Search

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

With the diversification of users' energy demands, accurate load forecasting is an important prerequisite for optimal scheduling and economic operation of the system, but a single‐load forecasting method cannot effectively predict multi‐energy loads accurately. Therefore, this paper proposes a multi‐energy load forecasting method based on bidirectional long short‐term memory (BiLSTM) and parallel feature extraction networks. Firstly, residual network and convolutional block attention module were used to extract the spatial coupling features of multi‐energy load data. Secondly, BiLSTM is used to capture the temporal features and long‐term dependencies in the load data, and the spatial coupling features are fused to obtain non‐linear prediction results. Finally, the non‐linear prediction results and the linear prediction results obtained by using multi‐energy linear regression were linearly superimposed to obtain the final prediction results. In this paper, IES load data of Tempe Campus of Arizona State University was used to verify and compared with several existing methods, and the results showed that Weighted Mean Absolute Percentage Error decreased by more than 20%. [ABSTRACT FROM AUTHOR]

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

Current research on apron conflict detection is often limited to the interaction between the aircraft as a whole and other objects, making it difficult to accomplish targeted identification of vulnerable and high‐cost aircraft components. However, the implementation of detailed aircraft identification is of great significance to enhance the safety of airport surface operations. Based on the excellent performance of High‐Resolution Network (HRNet) in keypoint detection, a lightweight end‐to‐end keypoint detection network, namely Squeeze and Excitation High‐Resolution Network (SEHRNet), is proposed in this paper to solve the problems of HRNet's slower computation and more redundancy. First, the errors arising from coordinate transformations in the coding and decoding process are solved by an improved feature map coding and decoding process. Second, replace the BasicBlock in HRNet with the Depthwise separable convolutions based on the Squeeze‐and‐Excitation Networks, which drastically cuts the computational cost of the network. Third, the improved Bottleneck module is used to further enhance the capability of feature extraction. Experimental results prove that, based on the aircraft keypoint detection dataset, the SEHRNet proposed in this paper shows stronger applicability compared to the current mainstream networks. Compared with the original HRNet, the improved network has higher accuracy, faster speed, and lighter model for aircraft keypoint detection. [ABSTRACT FROM AUTHOR]

Pixel‐level labeling of regions of interest in an image is a key step in building a labeled training dataset for supervised deep learning networks of images. However, traditional manual labeling of cancerous regions in digital pathological images by doctors is time‐consuming and inefficient. To address this issue, this paper proposes an automatic labeling method for whole slide images, which combines clustering and edge detection techniques. The proposed method utilizes the multi‐level feature fusion model and the Long‐Short Term Memory network to discriminate the cancerous nature of the whole slide images, thereby improving the classification accuracy of the whole slide images. Subsequently, the automatic labeling of cancerous regions is achieved by integrating a density‐based clustering algorithm and an edge point extraction algorithm, both based on the discriminated results of the cancerous properties of whole slide images. The experimental results demonstrate the effectiveness of the proposed method, which offers an efficient and accurate solution to the challenging task of cancerous region labeling in digital pathological images. [ABSTRACT FROM AUTHOR]

Gamma spectrum denoising can reduce the adverse effects of statistical fluctuations of radioactivity, gamma ray scattering, and electronic noise on the measured gamma spectrum. Traditional denoising methods are intricate and require analytical expertise in gamma spectrum analysis. This paper proposes a segmentation‐enhanced Convolutional Neural Network‐Stacked Denoising Autoencoder (CNN‐SDAE) method based on convolutional feature extraction network and stacked denoising autoencoder to achieve gamma spectrum denoising, which adopts the idea of data segmentation to enhance the learning ability of the neural network. By dividing the complete gamma spectrum into multiple segments and then using the segmentation‐enhanced CNN‐SDAE method for denoising, the method can achieve adaptive denoising without manually setting the threshold. The experimental results show that our method can effectively achieve gamma spectrum denoising while retaining the characteristics of the gamma spectrum. Compared with traditional methods, the denoising speed and effectiveness have been significantly improved, and the proposed method demonstrates an approximately 1.72‐fold enhancement in smoothing performance than the empirical mode decomposition method. Furthermore, in terms of retaining gamma spectrum characteristics, it also achieves a performance improvement of approximately three orders of magnitude than the wavelet method. [ABSTRACT FROM AUTHOR]

Structural features are capable of effectively capturing the overall texture variations in images. However, in locally prominent areas with visible veins, other characteristics such as directionality, convexity–concavity, and curvature also play a crucial role in recognition, and their impact cannot be overlooked. This paper introduces a novel approach, the histogram of variable curvature directional binary statistical (HVCDBS), which combines the structural and directional features of images. The proposed method is designed for extracting discriminative multifeature information in vein recognition. First, a multidirection and multicurvature Gabor filter is introduced for convolution with vein images, yielding directional and convexity–concavity information at each pixel, along with curvature information for the corresponding curve. Simultaneously incorporating the original image feature information, these four aspects of information are fused and encoded to construct a variable curvature binary pattern (VCBP) with multifeatures. Second, the feature map containing multifeature information is blockwise processed to build variable curvature binary statistical features. Finally, competitive Gabor directional binary statistical features are combined, and a matching score‐level fusion scheme is employed based on maximizing the interclass distance and minimizing the intraclass distance to determine the optimal weights. This process fuses the two feature maps into a one‐dimensional feature vector, achieving an effective representation of vein images. Extensive experiments were conducted on four widely utilized vein databases, and the results indicate that the proposed algorithm, compared with solely extraction of structural features, achieved higher recognition rates and lower equal error rates. [ABSTRACT FROM AUTHOR]

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

Visual defect recognition techniques based on deep learning models are crucial for modern industrial quality inspection. The backbone, serving as the primary feature extraction component of the defect recognition model, has not been thoroughly exploited. High‐performance vision transformer (ViT) is less adopted due to high computational complexity and limitations of computational resources and storage hardware in industrial scenarios. This paper presents LSA‐Former, a lightweight transformer architectural backbone that integrates the benefits of convolution and ViT. LSA‐Former proposes a novel self‐attention with linear computational complexity, enabling it to capture local and global semantic features with fewer parameters. LSA‐Former is pre‐trained on ImageNet‐1K and surpasses state‐of‐the‐art methods. LSA‐Former is employed as the backbone for various detectors, evaluated specifically on the PCB defect detection task. The proposed method reduces at least 18M parameters and exceeds the baseline by more than 2.2 mAP. [ABSTRACT FROM AUTHOR]

Fires not only cause devastating consequences for human life and property, but also lead to soil erosion in forests. Therefore, it is necessary to design a novel algorithm that can quickly monitor smoke from fires. Most existing smoke segmentation methods do not consider the segmentation accuracy of algorithms under limited computational resources. To address this research gap, this paper proposes a lightweight smoke segmentation algorithm based on DeepLabV3+ that achieves fast inference speed and high accuracy for different sizes smoke. To reduce the number of parameters, the feature extraction network of the DeeplabV3+ algorithm is replaced by MobileNetV2, which enhances the extraction ability of the algorithm in segment smoke images. Then, the Convolutional Block Attention Module (CBAM) is added to the encoder part to enhance the perception of the algorithm for small smoke and effectively alleviates smoke mis‐segmentation. Furthermore, a newly designed loss function is used in the network. The experimental results show that the proposed method has improved by 1.27% in Smoke IoU and 1.21% in mPA compared with other methods. The weight size has been reduced to 10.76% of the original DeepLabV3+, and the inference time is only 33.71ms. Therefore, it is a more suitable early fire detection algorithm for resource‐constrained environments. [ABSTRACT FROM AUTHOR]

To achieve real‐time and effective prediction of industrial site risks, this paper proposes an industrial risk prediction framework for multimodal data based on edge computing. First, the authors gather and annotate industrial risk multimodal data that consist of text descriptions, images, and videos. Then, the authors transfer the data to the edge server, and apply deep learning models such as Bidirectional Encoder Representations from Transformers (BERT), ResNet etc., to extract features and learn representations for text, image, and video data respectively. The authors input the fused feature data into an enhanced long short term memory (LSTM) model and train it on the dataset. Finally, the authors perform the risk prediction based on the collected multimodal data. The experimental results demonstrate that the method proposed in this paper exhibits superior performance, achieving a 1.4% enhancement in predictive accuracy. [ABSTRACT FROM AUTHOR]

This paper presents a novel bolt looseness detection method for power transmission towers based on vibration signal analysis. The proposed method utilizes pulse excitation to extract the vibration signal of the tower, which is then adaptively decomposed using the Variational Mode Decomposition of Spider Wasp optimizer (SWVMD). This overcomes limitations of traditional Variational Mode Decomposition methods by leveraging bio‐inspired optimization to improve signal decomposition. Simulated signals processed with different optimization methods verify the superiority of the SWO approach. Field tests on a 110‐kV transmission tower further demonstrate the effectiveness of the proposed SWVMD technique for analyzing on‐site vibration data. A new improved intrinsic multiscale sample entropy feature is also introduced for bolt state characterization. A Spider Wasp Support Vector Machine classifier is developed to realize accurate bolt loosening monitoring using the extracted features. Dynamic response tests under varying bolt conditions show that the method can identify early loosening and reduce tower damage risks compared to conventional techniques. This novel vibration‐based detection framework presents an innovative application of nature‐inspired computing for power infrastructure health monitoring. [ABSTRACT FROM AUTHOR]

Due to the inadequate utilization of data correlation and complementarity in the feature extraction process of multimodal remote sensing images, the paper proposes a deep learning semantic segmentation algorithm based on the Dual Channel Attention Mechanism (DCAM). This algorithm uses U‐Net as the backbone, combining the RGB remote sensing image as one input channel with the Convolutional Block Attention Module to extract colour space features. Simultaneously, it utilizes near‐infrared (NIR) as another input channel with the Self‐Attention Module (SAM) to extract shape space features. Finally, by concatenating the multi‐scale attention features of the RGB remote sensing image channel and the NIR remote sensing image channel, it achieves the correlation and complementarity of contextual features between the two modal remote sensing images. Experimental results on the GID‐15 dataset demonstrate that the DCAM algorithm significantly improves the segmentation accuracy, edge segmentation quality, and object segmentation integrity for various types of targets compared to current mainstream segmentation methods. [ABSTRACT FROM AUTHOR]

In order to solve the related problems of detection and tracking of shallow marine organisms, this paper designs a YOLO v5 multi‐target detection and tracking algorithm with attention mechanism. When working underwater, the authors usually encounter many difficulties. Different luminosity and complex coral background usually affect the detection of marine organisms. At the same time, the unrestricted movement of marine organisms, the ability to hide behind rocks and algae, and their mutual occlusion while swimming pose additional challenges to this task. Considering the characteristics of shallow marine organisms activity environment, the attention mechanism is added to the feature extraction network of YOLO v5 to reduce redundant information and improve the detection accuracy of shallow marine organism targets in complex environment. The improved algorithm improves the average detection accuracy of marine organisms target detection by 3.2%. Aiming at the problem of shallow marine organisms target tracking, a shallow marine organisms multi‐target tracking algorithm based on improved Deep Simple Online And Realtime Tracking (SORT) is designed. The improved YOLO v5 algorithm is used to replace Faster R‐CNN (Faster Region‐Convolutional Neural Networks) as the detector of DeepSORT tracking algorithm, and the cascade matching strategy is adopted to solve the problem that the target cannot be tracked continuously when it is occluded for a long time. The experimental results show that the shallow marine organisms multi‐target tracking algorithm based on improved DeepSORT reduces the number of id transformation of marine biological target tracking in shallow sea environment, and improves the accuracy of shallow marine organisms multi‐target tracking. [ABSTRACT FROM AUTHOR]

Accurate classification of substation equipment images remains challenging due to various factors such as unexpected illumination, viewing angles, scale variations, shadows, surface contaminants, and different elements sharing similar appearances. This paper presents a novel two‐stage substation equipment classification method based on dual‐scale attention. Leveraging the region proposal technique from Faster‐regions with CNN features (RCNN), the input images are initially decomposed into multiple scales to capture latent features. A dual‐scale attention module is introduced to enhance the precision of feature extraction. Furthermore, a two‐stage network is proposed to address the challenge of classifying closely similar substation equipment. A multi‐layer perceptron performs a coarse classification to categorize the equipment into broad categories. Then, a lightweight classifier is employed for fine‐grained subclassification, further distinguishing equipment within the same broad category. To mitigate the issue of limited training data, a specialized dataset is collected and annotated for the substation equipment classification. Experimental results demonstrate that the proposed method achieves remarkable accuracy, recall, and F1‐score surpassing 0.91, outperforming mainstream approaches in terms of recall and F1 scores. Ablation experiments further validate the significant contributions of both the dual‐scale attention and the two‐stage classification module in improving the overall performance of the classification network. [ABSTRACT FROM AUTHOR]

Various types of foreign fibres may be mixed in the planting, transportation, and production processes of cotton, which not only cause equipment to be out of control, but also leads to a decrease in the quality of cotton textile products and economic losses. The machine vision based detection method for cotton foreign fibres is widely used. Based on existing related research, we construct a classification dataset for cotton foreign fibres in practical scenarios, named the CF2113‐10 dataset. The authors design a basic foreign fibre classification network called CottonNet that balances performance and efficiency. The classification accuracy on the validation set reached 94.2%. In order to enhance the high‐level feature extraction ability, this paper improves the feature fusion method of residual networks and proposes CottonNet‐Res, which improves the classification accuracy to 95.1%. Finally, a classification model based on feature difference fitting, CottonNet‐Fusion, is proposed to address the classification problem of foreign fibre images sampled in complex environments. The classification accuracy of foreign fibre images sampled in ordinary scenes has improved to 97.4%, while the images sampled in complex environments maintain an accuracy of 90.3%. [ABSTRACT FROM AUTHOR]

Due to the excellent characteristics of Synthetic Aperture Radar (SAR), it has become an important technical means for land and sea target detection applications worldwide. However, the SAR image imaging process is often accompanied by speckle noise, which affects the accuracy of target detection. For this problem, this paper proposes an SAR image reconstruction model based on image denoising and feature extraction. Given a noisy SAR image, at each pixel of the image, the value of the singularity index of a metric defined by the signal gradient norm density is calculated. Then through a hierarchical decomposition of these singular indices, a set of pixels containing the most informative feature set of the image is extracted, and a denoised image is reconstructed using the extracted features. In comparison to traditional filtering and denoising techniques such as non-local filtering, this algorithm achieves remarkable local filtering and denoising effects while preserving the image's texture information. The denoising performance of the proposed method is evaluated through a series of quantitative indicators and visual comparisons. The results demonstrate that this method effectively reduces background clutter, resulting in a higher contrast between the target and the background. [ABSTRACT FROM AUTHOR]

Video steganography has the potential to be used to convey illegal information, and video steganalysis is a vital tool to detect the presence of this illicit act. Currently, all the motion vector (MV)‐based video steganalysis algorithms extract feature sets directly from the MVs, but ignoring the embedding operation may perturb the statistical distribution of other video encoding elements, such as the skipped macroblocks (no direct MVs). This paper proposes a novel 11‐dimensional feature set to detect MV‐based video steganography based on the above observation. The proposed feature is extracted based on the skipped macroblocks by recompression calibration. Specifically, the feature consists of two components. The first is the probability distribution of motion vector prediction (MVP) difference, and the second is the probability distribution of partition state transfer. Extensive experiments on different conditions demonstrate that the proposed feature set achieves good detection accuracy, especially in lower embedding capacities. In addition, the loss of detection performance caused by recompression calibration using mismatched quantization parameters (QP) is within the acceptable range, so the proposed method can be used in practical scenarios. [ABSTRACT FROM AUTHOR]

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

The text in the natural scene can express rich semantic information, which helps people understand and analyse daily things. This paper focuses on the problems of discrete text spatial distribution and variable text geometric size in natural scenes with complex backgrounds and proposes an end‐to‐end natural scene text detection method based on DBNet. The authors first use IResNet as the backbone network, which does not increase network parameters while retaining more text features. Furthermore, a module with Transformer is introduced in the feature extraction stage to strengthen the correlation between high‐level feature pixels. Then, the authors add a spatial pyramid pooling structure in the end of feature extraction, which realises the combination of local and global features, enriches the expressive ability of feature maps, and alleviates the detection limitations caused by the geometric size of features. Finally, to better integrate the features of each level, a dual attention module is embedded after multi‐scale feature fusion. Extensive experiments on the MSRA‐TD500, CTW1500, ICDAR2015, and MLT2017 data set are conducted. The results showed that IDBNet can improve the average precision, recall, and F‐measure of a text compared with the state of art text detection methods and has higher predictive ability and practicability. [ABSTRACT FROM AUTHOR]

The bridge bottom crack detection provides important state information for bridge disease control and safety assessment. This paper proposes a detection method based on deep learning Faster R‐CNN and BIM (Building Information Modeling). The UAV (Unmanned Aerial Vehicle) was used for close aerial photography to obtain high‐resolution crack images of the concrete surface at the bottom of a bridge. Through deep learning algorithms, a Faster R‐CNN model is trained and established for crack identifications. The crack identification accuracy rate and recall rate reach 92.03% and 96.54%, respectively. Crack images are mapped to a BIM model developed for the chosen bridge, and the box girder family with cracks and the three crack families of transverse cracks, longitudinal cracks and turtle cracks are established. The cracks are located and the visualization of the beam bridge with cracks was completed. In order to better assess the health condition of the bridge. The results show that the combination of UAV bridge crack detection and modelling solves the remote, visual and automated detection of cracks on the surface of bridge structures, which are difficult to reach manually, and has important scientific research and engineering application value. [ABSTRACT FROM AUTHOR]

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

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

The network structure of digital watermarking algorithm based on deep learning is usually encoder‐noise layer‐decoder. Most of the existing encoders suffer from the problem of insufficient feature extraction, and the introduction of simulated differentiable joint photographic experts group (JPEG) compression in the noise layer cannot ensure the robustness under real JPEG. In this paper, a watermarking algorithm based on multi‐scale auto‐encoder is proposed, which can effectively extract the image feature information by combining with the channel attention mechanism. At the same time, some parameters of decoder and encoder are shared to reduce redundant feature embedding and improve extraction accuracy. This paper also proposes a robust training scheme against JPEG compression, which can guide the model to store the watermark in the low‐frequency region needed for decoding. Experimental results show that the peak signal‐to‐noise ratio (PSNR) of the proposed algorithm is above 48 and the decoding rate is above 99% under JPEG compression with quality factor Q = 50. Moreover, this scheme can effectively promote the combination of noise layer in training. In addition, the proposed algorithm is also robust to other common network noises. [ABSTRACT FROM AUTHOR]

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

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

Head pose estimation is an especially challenging task due to the complexity nonlinear mapping from 2D feature space to 3D pose space. To address the above issue, this paper presents a novel and efficient head pose estimation framework based on particle swarm optimized contrastive learning and multimodal entangled graph convolution network. Firstly, a new network, the region and difference‐aware feature pyramid network (RD‐FPN), is proposed for 2D keypoints detection to alleviate the background interference and enhance the feature expressiveness. Then, particle swarm optimized contrastive learning is constructed to alternatively match 2D and 3D keypoints, which takes the multimodal keypoints matching accuracy as the optimization objective, while considering the similarity of cross‐modal positive and negative sample pairs from contrastive learning as a local contrastive constraint. Finally, multimodal entangled graph convolution network is designed to enhance the ability of establishing geometric relationships between keypoints and head pose angles based on second‐order bilinear attention, in which point‐edge attention is introduced to improve the representation of geometric features between multimodal keypoints. Compared with other methods, the average error of our method is reduced by 8.23%, indicating the accuracy, generalization, and efficiency of our method on the 300W‐LP, AFLW2000, BIWI datasets. [ABSTRACT FROM AUTHOR]

Synthetic images facilitate stereo matching. However, synthetic images may suffer from image distortion, domain bias, and stereo mismatch, which would significantly restrict the widespread use of stereo matching models in the real world. The first goal in this paper is to synthesize real‐looking images for minimizing the domain bias between the synthesized and real images. For this purpose, sharpened disparity maps are produced from a mono real image. Then, stereo image pairs are synthesized using these imperfect disparity maps and the single real image in the proposed pipeline. Although the synthesized images are as realistic as possible, the domain styles of the synthesized images are always very different from the real images. Thus, the second goal is to enhance the domain generalization ability of the stereo matching network. For that, the feature extraction layer is replaced with a teacher–student model. Then, a constraint of binocular contrast features is imposed on the output of the model. When tested on the KITTI, ETH3D, and Middlebury datasets, the accuracy of the method outperforms traditional methods by at least 30%. Experiments demonstrate that the approaches are general and can be conveniently embedded into existing stereo networks. [ABSTRACT FROM AUTHOR]

Suitable and effective matching area selection is crucial for gravity matching‐aided navigation. In this paper, an all‐field extended extremum algorithm based on an adaptive threshold (AT‐AEE) is proposed for matching area selection in the Arctic Sea. The gradient data is obtained by using the convolution of gravity reference graph data and all‐field extended extremum parameters. Then, the adaptive threshold method was employed to determine the optimal gradient threshold based on gravity anomaly data across various test areas. Data points with gradients exceeding the specified threshold are identified as local candidate points for matching areas. The test areas containing a certain proportion of local candidate points are designated as the suitable matching areas. Nine test areas in the Arctic Sea with different gravity change characteristics were chosen for simulation experiments to verify the performance of the proposed algorithm. Simulation experiments showed that superior navigation positioning results could be obtained in the matching areas selected by the AT‐AEE algorithm. Compared to traditional algorithm, the matching areas derived from the AT‐AEE algorithm performed with a better consistency in the gravity matching navigation results. In suitable matching areas with the proportion of local candidate points reaching 70%, the average positioning errors could be reduced to less than 1.5 n miles. [ABSTRACT FROM AUTHOR]

A comparative study of two force perception skill learning approaches for robot‐assisted spinal surgery, the impedance model method and the imitation learning (IL) method, is presented. The impedance model method develops separate models for the surgeon and patient, incorporating spring‐damper and bone‐grinding models. Expert surgeons' feature parameters are collected and mapped using support vector regression and image navigation techniques. The imitation learning approach utilises long short‐term memory networks (LSTM) and addresses accurate data labelling challenges with custom models. Experimental results demonstrate skill recognition rates of 63.61%–74.62% for the impedance model approach, relying on manual feature extraction. Conversely, the imitation learning approach achieves a force perception recognition rate of 91.06%, outperforming the impedance model on curved bone surfaces. The findings demonstrate the potential of imitation learning to enhance skill acquisition in robot‐assisted spinal surgery by eliminating the laborious process of manual feature extraction. [ABSTRACT FROM AUTHOR]

Short‐term wind speed prediction is essential for economical wind power utilization. The real‐world wind speed data are typically intermittent and fluctuating, presenting great challenges to existing shallow models. In this paper, we present a novel deep hybrid model for multistep wind speed prediction, namely, LR‐FFT‐RP‐MLP/LSTM (linear fast Fourier transform rank pooling multiple‐layer perceptron/long short‐term memory). Our hybrid model processes the local and global input features simultaneously. We leverage RP for the local feature extraction to capture the temporal structure while maintaining the temporal order. Besides, to understand the wind periodic patterns, we exploit FFT to extract global features and relevant frequency components in the wind speed data. The resulting local and global features are, respectively, integrated with the original data and are fed into an MLP/LSTM layer for the initial wind speed predictions. Finally, we leverage a linear regression layer to collaborate these initial predictions to produce the final wind speed prediction. The proposed hybrid model is evaluated using real wind speed data collected from 2010 to 2020, demonstrating superior forecasting capabilities when compared with state‐of‐the‐art single and hybrid models. Overall, this study presents a promising approach for improving the accuracy of wind speed forecasting. [ABSTRACT FROM AUTHOR]

Remote sensing scene images contain numerous feature targets with unrelated semantic information, so how to extract to the local key information and semantic features of the image becomes the key to achieving accurate classification. Existing Convolutional Neural Networks (CNNs) mostly concentrate on the global representation of an image and lose the shallow features. To overcome these issues, this paper proposes LPNet for remote sensing scene image classification. First, LPNet employs LKConv to extract the semantic features in the image, while using standard convolution to extract local key information in the image. Additionally, the LPNet applies a shortcut residual concatenation branch to reuse features. Then, parameter fusion combines parameters from previous branches, improving the capacity of the model to obtain a more comprehensive and rich feature representation of the image. Finally, considering the relationship between the classification ability of the model and the depth of feature extraction, the Feature Mixture (FM) Block is used to deepen the model for feature extraction. Comparative experiments on four publicly available datasets show that LPNet provides comparable results to other state‐of‐the‐art methods. The effectiveness of LPNet is further demonstrated by visualizing the effective receptive fields (ERFs). [ABSTRACT FROM AUTHOR]

This paper introduces a new descriptor called orientation‐magnitude response maps as a single 2D image to effectively explore motion patterns. Moreover, boosted multi‐stream CNN‐based model with various attention modules is designed for human action recognition. The model incorporates a convolutional self‐attention autoencoder to represent compressed and high‐level motion features. Sequential convolutional self‐attention modules are used to exploit the implicit relationships within motion patterns. Furthermore, 2D discrete wavelet transform is employed to decompose RGB frames into discriminative coefficients, providing supplementary spatial information related to the actors actions. A spatial attention block, implemented through the weighted inception module in a CNN‐based structure, is designed to weigh the multi‐scale neighbours of various image patches. Moreover, local and global body pose features are combined by extracting informative joints based on geometry features and joint trajectories in 3D space. To provide the importance of specific channels in pose descriptors, a multi‐scale channel attention module is proposed. For each data modality, a boosted CNN‐based model is designed, and the action predictions from different streams are seamlessly integrated. The effectiveness of the proposed model is evaluated across multiple datasets, including HMDB51, UTD‐MHAD, and MSR‐daily activity, showcasing its potential in the field of action recognition. [ABSTRACT FROM AUTHOR]

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

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

Slug flow processes draw much attention in chemical and pharmaceutical manufacturing thanks to their ability to eliminate downtime costs and batch‐to‐batch variation. Using in‐line video can monitor the current process status and improve the stability of the slug flow. However, there are no effective image processing methods aiming at such videos from chemical experiments due to limited training sample size and the variety of experimental settings. The paper proposes a training‐free method to automatically detect and measure the slugs from in‐line videos. Multiple image features are fused to identify the slug shapes under various lighting conditions, a six‐point model is fitted to achieve better volume estimation, and a consistency score is estimated to quantify the detection uncertainty. The proposed algorithm achieves similar results to manual labeling for various types of slug flow processes, improving the accuracy of slug column estimation by a large margin compared to the existing automatic methods. Finally, using it to monitor the slug flow process's stability and the change of the slug volume in an injection point are demonstrated. The method not only shows that handcrafted image features have the capability for detection and segmentation from chemical experiment images but also paves the road for a training‐based algorithm for the task. [ABSTRACT FROM AUTHOR]

Inversion of magnetic basement interfaces in basins is essential for interpreting potential field data and studying geothermal resource distribution, as well as basin formation and evolution. This paper introduces a novel method for inverting magnetic basement interfaces using a random forest regression (RFR) algorithm that combines potential field processing and machine learning techniques. The method creates magnetic base interface models and corresponding magnetic anomaly data through the random midpoint displacement method and magnetic interface finite element forward simulation. These anomalies are then processed using techniques such as directional transformations, analytical continuation, spatial derivatives, and fractional transformations. Feature attributes are extracted, and Gini importance is utilized to measure the contributions of feature factors, identify effective features, and enhance algorithm efficiency. The validity and practicality of the method are demonstrated through the analysis of both idealized and noisy models. The proposed machine learning‐based approach is more intelligent, efficient, and accurately represents the relief of magnetic base interfaces. When applied to magnetic survey data in the Datong Basin, it produced a reliable basin base model that aligns with known structural information, paving the way for further research in magnetic interface inversion. Key Points: A machine learning method based on random forest regression algorithm is used to recover the relief of the magnetic basement interface by using high‐precision magnetic dataApplying potential field processing and transformation to feature extraction for machine learningThe proposed technique intelligently and efficiently restores the 3D relief of the magnetic basement interface, and it has been successfully implemented in the Datong Basin's Tianzhen‐Yanggao sag [ABSTRACT FROM AUTHOR]

Manual acupuncture manipulation (MAM) is essential in traditional Chinese medicine treatment. MAM action recognition is important for junior acupuncturists' training and education; however, there are obvious personalized differences in hand gestures among expert acupuncturists for the same type of MAM. In addition, during the MAM operations, the magnitude and frequency of the expert acupuncturists' hand shape and relative needle‐holding finger position changes are tiny and fast, resulting in difficulties in observing MAM action details. Thus, we propose a Spatial Multiscale Interactive Fusion MAM Recognition Network to solve the difficulties in MAM recognition. First, this paper presents an optical flow‐based hand motion contour global feature extraction method for acupuncture hand shape. Second, to explore the motion rule between the needle‐holding fingers during the MAM operations, we design a quantitative description method of the relative motion of the needle‐holding fingers: an "interactive attention module," which achieves feature fusion and mines the correlation between different scales of MAM action features. Finally, the proposed MAM recognition method was validated by 20 acupuncturists from the Beijing University of Traditional Chinese Medicine and 10 from the Beijing Zhongguancun Hospital who participated in the MAM video signal collection. The proposed recognition method achieves the highest average validation accuracy of 95.3% and the highest test accuracy of 96.0% for four typical MAMs, proving its feasibility and effectiveness. [ABSTRACT FROM AUTHOR]

In response to the low matching accuracy of stereo matching algorithms in image regions with specular reflection, this paper proposes a multidimensional fusion stereo matching algorithm named MFANet. The algorithm embeds a multispectral attention module into the residual feature extraction network, utilizing two‐dimensional discrete cosine transforms to extract frequency features. In the pyramid pooling module, a coordinated attention mechanism is introduced to capture relevant positional information. In the cost aggregation part, the MFANet algorithm incorporates a three‐dimensional attention mechanism, focusing on the more important semantic information in high‐level features. By combining detailed information from low‐level features, semantic information from high‐level features, and contextual information, the algorithm generates features that are more conducive to disparity prediction. The MFANet algorithm is evaluated on three standard datasets (SceneFlow, KITTI2015, and KITTI2012). Experimental results demonstrate its robustness against specular reflection interference, accurate prediction of disparities in specular reflection pathological regions, and promising application prospects. [ABSTRACT FROM AUTHOR]

In order to balance accuracy and real‐time performance in semantic segmentation, this paper proposes a real‐time semantic segmentation algorithm model based on attention mechanism and multi‐branch feature fusion using Fast convolutional neural network model (Fast‐SCNN). In this method, the spatial detail feature enhancement branch is introduced to enhance spatial detail features firstly. Then, through rational design of fusion module, the feature information of each branch is optimized to achieve better fusion of deep and shallow features. At the end of the feature fusion module, an adaptive feature enhancement focus module is introduced to capture the interdependence between remote pixels. The experimental results show that the proposed algorithm achieves 71.55% segmentation accuracy on Cityscapes dataset, the reasoning speed FPS is 97.6 frames/s, and the number of parameters is 1.39 M, which verifies the effectiveness of the network model constructed by the algorithm. Code is available at https://github.com/ccchhheeennn/model. [ABSTRACT FROM AUTHOR]

Most existing multi‐view stereo (MVS) methods fail to consider global context information in the stage of feature extraction and cost aggregation. As transformers have shown remarkable performance on various vision tasks due to their ability to perceive global contextual information, this paper proposes a transformer‐based feature enhancement network (TF‐MVSNet) to facilitate feature representation learning by combining local features (both 2D and 3D) with long‐range contextual information. To reduce memory consumption of feature matching, the cross‐attention mechanism is leveraged to efficiently construct 3D cost volumes under the epipolar constraint. Additionally, a colour‐guided network is designed to refine depth maps at a coarse stage, hence reducing incorrect depth predictions at a fine stage. Extensive experiments were performed on the DTU dataset and Tanks and Temples (T&T) benchmark and results are reported. [ABSTRACT FROM AUTHOR]

Scene text in natural images carries additional semantic information to aid in image classification. Existing methods lack full consideration of the deep understanding of the text and the visual text relationship, which results in the difficult to judge the semantic accuracy and the relevance of the visual text. This paper proposes image classification based on Cross modal Knowledge Learning of Scene Text (CKLST) method. CKLST consists of three stages: cross‐modal scene text recognition, text semantic enhancement, and visual‐text feature alignment. In the first stage, multi‐attention is used to extract features layer by layer, and a self‐mask‐based iterative correction strategy is utilized to improve the scene text recognition accuracy. In the second stage, knowledge features are extracted using external knowledge and are fused with text features to enhance text semantic information. In the third stage, CKLST realizes visual‐text feature alignment across attention mechanisms with a similarity matrix, thus the correlation between images and text can be captured to improve the accuracy of the image classification tasks. On Con‐Text dataset, Crowd Activity dataset, Drink Bottle dataset, and Synth Text dataset, CKLST can perform significantly better than other baselines on fine‐grained image classification, with improvements of 3.54%, 5.37%, 3.28%, and 2.81% over the best baseline in mAP, respectively. [ABSTRACT FROM AUTHOR]

Occluded person re‐identification (Re‐ID) is to identify a particular person when the person's body parts are occluded. However, challenges remain in enhancing effective information representation and suppressing background clutter when considering occlusion scenes. This paper proposes a novel attention map‐driven network (AMD‐Net) for occluded person Re‐ID. In AMD‐Net, human parsing labels are introduced to supervise the generation of partial attention maps, while a spatial‐frequency interaction module is suggested to complement the higher‐order semantic information from the frequency domain. Furthermore, a Taylor‐inspired feature filter for mitigating background disturbance and extracting fine‐grained features is proposed. Moreover, a part‐soft triplet loss, which is robust to non‐discriminative body partial features is also designed. Experimental results on Occluded‐Duke, Occluded‐Reid, Market‐1501, and Duke‐MTMC datasets show that this method outperforms existing state‐of‐the‐art methods. The code is available at: https://github.com/ISCLab‐Bistu/SA‐ReID. [ABSTRACT FROM AUTHOR]

A road multi‐object detection algorithm is one of the core algorithms for intelligent road cleaning robots relying on machine vision. Most existing object detection algorithms analyse all image regions and finally calculate the category and location of each object. However, it is not necessary to analyse all areas of the image when detecting objects on the road surface where the background changes little, and the number of objects is small because there will be a lot of invalid calculations. If we can perform targeted local analysis on images instead of analysing all image regions, it will improve the detection efficiency. Therefore, this paper proposes a multi‐object detection method using a binocular camera and a convolutional neural network (CNN) that effectively reduces invalid calculations during the detection and improves detection efficiency. In the developed method, the binocular vision image acquired by the binocular camera is stereo matched and equalized, while linear regression and coordinate transformation eliminate the angle of the camera pair concerning the road surface. Then, the coordinates of the regions of interest (ROI) is calculated in the left vision image and the features within the ROI is extracted from the corresponding CNN's feature map. Next, ROI pooling resizes the extracted feature maps of different sizes to the same size, which are then input to the fully connected layers to output the results. The proposed binocular network and faster R‐CNN (VGG16) are trained and tested on a dataset involving 1000 road waste images. The experimental results demonstrate that the developed binocular network improves the detection accuracy and speed by 28.56% and 78.39%, respectively, compared with faster R‐CNN (VGG16), providing a reliable basis for a machine vision‐based intelligent road cleaning robot. [ABSTRACT FROM AUTHOR]

To treat the novel COronaVIrus Disease (COVID), comparatively fewer medicines have been approved. Due to the global pandemic status of COVID, several medicines are being developed to treat patients. The modern COVID medicines development process has various challenges, including predicting and detecting hazardous COVID medicine responses. Moreover, correctly predicting harmful COVID medicine reactions is essential for health safety. Significant developments in computational models in medicine development can make it possible to identify adverse COVID medicine reactions. Since the beginning of the COVID pandemic, there has been significant demand for developing COVID medicines. Therefore, this paper presents the transfer‐learning methodology and a multilabel convolutional neural network for COVID (MLCNN‐COV) medicines development model to identify negative responses of COVID medicines. For analysis, a framework is proposed with five multilabel transfer‐learning models, namely, MobileNetv2, ResNet50, VGG19, DenseNet201, and Inceptionv3, and an MLCNN‐COV model is designed with an image augmentation (IA) technique and validated through experiments on the image of three‐dimensional chemical conformer of 17 number of COVID medicines. The RGB color channel is utilized to represent the feature of the image, and image features are extracted by employing the Convolution2D and MaxPooling2D layer. The findings of the current MLCNN‐COV are promising, and it can identify individual adverse reactions of medicines, with the accuracy ranging from 88.24% to 100%, which outperformed the transfer‐learning model's performance. It shows that three‐dimensional conformers adequately identify negative COVID medicine responses. [ABSTRACT FROM AUTHOR]

Due to the robustness of skeleton data to human scale, illumination changes, dynamic camera views, and complex backgrounds, great progress has been made in skeleton‐based video anomaly detection in recent years. The spatio‐temporal graph convolutional network has been proven to be effective in modelling the spatio‐temporal dependencies of non‐Euclidean data such as human skeleton graphs, and the autoencoder based on this basic unit is widely used to model sequence features. However, due to the limitations of the convolution kernel, the model cannot capture the correlation between non‐adjacent joints, and it is difficult to deal with long‐term sequences, resulting in an insufficient understanding of behaviour. To address this issue, this paper applies the Transformer to the human skeleton and proposes the Spatio‐Temporal Enhanced Graph‐Transformer AutoEncoder (STEGT‐AE) to improve the capability of modelling. In addition, the multi‐memory model with skip connections is employed to provide different levels of coding features, thereby enhancing the ability of the model to distinguish similar heterogeneous behaviours. Furthermore, the STEGT‐AE has a single encoder‐double decoder architecture, which can improve the detection performance by the combining reconstruction and prediction error. The experimental results show that performances of STEGT‐AE is significantly better than other advanced algorithms on four baseline datasets. [ABSTRACT FROM AUTHOR]

Grasping detection, which involves identifying and assessing the grasp ability of objects by robotic systems, has garnered significant attention in recent years due to its pivotal role in the development of robotic systems and automated assembly processes. Despite notable advancements in this field, current methods often grapple with both practical and theoretical challenges that hinder their real‐world applicability. These challenges encompass low detection accuracy, the burden of oversized model parameters, and the inherent complexity of real‐world scenarios. In response to these multifaceted challenges, a novel lightweight grasping detection model that not only addresses the technical aspects but also delves into the underlying theoretical complexities is introduced. The proposed model incorporates attention mechanisms and residual modules to tackle the theoretical challenges posed by varying object shapes, sizes, materials, and environmental conditions. To enhance its performance in the face of these theoretical complexities, the proposed model employs a Convolutional Block Attention Module (CBAM) to extract features from RGB and depth channels, recognising the multifaceted nature of object properties. Subsequently, a feature fusion module effectively combines these diverse features, providing a solution to the theoretical challenge of information integration. The model then processes the fused features through five residual blocks, followed by another CBAM attention module, culminating in the generation of three distinct images representing capture quality, grasping angle, and grasping width. These images collectively yield the final grasp detection results, addressing the theoretical complexities inherent in this task. The proposed model's rigorous training and evaluation on the Cornell Grasp dataset demonstrate remarkable detection accuracy rates of 98.44% on the Image‐wise split and 96.88% on the Object‐wise split. The experimental results strongly corroborate the exceptional performance of the proposed model, underscoring its ability to overcome the theoretical challenges associated with grasping detection. The integration of the residual module ensures rapid training, while the attention module facilitates precise feature extraction, ultimately striking an effective balance between detection time and accuracy. [ABSTRACT FROM AUTHOR]

Inverse halftoning is a technology that converts a binary image into a continuous tone image. Due to the wide application of inverse halftoning, many scholars have proposed several deep convolutional neural networks (DCNN) to optimize their performance. According to the observation, there is still room for improvement in content generation and detail recovery of the inverse halftone images generated by using the existing methods. Therefore, an inverse halftoning method based on supervised DCNN is proposed in this paper. The method consists of two parts: the multi‐level feature extraction model uses the down‐sampling to extract the features from the halftone image and remove the halftone noise dots on flat areas, which is implemented by four convolutional layers; the image reconstruction model uses up‐sampling to reconstruct image information, which is realized by four convolutional layers and two dense residual blocks. At the same time, in order to further recover the details, the down‐sampling feature maps and up‐sampling feature maps of the same size are concatenated by addition layers. Experimental results show that compared with other methods, the inverse halftone images obtained by the proposed network have better results in both subjective and objective evaluations. [ABSTRACT FROM AUTHOR]

Aiming at the shortcomings of feature extraction and fault identification in fault diagnosis of wind power converters, a novel method for open circuit fault diagnosis of wind power converters based on variational mode decomposition (VMD) energy entropy (EE) and time domain feature analysis (TDFA) is proposed. Primarily, the three‐phase output current at the grid side of the wind power converter is collected as the original signal, and the VMD is used to decompose the original signal into a series of intrinsic mode functions (IMF). To reduce noise interference as much as possible, the Pearson correlation coefficient between each mode component and the original signal under different fault states is analyzed, and the IMF component containing the major failure features is selected to calculate the energy entropy of each component; afterward, according to the Pearson correlation coefficient results, the modal components of the first layer are selected for time domain feature analysis; finally, the feature matrix that combines energy entropy and time domain feature analysis is inputted into the long short‐term memory neural network for training and fault identification. The simulation and experimental results show that the open circuit fault diagnosis method proposed in this paper has high accuracy and robustness. [ABSTRACT FROM AUTHOR]

The rapid and accurate identification of single‐phase earth fault is of prime concern for many scholars from industry and academia, because its fault characteristics are extremely weak while the related potential hazard is extremely severe. In this context, this paper borrows from Deep Learning and in turn innovatively puts forward a multilayer perceptron (MLP)‐based single‐phase earth fault detection model augmented with kernel principal component analysis (KPCA). First, KPCA is applied to building fault feature extraction engineering via the transformation of fault features from low‐dimensional linear indivisible space to high‐dimensional one. Second, a MLP‐based model is used for basic model reference where many optimization strategies together with dropout technique are introduced and custom‐designed in tuning this model to achieve the best detection accuracy and convergence characteristic. Numerical studies demonstrate the superiority of the proposed KPCA‐MLP‐based single‐phase earth fault detection model. [ABSTRACT FROM AUTHOR]