Search

Document forgery is a significant issue in Korea, with around ten thousand cases reported every year. Analyzing paper plays a crucial role in examining questionable documents such as marketable securities and contracts, which can aid in solving criminal cases of document forgery. Paper analysis can also provide essential insights in other types of criminal cases, serving as an important clue for solving cases such as the source of a blackmail letter. The papermaking process generates distinct forming fabric marks and formations, which are critical features for paper classification. These characteristics are observable under transmitted light and are created by the forming fabric pattern and the distribution of pulp fibers, respectively. In this study, we propose a novel approach for paper identification based on hybrid features. This method combines texture features extracted from images converted using the gray‐level co‐occurrence matrix (GLCM) approach and a convolutional neural network (CNN), with another set of features extracted by the CNN using the same images as input. We applied the proposed method to classification tasks for seven major paper brands available in the Korean market, achieving an accuracy of 97.66%. The results confirm the applicability of this method for visually inspecting paper products and demonstrate its potential for assisting in solving criminal cases involving document forgery. [ABSTRACT FROM AUTHOR]

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]

Since deep low‐frequency tremors are considered to be associated with large earthquakes that occur adjacently on the same subducting plate interface, it is important to investigate tremors that occurred before the establishment of modern seismograph networks such as the High Sensitivity Seismograph Network (Hi‐net). We propose a deep‐learning solution to detect evidence of tremors in scanned images of paper seismogram records from over 50 years ago. In this study, we fine‐tuned a convolutional neural network (CNN) based on the Residual Network, which was pre‐trained using images of synthetic waveforms from our previous study, using a data set comprised of images generated from real seismic data recorded digitally by Hi‐net to facilitate a supervised analysis. The fine‐tuned CNN was able to predict the presence or absence of tremors in the Hi‐net images with an accuracy of 98.64%. Gradient‐weighted Class Activation Mapping heatmaps created to visualize model predictions indicated that the CNN's ability to detect tremors is not degraded by the presence of teleseisms. Once validated using the Hi‐net images, the CNN was applied to paper seismograms recorded from 1966 to 1977 at the Kumano observatory in southwest Japan, operated by Earthquake Research Institute, The University of Tokyo. The CNN showed potential for detecting tremors in scanned images of paper seismogram records from the past, facilitating downstream tasks such as the creation of new tremor catalogs. However, further training using an augmented data set to control for variables such as inconsistent plotting pen thickness is required to develop a universally applicable model. Plain Language Summary: In 2002, deep low‐frequency tremors, which periodically occur with much smaller amplitudes and longer durations than common earthquakes, were discovered owing to the establishment of dense seismic arrays in Japan. These tremors are considered to be associated with megathrust earthquakes because they occur in deeper regions of plate boundaries compared with common earthquakes. Investigating tremors that occurred before the establishment of dense seismic arrays is important since megathrust earthquakes recur on intervals of 100–200 years, and digital records from modern seismic arrays cover only a fraction of that time. In this study, we developed a convolutional neural network based on the Residual Network (ResNet) that extracts tremors from images of waveforms recorded more than 50 years ago, when seismometers drew waveforms directly on drum‐rolled paper using a pen. The proposed ResNet, which was trained on seismogram images generated from synthetic waveforms and real data recorded digitally by modern seismic arrays, was applied to scanned images of paper seismograms recorded from 1966 to 1977 at an observatory in southwest Japan. A list of tremors was successfully obtained; however, further training using data that accounts for variables such as inconsistent plotting pen thickness is required to develop a universally applicable model. Key Points: Convolutional neural network model for detection of deep low‐frequency tremors from seismogram images is proposedThe model trained with seismogram images converted from real seismic data successfully detects tremorsThe detection performances of the trained model for the paper records at the Kumano observatory in southwest Japan are discussed [ABSTRACT FROM AUTHOR]

Researchers usually face difficulties in finding scientific papers relevant to their research interests due to increasing growth. Recommender systems emerge as a leading solution to filter valuable items intelligently. Recently, deep learning algorithms, such as convolutional neural network, improved traditional recommendation technologies, for example, the graph‐based or content‐based methods. However, existing graph‐based methods ignore high‐order association between users and items on graphs, and content‐based methods ignore global features of texts for explicit user preferences. Therefore, this paper proposes a Content‐based and knowledge Graph‐based Paper Recommendation method (CGPRec), which uses a two‐layer self‐attention block to obtain global features of texts for more complete explicit user preferences, and proposes an improved graph convolutional network for modeling high‐order associations on the knowledge graph to mine implicit user preferences. And the knowledge graph in this paper is constructed with concept nodes, user nodes, paper nodes, and other meta‐data nodes. Experimental results on a public dataset, CiteULike‐a, and a real application log dataset, AHData, show that our model outperforms compared with baseline methods. [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]

Insufficient and imbalance data samples often prevent the development of accurate deep learning models for manufacturing defect detection. By applying data augmentation methods ‐ including VAE latent space oversampling and random data generation, and GAN multi‐modal complementary data generation, we overcome the dataset limitations and achieve Pass/No‐Pass accuracies of over 90%. [ABSTRACT FROM AUTHOR]

This paper proposes applying a novel deep‐learning model, TBDLNet, to recognize CT images to classify multidrug‐resistant and drug‐sensitive tuberculosis automatically. The pre‐trained ResNet50 is selected to extract features. Three randomized neural networks are used to alleviate the overfitting problem. The ensemble of three RNNs is applied to boost the robustness via majority voting. The proposed model is evaluated by five‐fold cross‐validation. Five indexes are selected in this paper, which are accuracy, sensitivity, precision, F1‐score, and specificity. The TBDLNet achieves 0.9822 accuracy, 0.9815 specificity, 0.9823 precision, 0.9829 sensitivity, and 0.9826 F1‐score, respectively. The TBDLNet is suitable for classifying multidrug‐resistant tuberculosis and drug‐sensitive tuberculosis. It can detect multidrug‐resistant pulmonary tuberculosis as early as possible, which helps to adjust the treatment plan in time and improve the treatment effect. [ABSTRACT FROM AUTHOR]

Currently, deep learning methods for low‐light image enhancement tasks mainly focus on the illumination of images, while neglecting the problems of image noise and feature loss. To address this issue, this paper proposes a novel low‐light image enhancement network called DAF‐Retinex, based on the Retinex‐Net. To address the issue of image noise, different from traditional image denoise methods, this paper utilizes a fully convolutional neural network to denoise the reflection component, additionally, a denoising loss function is introduced to suppress noise. For preserving image details and extracting features, this paper creatively introduces self‐calibrated convolutions into low‐light image enhancement tasks, furthermore, a feature augmented attention block consisting of feature‐guided attention (FGA) is designed for feature learning to effectively enhance image illumination and extract image detail features. Experimental results demonstrate that the proposed algorithm in this paper effectively removes image noise and extracts detailed features, resulting in visually improved outcomes. On public datasets, the average improvement in objective evaluation metrics of image quality such as PSNR, SSIM, and NIQE are 1.13%, 4.12%, and 1.28%, respectively. [ABSTRACT FROM AUTHOR]

This document is a guest editorial from the journal IET Generation, Transmission & Distribution. It emphasizes the need to improve the reliability and resilience of modern power systems in the face of various threats. The editorial highlights the importance of modeling, assessing, and enhancing the reliability and resilience of power grids that are increasingly incorporating grid-edge resources. The document also provides a summary of the papers included in a special issue of the journal, which cover topics such as planning reliable energy systems, analyzing power grid operations, and enhancing service restoration and grid-support load response. Additionally, the text discusses the issue of equity in power distribution system restoration processes and proposes a model called the equity-aware power distribution system restoration model. The model aims to balance equity and resilience in restoring power after outages by focusing on fair distribution of energy resources while maintaining operational efficiency. The text also includes brief biographies of several authors who have contributed to the field of power electronics and power system reliability. [Extracted from the article]

Video‐based emotion recognition has been a long‐standing research topic for computer scientists and psychiatrists. In contrast to traditional discrete emotional models, emotion recognition based on continuous emotional models can better describe the progression of emotions. Quantitative analysis of emotions will have crucial impacts on promoting the development of intelligent products. The current solutions to continuous emotion recognition still have many issues. The original continuous emotion dataset contains incomplete data annotations, and the existing methods often ignore temporal information between frames. The following measures are taken in response to the above problems. Initially, aiming at the problem of incomplete video labels, the correlation between discrete and continuous video emotion labels is used to complete the dataset labels. This correlation is used to propose a mathematical model to fill the missing labels of the original dataset without adding data. Moreover, this paper proposes a continuous emotion recognition network based on an optimized temporal convolutional network, which adds a feature extraction submodule and a residual module to retain shallow features while improving the feature extraction ability. Finally, validation experiments on the Aff‐wild2 dataset achieved accuracies of 0.5159 and 0.65611 on the valence and arousal dimensions, respectively, by adopting the above measures. [ABSTRACT FROM AUTHOR]

Recently, deep learning (DL) based dynamic security assessment (DSA) methods have been very successful. However, although a DSA model can be trained well for a specific topology, it often does not perform well for other topologies. Since the topology in real‐world power systems is frequently changing, the performance reduction of DL‐based DSA methods is very serious, which is a challenging and urgent problem. This paper proposes a novel DSA method based on a convolutional neural network (CNN) to solve this problem. In the proposed method, a strong yet simple domain adaptation approach named adaptive batch normalization (AdaBN) is used, which significantly enhances the extensibility and generalizability of the DSA model when the topology changes and eliminates the need to train a large number of models. This approach achieves a deep adaptation effect by modulating the statistics from the source domain to the target domain in all batch normalization layers across the model. Unlike other domain adaptation methods, this method is parameter‐free, requires no additional components, and has advanced performance despite its simplicity. In addition, this paper introduces TGAN‐based data augmentation to deal with the difficulty of costly data collection and labelling. This data augmentation makes the proposed model applicable to small databases. The test results of the proposed method on IEEE 39‐bus and IEEE 118‐bus systems show that this method can evaluate system dynamic security during topology changes and in the face of data noise with high accuracy. [ABSTRACT FROM AUTHOR]

The discrepancy in data distribution between training and testing scenarios, as well as the inductive bias of convolutional neural networks towards image styles, reduces the model's generalization ability. Many unsupervised domain generalization methods based on feature decoupling suffer from an initial neglect of explicit decoupling of content and style features, resulting in content features that still contain considerable redundant information, thereby restricting improvements in generalization capability. To tackle this problem, this paper optimizes the learning process of domain‐invariant (content) features into an information compression issue, minimizing redundancy in content features. Furthermore, to enhance decoupled learning, this paper introduces innovative cross‐domain loss functions and image reconstruction modules that explicitly decouple and merge content and style across different domains. Extensive experiments demonstrate the method's significant enhancements over recent cutting‐edge approaches. [ABSTRACT FROM AUTHOR]

Background and Aims: Alzheimer's disease (AD) is a degenerative neurological condition that worsens over time and leads to deterioration in cognitive abilities, reduced memory, and, eventually, a decrease in overall functioning. Timely and correct identification of Alzheimer's is essential for effective treatment. The systematic study specifically examines the application of deep learning (DL) algorithms in identifying AD using three‐dimensional (3D) imaging methods. The main goal is to evaluate these methods' current state, efficiency, and potential enhancements, offering valuable insights into how DL could improve AD's rapid and precise diagnosis. Methods: We searched different online repositories, such as IEEE Xplore, Elsevier, MDPI, PubMed Central, Science Direct, ACM, Springer, and others, to thoroughly summarize current research on DL methods to diagnose AD by analyzing 3D imaging data published between 2020 and 2024. We use PRISMA (Preferred Reporting Items for Systematic Reviews and Meta‐Analyses) guidelines to ensure the organization and understandability of the information collection process. We thoroughly analyzed the literature to determine the primary techniques used in these investigations and their findings. Results and Conclusion: The ability of convolutional neural networks (CNNs) and their variations, including 3D CNNs and recurrent neural networks, to detect both temporal and spatial characteristics in volumetric data has led to their widespread use. Methods such as transfer learning, combining multimodal data, and using attention procedures have improved models' precision and reliability. We selected 87 articles for evaluation. Out of these, 31 papers included various concepts, explanations, and elucidations of models and theories, while the other 56 papers primarily concentrated on issues related to practical implementation. This article introduces popular imaging types, 3D imaging for Alzheimer's detection, discusses the benefits and restrictions of the DL‐based approach to AD assessment, and gives a view toward future developments resulting from critical evaluation. [ABSTRACT FROM AUTHOR]

Dual‐layer LCDs have the advantage of high contrast ratio, but due to the physical distance between the two LC panels, parallax error may appear when viewed off‐axis, affecting the display quality. In this paper, we propose a convolutional neural network‐based algorithm to mitigate parallax error and improve the display quality. First, a suitable training data set is selected and the input image is processed by a convolutional neural network to output a front image and a rear image. These two images are staggered and multiplied to obtain reproduced images at different angles. The reproduced image is compared with the original image by means of a loss function, and the parameters in the convolution are continuously updated to achieve the best display quality. The algorithm proposed in this paper can effectively mitigate the parallax error phenomenon of a dual‐layer LCD and improve the display quality, and the computational efficiency is also higher than the traditional algorithms. [ABSTRACT FROM AUTHOR]

Concerning the problems that the traditional Convolutional Neural Network (CNN) ignores contextual semantic information, and the traditional Recurrent Neural Network (RNN) has information memory loss and vanishing gradient, this paper proposes a Bi‐directional Encoder Representations from Transformers (BERT)‐based dual‐channel parallel hybrid neural network model for text sentiment analysis. The BERT model is used to convert text into word vectors; the dual‐channel parallel hybrid neural network model constructed by CNN and Bi‐directional Long Short‐Term Memory (BiLSTM) extracts local and global semantic features of the text, which can obtain more comprehensive sentiment features; the attention mechanism enables some words to get more attention that highlights important words and improves the model's sentiment classification ability. Finally, the dual‐channel output features are fused for sentiment classification. The experimental results on the hotel review datasets show that the Accuracy of the proposed model in sentiment classification reaches 92.35% and the F1 score reaches 91.59%. [ABSTRACT FROM AUTHOR]

Because roads are the major backbone of the transportation network, research about crack detection on road surfaces has been popular in computer and infrastructure engineering. When training a convolutional neural network (CNN) for pixel‐level road crack detection, three common challenges include (1) the data are severely imbalanced, (2) crack pixels can be easily confused with normal road texture and other visual noises, and (3) there are many unexplainable characteristics regarding the CNN itself. When it comes to very fine and thin cracks, these challenges are exaggerated and a new challenge is introduced, as there can be a discrepancy between the actual width and the annotated width of a crack. To tackle all these challenges of thin crack detection, this paper proposes a new variant of CNN named ThinCrack U‐Net, designed to provide thin results upon pixel‐level crack detection on road surfaces. The main contribution is to demystify how pixel‐level thin crack detection results are affected by different loss functions as well as various combinations of the U‐Net components. The experimental results show that ThinCrack U‐Net yields a significant performance boost in CrackTree260, from 65.71% to 94.48% F‐measure, compared to the existing variant of U‐Net previously proposed in the context of pixel‐level thin crack detection. Finally, this paper locates the source of undesirable result thickness and solves it with the balanced usage of downsampling/upsampling layers and atrous convolution. Unlike suggested by previous works, different loss functions show no significant impact on ThinCrack U‐Net, whereas normalization layers are proved crucial in pixel‐level thin crack detection. [ABSTRACT FROM AUTHOR]

We propose an efficient deep convolutional neural network for a super‐resolution which is capable of multiple‐quality input, by analyzing the input quality and choosing appropriate features automatically. To implement the network in an FPGA and an ASIC, we employ a network trimming technique to compress the neural network. [ABSTRACT FROM AUTHOR]

The combination of computer algorithms to diagnose clinical images has attracted more and more attention. This research aims to improve the efficiency of gastric cancer (GC) diagnosis, so deep learning (DL) algorithms are tentatively used to assist doctors in the diagnosis of gastric cancer. In the experiment, the collected 3591 gastroscopic images were divided into network training set and experimental verification test set. The lesion samples in the image are all marked by many endoscopists with many years of clinical experience. In order to improve the experimental effect, 5261 endoscopic images were obtained by expanding the training set. Then the obtained training set is input into the convolutional neural network (CNN) for training, and finally get the algorithm model DLU‐Net. By inputting 598 test set samples into the CNN constructed in this paper, five results such as advanced GC, early GC, precancerous lesions, normal and benign lesions can be identified and output, with a total accuracy of 94.1%. It can be concluded that the DL algorithm model constructed in this paper can effectively identify the staging characteristics of cancer as well as gastroscopic images, greatly improve efficiency, and effectively assist physicians in the diagnosis of GC under gastroscopy. [ABSTRACT FROM AUTHOR]

In recent years, fingerprint authentication has gained widespread adoption in diverse identification systems, including smartphones, wearable devices, and attendance machines, etc. Nonetheless, these systems are vulnerable to spoofing attacks from suspicious fingerprints, posing significant risks to privacy. Consequently, a fingerprint presentation attack detection (PAD) strategy is proposed to ensure the security of these systems. Most of the previous work concentrated on how to build a deep learning framework to improve the PAD performance by augmenting fingerprint samples, and little attention has been paid to the fundamental difference between live and fake fingerprints to optimize feature extractors. This paper proposes a new fingerprint liveness detection method based on Siamese attention residual convolutional neural network (Res‐CNN) that offers an interpretative perspective to this challenge. To leverage the variance in ridge continuity features (RCFs) between live and fake fingerprints, a Gabor filter is utilized to enhance the texture details of the fingerprint ridges, followed by the construction of an attention Res‐CNN model to extract RCF between the live and fake fingerprints. The model mitigates the performance deterioration caused by gradient disappearance. Furthermore, to highlight the difference in RCF, a Siamese attention residual network is devised, and the ridge continuity amplification loss function is designed to optimize the training process. Ultimately, the RCF parameters are transferred to the model, and transfer learning is utilized to aid its acquisition, thereby assuring the model's interpretability. The experimental outcomes conducted on three publicly accessible fingerprint datasets demonstrate the superiority of the proposed method, exhibiting remarkable performance in both true detection rate and average classification error rate. Moreover, our method exhibits remarkable capabilities in PAD tasks, including cross‐material experiments and cross‐sensor experiments. Additionally, we leverage Gradient‐weighted Class Activation Mapping to generate a heatmap that visualizes the interpretability of our model, offering a compelling visual validation. [ABSTRACT FROM AUTHOR]

Accurate forecasting of electric vehicle (EV) load is essential for grid stability and energy management. EV load forecasting is influenced by multiple factors. At present, the load forecasting model for EVs mainly uses collected sample data to build a data‐driven model. But these algorithms need to collect all the data together to train the model, ignoring the privacy of each data collection source. In a competitive market environment, each device service provider is not willing to share the sample data they store. Aiming at this problem, this paper proposes an EV load diagnosis algorithm considering data privacy. Firstly, a convolutional neural network with dual attention mechanism is constructed as the basic time series forecasting model. The association rule algorithm is used to select weather data with strong associations as the inputs of the model. Each service provider uses local data to perform deep learning network. All models are then trained using a federated learning framework. During the entire training process, historical data is stored locally, and only model parameter information is shared and interacted; thus data privacy is protected. Finally, the validity of the algorithm in this paper is verified by using real collected EV load data. [ABSTRACT FROM AUTHOR]

Convolutional neural networks (CNNs) have been widely used in satellite remote sensing. However, satellites in orbit with limited resources and power consumption cannot meet the storage and computing power requirements of current million‐scale artificial intelligence models. This paper proposes a new generation of high flexibility and intelligent CNNs hardware accelerator for satellite remote sensing in order to make its computing carrier more lightweight and efficient. A data quantization scheme for INT16 or INT8 is designed based on the idea of dynamic fixed point numbers and is applied to different scenarios. The operation mode of the systolic array is divided into channel blocks, and the calculation method is optimized to increase the utilization of on‐chip computing resources and enhance the calculation efficiency. An RTL‐level CNNs field programable gate arrays accelerator with microinstruction sequence scheduling data flow is then designed. The hardware framework is built upon the Xilinx VC709. The results show that, under INT16 or INT8 precision, the system achieves remarkable throughput in most convolutional layers of the network, with an average performance of 153.14 giga operations per second (GOPS) or 301.52 GOPS, which is close to the system's peak performance, taking full advantage of the platform's parallel computing capabilities. [ABSTRACT FROM AUTHOR]

Segmentation is crucial in diagnosing retinal diseases by accurately identifiying retinal vessels. This paper addresses the complexity of segmenting retinal vessels, highlighting the need for precise analysis of blood vessel structures. Despite the progress made by convolutional neural networsks (CNNs) in image segmentation, their limitations in capturing the global structure of retinal vsessels and maintaining segmentation continuity present challenges. To tackle these issues, our proposed network integrates graph convolutional networks (GCNs) and attention mechansims. This allows the model to consider pixel relationships and learn vessel graphical structures, significantly improving segmentation accuracy. Additionally, the attentional feature fusion module, including pixel‐wise and channel‐wise attention mechansims within the U‐Net architecture, refines the model's focus on relevant features. This paper emphasizes the importance of continuty preservation, ensuring an accurate representation of pixel‐level information and structural details during sefmentation. Therefore, our method performs as an effective solution to overcome challenges in retinal vessel segmentation. The proposed method outperformed the state‐of‐the‐art approaches on DRIVE (Digital Retinal Images for Vessel Extraction) and STARE (Structed Analysis of the Retina) datasets with accuracies of 0.12% and 0.14%, respecttively. Importantly, our proposed approach excelled in delineating slender and diminutive blood vessels, crucial for diagnosing vascular‐related diseases. Implementation is accessible on https://github.com/CVLab‐SHUT/VGA‐Net. [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]

Great progress has been made in deep learning image reconstruction, but there are still problems that need to be improved, such as the extraction of image texture details and the improvement of the overall contour quality of the image, and how to reduce the transmission cost is also the focus of research. This paper proposes a fast bilateral network suitable for both grayscale and color image reconstruction. In the compression network, bilinear interpolation, fully connected layer and convolutional neural network are selected for image compression. The reconstruction network is divided into two parts: the texture path and contour path, the former reconstructs the remaining texture details of the image, and the latter performs deep contour reconstruction. The bilateral complementary residual connection method transfers the texture information to the contour path and improves the contour quality, and the improvement of the contour quality can improve the learning of texture details. Through a large number of data tests, it shows that the network in this paper has achieved comparable or better results in terms of image reconstruction quality, time‐consuming and robustness against noise. It solves the problem of memory consumption for storing a large number of images, and also provides convenience for shortening space and time during image transmission. [ABSTRACT FROM AUTHOR]

The problems of insufficient recognition accuracy, poor real‐time performance and lack of consideration of actual working conditions in the process of intelligent construction of coal mines make this technology still in the research stage and not applied in practical engineering. The purpose of this paper is to establish an accurate and real‐time recognition model, which can quickly distinguish the vibration acceleration signals of coal and gangue under the influence of external factors such as impact position, velocity, and direction by using the different physical properties of coal and gangue particles. Therefore, the accuracy and real‐time of coal gangue recognition model established by different convolutional neural networks (CNN) structures and different position signal input are studied. First, to meet the real‐time requirements, an original CNN recognition model composed of single convolution layer and single pooling layer is established, and the data collected by seven sensors are input in the form of two‐dimensional matrix. However, the stability of the training and test results is insufficient. To solve this problem, once improved CNN (OI‐CNN) recognition model with multiconvolution layers and multipooling layers is built by deepening the network. The experimental results show that the stability and accuracy are improved, but the real‐time performance is poor. Furthermore, through parameter adjustment, the OI‐CNN is changed to the twice improved CNN (TI‐CNN), and the sensor data at different positions are input in the form of one‐dimensional vectors. The results show that the accuracy and real‐time performance of the TI‐CNN coal gangue recognition model are further improved. Finally, according to the research purpose of this paper, the weights of CNN indexes are given, and a multi‐index comprehensive evaluation system (MICES) is established. With the original CNN recognition model as the control, the OI‐CNN recognition model and the TI‐CNN recognition model at different positions are quantitatively compared to obtain the comprehensive evaluation scores of each model. The results show that the MICES of the coal gangue recognition model established based on the TI‐CNN structure and the data input of a single position sensor is the highest, while the sensor position has little effect on the recognition results. [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]

In recent years, deep learning‐based fault diagnosis technology for high‐voltage circuit breakers (HVCB) has advanced significantly, but the working environment of HVCBs is complex, resulting in unsatisfactory fault diagnosis results of HVCBs in noisy environment and existing deep learning methods are difficult to solve this problem. This paper proposes a multi‐channel convolutional neural network combines dense residual structure and attention mechanism to achieve high‐precision and high‐robust diagnosis of HVCBs in noisy backgrounds. A dense residual network is introduced into the convolutional neural network to prevent feature loss during network propagation to preserve the difference information between the network layers as much as possible, Simultaneously, a channel attention mechanism is introduced to adaptively adjust the weights of different convolution channels. The model can extract multi‐scale features from the original signal and fully exploit the intrinsic relationship between the vibration signal and the HVCB's operating state. The experimental results show that the diagnostic method can still meet the requirements of fault diagnosis in the presence of noise, with an average diagnostic accuracy rate of 85.92% when the signal‐to‐noise ratio is −4. The model outperforms the traditional single‐channel model in terms of diagnostic accuracy and stability. [ABSTRACT FROM AUTHOR]

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]

Accurate power load prediction is an important guide for power system planning and operation. High‐ or low‐load prediction results will affect the operation of the power system. In recent years, deep learning technology represented by convolution neural network (CNN) and transformer has been proved to be suitable for power load prediction. This paper proposes a new short‐term power load hybrid forecasting model, called channel enhanced attention (CEA) and temporal convolutional network (TCN)‐based transformer comprehensive forecasting model. This method combines the short‐term feature extraction ability of TCN with the long‐term dependent capture ability of transformer for short‐term load forecasting. And the CEA designed in this study is added to improve the prediction accuracy. On the same dataset, the designed model predicts power load mean square errors of 0.056 and 0.146 for the next 24 h and the next week, respectively, which is 0.002 to 0.073 and 0.012 to 0.024 lower than the baseline model. The experimental results show that the hybrid short‐term power load prediction model proposed in this paper is significantly better than the existing methods. The predicted curve is in agreement with the actual charge change, which provides a good guidance for short‐term power load prediction. [ABSTRACT FROM AUTHOR]

The endless adverse effects of air pollution incidents have raised significant public concerns in the past few decades. The measure of air pollution, that is, the air quality index (AQI), is highly volatile and associated with different kinds of uncertainties. Following this, the study and development of accurate fuzzy time series forecasting (TSF) methods for predicting the AQI have a significant role in air pollution control and management. Motivated by this, in this paper, a systematic study is made to evaluate the true potential of fuzzy TSF methods employing traditional fuzzy set (TFS), intuitionistic fuzzy set (IFS), hesitant fuzzy set (HFS), and neutrosophic fuzzy set (NFS) in forecasting the AQI. Two novel high‐order fuzzy TSF methods, TFS‐multilayer perceptron (MLP) and HFS‐MLP, are proposed employing TFS and HFS in which ratio trend variation of AQI data is used instead of original AQI, MLP is used to model the fuzzy logical relationships (FLRs), and none/mean of aggregated membership values are used while modeling the FLRs using MLP. The results from the proposed fuzzy TSF methods are compared with recently proposed fuzzy TSF methods employing TFS, IFS, and NFS and six popular machine learning models, including MLP, support vector regression (SVR), Bagging Regressors, XGBoost, long‐short term memory (LSTM), and convolutional neural network (CNN). The "Wilcoxon Signed‐Rank test" and "Friedman and Nemenyi hypothesis test" are applied to the results obtained by employing different ratios in the train‐validation‐test to draw decisive conclusions reliably. The simulation results show the statistical dominance of the proposed TFS‐MLP method over all other crisp and fuzzy TSF methods employed in this paper. [ABSTRACT FROM AUTHOR]

ABSTRACT Machine vision has had a substantial impact on human‐computer interaction and psychological research. The ability of robots to generate realistic facial expressions has been enhanced by advancements in artificial intelligence, neural networks, and deep learning, thereby nurturing more profound emotive connections between humans and machines. This paper offers an in‐depth look of the most recent developments in emotion classification technologies, with a specific focus on the period from 2019 to 2023. This research addresses the integration of facial and body gesture analysis into emotion detection, emphasising the development of methods such as partial transfer learning, sign‐based measurement systems, and lightweight convolutional neural networks. By analysing the most recent research, the paper not only provides a comprehensive overview of the most advanced methods, but also emphasises their superiority over previous approaches in terms of efficiency, and applicability. The integration of gestures into emotion analysis is underscored as a critical area for further investigation, providing novel opportunities for comprehending and interpreting the intricate layers of nonverbal communication. The objective of this survey is to provide a resource for researchers and practitioners who are interested in advancing the field of emotion classification by utilising innovative methodologies. [ABSTRACT FROM AUTHOR]

In the field of railway infrastructure maintenance, timely and accurate detection of component anomalies is crucial for safety and efficiency. This paper presents the Cascade Region‐based convolutional neural network with Predefined Proposal Templates (CR‐PPT), an innovative method for railroad components inspection in complex railway infrastructure using edge‐computing devices. Unlike previous systems, CR‐PPT employs a series of predefined templates that enable it to detect both the presence and missing elements within various fastening systems. Our experimental analysis pinpoints the most effective network configurations for CR‐PPT. Furthermore, the paper examines CR‐PPT's proficiency in zero‐shot learning and fine‐tuning, highlighting its adaptability to new fastening systems. We have developed an optimized inference pipeline on NVIDIA Jetson AGX Orin, significantly enhancing its applicability for railway inspection practices. Field blind tests validate the model's high precision and efficiency, greatly reducing the time and labor required for inspections. The findings highlight CR‐PPT's potential as an efficient and robust tool for track health assessment, marking a notable progression in the integration of AI and computer vision in rail track inspection. [ABSTRACT FROM AUTHOR]

Purpose: In recent years, the use of deep learning for medical image segmentation has become a popular trend, but its development also faces some challenges. Firstly, due to the specialized nature of medical data, precise annotation is time‐consuming and labor‐intensive. Training neural networks effectively with limited labeled data is a significant challenge in medical image analysis. Secondly, convolutional neural networks commonly used for medical image segmentation research often focus on local features in images. However, the recognition of complex anatomical structures or irregular lesions often requires the assistance of both local and global information, which has led to a bottleneck in its development. Addressing these two issues, in this paper, we propose a novel network architecture. Methods: We integrate a shift window mechanism to learn more comprehensive semantic information and employ a semi‐supervised learning strategy by incorporating a flexible amount of unlabeled data. Specifically, a typical U‐shaped encoder‐decoder structure is applied to obtain rich feature maps. Each encoder is designed as a dual‐branch structure, containing Swin modules equipped with windows of different size to capture features of multiple scales. To effectively utilize unlabeled data, a level set function is introduced to establish consistency between the function regression and pixel classification. Results: We conducted experiments on the COVID‐19 CT dataset and DRIVE dataset and compared our approach with various semi‐supervised and fully supervised learning models. On the COVID‐19 CT dataset, we achieved a segmentation accuracy of up to 74.56%. Our segmentation accuracy on the DRIVE dataset was 79.79%. Conclusions: The results demonstrate the outstanding performance of our method on several commonly used evaluation metrics. The high segmentation accuracy of our model demonstrates that utilizing Swin modules with different window sizes can enhance the feature extraction capability of the model, and the level set function can enable semi‐supervised models to more effectively utilize unlabeled data. This provides meaningful insights for the application of deep learning in medical image segmentation. Our code will be released once the manuscript is accepted for publication. [ABSTRACT FROM AUTHOR]

Bird‐related outages greatly threaten the safety of overhead transmission and distribution lines, while electrocution and collisions of birds with power lines, especially endangered species, are significant environmental concerns. Automatic bird recognition can be helpful to mitigate this contradiction. This paper proposes a method for automatic classification of bird species related to power line faults combining deep convolution features with error‐correcting output codes support vector machine (ECOC‐SVM). An image dataset of about 20 high‐risk and 20 low‐risk bird species was constructed, and the feed‐forward denoising convolutional neural network was used for image preprocessing. The deep convolution features of bird images were extracted by DarkNet‐53, and taken as inputs of the ECOC‐SVM for model training and bird species classification. The gradient‐weighted class activation mapping was used for visual explanations of the model decision region. The experimental results indicate that the average accuracy of the proposed method can reach 94.39%, and its performance was better than other models using different feature extraction networks and classification algorithms. [ABSTRACT FROM AUTHOR]

Transformer possesses a broader perceptual scope, while the Convolutional Neural Network (CNN) excels at capturing local information. In this paper, the authors propose the Multi‐Sclale Feature Aggregation Network (MSFA‐Net) for single‐image dehazing which is fused with the advantages of Transformer and CNN. Our MSFA‐Net is based on the encoder–decoder structure, and there are four main innovations. Firstly, the authors make some improvements to the original Swin Transformer to make it more effective for dehazing tasks, and the authors name it Spatial Information Aggregation Transformer (SIAT). The authors place the SIAT in both encoder and decoder of MSFA‐Net for feature extraction. The authors propose an upsampling module called Efficient Spatial Resolution Recovery (ESRR) which is placed in the decoder part. Compared to commonly used transposed convolutions, the authors' ESRR module has fewer computational cost. Considering that the haze distribution is always uneven and the information from each channel is different, the authors introduce the Dynamic Multi‐Attention (DMA) module to provide pixel‐wise weights and channel‐wise weights for input features. The authors place the DMA module between the encoder and decoder parts. As the network depth increases, the spatial structural information from the high‐resolution layer tends to degrade. To deal with the problem, the authors propose the Multi‐Scale Feature Fusion (MSFF) module to recover missing spatial structural information. The authors place the MSFF module in both the encoder and decoder parts. Extensive experimental results show that the authors' proposed dehazing network achieves state‐of‐the‐art dehazing performance with relatively low computational cost. [ABSTRACT FROM AUTHOR]

Effective extraction of building from remote sensing images requires both global and local information. Despite convolutional neural networks (CNNs) excelling at capturing local details, their intrinsic focus on local operations poses challenge in effectively extracting global features, especially in the context of large‐scale buildings. In contrast, transformers excel at capturing global information, but compared to CNNs, they tend to overly rely on large‐scale datasets and pre‐trained parameters. To tackle the challenge, this paper presents the multi‐scale and dual‐branch feature fusion network (MDTrans). Specifically, the CNN and transformer branches are integrated in a dual‐branch parallel manner during both encoding and decoding stages, local information for small‐scale buildings is extracted by utilizing Dense Connection Blocks in the CNN branch, while crucial global information for large‐scale buildings is effectively captured through Swin Transformer Block in the transformer branch. Additionally, Dual Branch Information Fusion Block is designed to fuse local and global features from the two branches. Furthermore, Multi‐Convolutional Block is designed to further enhance the feature extraction capability of buildings with different sizes. Through extensive experiments on the WHU, Massachusetts, and Inria building datasets, MDTrans achieves intersection over union (IoU) scores of 91.36%, 64.69%, and 79.25%, respectively, outperforming other state‐of‐the‐art models. [ABSTRACT FROM AUTHOR]

Medical image segmentation through the use of deep learning is becoming a trend targeting to automate disease detection and provide effective treatment. Traditionally huge manual efforts are associated with medical image processing by medical staff. The wide use of neural networks driven by the progressive advancement in computing power and the availability of training data provides instrumental means to automate medical image processing. A polyp refers to an abnormal growth that can occur in various parts of the body. While the majority of polyps are noncancerous or benign, there are instances where certain types can develop into cancer. Detecting and segmenting polyps is highly valuable for identifying early signs and potentially enabling more effective treatment of colon cancer. In this paper, we introduce a novel method for segmenting polyp images. The proposed method utilizes convolutional neural networks (CNNs) and employs an enhanced attention mechanism. To cater to a more granular attention view, this paper enhances the Convolutional Block Attention Module by introducing the multi‐focal channel attention (MFCA) concept, which we call MFCA. In the proposed MFCA channel attention, focal attention spots allow us to consider scattered areas of interest more effectively. To evaluate the effectiveness of the proposed method, multiple experiments are conducted on five well‐known benchmark datasets for polyp image segmentation: Kvasir, CVC‐Clinic DB, CVC‐Colon DB, CVC‐T, and ETIS‐Larib. Various testing scenarios are examined, including the impact of two focal attention spots and four focal attention spots. The experimental results demonstrated that the proposed method achieved superior performance compared to previous state‐of‐the‐art techniques on two of the benchmark datasets, and ranked second on a third dataset. [ABSTRACT FROM AUTHOR]

Epilepsy is a disorder that interferes with regular brain activity and can occasionally cause seizures, odd sensations, and momentary unconsciousness. Epilepsy is frequently diagnosed using electroencephalograph (EEG) records, although conventional analysis is subjective and prone to error. The dynamic and non‐stationary nature of EEG structure restricted the performance of Deep Learning (DL) approaches used in earlier work to improve EEG classification. Our multi‐channel EEG classification model, dubbed LConvNet in this paper, combines Convolutional Neural Networks (CNN) for extracting spatial features and Long Short‐Term Memory (LSTM) for identifying temporal dependencies. To discriminate between epileptic and healthy EEG signals, the model is trained using open‐source secondary EEG data from Temple University Hospital (TUH). Our model outperformed other EEG classification models employed in comparable tasks, such as EEGNet, DeepConvNet, and ShallowConvNet, which had accuracy rates of 86%, 96%, and 78%, respectively. Our model attained an amazing accuracy rate of 97%. During additional testing, our model also displayed excellent performance in trainability, scalability, and parameter efficiency. [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]

Thanks to the great developments of the latest Field Programmable Gate Array (FPGA), the performance bottleneck of Deep Learning hardware accelerators has been converted to computing ability. In this paper, a novel FPGA‐based Convolutional Neural Network (CNN) Accelerator architecture, named the Effective Pipeline Architecture (EPA) is proposed to optimize the resource usage for the implementation of the CNN calculation. As the unique storage strategies, which contain many creative designing details, are adopted and optimized for different CNN models and layers, great DSP computing efficiency can be achieved in the fine‐grained pipeline. Moreover, compared with the traditional architectures, through the kernel combination and data scheduling, twice throughput for the general matrix multiplication is realized in a great many parallel DSP48E resources. As a result, the realization of Yolov2‐Tiny achieves 873 Giga Operations Per Second (GOPS) by 902 DSPs with 67 Frames Per Second (FPS), and the computing efficiency in most layers can even reach more than 90%, which improves the calculation performance and efficiency comparing with the previous designs, and is significant to meet the increasing computing requirement. [ABSTRACT FROM AUTHOR]

Proceedings of the 2019 20th International Conference on Parallel and Distributed Computing, Applications and Technologies (PDCAT 2019); December 5, 2019:166-172; IEEE. Parallel and distributed computing has been the basis to many emerging areas, such as smart networks, cloud computing, big data analysis, and blockchain technology. We hope that this special issue provides valuable information and references for pursuit of research in the field of parallel and distributed computing and its relevant areas. [Extracted from the article]

In this paper, an additive margin network with adaptive feature recalibration, AMNets, for handling a wide range of visual tasks, is proposed. The new AMNets consists of three improvements on convolutional neural networks: (1) squeeze‐and‐excitation mechanism was embedded into the the residual block of single layer to improve the performance of the classification, (2) softmax loss was replaced by the additive margin softmax loss to minimize intra‐class variance and maximize inter‐class variance, and (3) Adam optimizer was exploited to update iteratively the network parameters. Experiments on the Brain Stroke CT Image Dataset show that our additive margin network is quite effective to improve state‐of‐the‐art algorithms. Network algorithms have been extensively used in medical image field to pursuit a more accuracy of disease recognition. This paper proposes AMNets, an additive margin network with adaptive feature recalibration for handling a wide range of visual tasks in medicine. [ABSTRACT FROM AUTHOR]

Power transformers play a critical role in the performance of power systems. This equipment is costly due to significant copper and iron prices and manufacturing costs. Therefore, maintenance and protection of such equipment is essential. Despite its robust performance, maloperation of differential protection (DP) in transformers may cause operational challenges to power system operators. The differential relay may operate incorrectly after the transformer energization leads to an inrush current (IC) and the relay identifies the event as an internal fault, and consequently issues the trip command. The other case of maloperation includes, but not limited to, a moment when the current transformer saturates due to an external fault. In this paper, a novel approach for DP is proposed, that is based on signal processing methods. In this paper, variational mode decomposition (VMD) and the deep neural network are implemented by using the convolutional neural network (CNN) and bi‐directional long short‐term memory (BiLSTM) models. The VMD decomposes differential current signal (DCS) to intrinsic mode functions with corresponding narrow‐band property frequency spectrums, which provides more detailed information about signal characteristics in different frequency bands. At the next stage, an effective feature for the BiLSTM is extracted by the CNN with the convolutional layers to classify events and proper discrimination. Extensive simulations on a 500 MVA transformer in MATLAB demonstrate the effectiveness of the proposed protection approach to differentiate ICs from internal and external faults with 99.8% accuracy in less than 1/8th of a power cycle. [ABSTRACT FROM AUTHOR]

The extraction of ionospheric echo plays a key role in the research of radio wave propagation theory and is the basis of the design, application, and test of the radio engineering system. However, it is too complicated to achieve because of several negative factors, such as environmental noise, thermal noise, ionospheric time‐varying dispersion characteristics, and so on. In this paper, a novel ionospheric echoes extraction model, referred to as IECAENet, is proposed based on the convolutional neural networks. First, VGGNet is introduced as the classification module to extract echoes from different kinds of ionograms, including vertical ionograms, oblique ionograms, and backscatter ionograms. Then, the echoes extraction module is designed. It considers not only the ionogram features but also an explicit hint, named echo mask, that expresses the location of the echoes. Finally, the residual learning technology and skip connection structure are introduced to improve the performance of the module. Experimental results on a real data set indicate that IECAENet outperforms the baselines for the ionospheric echoes extraction. Using the false alarm probability that IECAENet has an optimal performance as the benchmark, the detection probabilities of the vertical ionogram, oblique ionogram, and backscatter ionogram are improved by 22.18%, 22.56%, and 6.67%, respectively, compared with the traditional methods. Key Points: This is the first time a residual convolution neural network has been used to extract ionogram echoTo improve the extraction performance, the mask that expresses the echo region is proposed and a new joint loss function is designedThe extraction performance of the model surpasses the performance of some traditional methods [ABSTRACT FROM AUTHOR]

Inspection of insect sticky paper traps is an essential task for an effective integrated pest management (IPM) programme. However, identification and counting of the insect pests stuck on the traps is a very cumbersome task. Therefore, an efficient approach is needed to alleviate the problem and to provide timely information on insect pests. In this research, an automatic method for the multi‐class recognition of small‐size greenhouse insect pests on sticky paper trap images acquired by wireless imaging devices is proposed. The developed algorithm features a cascaded approach that uses a convolutional neural network (CNN) object detector and CNN image classifiers, separately. The object detector was trained for detecting objects in an image, and a CNN classifier was applied to further filter out non‐insect objects from the detected objects in the first stage. The obtained insect objects were then further classified into flies (Diptera: Drosophilidae), gnats (Diptera: Sciaridae), thrips (Thysanoptera: Thripidae) and whiteflies (Hemiptera: Aleyrodidae), using a multi‐class CNN classifier in the second stage. Advantages of this approach include flexibility in adding more classes to the multi‐class insect classifier and sample control strategies to improve classification performance. The algorithm was developed and tested for images taken by multiple wireless imaging devices installed in several greenhouses under natural and variable lighting environments. Based on the testing results from long‐term experiments in greenhouses, it was found that the algorithm could achieve average F1‐scores of 0.92 and 0.90 and mean counting accuracies of 0.91 and 0.90, as tested on a separate 6‐month image data set and on an image data set from a different greenhouse, respectively. The proposed method in this research resolves important problems for the automated recognition of insect pests and provides instantaneous information of insect pest occurrences in greenhouses, which offers vast potential for developing more efficient IPM strategies in agriculture. [ABSTRACT FROM AUTHOR]

There are many different types of nuclei in a tumor tissue. We can identify the specific nuclei and their distribution in the tissue to reflect the current cancer state of histopathological images. However, due to the existence of cellular heterogeneity, the recognition of nuclei in histopathological images has always been a problem of computer vision. In the paper, we use the transfer learning of Deep Convolutional Neural Network to classify nuclei, and found that adjusting the size of the nuclear image to a certain size can improve the accuracy of the nuclei classification model, while not significantly reducing the nuclei classification efficiency. Through further research, it was confirmed that the environment around the nuclei can bring great help to the model classification. Based on the principle, we design a feature fusion model. We extract features from nuclei image different sizes by CNN, fuse the features, and then use fully connected layer to classify the features. Experiments have proved that the feature fusion model has a considerable improvement in accuracy compared to the normal classification model. [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]