Search

To address the challenges of sparse point clouds in current MIMO millimeter-wave radar environmental mapping, this paper proposes a dense 3D millimeter-wave radar point cloud environmental mapping algorithm. In the preprocessing phase, a radar SLAM-based approach is introduced to construct local submaps, which replaces the direct use of radar point cloud frames. This not only reduces data dimensionality but also enables the proposed method to handle scenarios involving vehicle motion with varying speeds. Building on this, a 3D-RadarHR cross-modal learning network is proposed, which uses LiDAR as the target output to train the radar submaps, thereby generating a dense millimeter-wave radar point cloud map. Experimental results across multiple scenarios, including outdoor environments and underground tunnels, demonstrate that the proposed method can increase the point cloud density of millimeter-wave radar environmental maps by over 50 times, with a point cloud accuracy better than 0.1 m. Compared to existing algorithms, the proposed method achieves superior environmental map reconstruction performance while maintaining a real-time processing rate of 15 Hz. [ABSTRACT FROM AUTHOR]

Millimeter-wave radars are widely used in various environments due to their excellent detection capabilities. However, the detection performance in severe weather environments is still an important research challenge. In this paper, the propagation characteristics of millimeter-wave radar in a rainfall environment are thoroughly investigated, and the modeling of the millimeter-wave radar echo signal in a rainfall environment is completed. The effect of rainfall on radar detection performance is verified through experiments, and an anti-rain clutter interference method based on a convolutional neural network is proposed. The method combines image recognition and classification techniques to effectively distinguish target signals from rain clutter in radar echo signals based on feature differences. In addition, this paper compares the recognition results of the proposed method with VGGnet and Resnet. The experimental results show that the proposed convolutional neural network method significantly improves the target detection capability of the radar system in a rainfall environment, verifying the method's effectiveness and accuracy. This study provides a new solution for the application of millimeter-wave radar in severe weather conditions. [ABSTRACT FROM AUTHOR]

Analysis of unintended compromising emissions from Video Display Units (VDUs) is an important topic in research communities. This paper examines the feasibility of recovering the information displayed on the monitor from reconstructed video frames. The study holds particular significance for our understanding of security vulnerabilities associated with the electromagnetic radiation of digital displays. Considering the amount of noise that reconstructed TEMPEST video frames have, the work in this paper focuses on two different approaches to de-noising images for efficient optical character recognition. First, an Adaptive Wiener Filter (AWF) with adaptive window size implemented in the spatial domain was tested, and then a Convolutional Neural Network (CNN) with an encoder–decoder structure that follows both classical auto-encoder model architecture and U-Net architecture (auto-encoder with skip connections). These two techniques resulted in an improvement of more than two times on the Structural Similarity Index Metric (SSIM) for AWF and up to four times for the SSIM for the Deep Learning (DL) approach. In addition, to validate the results, the possibility of text recovery from processed noisy frames was studied using a state-of-the-art Tesseract Optical Character Recognition (OCR) engine. The present work aims to bring to attention the security importance of this topic and the non-negligible character of VDU information leakages. [ABSTRACT FROM AUTHOR]

Featured Application: The model proposed in this paper can help stock investors to get high returns on newly listed stocks. Most previous stock investing methods were unable to predict newly listed stocks because they did not have historical data on newly listed stocks. In this paper, we use the Q-learning algorithm based on a convolutional neural network and add sentiment analysis to establish a prediction method for Chinese stock investment tasks. There are 118 companies that are ranked in the Chinese top 150 list for two consecutive years in both 2022 and 2023. We collected all comments under the stock bar of these 118 stocks for each day from 1 January 2022 to 1 July 2024, totaling nearly 10 million comments. There are 90 stocks left after the preprocessing of 118 stocks. We use these 90 stocks as the dataset. The stock's closing price, volume, and comment text data are fed together to the agent, and the trained agent outputs investment behaviors that maximize future returns. We apply the trained model to two test sets that are completely different from the training set and compare it to several other methods. Our proposed method called SADQN-S obtains results of 1.1229 and 1.1054 on the two test sets. SADQN-S obtained higher final total assets than the other methods on both test sets. This shows that our model can help stock investors earn high returns on newly listed stocks. [ABSTRACT FROM AUTHOR]

The use of satellites to cover remote areas is a promising approach for increasing communication availability and reliability. The satellite resources, however, can be quite costly, and developing ways to optimize their usage is of great interest. Optimizing spectral efficiency while keeping the transmission error rate above a certain threshold represents one of the crucial aspects of resource optimization. This paper provides a novel strategy for adaptive coding and modulation (ACM) employment in land mobile satellite networks. The proposed solution incorporates machine learning techniques to predict channel state information and subsequently increase the overall spectral efficiency of the network. The Digital Video Broadcasting Satellite Second Generation (DVB-S2X) satellite protocol is considered as the use case, and by using the developed channel simulator, this paper performs an evaluation of the proposed machine learning solutions for channels with various characteristics, with a total of 90 different observed channels. The results show that a convolutional neural network with a modified loss function consistently achieves an improvement (over 100% in some scenarios) of spectral efficiency compared to the state-of-the-art ACM implementation while keeping the transmission error rate under 0.01 for single channel evaluation. When observing two channels, an improvement of more than 300% compared to the outdated information spectral efficiency was obtained in multiple scenarios, showing the effectiveness of the proposed approach and allowing optimization of the handover strategy in satellite networks that allow user-centric handover executions. [ABSTRACT FROM AUTHOR]

In order to achieve impact load localization of complex structures such as ships, this paper proposes a multi-scale feature fusion convolutional neural network (MSFF-CNN) method for impact load localization. An end-to-end machine learning model is used, where the raw vibration signals of impact loads are directly fed into the network model to avoid the process of feature extraction. Automatic feature learning and feature concatenation of the signal are achieved through four independent convolutional layers, each using a different size of convolutional kernel. Data normalization and L2 regularization techniques are introduced to enhance the data and prevent overfitting. Classification and localization of impact loads are accomplished using a softmax classification layer. Validation experiments are carried out using a ship's stern compartment model. Our results show that the classification and localization accuracy of the impact load sample group of MSFF-CNN reaches 94.29% compared with a traditional CNN. The method further improves the ability of the network to extract state features, takes local perception and global vision into account, effectively improves the classification ability of the model, and has good prospects for engineering applications. [ABSTRACT FROM AUTHOR]

Simple Summary: Through gesture recognition and detection of sika deer, farmers can observe the gestures of sika deer without physical contact, providing data and technical support for the intelligent and welfare-oriented breeding of sika deer. This study is based on the YOLOv8 network model. By optimizing the convolution module, incorporating the attention mechanism, and enhancing the detection head module, a new method for detecting sika deer poses was developed. The method was assessed using four behavioral datasets, which included standing, lying, eating, and attacking. The pose-recognition accuracy of sika deer significantly improved to an average of 91.6%, laying a foundation for the health assessment and information management of sika deer. As the sika deer breeding industry flourishes on a large scale, accurately assessing the health of these animals is of paramount importance. Implementing posture recognition through target detection serves as a vital method for monitoring the well-being of sika deer. This approach allows for a more nuanced understanding of their physical condition, ensuring the industry can maintain high standards of animal welfare and productivity. In order to achieve remote monitoring of sika deer without interfering with the natural behavior of the animals, and to enhance animal welfare, this paper proposes a sika deer individual posture recognition detection algorithm GFI-YOLOv8 based on YOLOv8. Firstly, this paper proposes to add the iAFF iterative attention feature fusion module to the C2f of the backbone network module, replace the original SPPF module with AIFI module, and use the attention mechanism to adjust the feature channel adaptively. This aims to enhance granularity, improve the model's recognition, and enhance understanding of sika deer behavior in complex scenes. Secondly, a novel convolutional neural network module is introduced to improve the efficiency and accuracy of feature extraction, while preserving the model's depth and diversity. In addition, a new attention mechanism module is proposed to expand the receptive field and simplify the model. Furthermore, a new pyramid network and an optimized detection head module are presented to improve the recognition and interpretation of sika deer postures in intricate environments. The experimental results demonstrate that the model achieves 91.6% accuracy in recognizing the posture of sika deer, with a 6% improvement in accuracy and a 4.6% increase in mAP50 compared to YOLOv8n. Compared to other models in the YOLO series, such as YOLOv5n, YOLOv7-tiny, YOLOv8n, YOLOv8s, YOLOv9, and YOLOv10, this model exhibits higher accuracy, and improved mAP50 and mAP50-95 values. The overall performance is commendable, meeting the requirements for accurate and rapid identification of the posture of sika deer. This model proves beneficial for the precise and real-time monitoring of sika deer posture in complex breeding environments and under all-weather conditions. [ABSTRACT FROM AUTHOR]

In orthopedics, bone drilling is a crucial part of a surgical method commonly carried out for internal fixation in bone fracture treatment. The primary purpose of bone drilling is the creation of holes for screw insertion to immobilize fractured parts. The bone drilling task depends on the orthopedist and surgeon's high level of skill and experience. This paper aimed to provide a summary of previously published review studies in the field of bone drilling. This review paper also presents a comprehensive review of the application of machine learning for bone drilling and as a future direction for automation systems. This review can also help medical surgeons and bone drillers understand the latest improvements through parameter selection and optimization strategies to reduce bone damage in bone drilling procedures. Apart from the review, bone drilling vibration data collected in a university laboratory experiment is also presented in this study. The vibration data consist of three different layers of femur cow bone, which are processed and classified using several deep learning (DL) methods such as long short-term memory (LSTM), convolutional neural network (CNN), and recurrent neural network (RNN). These DL methods are used in the bone drilling lab case study to prove that the layers of bone drilling are associated with the vibration signal and that they can be classified and predicted using DL methods. The result shows that LSTM is outperformed by CNN and RNN. [ABSTRACT FROM AUTHOR]

Personal credit assessment plays a crucial role in the financial system, which not only relates to the financial activities of individuals but also affects the overall credit system and economic health of society. However, the current problem of data imbalance affecting classification results in the field of personal credit assessment has not been fully solved. In order to solve this problem better, we propose a data-enhanced classification algorithm based on a Pixel Convolutional Neural Network (PixelCNN) and a Generative Adversarial Network (Wasserstein GAN, WGAN). Firstly, the historical data containing borrowers' borrowing information are transformed into grayscale maps; then, data enhancement of default images is performed using the improved PixelCNN-WGAN model; and finally, the expanded image dataset is inputted into the CNN, AlexNet, SqueezeNet, and MobileNetV2 for classification. The results on the real dataset LendingClub show that the data enhancement algorithm designed in this paper improves the accuracy of the four algorithms by 1.548–3.568% compared with the original dataset, which can effectively improve the classification effect of the credit data, and to a certain extent, it provides a new idea for the classification task in the field of personal credit assessment. [ABSTRACT FROM AUTHOR]

The accurate prediction of soil moisture content helps to evaluate the quality of farmland. Taking the black soil in the Nanguan District of Changchun City as the research object, this paper proposes a stacking ensemble learning model integrating hybrid neural networks to address the issue that it is difficult to improve the accuracy of inversion soil moisture content by a single model. First, raw hyperspectral data are processed by removing edge noise and standardization. Then, the gray wolf optimization (GWO) algorithm is adopted to optimize a convolutional neural network (CNN), and a gated recurrent unit (GRU) and an attention mechanism are added to construct a hybrid neural network model (GWO–CNN–GRU–Attention). To estimate soil water content, the hybrid neural network model is integrated into the stacking model along with Bagging and Boosting algorithms and the feedforward neural network. Experimental results demonstrate that the GWO–CNN–GRU–Attention model proposed in this paper can better predict soil water content; the stacking method of integrating hybrid neural networks overcomes the limitations of a single model's instability and inferior accuracy. The relative prediction deviation (RPD), root mean square error (RMSE), and coefficient of determination (R2) on the test set are 4.577, 0.227, and 0.952, respectively. The average R2 and RPD increased by 0.056 and 1.418 in comparison to the base learner algorithm. The study results lay a foundation for the fast detection of soil moisture content in black soil areas and provide a data source for intelligent irrigation in agriculture. [ABSTRACT FROM AUTHOR]

This paper presents a hybrid study of convolutional neural networks (CNNs), machine learning (ML), and transfer learning (TL) in the context of brain magnetic resonance imaging (MRI). The anatomy of the brain is very complex; inside the skull, a brain tumour can form in any part. With MRI technology, cross-sectional images are generated, and radiologists can detect the abnormalities. When the size of the tumour is very small, it is undetectable to the human visual system, necessitating alternative analysis using AI tools. As is widely known, CNNs explore the structure of an image and provide features on the SoftMax fully connected (SFC) layer, and the classification of the items that belong to the input classes is established. Two comparison studies for the classification of meningioma tumours and healthy brains are presented in this paper: (i) classifying MRI images using an original CNN and two pre-trained CNNs, DenseNet169 and EfficientNetV2B0; (ii) determining which CNN and ML combination yields the most accurate classification when SoftMax is replaced with three ML models; in this context, Random Forest (RF), K-Nearest Neighbors (KNN), and Support Vector Machine (SVM) were proposed. In a binary classification of tumours and healthy brains, the EfficientNetB0-SVM combination shows an accuracy of 99.5% on the test dataset. A generalisation of the results was performed, and overfitting was prevented by using the bagging ensemble method. [ABSTRACT FROM AUTHOR]

Emotion recognition commonly relies on single-modal recognition methods, such as voice and video signals, which demonstrate a good practicability and universality in some scenarios. Nevertheless, as emotion-recognition application scenarios continue to expand and the data volume surges, single-modal emotion recognition proves insufficient to meet people's needs for accuracy and comprehensiveness when the amount of data reaches a certain scale. Thus, this paper proposes the application of multimodal thought to enhance emotion-recognition accuracy and conducts corresponding data preprocessing on the selected dataset. Appropriate models are constructed for both audio and video modalities: for the audio-modality emotion-recognition task, this paper adopts the "time-distributed CNNs + LSTMs" model construction scheme; for the video-modality emotion-recognition task, the "DeepID V3 + Xception architecture" model construction scheme is selected. Furthermore, each model construction scheme undergoes experimental verification and comparison with existing emotion-recognition algorithms. Finally, this paper attempts late fusion and proposes and implements a late-fusion method based on the idea of weight adaptation. The experimental results demonstrate the superiority of the multimodal fusion algorithm proposed in this paper. When compared to the single-modal emotion-recognition algorithm, the accuracy of recognition is increased by almost 4%, reaching 84.33%. [ABSTRACT FROM AUTHOR]

The past few decades have witnessed remarkable progress in the application of artificial intelligence (AI) and machine learning (ML) in medicine, notably in medical imaging. The application of ML to dental and oral imaging has also been developed, powered by the availability of clinical dental images. The present work aims to investigate recent progress concerning the application of ML in the diagnosis of oral diseases using oral X-ray imaging, namely the quality and outcome of such methods. The specific research question was developed using the PICOT methodology. The review was conducted in the Web of Science, Science Direct, and IEEE Xplore databases, for articles reporting the use of ML and AI for diagnostic purposes in X-ray-based oral imaging. Imaging types included panoramic, periapical, bitewing X-ray images, and oral cone beam computed tomography (CBCT). The search was limited to papers published in the English language from 2018 to 2022. The initial search included 104 papers that were assessed for eligibility. Of these, 22 were included for a final appraisal. The full text of the articles was carefully analyzed and the relevant data such as the clinical application, the ML models, the metrics used to assess their performance, and the characteristics of the datasets, were registered for further analysis. The paper discusses the opportunities, challenges, and limitations found. [ABSTRACT FROM AUTHOR]

Intelligent image and optical information processing have paved the way for the recent epoch of new intelligence and information era. This Special Issue focuses on the intelligent processing of images and optical information acquired by various imaging methods. Optimization and Clustering The theoretical aspects of optimization and clustering are emphasized in the last two papers. On the paper entitled 'An Effective Optimization Method for Machine Learning Based on ADAM', Dokkyun Yi, Jaehyun Ahn, and Sangmin Ji [[20]] proposed a novel optimization method for non-convex cost functions to make machine learning more efficient. [Extracted from the article]

This document is a special issue of the journal Biomimetics, focusing on the design and control of bio-inspired robots. It explores various aspects of bionics in robotics, including robot design, perception, control, and decision-making, as well as incorporating neuroscience and brain science. The issue covers a wide range of topics, such as stiffness adjustment for continuum robots, biomimetic motor control, stroke rehabilitation, reinforcement learning for quadruped robots, improved spiking neural networks, energy-efficient image segmentation, kinematics analysis, synthetic nervous systems for robotic control, online running-gait generation, and bio-inspired perception and navigation for service robots. The document also discusses specific papers within the special issue that address challenges in robotic perception and navigation, legged robot control, and motion control of continuum robots and robotic arms. It concludes by announcing plans for a second special issue on related topics. [Extracted from the article]

In the dynamic visual cabinet, the occurrence of motion blur when consumers take out commodities will reduce the accuracy of commodity detection. Recently, although Transformer-based video deblurring networks have achieved results compared to Convolutional Neural Networks in some blurring scenarios, they are still challenging for the non-uniform blurring problem that occurs when consumers pick up the commodities, such as the problem of difficult alignment of blurred video frames of small commodities and the problem of underutilizing the effective information between the video frames of commodities. Therefore, an improved Transformer video deblurring network is proposed. Firstly, a multi-scale Transformer feature extraction method is utilized for non-uniform blurring. Secondly, for the problem of difficult alignment of small-item-blurred video frames, a temporal interactive attention mechanism is designed for video frame alignment. Finally, a feature recurrent fusion mechanism is introduced to supplement the effective information of commodity features. The experimental results show that the proposed method has practical significance in improving the accuracy of commodity detection. Moreover, compared with the recent Transformer deblurring algorithm Video Restoration Transformer, the Peak Signal-to-Noise Ratio of this paper's algorithm is higher than that of the Deep Video Deblurring dataset and the Fuzzy Commodity Dataset by 0.23 dB and 0.81 dB, respectively. [ABSTRACT FROM AUTHOR]

The rapid increase in the number of vehicles has led to increasing traffic congestion, traffic accidents, and motor vehicle crime rates. The management of various parking lots has also become increasingly challenging. Vehicle-type recognition technology can reduce the workload of humans in vehicle management operations. Therefore, the application of image technology for vehicle-type recognition is of great significance for integrated traffic management. In this paper, an improved faster region with convolutional neural network features (Faster R-CNN) model was proposed for vehicle-type recognition. Firstly, the output features of different convolution layers were combined to improve the recognition accuracy. Then, the average precision (AP) of the recognition model was improved through the contextual features of the original image and the object bounding box optimization strategy. Finally, the comparison experiment used the vehicle image dataset of three vehicle types, including cars, sports utility vehicles (SUVs), and vans. The experimental results show that the improved recognition model can effectively identify vehicle types in the images. The AP of the three vehicle types is 83.2%, 79.2%, and 78.4%, respectively, and the mean average precision (mAP) is 1.7% higher than that of the traditional Faster R-CNN model. [ABSTRACT FROM AUTHOR]

Since plant diseases occurring during the growth process are a significant factor leading to the decline in both yield and quality, the classification and detection of plant leaf diseases, followed by timely prevention and control measures, are crucial for safeguarding plant productivity and quality. As the traditional convolutional neural network structure cannot effectively recognize similar plant leaf diseases, in order to more accurately identify the diseases on plant leaves, this paper proposes an effective plant disease image recognition method aECA-ResNet34. This method is based on ResNet34, and in the first and the last layers of this network, respectively, we add this paper's improved aECAnet with the symmetric structure. aECA-ResNet34 is compared with different plant disease classification models on the peanut dataset constructed in this paper and the open-source PlantVillage dataset. The experimental results show that the aECA-ResNet34 model proposed in this paper has higher accuracy, better performance, and better robustness. The results show that the aECA-ResNet34 model proposed in this paper is able to recognize diseases of multiple plant leaves very accurately. [ABSTRACT FROM AUTHOR]

In this paper, we utilize a machine learning model (the convolutional neural network) to analyze aerial images of winter hard red wheat planted areas and cloud coverage over the planted areas as a proxy for future yield forecasts. We trained our model to forecast the futures price 20 days ahead and provide recommendations for either a long or short position on wheat futures. Our method shows that achieving positive alpha within a short time window is possible if the algorithm and data choice are unique. However, the model's performance can deteriorate quickly if the input data become more easily available and/or the trading strategy becomes crowded, as was the case with the aerial imagery we utilized in this paper. [ABSTRACT FROM AUTHOR]

This document is a special issue of the journal "Processes" focused on the application of power electronics technologies in power systems. It contains 15 articles divided into four sections: inverter, converter, control technique, and others. The articles cover topics such as optimal control of inverters, high-efficiency power converters, control methods for power electronics, and various applications of power electronics. The articles provide theoretical analysis, model derivation, actual measurement, and verification, making them valuable for research in this field. The authors express gratitude to all contributors and declare no conflicts of interest. [Extracted from the article]

Carbon fiber reinforced plastics inevitably develop defects such as delamination, inclusions, and impacts during manufacturing and usage, which can adversely affect their performance. Ultrasonic phased array inspection is the most effective method for conducting nondestructive testing to ensure their quality. However, the diversity of defects within carbon fiber reinforced plastics makes it challenging for the current ultrasonic phased array inspection techniques to accurately identify these defects. Therefore, this paper presents a method for the ultrasonic phased array nondestructive testing and classification of various internal defects in carbon fiber reinforced plastics based on convolutional neural networks. We prepared an ultrasonic C-scan dataset containing multiple types of internal defects, analyzed the defect features in the ultrasonic C-scan images, and established an autoencoded classifier network to recognize manufacturing defects and impact defects of varying sizes. The experiments showed that the proposed method demonstrates superior defect feature extraction capabilities and can more accurately identify both impact and manufacturing defects. [ABSTRACT FROM AUTHOR]

Predicting the Remaining Useful Life (RUL) is vital for ensuring the reliability and safety of equipment and components. This study introduces a novel method for predicting RUL that utilizes the Convolutional Block Attention Module (CBAM) to address the problem that Convolutional Neural Networks (CNNs) do not effectively leverage data channel features and spatial features in residual life prediction. Firstly, Fast Fourier Transform (FFT) is applied to convert the data into the frequency domain. The resulting frequency domain data is then used as input to the convolutional neural network for feature extraction; Then, the weights of channel features and spatial features are assigned to the extracted features by CBAM, and the weighted features are then input into the Long Short-Term Memory (LSTM) network to learn temporal features. Finally, the effectiveness of the proposed model is verified using the PHM2012 bearing dataset. Compared to several existing RUL prediction methods, the mean squared error, mean absolute error, and root mean squared error of the proposed method in this paper are reduced by 53%, 16.87%, and 31.68%, respectively, which verifies the superiority of the method. Meanwhile, the experimental results demonstrate that the proposed method achieves good RUL prediction accuracy across various failure modes. [ABSTRACT FROM AUTHOR]

Analysis of the human gait represents a fundamental area of investigation within the broader domains of biomechanics, clinical research, and numerous other interdisciplinary fields. The progression of visual sensor technology and machine learning algorithms has enabled substantial developments in the creation of human gait analysis systems. This paper presents a comprehensive review of the advancements and recent findings in the field of vision-based human gait analysis systems over the past five years, with a special emphasis on the role of vision sensors, machine learning algorithms, and technological innovations. The relevant papers were subjected to analysis using the PRISMA method, and 72 articles that met the criteria for this research project were identified. A detailing of the most commonly used visual sensor systems, machine learning algorithms, human gait analysis parameters, optimal camera placement, and gait parameter extraction methods is presented in the analysis. The findings of this research indicate that non-invasive depth cameras are gaining increasing popularity within this field. Furthermore, depth learning algorithms, such as convolutional neural networks (CNNs) and long short-term memory (LSTM) networks, are being employed with increasing frequency. This review seeks to establish the foundations for future innovations that will facilitate the development of more effective, versatile, and user-friendly gait analysis tools, with the potential to significantly enhance human mobility, health, and overall quality of life. This work was supported by [GOBIERNO DE ESPANA/PID2023-150967OB-I00]. [ABSTRACT FROM AUTHOR]

In advanced driver-assistance systems (ADASs), the misalignment of the mounting angle of the automotive radar significantly affects the accuracy of object detection and tracking, impacting system safety and performance. This paper introduces the Automotive Radar Alignment Detection Network (AutoRAD-Net), a novel model that leverages complex-valued convolutional neural network (CV-CNN) to address azimuth misalignment challenges in automotive radars. By utilizing complex-valued inputs, AutoRAD-Net effectively learns the physical properties of the radar data, enabling precise azimuth alignment. The model was trained and validated using mounting angle offsets ranging from −3° to +3° and exhibited errors no greater than 0.15° across all tested offsets. Moreover, it demonstrated reliable predictions even for unseen offsets, such as −1.7°, showcasing its generalization capability. The predicted offsets can then be used for physical radar alignment or integrated into compensation algorithms to enhance data interpretation accuracy in ADAS applications. This paper presents AutoRAD-Net as a practical solution for azimuth alignment, advancing radar reliability and performance in autonomous driving systems. [ABSTRACT FROM AUTHOR]

The development of deep learning has led to the proposal of various models for human activity recognition (HAR). Convolutional neural networks (CNNs), initially proposed for computer vision tasks, are examples of models applied to sensor data. Recently, high-performing models based on Transformers and multi-layer perceptrons (MLPs) have also been proposed. When applying these methods to sensor data, we often initialize hyperparameters with values optimized for image processing tasks as a starting point. We suggest that comparable accuracy could be achieved with fewer parameters for sensor data, which typically have lower dimensionality than image data. Reducing the number of parameters would decrease memory requirements and computational complexity by reducing the model size. We evaluated the performance of two MLP-based models, MLP-Mixer and gMLP, by reducing the values of hyperparameters in their MLP layers from those proposed in the respective original papers. The results of this study suggest that the performance of MLP-based models is positively correlated with the number of parameters. Furthermore, these MLP-based models demonstrate improved computational efficiency for specific HAR tasks compared to representative CNNs. [ABSTRACT FROM AUTHOR]

This review explores the application of convolutional neural networks (CNNs) and recurrent neural networks (RNNs) in food safety detection and risk prediction. This paper highlights the advantages of CNNs in image processing and feature recognition, as well as the powerful capabilities of RNNs (especially their variant LSTM) in time series data modeling. This paper also makes a comparative analysis in many aspects: Firstly, the advantages and disadvantages of traditional food safety detection and risk prediction methods are compared with deep learning technologies such as CNNs and RNNs. Secondly, the similarities and differences between CNNs and fully connected neural networks in processing image data are analyzed. Furthermore, the advantages and disadvantages of RNNs and traditional statistical modeling methods in processing time series data are discussed. Finally, the application directions of CNNs in food safety detection and RNNs in food safety risk prediction are compared. This paper also discusses combining these deep learning models with technologies such as the Internet of Things (IoT), blockchain, and federated learning to improve the accuracy and efficiency of food safety detection and risk warning. Finally, this paper mentions the limitations of RNNs and CNNs in the field of food safety, as well as the challenges in the interpretability of the model, and suggests the use of interpretable artificial intelligence (XAI) technology to improve the transparency of the model. [ABSTRACT FROM AUTHOR]

Wind power prediction is essential for ensuring the stability and efficient operation of modern power systems, particularly as renewable energy integration continues to expand. This paper presents a comprehensive review of machine learning techniques applied to wind power prediction, emphasizing their advantages over traditional physical and statistical models. Machine learning methods, especially deep learning approaches such as Convolutional Neural Networks (CNNs), Long Short-Term Memory Networks (LSTMs), and ensemble learning techniques like XGBoost, excel in addressing the nonlinearity and complexity of wind power data. The review also explores critical aspects such as data preprocessing, feature selection strategies, and model optimization techniques, which significantly enhance prediction accuracy and robustness. Challenges such as data acquisition difficulties, complex terrain influences, and sensor quality issues are examined in depth, with proposed solutions discussed. Additionally, the paper highlights future research directions, including the potential of multi-model fusion, emerging deep learning technologies like Transformers, and the integration of smart sensors and IoT technologies to develop intelligent, automated, and reliable prediction systems. By addressing existing challenges and leveraging advanced machine learning techniques, this work provides valuable insights into the current state of wind power prediction research and offers strategic guidance for enhancing the applicability and reliability of prediction models in practical scenarios. [ABSTRACT FROM AUTHOR]

The issue of power quality disturbances in modern power systems has become increasingly complex and severe, with multiple disturbances occurring simultaneously, leading to a decrease in the recognition accuracy of traditional algorithms. This paper proposes a composite power quality disturbance identification method based on the integration of improved Complementary Ensemble Empirical Mode Decomposition (CEEMDAN), Hilbert Transform (HT), and Extreme Learning Machine (ELM). Addressing the limitations of traditional signal processing techniques in handling nonlinear and non-stationary signals, this study first preprocesses the collected initial power quality signals using the improved CEEMDAN method to reduce modal aliasing and spurious components, thereby enabling a more precise decomposition of noisy signals into multiple Intrinsic Mode Functions (IMFs). Subsequently, the HT is utilized to conduct a thorough analysis of the reconstructed signals, extracting their time-amplitude information and instantaneous frequency characteristics. This feature information provides a rich data foundation for subsequent classification and identification. On this basis, an improved ELM is introduced as the classifier, leveraging its powerful nonlinear mapping capabilities and fast learning speed to perform pattern recognition on the extracted features, achieving accurate identification of composite power quality disturbances. To validate the effectiveness and practicality of the proposed method, a simulation experiment is designed. Upon examination, the approach introduced in this study retains a fault diagnosis accuracy exceeding 95%, even amidst significant noise disturbances. In contrast to conventional techniques, such as Convolutional Neural Network (CNN) and Support Vector Machine (SVM), this method achieves an accuracy enhancement of up to 5%. Following optimization via the Particle Swarm Optimization (PSO) algorithm, the model's accuracy is boosted by 3.6%, showcasing its favorable adaptability. [ABSTRACT FROM AUTHOR]

During extreme space weather events, transient geomagnetic disturbances initiated by solar eruptive activities can induce geomagnetically induced currents (GICs), which have severe impacts on power grid systems and oil/gas pipelines. Observations indicate that GICs in power grids are characterized by large fluctuation amplitudes, broad frequency ranges, and significant randomness. Their behavior is influenced by several factors, including the sources of space weather disturbance, Earth's electrical conductivity distribution, the structural integrity and performance of power grid equipment, and so on. This paper presents a hybrid prediction using actual GIC data from power grids and deep learning techniques. We employ various technical methods, including complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), convolutional neural networks (CNNs), long short-term memory (LSTM) networks, and attention mechanisms, to investigate short-term prediction methods for local grid GICs. The study uses GIC monitoring samples from 8 November 2004 for model training and testing. The results are evaluated using the coefficient of determination R 2 , root mean square error (RMSE), and mean absolute error (MAE). Preliminary research suggests that the combined CEEMDAN–CNN–LSTM–attention model significantly improves prediction accuracy and reduces the time delay in GIC prediction during geomagnetic storms compared to using LSTM neural networks alone. [ABSTRACT FROM AUTHOR]

Reconfigurable processor-based acceleration of deep convolutional neural network (DCNN) algorithms has emerged as a widely adopted technique, with particular attention on sparse neural network acceleration as an active research area. However, many computing devices that claim high computational power still struggle to execute neural network algorithms with optimal efficiency, low latency, and minimal power consumption. Consequently, there remains significant potential for further exploration into improving the efficiency, latency, and power consumption of neural network accelerators across diverse computational scenarios. This paper investigates three key techniques for hardware acceleration of sparse neural networks. The main contributions are as follows: (1) Most neural network inference tasks are typically executed on general-purpose computing devices, which often fail to deliver high energy efficiency and are not well-suited for accelerating sparse convolutional models. In this work, we propose a specialized computational circuit for the convolutional operations of sparse neural networks. This circuit is designed to detect and eliminate the computational effort associated with zero values in the sparse convolutional kernels, thereby enhancing energy efficiency. (2) The data access patterns in convolutional neural networks introduce significant pressure on the high-latency off-chip memory access process. Due to issues such as data discontinuity, the data reading unit often fails to fully exploit the available bandwidth during off-chip read and write operations. In this paper, we analyze bandwidth utilization in the context of convolutional accelerator data handling and propose a strategy to improve off-chip access efficiency. Specifically, we leverage a compiler optimization plugin developed for Vitis HLS, which automatically identifies and optimizes on-chip bandwidth utilization. (3) In coefficient-based accelerators, the synchronous operation of individual computational units can significantly hinder efficiency. Previous approaches have achieved asynchronous convolution by designing separate memory units for each computational unit; however, this method consumes a substantial amount of on-chip memory resources. To address this issue, we propose a shared feature map cache design for asynchronous convolution in the accelerators presented in this paper. This design resolves address access conflicts when multiple computational units concurrently access a set of caches by utilizing a hash-based address indexing algorithm. Moreover, the shared cache architecture reduces data redundancy and conserves on-chip resources. Using the optimized accelerator, we successfully executed ResNet50 inference on an Intel Arria 10 1150GX FPGA, achieving a throughput of 497 GOPS, or an equivalent computational power of 1579 GOPS, with a power consumption of only 22 watts. [ABSTRACT FROM AUTHOR]

To meet the high-reliability requirements of real-time on-orbit tasks, this paper proposes a fault-tolerant reinforcement design method for spaceborne intelligent processing algorithms based on convolutional neural networks (CNNs). This method is built on a CNN accelerator using Field-Programmable Gate Array (FPGA) technology, analyzing the impact of Single-Event Upsets (SEUs) on neural network computation. The accelerator design integrates data validation, Triple Modular Redundancy (TMR), and other techniques, optimizing a partial fault-tolerant architecture based on SEU sensitivity. This fault-tolerant architecture analyzes the hardware accelerator, parameter storage, and actual computation, employing data validation to reinforce model parameters and spatial and temporal TMR to reinforce accelerator computations. Using the ResNet18 model, fault tolerance performance tests were conducted by simulating SEUs. Compared to the prototype network, this fault-tolerant design method increases tolerance to SEU error accumulation by five times while increasing resource consumption by less than 15%, making it more suitable for spaceborne on-orbit applications than traditional fault-tolerant design approaches. [ABSTRACT FROM AUTHOR]

Obstructive sleep apnea (OSA) represents a significant health concern. While polysomnography (PSG) remains the gold standard, its resource-intensive nature has encouraged the exploration of further alternative approaches. Most of these were based on the heart rate variability (HRV) analysis, but only a few of them have presented a recurrence-based approach. The present paper addresses this gap by integrating convolutional neural networks (CNNs) with HRV recurrence analysis. Employing three different and publicly available databases from PhysioNet's official repository (Apnea-ECG, MIT-BIH, and UCD-DB), the presented method was able to expose concealed patterns within the distance matrix of HRV's phase space, which is discernible at an appropriate level of abstraction through CNNs. Under the challenging context of external validation (MIT-BIH and UCD for training, and Apnea-ECG for testing), the results obtained were comparable to those presented in the state of the art, achieving a peak accuracy of 75%, while maintaining balanced sensitivity and specificity at 74% and 75%, respectively. Moreover, these results obtained by the proposed CNN-based recurrence analysis of HRV also outperformed traditional time–frequency models, which have yielded values of accuracy lower than 65%. Hence, this paper highlights the importance of the proposed method in gaining new insights into OSA's HRV dynamics, offering a contribution that adds to the existing analytical approaches in the state of the art. [ABSTRACT FROM AUTHOR]

Super-resolution (SR) of remote sensing images is essential to compensate for missing information in the original high-resolution (HR) images. Single-image super-resolution (SISR) technique aims to recover high-resolution images from low-resolution (LR) images. However, traditional SISR methods often result in blurred and unclear images due to the loss of high-frequency details in LR images at high magnifications. In this paper, a super-segmental reconstruction model STGAN for remote sensing images is proposed, which fuses the Generative Adversarial Networks (GANs) and self-attention mechanism based on the Reference Super Resolution method (RefSR). The core module of the model consists of multiple CNN-Swin Transformer blocks (MCST), each of which consists of a CNN layer and a specific modified Swin Transformer, constituting the feature extraction channel. In image hypersegmentation reconstruction, the optimized and improved correlation attention block (RAM-V) uses feature maps and gradient maps to improve the robustness of the model under different scenarios (such as land cover change). The experimental results show that the STGAN model proposed in this paper exhibits the best image data perception quality results with the best performance of LPIPS and PI metrics in the test set under RRSSRD public datasets. In the experimental test set, the PSNR reaches 31.4151, the SSIM is 0.8408, and the performance on the RMSE and SAM metrics is excellent, which demonstrate the model's superior image reconstruction details in super-resolution reconstruction and highlighting the great potential of RefSR's application to the task of super-scalar processing of remotely sensed images. [ABSTRACT FROM AUTHOR]

While navigating at sea, ships are influenced by various factors, including wind, waves, and currents, which can result in heave motion that significantly impacts operations and potentially leads to accidents. Accurate forecasting of ship heaving is essential to guarantee the safety of maritime navigation. Consequently, this paper proposes a hybrid neural network method that combines Convolutional Neural Networks (CNNs), Bidirectional Long Short-Term Memory Networks (BiLSTMs), and an Attention Mechanism to predict the heaving motion of ships in moderate to complex sea conditions. The data feature extraction ability of CNNs, the temporal analysis capabilities of BiLSTMs, and the dynamic adjustment function of Attention on feature weights were comprehensively utilized to predict a ship's heave motion. Simulations of a standard container ship's motion time series under complex sea state conditions were carried out. The model training and validation results indicate that, under sea conditions 4, 5, and 6, the CNN-BiLSTM-Attention method demonstrated significant improvements in MAPE, APE, and RMSE when compared to the traditional LSTM, Attention, and LSTM-Attention methods. The CNN-BiLSTM-Attention method could enhance the accuracy of the prediction. Heave displacement, pitch displacement, pitch velocity, pitch acceleration, and incoming wave height were chosen as key input features. Sensitivity analysis was conducted to optimize the prediction performance of the CNN-BiLSTM-Attention hybrid neural network method, resulting in a significant improvement in MAPE and enhancing the accuracy of ship motion prediction. The research presented in this paper establishes a foundation for future studies on ship motion prediction. [ABSTRACT FROM AUTHOR]

Brain–computer interfaces (BCI) are an effective tool for recognizing motor imagery and have been widely applied in the motor control and assistive operation domains. However, traditional intention-recognition methods face several challenges, such as prolonged training times and limited cross-subject adaptability, which restrict their practical application. This paper proposes an innovative method that combines a lightweight convolutional neural network (CNN) with domain adaptation. A lightweight feature extraction module is designed to extract key features from both the source and target domains, effectively reducing the model's parameters and improving the real-time performance and computational efficiency. To address differences in sample distributions, a domain adaptation strategy is introduced to optimize the feature alignment. Furthermore, domain adversarial training is employed to promote the learning of domain-invariant features, significantly enhancing the model's cross-subject generalization ability. The proposed method was evaluated on an fNIRS motor imagery dataset, achieving an average accuracy of 87.76% in a three-class classification task. Additionally, lightweight experiments were conducted from two perspectives: model structure optimization and data feature selection. The results demonstrated the potential advantages of this method for practical applications in motor imagery recognition systems. [ABSTRACT FROM AUTHOR]

A false data injection attack (FDIA) is one of the major threats to power systems, and identifying false data is critical to the stable operation of power systems. However, false data that closely resemble normal data hinder the accuracy of existing detection methods, and their performance further declines when exposed to ambient noise. To address these challenges, this paper proposes an attentional convolutional neural network based on distinction enhancement and information fusion (DEIF-ACNN) for FDIA detection. Firstly, by minimizing the loss of reconstruction and discrimination, this paper designed an autoencoder with a discriminator for normal data (NAE), which had the characteristic of producing a small loss for normal data. Secondly, the trained NAE is utilized to compute the feature correlation matrix between the original and reconstructed data to enhance the distinction between normal and false data. Finally, to enhance feature extraction and suppress ambient noise interference in detection, DEIF-ACNN incorporates a convolutional block attention module (CBAM) to emphasize key feature channels and highlight crucial regions in the feature matrix. Experimental results show that DEIF-ACNN outperforms other FDIA detection methods on IEEE-9, IEEE-14, and IEEE-118 bus power systems, achieving an accuracy of 99.22%, 99.83%, and 100.00%, respectively. In addition, the method exhibits the best robustness under different noise environments, and its accuracy is maintained at about 80%. [ABSTRACT FROM AUTHOR]

Depth completion is widely employed in Simultaneous Localization and Mapping (SLAM) and Structure from Motion (SfM), which are of great significance to the development of autonomous driving. Recently, the methods based on the fusion of vision transformer (ViT) and convolution have brought the accuracy to a new level. However, there are still two shortcomings that need to be solved. On the one hand, for the poor performance of ViT in details, this paper proposes a semi-convolutional vision transformer to optimize local continuity and designs a geometric perception module to learn the positional correlation and geometric features of sparse points in three-dimensional space to perceive the geometric structures in depth maps for optimizing the recovery of edges and transparent areas. On the other hand, previous methods implement single-stage fusion to directly concatenate or add the outputs of ViT and convolution, resulting in incomplete fusion of the two, especially in complex outdoor scenes, which will generate lots of outliers and ripples. This paper proposes a novel double-stage fusion strategy, applying learnable confidence after self-attention to flexibly learn the weight of local features. Our network achieves state-of-the-art (SoTA) performance with the NYU-Depth-v2 Dataset and the KITTI Depth Completion Dataset. It is worth mentioning that the root mean square error (RMSE) of our model on the NYU-Depth-v2 Dataset is 87.9 mm, which is currently the best among all algorithms. At the end of the article, we also verified the generalization ability in real road scenes. [ABSTRACT FROM AUTHOR]

Data imbalances present a serious problem for intelligent fault diagnosis. They can lead to reduced diagnostic precision, which can jeopardize equipment reliability and safety. Based on that, this paper proposes a novel fault diagnosis method combining the denoising diffusion implicit model (DDIM) with a new convolutional neural network framework. First, the Gramian angular difference field (GADF) is used to generate 2D images, which are then augmented using DDIM. Next, by utilizing the weight-sharing properties of a convolutional neural network and the self-attention mechanism along with the global data processing capabilities of Transformers, a TransNet model is constructed. The augmented data are input into the model for training to establish a fault diagnosis framework. Finally, the method is validated and analyzed using the CWRU bearing dataset and the Nanchang Railway Bureau dataset. The results show that the proposed method achieves over 99% recognition accuracy on the two datasets. Meanwhile, the proposed model provides better generalization performance and recognition accuracy than existing fault diagnosis methods. [ABSTRACT FROM AUTHOR]

The Magnetic Barkhausen Noise (MBN) is a non-destructive testing method, which, due to its high sensitivity to changes in the microstructure of the material, is increasingly being applied with success as a tool for evaluation of magnetic material state and properties. However, it is no less difficult to analyze the measurement signals and their correct interpretation due to the complex, non-deterministic and stochastic nature of the Barkhausen phenomenon. Depending on the material to be examined, a signal with different characteristics can be observed. Frequently, a signal with multi-phase Barkhausen activity characteristics is obtained, like in the case of grain-oriented electrical steels. Due to the increased computational capabilities of computers, more and more advanced signal analysis methods are being used and artificial intelligence is being involved as well. Recently, the time–frequency (TF) approach for MBN signal analysis was introduced and discussed in several papers, where short-time Fourier Transform (STFT) found frequent application with promising results. Due to the automation of the search for diagnostic patterns, the stage of selecting transformation parameters becomes extremely important in the process of preparing training data for evaluation algorithms. This paper investigates the influence of the STFT computational window size on the material state evaluation results obtained using convolutional neural network (CNN). The studies were performed for MBN signals obtained from grain-oriented electrical steel with anisotropic properties. The carried out work made it possible to draw connections on the importance of the choice of the window during the implementation of CNN network training. [ABSTRACT FROM AUTHOR]

Due to the challenge that the behavior of traffic participants in the driving environment is highly stochastic and uncertain, it is difficult for self-driving vehicles to make accurate decisions based only on the current environmental state. In this paper, we propose a driving strategy learning method based on spatial-temporal feature prediction. Firstly, the spatial interaction between vehicles is implicitly modeled using a graph convolutional neural network and multi-head attention mechanism, and the gated loop unit is embedded to capture the sequential temporal relationship to establish a prediction model incorporating spatial-temporal features. Then, a reinforcement learning-based driving strategy method is constructed using some of the predictive features of the ego-vehicle and surrounding vehicles as predictive state inputs. Finally, based on the real dataset and CARLA simulation platform, the prediction ability of the prediction model and the effectiveness of the prediction-based decision-making model are verified. The simulation results prove that the prediction algorithm can achieve the minimum error compared with the baseline trajectory prediction algorithm, and effectively improves the accuracy and reliability of the autopilot decision-making in various dynamic scenarios. [ABSTRACT FROM AUTHOR]

In this paper, technical code analysis and recognition of the defect signal of the suppression rigging based on a convolutional neural network are carried out given the difficulty and low recognition rate of the defect detection and recognition of the suppression rigging. Firstly, the magnetic induction signal of the suppression rigging defects is collected using CM-801 (Anshan, China), Kalman filtering is used to screen and pre-process the collected data, and the noise reduction data are presented in the form of a cloud image. The pressed rigging defect data set is constructed, and the region of broken wire defect and stress in the image is calibrated. The single-stage object detection algorithm YOLOv5 (You Only Look Once) based on convolutional neural network model calculation is used, the scale detection layer and positioning loss function of the YOLOv5 algorithm are improved and optimized, and the improved YOLOv5 algorithm is used for experiments. The experimental results show that the detection accuracy of the convolution neural network model can reach 97.1%, which can effectively identify the defect signal of the suppressed rigging. [ABSTRACT FROM AUTHOR]

Speech emotion recognition (SER) is important in facilitating natural human–computer interactions. In speech sequence modeling, a vital challenge is to learn context-aware sentence expression and temporal dynamics of paralinguistic features to achieve unambiguous emotional semantic understanding. In previous studies, the SER method based on the single-scale cascade feature extraction module could not effectively preserve the temporal structure of speech signals in the deep layer, downgrading the sequence modeling performance. To address these challenges, this paper proposes a novel multi-scale feature pyramid network. The enhanced multi-scale convolutional neural networks (MSCNNs) significantly improve the ability to extract multi-granular emotional features. Experimental results on the IEMOCAP corpus demonstrate the effectiveness of the proposed approach, achieving a weighted accuracy (WA) of 71.79% and an unweighted accuracy (UA) of 73.39%. Furthermore, on the RAVDESS dataset, the model achieves an unweighted accuracy (UA) of 86.5%. These results validate the system's performance and highlight its competitive advantage. [ABSTRACT FROM AUTHOR]

Electric shock protection is critical for ensuring power safety in low-voltage grids, and robust fault diagnosis methods provide an essential foundation for the accurate operation of such protection devices. However, current low-voltage electric shock protection devices often suffer from limitations in operational precision and in their ability to effectively recognize electric shock types. To address these challenges, this paper proposes a fault diagnosis method for low-voltage electric shocks based on an attention-enhanced parallel CNN-BiLSTM model. The method first utilizes CNN to extract local spatial features of the electric shock signal and BiLSTM to capture temporal features. An attention mechanism is then introduced to fuse the local spatial and temporal features with weighted emphasis. Finally, a fully connected layer maps the fused features to the output layer, generating diagnostic results. Visualization through T-SNE analysis validates the improvement in model performance due to the attention mechanism. Comparative experiments show that the proposed model outperforms single models and other combined models in terms of accuracy, precision, recall, F1 score, and convergence speed. The results demonstrate that the proposed model achieves a fault diagnosis accuracy of 99.55%. [ABSTRACT FROM AUTHOR]

The deep learning model has attracted widespread attention in the field of rolling bearing remaining useful life (RUL) prediction due to its advantages of less reliance on prior knowledge, high accuracy, and strong generalization. However, a large number of prediction models use very complicated artificial feature extraction and selection methods to build the original input features of the deep learning model and health indicator. These approaches do not fully exploit the capabilities of deep learning models as they continue to heavily rely on prior knowledge, The accuracy of their predictions largely hinges on the quality of the input features, and the generalization of manually crafted features remains uncertain. To address these challenges, in this paper, an end-to-end prediction model for the remaining useful life of rolling bearings is proposed, which is divided into three modules. First, a short-term Fourier transform module is incorporated into the model to automatically obtain the time–frequency information of the signal. Then, the convolutional next (ConvNext) module, which is a simple and efficient pure convolutional neural network, is utilized to extract features from the spectrogram. Finally, we capture the short-term dependence and long-term dependence by two parallel channels Transformer and self-attention convolutional long short-term memory (SA-ConvLSTM), and the self-attention mechanism is employed for the adaptive prediction of the bearing's remaining useful life. Through integration with artificial intelligence, this method proposes a high-performance solution for predicting the remaining useful life of bearings. It has minimal reliance on manual labor, stronger fitting capabilities, and can be widely used for predicting the remaining useful life of bearings. [ABSTRACT FROM AUTHOR]

With the wide deployment of edge devices, distributed network traffic data are rapidly increasing. Traditional detection methods for malicious traffic rely on centralized training, in which a single server is often used to aggregate private traffic data from edge devices, so as to extract and identify features. However, these methods face difficult data collection, heavy computational complexity, and high privacy risks. To address these issues, this paper proposes a federated learning-based distributed malicious traffic detection framework, FL-CNN-Traffic. In this framework, edge devices utilize a convolutional neural network (CNN) to process local detection, data collection, feature extraction, and training. A server aggregates model updates from edge devices using four federated learning algorithms (FedAvg, FedProx, Scaffold, and FedNova) to build a global model. This framework allows multiple devices to collaboratively train a model without sharing private traffic data, addressing the "Data Silo" problem while ensuring privacy. Evaluations on the USTC-TFC2016 dataset show that for independent and identically distributed (IID) data, this framework can reach or exceed the performance of centralized deep learning methods. For Non-IID data, this framework outperforms other neural networks based on federated learning, with accuracy improvements ranging from 2.59% to 4.73%. [ABSTRACT FROM AUTHOR]

Sugarcane is the primary crop in the global sugar industry, yet it remains highly susceptible to a wide range of diseases that significantly impact its yield and quality. An effective solution is required to address the issues caused by the manual identification of plant diseases, which is time-consuming and has low detection accuracy. This paper proposes the development of a robust Deep Ensemble Convolutional Neural Network (DECNN) model for the accurate detection of sugarcane leaf diseases. Initially, several transfer learning (TL) models, including EfficientNetB0, MobileNetV2, DenseNet121, NASNetMobile, and EfficientNetV2B0, were enhanced through the addition of specific layers. A comparative analysis was then conducted on the enlarged dataset of sugarcane leaf diseases, which was divided into six categories and 4800 images. The application of data augmentation, along with the addition of dense layers, batch normalization layers, and dropout layers, led to improved detection accuracy, precision, recall, and F1 scores for each model. Among the five enhanced transfer learning models, the modified EfficientNetB0 model demonstrated the highest detection accuracy, ranging from 97.08% to 98.54%. In conclusion, the DECNN model was developed by integrating the modified EfficientNetB0, MobileNetV2, and DenseNet121 models using a distinctive performance-based custom-weighted ensemble method, with weight optimization carried out using the Tree-structured Parzen Estimator (TPE) technique. This resulted in a model that achieved a detection accuracy of 99.17%, which outperformed the individual performance of the modified EfficientNetB0, MobileNetV2, and DenseNet121 models in detecting sugarcane leaf diseases. [ABSTRACT FROM AUTHOR]

To further enhance the recognition accuracy of automatic modulation recognition, improve communication efficiency, strengthen security, and optimize resource management, this paper designs a high-precision hybrid deep learning model featuring early-stage layer fusion. This model combines with Convolutional Neural Networks (CNN), Transformers, and Deep Neural Networks (DNN) to enhance the model's feature extraction capabilities, thereby improving modulation recognition accuracy. Experiments are performed on RadioML2016.10a and RadioML2018.01a, and the results show that this architecture can effectively combine the advantages of different types of models, making the overall performance more robust and suitable for complex automatic modulation recognition problems. [ABSTRACT FROM AUTHOR]

This paper presents a hardware implementation of a one-dimensional convolutional neural network using depthwise separable convolution (DSC) on the VC707 FPGA development board. The design processes the one-dimensional rolling bearing current signal dataset provided by Paderborn University (PU), employing minimal preprocessing to maximize the comprehensiveness of feature extraction. To address the high parameter demands commonly associated with convolutional neural networks (CNNs), the model incorporates DSC, significantly reducing computational complexity and parameter load. Additionally, the DoReFa-Net quantization method is applied to compress network parameters and activation function outputs, thereby minimizing memory usage. The quantized DSC model requires approximately 22 KB of storage and performs 1,203,128 floating-point operations in total. The implementation achieves a power consumption of 527 mW at a clock frequency of 50 MHz, while delivering a fault diagnosis accuracy of 96.12%. [ABSTRACT FROM AUTHOR]

The purpose of infrared and visible image fusion is to combine the advantages of both and generate a fused image that contains target information and has rich details and contrast. However, existing fusion algorithms often overlook the importance of incorporating both local and global feature extraction, leading to missing key information in the fused image. To address these challenges, this paper proposes a dual-branch fusion network combining convolutional neural network (CNN) and Transformer, which enhances the feature extraction capability and motivates the fused image to contain more information. Firstly, a local feature extraction module with CNN as the core is constructed. Specifically, the residual gradient module is used to enhance the ability of the network to extract texture information. Also, jump links and coordinate attention are used in order to relate shallow features to deeper ones. In addition, a global feature extraction module based on Transformer is constructed. Through the powerful ability of Transformer, the global context information of the image can be captured and the global features are fully extracted. The effectiveness of the proposed method in this paper is verified on different experimental datasets, and it is better than most of the current advanced fusion algorithms. [ABSTRACT FROM AUTHOR]