision of nadir SWH data bias from SWIM instruments. Key Points: A model of convolutional and long short‐term memory neural network is developed to calibrate the surface waves investigation and monitoring (SWIM) off‐nadir significant wave heightThe corrected SWIM off‐nadir significant wave height achieves comparable accuracy with the Jason‐3, HY‐2B, and buoysThe proposed model performs well in the calibration of the wind wave region and the swell region [ABSTRACT FROM AUTHOR]

Machine learned fault detection approaches are being increasingly used for fault detection in distribution grid. However, the performance of the models can be improved by customizing the models. In this regard, a customised artificial neural network (CANN) for fault detection in a distribution grid is proposed in this paper. The proposed work develops a CANN that combines the "up‐pyramid" and "down‐pyramid" model of ANN into a "custom‐pyramid" model. As a result, the same model can be used both for determining the types of fault as well as its location. The data needed to train the model has been taken from a reconfigured IEEE‐33 bus distribution system developed in Typhoon HIL real‐time simulator. Spectral‐kurtosis is utilized for extraction of features of the faulted transient signals which are used as input data to develop the CANN. The result showcases that the reduction of input features reduces computational complexity without compromising its accuracy. The proposed model classifies fault location with an accuracy of 95.43%. The proposed method also identifies fault type with an accuracy of 96.08%. Several test cases have been developed to test the method. The method proved to be able to perform in most of the cases. [ABSTRACT FROM AUTHOR]

In recent years, research on infrared and visible image fusion has mainly focused on deep learning‐based approaches, particularly deep neural networks with auto‐encoder architectures. However, these approaches suffer from problems such as insufficient feature extraction capability and inefficient fusion strategies. Therefore, this paper introduces a novel image fusion network to address the limitations of infrared and visible image fusion networks with auto‐encoder architectures. In the designed network, the encoder employs a multi‐branch cascade structure, and these convolution branches with different kernel sizes provide the encoder with an adaptive receptive field to extract multi‐scale features. In addition, the fusion layer incorporates a non‐local attention module that is inspired by the self‐attention mechanism. With its global receptive field, this module is used to build a non‐local attention fusion network, which works together with the l1${l}_1$‐norm spatial fusion strategy to extract, split, filter, and fuse global and local features. Comparative experiments on the TNO and MSRS datasets demonstrate that the proposed method outperforms other state‐of‐the‐art fusion approaches. [ABSTRACT FROM AUTHOR]

With the introduction of more recent deep learning models such as encoder‐decoder, text generation frameworks have gained a lot of popularity. In Natural Language Generation (NLG), controlling the information and style of the output produced is a crucial and challenging task. The purpose of this paper is to develop informative and controllable text using social media language by incorporating topic knowledge into a keyword‐to‐text framework. A novel Topic‐Controllable Key‐to‐Text (TC‐K2T) generator that focuses on the issues of ignoring unordered keywords and utilising subject‐controlled information from previous research is presented. TC‐K2T is built on the framework of conditional language encoders. In order to guide the model to produce an informative and controllable language, the generator first inputs unordered keywords and uses subjects to simulate prior human knowledge. Using an additional probability term, the model increases the likelihood of topic words appearing in the generated text to bias the overall distribution. The proposed TC‐K2T can produce more informative and controllable senescence, outperforming state‐of‐the‐art models, according to empirical research on automatic evaluation metrics and human annotations. [ABSTRACT FROM AUTHOR]

This paper introduces a new conceptual model to examine the impact of technological opportunism (technology sensing and response capabilities) on the adoption of incremental and radical technological innovation by small and medium enterprises (SMEs). We tested our hypotheses with data from 228 Indian SMEs using a symmetric method of partial least square structural equation modeling (PLS-SEM) and the asymmetric method of fuzzy–set qualitative comparative analysis (fsQCA) followed by sensitivity analysis done by an artificial neural network (ANN) modeling. PLS-SEM results highlighted the roles of technology sensing and response capabilities as key drivers of both incremental and radical product innovations and the strengthening of these relationships by market uncertainty triggered by external events and crises. Apart from this, the results of fsQCA demonstrated multiple configurations of dimensions associated with the adoption of technological innovations by SMEs. This paper extends the current literature by exploring the process by which SMEs may adopt different types of technological innovation. Our findings also have useful implications for SMEs aiming to adopt technological innovations. [ABSTRACT FROM AUTHOR]