Search

With the development of the power system, power users begin to use their own power supply in order to improve the power economy, but this also leads to the occurrence of the risk of self-provided power supply. The actual distribution network has few samples of power supply risk and it is difficult to identify the power supply risk by using conventional deep learning methods. In order to achieve high accuracy of self-provided power supply risk identification with small samples, this paper proposes a combination of transfer learning, convolutional block attention module (CBAM), and convolutional neural network (CNN) to identify the risk of self-provided power supply in an active distribution network. Firstly, in order to be able to further identify whether or not a risk will be caused based on completing the identification of the faulty line, we propose that it is necessary to identify whether or not the captive power supply on the faulty line is in operation. Second, in order to achieve high-precision identification and high-efficiency feature extraction, we propose to embed the CBAM into a CNN to form a CBAM-CNN model, so as to achieve high-efficiency feature extraction and high-precision risk identification. Finally, the use of transfer learning is proposed to solve the problem of low risk identification accuracy due to the small number of actual fault samples. Simulation experiments show that compared with other methods, the proposed method has the highest recognition accuracy and the best effect, and the risk recognition accuracy of active distribution network backup power is high in the case of fewer samples. [ABSTRACT FROM AUTHOR]

Medical image classification, a pivotal task for diagnostic accuracy, poses unique challenges due to the intricate and variable nature of medical images compared to their natural counterparts. While Convolutional Neural Networks (CNNs) and Transformers are prevalent in this domain, each architecture has its drawbacks. CNNs, despite their strength in local feature extraction, fall short in capturing global context, whereas Transformers excel at global information but can overlook fine-grained details. The integration of CNNs and Transformers in a hybrid model aims to bridge this gap by enabling simultaneous local and global feature extraction. However, this approach remains constrained in its capacity to model long-range dependencies, thereby hindering the efficient extraction of distant features. To address these issues, we introduce the MambaConvT model, which employs a state-space approach. It begins by locally processing input features through multi-core convolution, enhancing the extraction of deep, discriminative local details. Next, depth-separable convolution with a 2D selective scanning module (SS2D) is employed to maintain a global receptive field and establish long-distance connections, capturing the fine-grained features. The model then combines hybrid features for comprehensive feature extraction, followed by global feature modeling to emphasize on global detail information and optimize feature representation. This paper conducts thorough performance experiments on different algorithms across four publicly available datasets and two private datasets. The results demonstrate that MambaConvT outperforms the latest classification algorithms in terms of accuracy, precision, recall, F1 score, and AUC value ratings, achieving superior performance in the precise classification of medical images. [ABSTRACT FROM AUTHOR]

The motor is the primary impetus source of most mechanical equipment, and its failure will cause substantial economic losses and safety problems. Therefore, it is necessary to study online fault diagnosis techniques for motors, given the problems caused by shallow learning models or single-sensor fault analysis in previous motor fault diagnosis techniques, such as blurred fault features, inaccurate identification, and time and manpower consumption. In this paper, we proposed a model for motor fault diagnosis based on deep learning and multi-sensor information fusion. Firstly, a correlation adaptive weighting method is proposed in this paper, and it is used to integrate the collected multi-source homogeneous sensor information into multi-source heterogeneous sensor information through the data layer fusion. Secondly, the 1D-CNN is used to carry out feature extraction, feature layer fusion, and fault classification of multi-source heterogeneous information of the motor. Finally, the data of seven states (one healthy and six faulty) of the motor are collected by the motor drive test bench to realize the model's training, testing, and verification. The experimental results show that the fault diagnosis accuracy of the model is 99.3%. Thus, this method has important practical implications for improving the accuracy of motor fault diagnosis further. [ABSTRACT FROM AUTHOR]

Research has shown that neural machine translation performs poorly on low-resource and specific domain parallel corpora. In this paper, we focus on the problem of neural machine translation in the field of electrical engineering. To address the mistranslation caused by the Transformer model's limited ability to extract feature information from certain sentences, we propose two new models that integrate a convolutional neural network as a feature extraction layer into the Transformer model. The feature information extracted by the CNN is fused separately in the source-side and target-side models, which enhances the Transformer model's ability to extract feature information, optimizes model performance, and improves translation quality. On the dataset of the field of electrical engineering, the proposed source-side and target-side models improved BLEU scores by 1.63 and 1.12 percentage points, respectively, compared to the baseline model. In addition, the two models proposed in this paper can learn rich semantic knowledge without relying on auxiliary knowledge such as part-of-speech tagging and named entity recognition, which saves a certain amount of human resources and time costs. [ABSTRACT FROM AUTHOR]

Recent technological developments have enabled computers to identify and categorize facial expressions to determine a person's emotional state in an image or a video. This process, called "Facial Expression Recognition (FER)", has become one of the most popular research areas in computer vision. In recent times, deep FER systems have primarily concentrated on addressing two significant challenges: the problem of overfitting due to limited training data availability, and the presence of expression-unrelated variations, including illumination, head pose, image resolution, and identity bias. In this paper, a comprehensive survey is provided on deep FER, encompassing algorithms and datasets that offer insights into these intrinsic problems. Initially, this paper presents a detailed timeline showcasing the evolution of methods and datasets in deep facial expression recognition (FER). This timeline illustrates the progression and development of the techniques and data resources used in FER. Then, a comprehensive review of FER methods is introduced, including the basic principles of FER (components such as preprocessing, feature extraction and classification, and methods, etc.) from the pro-deep learning era (traditional methods using handcrafted features, i.e., SVM and HOG, etc.) to the deep learning era. Moreover, a brief introduction is provided related to the benchmark datasets (there are two categories: controlled environments (lab) and uncontrolled environments (in the wild)) used to evaluate different FER methods and a comparison of different FER models. Existing deep neural networks and related training strategies designed for FER, based on static images and dynamic image sequences, are discussed. The remaining challenges and corresponding opportunities in FER and the future directions for designing robust deep FER systems are also pinpointed. [ABSTRACT FROM AUTHOR]

Hyperspectral unmixing (HU) aims to decompose mixed pixels into a set of endmembers and corresponding abundances. Deep learning-based HU methods are currently a hot research topic, but most existing unmixing methods still rely on per-pixel training or employ convolutional neural networks (CNNs), which overlook the non-local correlations of materials and spectral characteristics. Furthermore, current research mainly focuses on linear mixing models, which limits the feature extraction capability of deep encoders and further improvement in unmixing accuracy. In this paper, we propose a nonlinear unmixing network capable of extracting global spatial-spectral features. The network is designed based on an autoencoder architecture, where a dual-stream CNNs is employed in the encoder to separately extract spectral and local spatial information. The extracted features are then fused together to form a more complete representation of the input data. Subsequently, a linear projection-based multi-head self-attention mechanism is applied to capture global contextual information, allowing for comprehensive spatial information extraction while maintaining lightweight computation. To achieve better reconstruction performance, a model-free nonlinear mixing approach is adopted to enhance the model's universality, with the mixing model learned entirely from the data. Additionally, an initialization method based on endmember bundles is utilized to reduce interference from outliers and noise. Comparative results on real datasets against several state-of-the-art unmixing methods demonstrate the superior of the proposed approach. [ABSTRACT FROM AUTHOR]

Convolutional neural networks (CNNs) and graph convolutional networks (GCNs) have made considerable advances in hyperspectral image (HSI) classification. However, most CNN-based methods learn features at a single-scale in HSI data, which may be insufficient for multi-scale feature extraction in complex data scenes. To learn the relations among samples in non-grid data, GCNs are employed and combined with CNNs to process HSIs. Nevertheless, most methods based on CNN-GCN may overlook the integration of pixel-wise spectral signatures. In this paper, we propose a pyramid cascaded convolutional neural network with graph convolution (PCCGC) for hyperspectral image classification. It mainly comprises CNN-based and GCN-based subnetworks. Specifically, in the CNN-based subnetwork, a pyramid residual cascaded module and a pyramid convolution cascaded module are employed to extract multiscale spectral and spatial features separately, which can enhance the robustness of the proposed model. Furthermore, an adaptive feature-weighted fusion strategy is utilized to adaptively fuse multiscale spectral and spatial features. In the GCN-based subnetwork, a band selection network (BSNet) is used to learn the spectral signatures in the HSI using nonlinear inter-band dependencies. Then, the spectral-enhanced GCN module is utilized to extract and enhance the important features in the spectral matrix. Subsequently, a mutual-cooperative attention mechanism is constructed to align the spectral signatures between BSNet-based matrix with the spectral-enhanced GCN-based matrix for spectral signature integration. Abundant experiments performed on four widely used real HSI datasets show that our model achieves higher classification accuracy than the fourteen other comparative methods, which shows the superior classification performance of PCCGC over the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

The vision transformer (ViT) has demonstrated performance comparable to that of convolutional neural networks (CNN) in the hyperspectral image classification domain. This is achieved by transforming images into sequence data and mining global spectral-spatial information to establish remote dependencies. Nevertheless, both the ViT and CNNs have their own limitations. For instance, a CNN is constrained by the extent of its receptive field, which prevents it from fully exploiting global spatial-spectral features. Conversely, the ViT is prone to excessive distraction during the feature extraction process. To be able to overcome the problem of insufficient feature information extraction caused using by a single paradigm, this paper proposes an MLP-mixer and a graph convolutional enhanced transformer (MGCET), whose network consists of a spatial-spectral extraction block (SSEB), an MLP-mixer, and a graph convolutional enhanced transformer (GCET). First, spatial-spectral features are extracted using SSEB, and then local spatial-spectral features are fused with global spatial-spectral features by the MLP-mixer. Finally, graph convolution is embedded in multi-head self-attention (MHSA) to mine spatial relationships and similarity between pixels, which further improves the modeling capability of the model. Correlation experiments were conducted on four different HSI datasets. The MGEET algorithm achieved overall accuracies (OAs) of 95.45%, 97.57%, 98.05%, and 98.52% on these datasets. [ABSTRACT FROM AUTHOR]

Rotated object detection is a crucial task in aerial image analysis. To address challenges such as multi-directional object rotation, complex backgrounds with occlusions, and the trade-off between speed and accuracy in remote sensing images, this paper introduces a lightweight progressive fusion calibration network for rotated object detection (LPFC-RDet). The network comprises three main modules: the Retentive Meet Transformers (RMT) feature extraction block, the Progressive Fusion Calibration module (PFC), and the Shared Group Convolution Lightweight detection head (SGCL). The RMT feature extraction block integrates a retentive mechanism with global context modeling to learn rotation-insensitive features. The PFC module employs pixel-level, local-level, and global-level weights to calibrate features, enhancing feature extraction from occluded objects while suppressing background interference. The SGCL detection head uses decoupled detection tasks and shared group convolution layers to achieve parameter sharing and feature interaction, improving accuracy while maintaining a lightweight structure. Experimental results demonstrate that our method surpasses state-of-the-art detectors on three widely used remote sensing object datasets: HRSC2016, UCAS_AOD, and DOTA. [ABSTRACT FROM AUTHOR]

Traditional image classification usually relies on manual feature extraction; however, with the rapid development of artificial intelligence and intelligent vision technology, deep learning models such as CNNs can automatically extract key features from input images to achieve efficient classification. This study focuses on the application of lightweight separable convolutional neural networks in domain-specific image classification tasks. In this paper, we discuss how to use the SSDLite object detection algorithm combined with the MobileNetV2 lightweight convolutional architecture for puppet dynasty recognition from images—a novel and challenging task. By constructing a system that combines object detection and image classification, we aimed to solve the problem of automatic puppet dynasty recognition to reduce manual intervention and improve recognition efficiency and accuracy. We hope that this will have significant implications in the fields of cultural protection and art history research. [ABSTRACT FROM AUTHOR]

Face swapping or face replacement is a challenging task that involves transferring a source face to a target face while maintaining the target's facial motion and expression. Although many studies have made a lot of encouraging progress, we have noticed that most of the current solutions have the problem of blurred images, abnormal features, and unnatural pictures after face swapping. To solve these problems, in this paper, we proposed a composite face-swapping generation network, which includes a face extraction module and a feature fusion generation module. This model retains the original facial expression features, as well as the background and lighting of the image while performing face swapping, making the image more realistic and natural. Compared with other excellent models, our model is more robust in terms of face identity, posture verification, and image quality. [ABSTRACT FROM AUTHOR]

Simple Summary: The use of computer vision technology has improved the effectiveness of individual sheep identification, but existing methods face challenges such as large parameter sizes, slow recognition speeds, and difficult deployment. To address this issue, we have made improvements and optimizations based on the Retinaface face recognition model to create a balanced speed-accuracy sheep face recognition model. The optimized model has fewer parameters, simpler computations, faster inference speeds, and higher recognition accuracy, making it well-suited for deployment on resource-constrained edge devices. This research is expected to promote the application of deep learning-based sheep face recognition methods in production. The recognition of sheep faces based on computer vision has improved the efficiency and effectiveness of individual sheep identification, providing technical support for the development of smart farming. However, current recognition models have problems such as large parameter sizes, slow recognition speed, and difficult deployment. Therefore, this paper proposes an efficient and fast basic module called Eblock and uses it to build a lightweight sheep face recognition model called SheepFaceNet, which achieves the best balance between speed and accuracy. SheepFaceNet includes two modules: SheepFaceNetDet for detection and SheepFaceNetRec for recognition. SheepFaceNetDet uses Eblock to construct the backbone network to enhance feature extraction capability and efficiency, designs a bidirectional FPN layer (BiFPN) to enhance geometric location ability, and optimizes the network structure, which affects inference speed, to achieve fast and accurate sheep face detection. SheepFaceNetRec uses Eblock to construct the feature extraction network, uses ECA channel attention to improve the effectiveness of feature extraction, and uses multi-scale feature fusion to achieve fast and accurate sheep face recognition. On our self-built sheep face dataset, SheepFaceNet recognized 387 sheep face images per second with an accuracy rate of 97.75%, achieving an advanced balance between speed and accuracy. This research is expected to further promote the application of deep-learning-based sheep face recognition methods in production. [ABSTRACT FROM AUTHOR]

With the advancement of neural networks, more and more neural networks are being applied to structural health monitoring systems (SHMSs). When an SHMS requires the integration of numerous neural networks, high-performance and low-latency networks are favored. This paper focuses on damage detection based on vibration signals. In contrast to traditional neural network approaches, this study utilizes a stochastic configuration network (SCN). An SCN is an incrementally learning network that randomly configures appropriate neurons based on data and errors. It is an emerging neural network that does not require predefined network structures and is not based on gradient descent. While SCNs dynamically define the network structure, they essentially function as fully connected neural networks that fail to capture the temporal properties of monitoring data effectively. Moreover, they suffer from inference time and computational cost issues. To enable faster and more accurate operation within the monitoring system, this paper introduces a stochastic convolutional feature extraction approach that does not rely on backpropagation. Additionally, a random node deletion algorithm is proposed to automatically prune redundant neurons in SCNs, addressing the issue of network node redundancy. Experimental results demonstrate that the feature extraction method improves accuracy by 30% compared to the original SCN, and the random node deletion algorithm removes approximately 10% of neurons. [ABSTRACT FROM AUTHOR]

The method of acoustic radiation signal detection not only enables contactless measurement but also provides comprehensive state information during equipment operation. This paper proposes an enhanced feature extraction network (EFEN) for fault diagnosis of rolling bearings based on acoustic signal feature learning. The EFEN network comprises four main components: the data preprocessing module, the information feature selection module (IFSM), the channel attention mechanism module (CAMM), and the convolutional neural network module (CNNM). Firstly, the one-dimensional acoustic signal is transformed into a two-dimensional grayscale image. Then, IFSM utilizes three different-sized convolution filters to process input image data and fuse and assign weights to feature information that can attenuate noise while highlighting effective fault information. Next, a channel attention mechanism module is introduced to assign weights to each channel. Finally, the convolutional neural network (CNN) fault diagnosis module is employed for accurate classification of rolling bearing faults. Experimental results demonstrate that the EFEN network achieves high accuracy in fault diagnosis and effectively detects rolling bearing faults based on acoustic signals. The proposed method achieves an accuracy of 98.52%, surpassing other methods in terms of performance. In comparative analysis of antinoise experiments, the average accuracy remains remarkably high at 96.62%, accompanied by a significantly reduced average iteration time of only 0.25 s. Furthermore, comparative analysis confirms that the proposed algorithm exhibits excellent accuracy and resistance against noise. [ABSTRACT FROM AUTHOR]

The application of edge computing combined with the Internet of Things (edge-IoT) has been rapidly developed. It is of great significance to develop a lightweight network for gearbox compound fault diagnosis in the edge-IoT context. The goal of this paper is to devise a novel and high-accuracy lightweight neural network based on Legendre multiwavelet transform and multi-channel convolutional neural network (LMWT-MCNN) to fast recognize various compound fault categories of gearbox. The contributions of this paper mainly lie in three aspects: The feature images are designed based on the LMWT frequency domain and they are easily implemented in the MCNN model to effectively avoid noise interference. The proposed lightweight model only consists of three convolutional layers and three pooling layers to further extract the most valuable fault features without any artificial feature extraction. In a fully connected layer, the specific fault type of rotating machinery is identified by the multi-label method. This paper provides a promising technique for rotating machinery fault diagnosis in real applications based on edge-IoT, which can largely reduce labor costs. Finally, the PHM 2009 gearbox and Paderborn University bearing compound fault datasets are used to verify the effectiveness and robustness of the proposed method. The experimental results demonstrate that the proposed lightweight network is able to reliably identify the compound fault categories with the highest accuracy under the strong noise environment compared with the existing methods. [ABSTRACT FROM AUTHOR]

Over the last 20 years, lithium-ion batteries have become widely used in many fields due to their advantages such as ease of use and low cost. However, there are concerns about the lifetime and reliability of these batteries. These concerns can be addressed by obtaining accurate capacity and health information. This paper proposes a method to predict the capacity of lithium-ion batteries with high accuracy. Four key features were extracted from current and voltage data obtained during charge and discharge cycles. To enhance prediction accuracy, the Pearson correlation coefficient between these features and battery capacities was analyzed and eliminations were made for some batteries. Using a genetic algorithm (GA), the parameter optimization of Convolutional Neural Network (CNN), Backpropagation (BP), and Recurrent Neural Network (RNN) algorithms was performed. The parameters that provide the best performance were determined in a shorter time using GA, which includes natural selection and genetic processes instead of a trial-and-error method. The study employed five metrics—Mean Square Error (MSE), Root Mean Square Error (RMSE), Normalized Root Mean Square Error (NRMSE), Mean Absolute Error (MAE), and Squared Correlation (R2)—to evaluate prediction accuracy. Predictions based on NASA experimental data were compared with the existing literature, demonstrating superior accuracy. Using 100 training data, 68 data predictions were made with a Root Mean Square Error (RMSE) of 0.1176%. This error rate represents an accuracy level 2.5 times higher than similarly accurate studies in the literature. [ABSTRACT FROM AUTHOR]

Aiming to address the issues of missing detailed information, the blurring of significant target information, and poor visual effects in current image fusion algorithms, this paper proposes an infrared and visible-light image fusion algorithm based on discrete wavelet transform and convolutional neural networks. Our backbone network is an autoencoder. A DWT layer is embedded in the encoder to optimize frequency-domain feature extraction and prevent information loss, and a bottleneck residual block and a coordinate attention mechanism are introduced to enhance the ability to capture and characterize the low- and high-frequency feature information; an IDWT layer is embedded in the decoder to achieve the feature reconstruction of the fused frequencies; the fusion strategy adopts the l 1 − n o r m fusion strategy to integrate the encoder's output frequency mapping features; a weighted loss containing pixel loss, gradient loss, and structural loss is constructed for optimizing network training. DWT decomposes the image into sub-bands at different scales, including low-frequency sub-bands and high-frequency sub-bands. The low-frequency sub-bands contain the structural information of the image, which corresponds to the important target information, while the high-frequency sub-bands contain the detail information, such as edge and texture information. Through IDWT, the low-frequency sub-bands that contain important target information are synthesized with the high-frequency sub-bands that enhance the details, ensuring that the important target information and texture details are clearly visible in the reconstructed image. The whole process is able to reconstruct the information of different frequency sub-bands back into the image non-destructively, so that the fused image appears natural and harmonious visually. Experimental results on public datasets show that the fusion algorithm performs well according to both subjective and objective evaluation criteria and that the fused image is clearer and contains more scene information, which verifies the effectiveness of the algorithm, and the results of the generalization experiments also show that our network has good generalization ability. [ABSTRACT FROM AUTHOR]

In system processing, video inevitably suffers from distortion, which leads to quality degradation and affects the user experience. Therefore, it is of great importance to design an accurate and effective objective video quality assessment (VQA) method. In this paper, by considering the multi-dimensional characteristics for video and visual perceptual mechanism, a two-stream convolutional network for VQA is proposed based on spatial–temporal analysis, named TSCNN-VQA. Specifically, for feature extraction, TSCNN-VQA first extracts spatial and temporal features by two different convolutional neural network branches, respectively. After that, the spatial–temporal joint feature fusion is constructed to obtain the joint spatial–temporal features. Meanwhile, the TSCNN-VQA also integrates an attention module to guarantee that the process conforms to the mechanism that the visual system perceives video information. Finally, the overall quality is obtained by non-linear regression. The experimental results in both the LIVE and CSIQ VQA datasets show that the performance indicators obtained by TSCNN-VQA are higher than those of existing VQA methods, which demonstrates that TSCNN-VQA can accurately evaluate video quality and has better consistency with the human visual system. [ABSTRACT FROM AUTHOR]

This paper delves into the realm of human activity recognition (HAR) by leveraging the capabilities of Siamese neural networks (SNNs), focusing on the comparative effectiveness of contrastive and triplet learning approaches. Against the backdrop of HAR's growing importance in healthcare, sports, and smart environments, the need for advanced models capable of accurately recognizing and classifying complex human activities has become paramount. Addressing this, we have introduced a Siamese network architecture integrated with convolutional neural networks (CNNs) for spatial feature extraction, bidirectional LSTM (Bi-LSTM) for temporal dependency capture, and attention mechanisms to prioritize salient features. Employing both contrastive and triplet loss functions, we meticulously analyze the impact of these learning approaches on the network's ability to generate discriminative embeddings for HAR tasks. Through extensive experimentation, the study reveals that Siamese networks, particularly those utilizing triplet loss functions, demonstrate superior performance in activity recognition accuracy and F1 scores compared with baseline deep learning models. The inclusion of a stacking meta-classifier further amplifies classification efficacy, showcasing the robustness and adaptability of our proposed model. Conclusively, our findings underscore the potential of Siamese networks with advanced learning paradigms in enhancing HAR systems, paving the way for future research in model optimization and application expansion. [ABSTRACT FROM AUTHOR]

Surface defect inspection is vital for the quality control of products and the fault diagnosis of equipment. Defect inspection remains challenging due to the low level of automation in some manufacturing plants and the difficulty in identifying defects. To improve the automation and intelligence levels of defect inspection, a CNN model is proposed for the high-precision defect inspection of USB components in the actual demands of factories. First, the defect inspection system was built, and a dataset named USB-SG, which contained five types of defects—dents, scratches, spots, stains, and normal—was established. The pixel-level defect ground-truth annotations were manually marked. This paper puts forward a CNN model for solving the problem of defect inspection tasks, and three strategies are proposed to improve the model's performance. The proposed model is built based on the lightweight SqueezeNet network, and a rich feature extraction block is designed to capture semantic and detailed information. Residual-based progressive feature integration is proposed to fuse the extracted features, which can reduce the difficulty of model fine-tuning and improve the generalization ability. Finally, a multi-step deep supervision scheme is proposed to supervise the feature integration process. The experiments on the USB-SG dataset prove that the model proposed in this paper has better performance than that of other methods, and the running speed can meet the real-time demand, which has broad application prospects in the industrial inspection scene. [ABSTRACT FROM AUTHOR]

In order to deal with the target recognition in the complex underwater environment, we carried out experimental research. This includes filtering noise in the feature extraction stage of underwater images rich in noise, or with complex backgrounds, and improving the accuracy of target classification in the recognition process. This paper discusses our contribution to improving the accuracy of underwater target classification. This paper proposes an underwater target classification algorithm based on the improved flow direction algorithm (FDA) and search agent strategy, which can simultaneously optimize the weight parameters, bias parameters, and super parameters of the extreme learning machine (ELM). As a new underwater target classifier, it replaces the full connection layer in the traditional classification network to build a classification network. In the first stage of the network, the DenseNet201 network pre-trained by ImageNet is used to extract features and reduce dimensions of underwater images. In the second stage, the optimized ELM classifier is trained and predicted. In order to weaken the uncertainty caused by the random input weight and offset of the introduced ELM, the fuzzy logic, chaos initialization, and multi population strategy-based flow direction algorithm (FCMFDA) is used to adjust the input weight and offset of the ELM and optimize the super parameters with the search agent strategy at the same time. We tested and verified the FCMFDA-ELM classifier on Fish4Knowledge and underwater robot professional competition 2018 (URPC 2018) datasets, and achieved 99.4% and 97.5% accuracy, respectively. The experimental analysis shows that the FCMFDA-ELM underwater image classifier proposed in this paper has a greater improvement in classification accuracy, stronger stability, and faster convergence. Finally, it can be embedded in the recognition process of underwater targets to improve the recognition performance and efficiency. [ABSTRACT FROM AUTHOR]

To address the challenges of complex backgrounds, small defect sizes, and diverse defect types in defect detection of wire bonding X-ray images, this paper proposes a convolutional-neural-network-based defect detection method called YOLO-CSS. This method designs a novel feature extraction network that effectively captures semantic features from different gradient information. It utilizes a self-adaptive weighted multi-scale feature fusion module called SMA which adaptively weights the contribution of detection results based on different scales of feature maps. Simultaneously, skip connections are employed at the bottleneck of the network to ensure the integrity of feature information. Experimental results demonstrate that on the wire bonding X-ray defect image dataset, the proposed algorithm achieves mAP 0.5 and mAP 0.5–0.95 values of 97.3% and 72.1%, respectively, surpassing the YOLO series algorithms. It also exhibits certain advantages in terms of model size and detection speed, effectively balancing detection accuracy and speed. [ABSTRACT FROM AUTHOR]

Short-to-medium-term electric load forecasting is crucial for grid planning, transformation, and load scheduling for power supply departments. Various complex and ever-changing factors such as weather, seasons, regional economic structures, and enterprise production cycles exert uncontrollable effects on the electric grid load. While the causal convolutional neural network can significantly enhance long-term sequence prediction, it may suffer from problems such as vanishing gradients and overfitting due to extended time series. To address this issue, this paper introduces a new power load data anomaly detection method, which leverages a convolutional neural network (CNN) to extract temporal and spatial information from the load data. The features extracted are then processed using a bidirectional long short-term memory network (BiLSTM) to capture the temporal dependencies in the data more adeptly. An enhanced random forest (RF) classifier is employed for anomaly detection in electric load data. Furthermore, the paper proposes a new model framework for electricity load forecasting that combines a dilated causal convolutional neural network with ensemble learning. This combination addresses issues such as vanishing gradients encountered in causal convolutional neural networks with long time series. Extreme gradient boosting (XGBoost), category boosting (CATBoost), and light gradient boosting machine (LightGBM) models act as the base learners for ensemble modeling to comprehend deep cross-features, and the prediction results generated by ensemble learning serve as a new feature set for secondary ensemble modeling. The dilated convolutional neural network broadens the receptive field of the convolutional kernel. All acquired feature values are concatenated and input into the dilated causal convolutional neural network for training, achieving short-to-medium-term electric load forecasting. Experimental results indicate that compared to existing models, its root mean squared error (RMSE) and mean squared error (MSE) in short-term and mid-term electricity load forecasting are reduced by 4.96% and 12.31%, respectively, underscoring the efficacy of the proposed framework. [ABSTRACT FROM AUTHOR]

Diabetes is a widely spread disease that significantly affects people's lives. The leading cause is uncontrolled levels of blood glucose, which develop eye defects over time, including Diabetic Retinopathy (DR), which results in severe visual loss. The primary factor causing blindness is considered to be DR in diabetic patients. DR treatment tries to control the disease's severity, as it is irreversible. The primary goal of this effort is to create a reliable method for automatically detecting the severity of DR. This paper proposes a new automated system (DR-NASNet) to detect and classify DR severity using an improved pretrained NASNet Model. To develop the DR-NASNet system, we first utilized a preprocessing technique that takes advantage of Ben Graham and CLAHE to lessen noise, emphasize lesions, and ultimately improve DR classification performance. Taking into account the imbalance between classes in the dataset, data augmentation procedures were conducted to control overfitting. Next, we have integrated dense blocks into the NASNet architecture to improve the effectiveness of classification results for five severity levels of DR. In practice, the DR-NASNet model achieves state-of-the-art results with a smaller model size and lower complexity. To test the performance of the DR-NASNet system, a combination of various datasets is used in this paper. To learn effective features from DR images, we used a pretrained model on the dataset. The last step is to put the image into one of five categories: No DR, Mild, Moderate, Proliferate, or Severe. To carry this out, the classifier layer of a linear SVM with a linear activation function must be added. The DR-NASNet system was tested using six different experiments. The system achieves 96.05% accuracy with the challenging DR dataset. The results and comparisons demonstrate that the DR-NASNet system improves a model's performance and learning ability. As a result, the DR-NASNet system provides assistance to ophthalmologists by describing an effective system for classifying early-stage levels of DR. [ABSTRACT FROM AUTHOR]

State-of-Health (SOH) prediction of lithium-ion batteries is crucial in battery management systems. In order to guarantee the safe operation of lithium-ion batteries, a hybrid model based on convolutional neural network (CNN)-bidirectional long short-term memory (BiLSTM) and attention mechanism (AM) is developed to predict the SOH of lithium-ion batteries. By analyzing the charging and discharging process of batteries, the indirect health indicator (HI), which is highly correlated with capacity, is extracted in this paper. HI is taken as the input of CNN, and the convolution and pooling operations of CNN layers are used to extract the features of battery time series data. On this basis, a BiLSTM depth model is built in this paper to collect the data coming from CNN forward and reverse dependencies and further emphasize the correlation between the serial data by AM to obtain an accurate SOH estimate. Experimental results based on NASA PCoE lithium-ion battery data demonstrate that the proposed hybrid model outperforms other single models, with the root mean square error (RMSE) of SOH prediction results all less than 0.01, and can accurately predict the SOH of lithium-ion batteries. [ABSTRACT FROM AUTHOR]

Vision-based welding seam tracking is an important and unique branch of welding automation. Active vision seam tracking systems achieve accurate feature extraction by using an auxiliary light source, but this will introduce extra costs and the real-time performance will be affected. In contrast, passive vision systems achieve better real-time performance and their structure is relatively simple. This paper proposes a passive vision welding seam tracking system in Plasma Arc Welding (PAW) based on semantic segmentation. The BiseNetV2 network is adopted in this paper and online hard example mining (OHEM) is used to improve the segmentation effect. This network structure is a lightweight structure allowing effective image feature extraction. According to the segmentation results, the offset between the welding seam and the welding torch can be calculated. The results of the experiments show that the proposed method can achieve 57 FPS and the average error of the offset calculation is within 0.07 mm, meaning it can be used for real-time seam tracking. [ABSTRACT FROM AUTHOR]

Hyperspectral imaging has emerged as a novel imaging modality in the medical field, offering the ability to acquire images of biological tissues while simultaneously providing biochemical insights for in-depth tissue analysis. This approach facilitates early disease diagnosis, presenting advantages over traditional medical imaging techniques. Addressing challenges such as the computational burden of existing convolutional neural networks (CNNs) and imbalances in sample data, this paper introduces a lightweight GhostMRNet for the classification of microscopic hyperspectral images of human blood cells. The proposed model employs Ghost Modules to replace conventional convolutional layers and a cascading approach with small convolutional kernels for multiscale feature extraction, aiming to enhance feature extraction capabilities while reducing computational complexity. Additionally, an SE (Squeeze-and-Excitation) module is introduced to selectively allocate weights to features in each channel, emphasizing informative features and efficiently achieving spatial–spectral feature extraction in microscopic hyperspectral imaging. We evaluated the performance of the proposed GhostMRNet and compared it with other state-of-the-art models using two real medical hyperspectral image datasets. The experimental results demonstrate that GhostMRNet exhibits a superior performance, with an overall accuracy (OA), average accuracy (AA), and Kappa coefficient reaching 99.965%, 99.565%, and 0.9925, respectively. In conclusion, the proposed GhostMRNet achieves a superior classification performance at a smaller computational cost, thereby providing a novel approach for blood cell detection. [ABSTRACT FROM AUTHOR]

Ship detection aims to automatically identify whether there are ships in the images, precisely classifies and localizes them. Regardless of whether utilizing early manually designed methods or deep learning technology, ship detection is dedicated to exploring the inherent characteristics of ships to enhance recall. Nowadays, high-precision ship detection plays a crucial role in civilian and military applications. In order to provide a comprehensive review of ship detection in optical remote-sensing images (SDORSIs), this paper summarizes the challenges as a guide. These challenges include complex marine environments, insufficient discriminative features, large scale variations, dense and rotated distributions, large aspect ratios, and imbalances between positive and negative samples. We meticulously review the improvement methods and conduct a detailed analysis of the strengths and weaknesses of these methods. We compile ship information from common optical remote sensing image datasets and compare algorithm performance. Simultaneously, we compare and analyze the feature extraction capabilities of backbones based on CNNs and Transformer, seeking new directions for the development in SDORSIs. Promising prospects are provided to facilitate further research in the future. [ABSTRACT FROM AUTHOR]

Accurate estimation of Li-ion battery capacity is critical for a battery management system (BMS). This paper proposes an innovative method which combines a convolutional neural network and incremental capacity analysis (ICA). In the present approach, the voltage and temperature, which significantly affect the ICA curve during the discharging process, are adopted as the inputs for CNN. Rather than extracting feature parameters of an IC curve, as is carried out in the available research, the present method uses the whole ICA curve as the input to avoid complicated feature extraction and correlation analysis. The results show that the maximum error of capacity estimation is less than 4.7%, the rectified mean squared error is less than 1.3% for each battery, and the overall RMSE is below 1.12%. [ABSTRACT FROM AUTHOR]

In the context of automatic charging for electric vehicles, collision localization for the end-effector of robots not only serves as a crucial visual complement but also provides essential foundations for subsequent response design. In this scenario, data-driven collision localization methods are considered an ideal choice. However, due to the typically high demands on the data scale associated with such methods, they may significantly increase the construction cost of models. To mitigate this issue to some extent, in this paper, we propose a novel approach for robot collision localization based on a sparse modular point matrix (SMPM) in the context of automatic charging for electric vehicles. This method, building upon the use of collision point matrix templates, strategically introduces sparsity to the sub-regions of the templates, aiming to reduce the scale of data collection. Additionally, we delve into the exploration of data-driven models adapted to SMPMs. We design a feature extractor that combines a convolutional neural network (CNN) with an echo state network (ESN) to perform adaptive feature extraction on collision vibration signals. Simultaneously, by incorporating a support vector machine (SVM) as a classifier, the model is capable of accurately estimating the specific region in which the collision occurs. The experimental results demonstrate that the proposed collision localization method maintains a collision localization accuracy of 91.27% and a collision localization RMSE of 1.46 mm, despite a 48.15% reduction in data scale. [ABSTRACT FROM AUTHOR]

This paper proposes an improved fault diagnosis algorithm that combines a modified fast kurtogram (FK) method with the lightweight convolutional neural network GhostNet. The FK algorithm can adaptively select resonance demodulation bands for envelope demodulation to extract fault features, but it may be disturbed by non-Gaussian noise. Hence, the fast average kurtogram (FAK) method based on sub-band averaging was introduced. This method effectively weakens the impact of pulse noise on the kurtosis graph by splitting the signal into equal-length sub-signals and calculating the average kurtosis value of all sub-signal filters. Simultaneously, to fully utilize the advantages of deep learning technology in feature extraction and classification, this study used the FAK to convert vibration signals from one-dimensional to two-dimensional kurtosis graphs as the input for the GhostNet model. This combination not only achieved accurate fault diagnosis and classification but also showed significant advantages in processing efficiency and resource utilization. The experimental results indicate that the algorithm excelled in extracting features and diagnosing periodic transient impact faults, and compared with traditional methods, it exhibited noticeable improvements in computational efficiency and resource management. [ABSTRACT FROM AUTHOR]

Speech is a complex mechanism allowing us to communicate our needs, desires and thoughts. In some cases of neural dysfunctions, this ability is highly affected, which makes everyday life activities that require communication a challenge. This paper studies different parameters of an intelligent imaginary speech recognition system to obtain the best performance according to the developed method that can be applied to a low-cost system with limited resources. In developing the system, we used signals from the Kara One database containing recordings acquired for seven phonemes and four words. We used in the feature extraction stage a method based on covariance in the frequency domain that performed better compared to the other time-domain methods. Further, we observed the system performance when using different window lengths for the input signal (0.25 s, 0.5 s and 1 s) to highlight the importance of the short-term analysis of the signals for imaginary speech. The final goal being the development of a low-cost system, we studied several architectures of convolutional neural networks (CNN) and showed that a more complex architecture does not necessarily lead to better results. Our study was conducted on eight different subjects, and it is meant to be a subject's shared system. The best performance reported in this paper is up to 37% accuracy for all 11 different phonemes and words when using cross-covariance computed over the signal spectrum of a 0.25 s window and a CNN containing two convolutional layers with 64 and 128 filters connected to a dense layer with 64 neurons. The final system qualifies as a low-cost system using limited resources for decision-making and having a running time of 1.8 ms tested on an AMD Ryzen 7 4800HS CPU. [ABSTRACT FROM AUTHOR]

Cloud and snow recognition technology is of great significance in the field of meteorology, and is also widely used in remote sensing mapping, aerospace, and other fields. Based on the traditional method of manually labeling cloud-snow areas, a method of labeling cloud and snow areas using deep learning technology has been gradually developed to improve the accuracy and efficiency of recognition. In this paper, from the perspective of designing an efficient and lightweight network model, a cloud snow recognition model based on a lightweight feature map attention network (Lw-fmaNet) is proposed to ensure the performance and accuracy of the cloud snow recognition model. The model is improved based on the ResNet18 network with the premise of reducing the network parameters and improving the training efficiency. The main structure of the model includes a shallow feature extraction module, an intrinsic feature mapping module, and a lightweight adaptive attention mechanism. Overall, in the experiments conducted in this paper, the accuracy of the proposed cloud and snow recognition model reaches 95.02%, with a Kappa index of 93.34%. The proposed method achieves an average precision rate of 94.87%, an average recall rate of 94.79%, and an average F1-Score of 94.82% for four sample recognition classification tasks: no snow and no clouds, thin cloud, thick cloud, and snow cover. Meanwhile, our proposed network has only 5.617M parameters and takes only 2.276 s. Compared with multiple convolutional neural networks and lightweight networks commonly used for cloud and snow recognition, our proposed lightweight feature map attention network has a better performance when it comes to performing cloud and snow recognition tasks. [ABSTRACT FROM AUTHOR]

This paper presents an on-chip implementation of an analog processor-in-memory (PIM)-based convolutional neural network (CNN) in a biosensor. The operator was designed with low power to implement CNN as an on-chip device on the biosensor, which consists of plates of 32 × 32 material. In this paper, 10T SRAM-based analog PIM, which performs multiple and average (MAV) operations with multiplication and accumulation (MAC), is used as a filter to implement CNN at low power. PIM proceeds with MAV operations, with feature extraction as a filter, using an analog method. To prepare the input feature, an input matrix is formed by scanning a 32 × 32 biosensor based on a digital controller operating at 32 MHz frequency. Memory reuse techniques were applied to the analog SRAM filter, which is the core of low power implementation, and in order to accurately grasp the MAC operational efficiency and classification, we modeled and trained numerous input features based on biosignal data, confirming the classification. When the learned weight data was input, 19 mW of power was consumed during analog-based MAC operation. The implementation showed an energy efficiency of 5.38 TOPS/W and was differentiated through the implementation of 8 bits of high resolution in the 180 nm CMOS process. [ABSTRACT FROM AUTHOR]

A network intrusion detection model that fuses a convolutional neural network and a gated recurrent unit is proposed to address the problems associated with the low accuracy of existing intrusion detection models for the multiple classification of intrusions and low accuracy of class imbalance data detection. In this model, a hybrid sampling algorithm combining Adaptive Synthetic Sampling (ADASYN) and Repeated Edited nearest neighbors (RENN) is used for sample processing to solve the problem of positive and negative sample imbalance in the original dataset. The feature selection is carried out by combining Random Forest algorithm and Pearson correlation analysis to solve the problem of feature redundancy. Then, the spatial features are extracted by using a convolutional neural network, and further extracted by fusing Averagepooling and Maxpooling, using attention mechanism to assign different weights to the features, thus reducing the overhead and improving the model performance. At the same time, a Gated Recurrent Unit (GRU) is used to extract the long-distance dependent information features to achieve comprehensive and effective feature learning. Finally, a softmax function is used for classification. The proposed intrusion detection model is evaluated based on the UNSW_NB15, NSL-KDD, and CIC-IDS2017 datasets, and the experimental results show that the classification accuracy reaches 86.25%, 99.69%, 99.65%, which are 1.95%, 0.47% and 0.12% higher than that of the same type of CNN-GRU, and can solve the problems of low classification accuracy and class imbalance well. [ABSTRACT FROM AUTHOR]

Small objects detection is a challenging task in computer vision due to the limited semantic information that can be extracted and the susceptibility to background interference. In this paper, we propose a decoupled multi-scale small object detection algorithm named DMS-YOLOv5. The algorithm incorporates a receptive field module into the feature extraction network for better focus on low-resolution small objects. The coordinate attention mechanism, which combines spatial and channel attention information, is introduced to reduce interference from background information and enhance the network's attention to object information. A detection layer tailored to small-sized objects is added to compensate for the loss of small object information in multiple downsampling operations, greatly improving the detection capability of small objects. Next, The decoupled network is introduced into the detection head network for branch processing of classification and bounding box regression tasks. Finally, the bounding box loss function is improved to alleviate missed detection problems caused by the concentration of small objects and mutual occlusion between objects. The improved method achieved a mean average precision improvement of 12.1% on VisDrone2019-DET dataset compared to the original method. In comparison experiments with similar methods, our proposed method also demonstrated good performance, validating its effectiveness. [ABSTRACT FROM AUTHOR]

A significant majority of the population in India makes their living through agriculture. Different illnesses that develop due to changing weather patterns and are caused by pathogenic organisms impact the yields of diverse plant species. The present article analyzed some of the existing techniques in terms of data sources, pre-processing techniques, feature extraction techniques, data augmentation techniques, models utilized for detecting and classifying diseases that affect the plant, how the quality of images was enhanced, how overfitting of the model was reduced, and accuracy. The research papers for this study were selected using various keywords from peer-reviewed publications from various databases published between 2010 and 2022. A total of 182 papers were identified and reviewed for their direct relevance to plant disease detection and classification, of which 75 papers were selected for this review after exclusion based on the title, abstract, conclusion, and full text. Researchers will find this work to be a useful resource in recognizing the potential of various existing techniques through data-driven approaches while identifying plant diseases by enhancing system performance and accuracy. [ABSTRACT FROM AUTHOR]

Achieving online inspection and recognition of laser welding quality is essential for intelligent industrial manufacturing. The weld penetration status is an important indicator for assessing the welding quality, and the optical signal is the most common changing feature in the laser welding process. This paper proposes a new method based on a photoelectric signal and neural network for laser welding penetration status identification. A laser welding experimental system platform based on a photoelectric sensor is built, the laser welding experimental material is DC01 mild steel, and the photoelectric signal in the laser welding process is collected. The collected signal is then processed, and features are extracted using wavelet packet transform and probability density analyses. The mapping relationship between the signal features and weld penetration status is investigated. A deep learning convolutional neural network (CNN)-based weld penetration status recognition model is constructed, with multiple eigenvalue vectors as input, and the model training and recognition results are analyzed and compared. The experimental results show that the photoelectric signal features are highly correlated with the weld penetration status, and the constructed CNN weld penetration status recognition model has an accuracy of up to 98.5% on the test set, demonstrating excellent performance in identifying the quality of the laser welding. This study provides the basis for the online inspection and intelligent identification of laser welding quality. [ABSTRACT FROM AUTHOR]

Biometric technology is fast gaining pace as a veritable developmental tool. So far, biometric procedures have been predominantly used to ensure identity and ear recognition techniques continue to provide very robust research prospects. This paper proposes to identify and review present techniques for ear biometrics using certain parameters: machine learning methods, and procedures and provide directions for future research. Ten databases were accessed, including ACM, Wiley, IEEE, Springer, Emerald, Elsevier, Sage, MIT, Taylor & Francis, and Science Direct, and 1121 publications were retrieved. In order to obtain relevant materials, some articles were excused using certain criteria such as abstract eligibility, duplicity, and uncertainty (indeterminate method). As a result, 73 papers were selected for in-depth assessment and significance. A quantitative analysis was carried out on the identified works using search strategies: source, technique, datasets, status, and architecture. A Quantitative Analysis (QA) of feature extraction methods was carried out on the selected studies with a geometric approach indicating the highest value at 36%, followed by the local method at 27%. Several architectures, such as Convolutional Neural Network, restricted Boltzmann machine, auto-encoder, deep belief network, and other unspecified architectures, showed 38%, 28%, 21%, 5%, and 4%, respectively. Essentially, this survey also provides the various status of existing methods used in classifying related studies. A taxonomy of the current methodologies of ear recognition system was presented along with a publicly available occlussion and pose sensitive black ear image dataset of 970 images. The study concludes with the need for researchers to consider improvements in the speed and security of available feature extraction algorithms. [ABSTRACT FROM AUTHOR]

Most traditional artificial intelligence-based fault location methods are very dependent on fault signal selection and feature extraction, which is often based on prior knowledge. Further, these methods are usually very sensitive to line parameters and selected fault characteristics, so the generalization performance is poor and cannot be applied to different lines. In order to solve the above problems, this paper proposes a two-terminal fault location fusion model, which combines a convolutional neural network (CNN), an attention module (AM), and multi-head long short-term memory (multi-head-LSTM). First, the CNN is used to accomplish the self-extraction of fault data features. Second, the CBAM (convolutional block attention module) model is embedded into the convolutional neural network to selectively learn fault features autonomously. Furthermore, the LSTM is combined to learn the deep timing characteristics. Finally, a MLP output layer is used to determine the optimal weights to construct a fusion model based on the results of the two-terminal relative fault location model and then output the final location result. Simulation studies show that this method has a high location accuracy, does not require the design of complex feature extraction algorithms, and exhibits good generalization performance for lines with different parameters, which is of great importance for the development of AI-based methods of fault location. [ABSTRACT FROM AUTHOR]

The frequency-hopping communication system has been widely used in anti-jamming communication due to its anti-interception and anti-jamming performance. With the increasingly complex electromagnetic environment, the frequency-hopping communication system needs more flexible frequency-hopping patterns to deal with interferences, which brings great challenges to the communication receiver. In this paper, an intelligent receiving scheme of frequency-hopping sequences is proposed, which combines time–frequency analysis with deep learning to realize an intelligent estimation of frequency-hopping sequences. A hybrid network module is designed by combining a convolutional neural network (CNN) with a gated recurrent unit (GRU). In the proposed network module, the combination of a residual network (ResNet) and squeeze and extraction (SE) improves the feature extraction and expression capabilities of the CNN network. The GRU network is proposed to solve the problem of dealing with signals with variant input lengths. A transfer learning scheme is further proposed to deal with communications systems with different frequency-hopping sets. Simulation results show that the proposed method has strong generalization ability and robustness, and the bit error rate (BER) performance of intelligent receiving is close to the receiving performance under ideal conditions. [ABSTRACT FROM AUTHOR]

Automatic extraction of building contours from high-resolution images is of great significance in the fields of urban planning, demographics, and disaster assessment. Network models based on convolutional neural network (CNN) and transformer technology have been widely used for semantic segmentation of buildings from high resolution remote sensing images (HRSI). However, the fixed geometric structure and the local receptive field of the convolutional kernel are not good at global feature extraction, and the transformer technique with self-attention mechanism introduces computational redundancies and extracts local feature details poorly in the process of modeling the global contextual information. In this paper, a dual-branch fused reconstructive transformer network, DFRTNet, is proposed for efficient and accurate building extraction. In the encoder, the traditional transformer is reconfigured by designing the local and global feature extraction module (LGFE); the branch of global feature extraction (GFE) performs dynamic range attention (DRA) based on the idea of top-k attention for extracting global features; furthermore, the branch of local feature extraction (LFE) is used to obtain fine-grained features. The multilayer perceptron (MLP) is employed to efficiently fuse the local and global features. In the decoder, a simple channel attention module (CAM) is used in the up-sampling part to enhance channel dimension features. Our network achieved the best segmentation accuracy on both the WHU and Massachusetts building datasets when compared to other mainstream and state-of-the-art methods. [ABSTRACT FROM AUTHOR]

The joint use of hyperspectral image (HSI) and Light Detection And Ranging (LiDAR) data has been widely applied for land cover classification because it can comprehensively represent the urban structures and land material properties. However, existing methods fail to combine the different image information effectively, which limits the semantic relevance of different data sources. To solve this problem, in this paper, an Attention-guided Fusion and Classification framework based on Convolutional Neural Network (AFC-CNN) is proposed to classify the land cover based on the joint use of HSI and LiDAR data. In the feature extraction module, AFC-CNN employs the three dimensional convolutional neural network (3D-CNN) combined with a multi-scale structure to extract the spatial-spectral features of HSI, and uses a 2D-CNN to extract the spatial features from LiDAR data. Simultaneously, the spectral attention mechanism is adopted to assign weights to the spectral channels, and the cross attention mechanism is introduced to impart significant spatial weights from LiDAR to HSI, which enhance the interaction between HSI and LiDAR data and leverage the fusion information. Then two feature branches are concatenated and transferred to the feature fusion module for higher-level feature extraction and fusion. In the fusion module, AFC-CNN adopts the depth separable convolution connected through the residual structures to obtain the advanced features, which can help reduce computational complexity and improve the fitting ability of the model. Finally, the fused features are sent into the linear classification module for final classification. Experimental results on three datasets, i.e., Houston, MUUFL and Trento datasets show that the proposed AFC-CNN framework achieves better classification accuracy compared with the state-of-the-art algorithms. The overall accuracy of AFC-CNN on Houston, MUUFL and Trento datasets are 94.2%, 95.3% and 99.5%, respectively. [ABSTRACT FROM AUTHOR]

To enhance the detection capability of weak targets and reduce the dependence of single-photon lidar target detection on the number of the time-correlated single-photon counting detection cycles, a convolutional neural network (CNN) based on the point cloud (CNN-PC) method is proposed in this paper for detecting targets in single-photon lidar. This approach utilizes the exceptional feature extraction capabilities offered by CNN. The CNN-PC method utilizes the feature extraction module of the trained CNN to simultaneously extract features from two-dimensional point cloud slices. Subsequently, it combines these features and feeds them into the classification module of the trained CNN for final target detection. By training the CNN using point cloud slices generated with a minimal number of detection cycles and employing a parallel structure to extract features from multiple point cloud slices, the CNN-PC method exhibits remarkable flexibility in adapting to varying numbers of detection cycles. Both simulation and experimental results demonstrate that the CNN-PC method outperforms the classical constant false alarm rate method in terms of the target detection probability at the same signal-to-noise ratio and in terms of the imaging rate and error rate at the same number of detection cycles. [ABSTRACT FROM AUTHOR]

In dynamic environments, convolutional neural networks (CNNs) often produce image feature maps with significant redundancy due to external factors such as moving objects and occlusions. These feature maps are inadequate as precise image descriptors for similarity measurement, hindering loop closure detection. Addressing this issue, this paper proposes feature compression of convolutional neural network output. The approach is detailed as follows: (1) employing ResNet152 as the backbone feature-extraction network, a Siamese neural network is constructed to enhance the efficiency of feature extraction; (2) utilizing KL transformation to extract principal components from the backbone network's output, thereby eliminating redundant information; (3) employing the compressed features as input for NetVLAD to construct a spatially informed feature descriptor for similarity measurement. Experimental results demonstrate that, on the New College dataset, the proposed improved method exhibits an approximately 9.98% enhancement in average accuracy compared to the original network. On the City Center dataset, there is an improvement of approximately 2.64%, with an overall increase of about 23.51% in time performance. These findings indicate that the enhanced ResNet152 performs better than the original network in environments with more moving objects and occlusions. [ABSTRACT FROM AUTHOR]

Early rice disease detection is vital in preventing damage to agricultural product output and quantity in the agricultural field. Manual observations of rice diseases are tedious, costly, and time-consuming, especially when classifying disease patterns and color while dealing with non- native diseases. Hence, image processing and Machine Learning (ML) techniques are used to detect rice disease early and within a relatively brief time period. This article aims to demonstrate the performance of different ML algorithms in rice disease detection through image processing. We critically examined different techniques, and the outcomes of previous research have been reviewed to compare the performance of rice disease classifications. Performance has been evaluated based on the criteria of feature extraction, clustering, segmentation, noise reduction, and level of accuracy of disease detection techniques. This paper also showcases various algorithms for different datasets in terms of training methods, image preprocessing with clustering and filtering criteria, and testing with reliable outcomes. Through this review, we provide valuable insights into the current state of ML-based approaches for the early detection of rice diseases, and assist future research and improvement. In addition, we discuss several challenges that must be overcome in order to achieve effective identification of rice diseases. [ABSTRACT FROM AUTHOR]

Unsupervised anomalous sound detection by machines holds significant importance within the realm of industrial automation. Currently, the task of machine-based anomalous sound detection in complex industrial settings is faced with issues such as the challenge of extracting acoustic feature information and an insufficient feature extraction capability within the detection network. To address these challenges, this study proposes a machine anomalous sound detection method using the lMS spectrogram and ES-MobileNetV3 network. Firstly, the log-Mel spectrogram feature and the SincNet spectrogram feature are extracted from the raw wave, and the new lMS spectrogram is formed after fusion, serving as network input features. Subsequently, based on the MobileNetV3 network, an improved detection network, ES-MobileNetV3, is proposed in this paper. This network incorporates the Efficient Channel Attention module and the SoftPool method, which collectively reduces the loss of feature information and enhances the feature extraction capability of the detection network. Finally, experiments are conducted on the dataset provided by DCASE 2020 Task 2. Our proposed method attained an averaged area under the receiver operating characteristic curve (AUC) of 96.67% and an averaged partial AUC (pAUC) of 92.38%, demonstrating superior detection performance compared to other advanced methods. [ABSTRACT FROM AUTHOR]

Light field (LF) reconstruction is a technique for synthesizing views between LF images and various methods have been proposed to obtain high-quality LF reconstructed images. In this paper, we propose a progressive exploration network using efficient channel fusion for light field reconstruction (Prex-Net), which consists of three parts to quickly produce high-quality synthesized LF images. The initial feature extraction module uses 3D convolution to obtain deep correlations between multiple LF input images. In the channel fusion module, the extracted initial feature map passes through successive up- and down-fusion blocks and continuously searches for features required for LF reconstruction. The fusion block collects the pixels of channels by pixel shuffle and applies convolution to the collected pixels to fuse the information existing between channels. Finally, the LF restoration module synthesizes LF images with high angular resolution through simple convolution using the concatenated outputs of down-fusion blocks. The proposed Prex-Net synthesizes views between LF images faster than existing LF restoration methods and shows good results in the PSNR performance of the synthesized image. [ABSTRACT FROM AUTHOR]

Analyzing the condition and function of the heart is very important because cardiovascular diseases (CVDs) are responsible for high mortality rates worldwide and can lead to strokes and heart attacks; thus, early diagnosis and treatment are important. Phonocardiogram (PCG) signals can be used to analyze heart rate characteristics to detect heart health and detect heart-related diseases. In this paper, we propose a method for designing using wavelet analysis techniques and an ensemble of deep learning models from phonocardiogram (PCG) for heart sound classification. For this purpose, we use wavelet scattering transform (WST) and continuous wavelet transform (CWT) as the wavelet analysis approaches for 1D-convolutional neural network (CNN) and 2D-CNN modeling, respectively. These features are insensitive to translations of the input on an invariance scale and are continuous with respect to deformations. Furthermore, the ensemble model is combined with 1D-CNN and 2D-CNN. The proposed method consists of four stages: a preprocessing stage for dividing signals at regular intervals, a feature extraction stage through wavelet scattering transform (WST) and continuous wavelet transform (CWT), a design stage of individual 1D-CNN and 2D-CNN, and a classification stage of heart sound by the ensemble model. The datasets used for the experiment were the PhysioNet/CinC 2016 challenge dataset and the PASCAL classifying heart sounds challenge dataset. The performance evaluation is performed by precision, recall, F1-score, sensitivity, and specificity. The experimental results revealed that the proposed method showed good performance on two datasets in comparison to the previous methods. The ensemble method of the proposed deep learning model surpasses the performance of recent studies and is suitable for predicting and diagnosing heart-related diseases by classifying heart sounds through phonocardiogram (PCG) signals. [ABSTRACT FROM AUTHOR]

The importance of network security has become increasingly prominent due to the rapid development of network technology. Network intrusion detection systems (NIDSs) play a crucial role in safeguarding networks from malicious attacks and intrusions. However, the issue of class imbalance in the dataset presents a significant challenge to NIDSs. In order to address this concern, this paper proposes a new NIDS called CBF-IDS, which combines convolutional neural networks (CNNs) and bidirectional long short-term memory networks (BiLSTMs) while employing the focal loss function. By utilizing CBF-IDS, spatial and temporal features can be extracted from network traffic. Moreover, during model training, CBF-IDS applies the focal loss function to give more weight to minority class samples, thereby mitigating the impact of class imbalance on model performance. In order to evaluate the effectiveness of CBF-IDS, experiments were conducted on three benchmark datasets: NSL-KDD, UNSW-NB15, and CIC-IDS2017. The experimental results demonstrate that CBF-IDS outperforms other classification models, achieving superior detection performance. [ABSTRACT FROM AUTHOR]