Search

Accurate and comprehensive detection of pavement cracks is important for maintaining road quality and ensuring traffic safety. However, the complexity of road surfaces and the diversity of cracks make it difficult for existing methods to accomplish this challenging task. This paper proposes a novel network named the global graph multiscale network (GGMNet) for automated pixel-level detection of pavement cracks. The GGMNet network has several innovations compared with the mainstream road crack detection network: (1) a global contextual Res-block (GC-Resblock) is proposed to guide the network to emphasize the identities of cracks while suppressing background noises; (2) a graph pyramid pooling module (GPPM) is designed to aggregate the multi-scale features and capture the long-range dependencies of cracks; (3) a multi-scale features fusion module (MFF) is established to efficiently represent and deeply fuse multi-scale features. We carried out extensive experiments on three pavement crack datasets. These were DeepCrack dataset, with complex background noises; the CrackTree260 dataset, with various crack structures; and the Aerial Track Detection dataset, with a drone's perspective. The experimental results demonstrate that GGMNet has excellent performance, high accuracy, and strong robustness. In conclusion, this paper provides support for accurate and timely road maintenance and has important reference values and enlightening implications for further linear feature extraction research. [ABSTRACT FROM AUTHOR]

Deep learning models have a high application value in runoff forecasting, but their prediction mechanism is difficult to interpret and their computational cost is high when dealing with complex hydrological relationships, limiting their feasibility in hydrological process mechanism analysis. To address these concerns, the paper first introduces an attention mechanism (AM) for building a long short-term memory network (LSTM) model with AM in the hidden layer (AM-LSTM). The AM-LSTM model employs attention layers to improve information extraction from hidden layers, resulting in a more accurate representation of the relationships between runoff-related elements. Furthermore, in the hidden layers of the AM-LSTM model, interpretable spatiotemporal attention units are established, which not only improves the model's prediction accuracy but also provides interpretability to the forecasting process. Furthermore, parallelization techniques are used in the paper to address the issue of model runtime cost. Simultaneously, to address the accuracy degradation caused by parallelization, the paper employs wavelet denoising (WD) techniques and builds the WD-AM-LSTM model. This accomplishment enables the runoff forecasting model to predict runoff in real time and with high accuracy. Based on validation using ten-day runoff data from the Huanren Reservoir in the Hun River's middle reaches, the results show that, with two layers and an eight-batch size, the AM-LSTM model outperforms the LSTM model in capturing spatiotemporal runoff features. During the model testing phase, the AM-LSTM model improves the MAE, RMSE, and NSE performance metrics by 8.46%, 13%, and 3.82%, respectively. The WD-AM-LSTM model effectively mitigates the noise impact caused by data parallelization under the conditions of two layers and a batch size of 512, achieving the same level of prediction performance while reducing computational cost by 92.01%. By incorporating attention mechanisms and wavelet denoising techniques, this study obtains high-speed and accurate predictions with interpretable results. It expands the deep learning models' applicability in ten-day runoff forecasting work. [ABSTRACT FROM AUTHOR]

Simple Summary: The Amur tiger is an endangered species in the world, and effective statistics on its individuals and population through re-identification will contribute to ecological diversity investigation and assessment. Due to the fact that the fur texture features of the Amur tiger contain genetic information, the main method of identifying Amur tigers is to distinguish their fur and facial features. In summary, this paper proposes a serial multi-scale feature fusion and enhancement network for Amur tiger re-identification, and designs a global inverted pyramid multi-scale feature fusion module and a local dual-domain attention feature enhancement module. We aim to enhance the learning of fine-grained features and differences in fur texture by better fusing and enhancing global and local features. Our proposed network and module have achieved excellent results on the public dataset of the ATRW. The Amur tiger is an important endangered species in the world, and its re-identification (re-ID) plays an important role in regional biodiversity assessment and wildlife resource statistics. This paper focuses on the task of Amur tiger re-ID based on visible light images from screenshots of surveillance videos or camera traps, aiming to solve the problem of low accuracy caused by camera perspective, noisy background noise, changes in motion posture, and deformation of Amur tiger body patterns during the re-ID process. To overcome this challenge, we propose a serial multi-scale feature fusion and enhancement re-ID network of Amur tiger for this task, in which global and local branches are constructed. Specifically, we design a global inverted pyramid multi-scale feature fusion method in the global branch to effectively fuse multi-scale global features and achieve high-level, fine-grained, and deep semantic feature preservation. We also design a local dual-domain attention feature enhancement method in the local branch, further enhancing local feature extraction and fusion by dividing local feature blocks. Based on the above model structure, we evaluated the effectiveness and feasibility of the model on the public dataset of the Amur Tiger Re-identification in the Wild (ATRW), and achieved good results on mAP, Rank-1, and Rank-5, demonstrating a certain competitiveness. In addition, since our proposed model does not require the introduction of additional expensive annotation information and does not incorporate other pre-training modules, it has important advantages such as strong transferability and simple training. [ABSTRACT FROM AUTHOR]

Simple Summary: Researching and developing an automated and intelligent method to monitor the pangolin breeding process can effectively help human observation, analysis, breeding and daily behavior studies of pangolins, and has significant implications for the protection and breeding research of pangolin populations. In this paper, a pangolin breeding attention and temporal relative network (PBATn) was used to monitor and identify the breeding and daily behaviors of pangolins. This study demonstrates that the deep learning system can accurately observe pangolin breeding behavior, rendering it useful for analyzing the behavior of these animals. With declining populations in the wild, captive rescue and breeding have become one of the most important ways to protect pangolins from extinction. At present, the success rate of artificial breeding is low, due to the insufficient understanding of the breeding behavior characteristics of pangolins. The automatic recognition method based on machine vision not only monitors for 24 h but also reduces the stress response of pangolins. This paper aimed to establish a temporal relation and attention mechanism network (Pangolin breeding attention and transfer network, PBATn) to monitor and recognize pangolin behaviors, including breeding and daily behavior. There were 11,476 videos including breeding behavior and daily behavior that were divided into training, validation, and test sets. For the training set and validation set, the PBATn network model had an accuracy of 98.95% and 96.11%, and a loss function value of 0.1531 and 0.1852. The model is suitable for a 2.40 m × 2.20 m (length × width) pangolin cage area, with a nest box measuring 40 cm × 30 cm × 30 cm (length × width × height) positioned either on the left or right side inside the cage. A spherical night-vision monitoring camera was installed on the cage wall at a height of 2.50 m above the ground. For the test set, the mean Average Precision (mAP), average accuracy, average recall, average specificity, and average F1 score were found to be higher than SlowFast, X3D, TANet, TSN, etc., with values of 97.50%, 99.17%, 97.55%, 99.53%, and 97.48%, respectively. The recognition accuracies of PBATn were 94.00% and 98.50% for the chasing and mounting breeding behaviors, respectively. The results showed that PBATn outperformed the baseline methods in all aspects. This study shows that the deep learning system can accurately observe pangolin breeding behavior and it will be useful for analyzing the behavior of these animals. [ABSTRACT FROM AUTHOR]

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

Deep Self-Attention Network (Transformer) is an encoder–decoder architectural model that excels in establishing long-distance dependencies and is first applied in natural language processing. Due to its complementary nature with the inductive bias of convolutional neural network (CNN), Transformer has been gradually applied to medical image processing, including kidney image processing. It has become a hot research topic in recent years. To further explore new ideas and directions in the field of renal image processing, this paper outlines the characteristics of the Transformer network model and summarizes the application of the Transformer-based model in renal image segmentation, classification, detection, electronic medical records, and decision-making systems, and compared with CNN-based renal image processing algorithm, analyzing the advantages and disadvantages of this technique in renal image processing. In addition, this paper gives an outlook on the development trend of Transformer in renal image processing, which provides a valuable reference for a lot of renal image analysis. [ABSTRACT FROM AUTHOR]

UAV transmission tower inspection is the use of UAV technology for regular inspection and troubleshooting of towers on transmission lines, which helps to improve the safety and reliability of transmission lines and ensures the stability of the power supply. From the traditional manual tower boarding to the current way of manually selecting target camera shooting points from 3D point clouds to plan the inspection path of the UAV, operational efficiency has drastically improved. However, indoor planning work is still labor-consuming and expensive. In this paper, a deep learning-based point cloud transmission tower segmentation (PCTTS) model combined with the corresponding target point localization algorithm is proposed for automatic segmentation of transmission tower point cloud data and automatically localizing the key inspection component as the target point for UAV inspection. First, we utilize octree sampling with unit ball normalization to simplify the data and ensure translation invariance before putting the data into the model. In the feature extraction stage, we encode the point set information and combine Euclidean distance and cosine similarity features to ensure rotational invariance. On this basis, we adopt multi-scale feature extraction, construct a local coordinate system, and introduce the offset-attention mechanism to enhance model performance further. Then, after the feature propagation module, gradual up-sampling is used to obtain the features of each point to complete the point cloud segmentation. Finally, combining the segmentation results with the target point localization algorithm completes the automatic extraction of UAV inspection target points. The method has been applied to six kinds of transmission tower point cloud data of part segmentation results and three kinds of transmission tower point cloud data of instance segmentation results. The experimental results show that the model achieves mIOU of 94.1% on the self-built part segmentation dataset and 86.9% on the self-built instance segmentation dataset, and the segmentation accuracy outperforms that of the methods for point cloud segmentation, such as PointNet++, DGCNN, Point Transformer, and PointMLP. Meanwhile, the experimental results of UAV inspection target point localization also verify the method's effectiveness in this paper. [ABSTRACT FROM AUTHOR]

Salient object detection (SOD) aims to identify the most visually striking objects in a scene, simulating the function of the biological visual attention system. The attention mechanism in deep learning is commonly used as an enhancement strategy which enables the neural network to concentrate on the relevant parts when processing input data, effectively improving the model's learning and prediction abilities. Existing saliency object detection methods based on RGB deep learning typically treat all regions equally by using the extracted features, overlooking the fact that different regions have varying contributions to the final predictions. Based on the U2Net algorithm, this paper incorporates the split coordinate channel attention (SCCA) mechanism into the feature extraction stage. SCCA conducts spatial transformation in width and height dimensions to efficiently extract the location information of the target to be detected. While pixel-level semantic segmentation based on annotation has been successful, it assigns the same weight to each pixel which leads to poor performance in detecting the boundary of objects. In this paper, the Canny edge detection loss is incorporated into the loss calculation stage to improve the model's ability to detect object edges. Based on the DUTS and HKU-IS datasets, experiments confirm that the proposed strategies effectively enhance the model's detection performance, resulting in a 0.8% and 0.7% increase in the F1-score of U2Net. This paper also compares the traditional attention modules with the newly proposed attention, and the SCCA attention module achieves a top-three performance in prediction time, mean absolute error (MAE), F1-score, and model size on both experimental datasets. [ABSTRACT FROM AUTHOR]

This paper introduces a novel face photo-to-sketch synthesis method using a multi-scale feature-enhanced generative adversarial network (MFEGAN). The MFEGAN framework captures features at various scales through a multi-scale feature extraction module, enhanced by an attention mechanism. An improved attention residual block in the generator adaptively refines deep image features, improving overall quality. A pre-trained feature extraction network extracts and fuses face-specific features, enriching identity information. Multi-scale perceptual and focal frequency losses optimize detail quality, aligning with human perception. Experimental results show that MFEGAN outperforms existing methods in visual appeal and fidelity to original identity features. [ABSTRACT FROM AUTHOR]

Accurate power load forecasting is crucial for the sustainable operation of smart grids. However, the complexity and uncertainty of load, along with the large-scale and high-dimensional energy information, present challenges in handling intricate dynamic features and long-term dependencies. This paper proposes a computational approach to address these challenges in short-term power load forecasting and energy information management, with the goal of accurately predicting future load demand. The study introduces a hybrid method that combines multiple deep learning models, the Gated Recurrent Unit (GRU) is employed to capture long-term dependencies in time series data, while the Temporal Convolutional Network (TCN) efficiently learns patterns and features in load data. Additionally, the attention mechanism is incorporated to automatically focus on the input components most relevant to the load prediction task, further enhancing model performance. According to the experimental evaluation conducted on four public datasets, including GEFCom2014, the proposed algorithm outperforms the baseline models on various metrics such as prediction accuracy, efficiency, and stability. Notably, on the GEFCom2014 dataset, FLOP is reduced by over 48.8%, inference time is shortened by more than 46.7%, and MAPE is improved by 39%. The proposed method significantly enhances the reliability, stability, and cost-effectiveness of smart grids, which facilitates risk assessment optimization and operational planning under the context of information management for smart grid systems. [ABSTRACT FROM AUTHOR]

Accurate prediction of wind power is crucial for the efficient operation and risk management of wind farms. This paper introduces a deep learning model for wind power prediction that integrates an Attention mechanism with a convolutional neural network (CNN) and a gated recurrent unit (GRU) neural network. Addressing the randomness, intermittency, volatility and uncertainty of wind speed, we first apply swarm decomposition (SWD) to preprocess the original wind power data into subsequences. Subsequently, the CNN extracts spatial features, and the GRU identifies temporal correlations. The Attention mechanism enhances feature significance, further optimizing prediction accuracy. Complex error sequences generated by the CNN–GRU–Attention (CGA) model are corrected using the autoregressive integrated moving average (ARIMA). We evaluated the model’s performance using three wind power datasets against 16 other models, employing six evaluation indices (MSE, RMSE, MAPE, Theil’s U, TIC and SPL) and the Diebold–Mariano (DM) test and model confidence set (MCS) for model testing. Our results demonstrate the proposed model’s superior accuracy and efficiency in predicting wind power. [ABSTRACT FROM AUTHOR]

Deep learning has shown superior performance in various applications. The emergence of graph convolution neural networks (GCNs) enables deep learning to learn the latent representation from graph-structured data with rich attributes. To be specific, the message passing mechanism of GCNs can aggregate and update messages through the topological relationship between nodes in a graph. The graph attention network (GAT) introduces the attention mechanism into GCNs when aggregating messages and achieves significant performance on the node classification task. However, focusing on each node in the neighborhood, GAT becomes extremely complex. In addition, although stacking network layers could obtain a wider receptive field, it also brings high time cost and leads to the difficulty of training. To handle this problem, this paper only divides the messages into two types, i.e. self message and neighborhood message. The neighborhood message comes from the neighborhood with(out) self-loop while the self message comes from the node itself. Then, we design a light attention mechanism that only focuses on two weights, one for the self message, and the other for the neighborhood message, to adaptively reveal the different contributions of messages from a node as well as its neighborhood. In addition, we also adopt linear propagation, a shallow and efficient method, to aggregate messages from distant neighbors and thus obtain a wider neighborhood receiving field. To verify the effectiveness of our proposed approach, extensive experiments have been conducted on the semi-supervised node classification task. Results show that our proposed approach achieves comparable or even better performance than the baseline methods with complicated GCN structures on the benchmark datasets. Specifically, the proposed light attention mechanism focusing on message passing exhibits a great efficiency improvement with the training time cost less than half of GAT. [ABSTRACT FROM AUTHOR]

Whenever there is too much information out there, it is desirable to summarize. If humans are trying to create the summary, it will take lot of time. Now to make the problem of summarizing information easier and more effortless one can automate the summarization process which can reduce the time taken in creating summary. This is called as automatic summarization. The two ways of summarization are extractive summarization and abstractive summarization. Extractive summarization and its applications have been the subject of extensive research and have received state of art solution. But abstractive summarization still is a progressive field as it is difficult to create abstractive summary as humans do. Also, it is still a question i.e., how to evaluate the quality of a summary? Therefore, this paper is a comprehensive survey on the dataset used with its details and statistics, analysis of various abstractive summarization techniques and important parameters for evaluating the quality of summary. Deep leaning based models have given new direction in this field. The author also focuses on problems and challenges faced in the generation of summary which are opening the future research scope in this domain. [ABSTRACT FROM AUTHOR]

The advancement of pneumonia detection technology is crucial for the automation and the enhancement of diagnostic accuracy in pneumonia. Recent developments have seen the application of automatic detection methods utilizing deep learning in medical imaging. However, the diagnosis of pneumonia is often hampered by the small size and indistinct boundaries of lesions. To enhance diagnostic efficiency and mitigate errors due to human factors, this paper introduces an improved pneumonia detection algorithm, YOLOv5-TAF. First, the incorporation of the Triplet Attention module into the backbone network establishes inter-dimension dependencies, augmenting model accuracy. Second, Adaptive Spatial Feature Fusion (ASFF) is employed to dynamically learn and apply spatial weights to each scale feature map, effectively filtering out conflicting information and enhancing the network's capability to integrate features of varying scales. Additionally, the substitution of the original activation function with FReLU increases the sensitivity of the activation space and markedly improves image quality. Comprehensive experimental analyses on the Chest X-Ray Images dataset have demonstrated that the YOLOv5-TAF algorithm achieves a mean Average Precision (mAP) of 91.71%, which is 3.57% higher than the YOLOv5s algorithm, with a detection speed of 58.72 frames/s. When compared with faster-RCNN, SSD, YOLOv8s, and other object detection algorithms, YOLOv5-TAF shows superior practicability in pneumonia detection. [ABSTRACT FROM AUTHOR]

In aerial image detection, difficulties in feature extraction and low detection accuracy arise due to background interference, occlusion, and the presence of multiple small objects. This paper proposes a DM-YOLOX aerial object target detection method with intensive attention mechanism. Firstly, the proposed approach incorporates coordinate attention (CA) and a dense connection method into the backbone network architecture, enabling adaptive channel weighting throughout the feature extraction process. This facilitates the enhancement of significant features while suppressing less relevant ones, thereby augmenting the network's capacity to represent object features and ensuring retention and reinforcement of key features. Secondly, the multibranch extraction module (MBE) is incorporated into the feature fusion network to enhance the network's ability in extracting multi-scale feature information from images with extensive coverage, thereby enhancing the detection accuracy and efficiency of small- and medium-sized objects in complex scenes. Finally, the utilization of SIoU instead of IoU as the bounding box loss function effectively addresses the issue of mismatch between real and predicted boxes, leading to accelerated network convergence and improved performance during model training. After training and testing on the VisDrone 2019 dataset, this method effectively detects small objects in complex environments. The DM-YOLOX model shows a significant improvement of 2.7% in mAP compared to the baseline network, while achieving an 8% increase in frames per second (FPS). [ABSTRACT FROM AUTHOR]

Due to the rapid advancement of GPU computing, deep learning has lately been widely used in image denoising. Most deep learning methods require noise-free images as labels, which are often difficult or impossible to obtain. Therefore, denoising network models have to be trained with a pair of noisy and low-noise images. However, the restored images still face the problem of losing detail information. In this paper, we propose a novel denoising network model based on the concept of Noise2Noise (N2N), where pairs of noisy images are utilized to train a neural network that can learn the noise distribution relationship between them. This newly-proposed model (RA-UNet) draws inspiration from the classical UNet architecture and is designed with a multi-Residual convolutional block with Attention that can adapt different scales to mine the key information of images and recover clearer images. The denoising performance of RA-UNet is comparable and better than that of the conventional CBM3D, while the proposed RA-UNet performs significantly better on both PSNR and SSIM with less 2.5 % FLOPs and less 3 % running time compared to existing deep learning-based methods, such as DnCNN and ADNet. From the perspective of visual quality, RA-UNet can restore images with higher clarity. Compared with the UNet model, our model improves the average PSNR and SSIM obtained by testing Gaussian noise ( σ = 50 ) images on four classic datasets by 2.28 dB and 0.0552, respectively. [ABSTRACT FROM AUTHOR]

Ship detection and identification play pivotal roles in ensuring navigation safety and facilitating efficient maritime traffic management. Aiming at ship detection in complex environments, which often faces problems such as the dense occlusion of ship targets, low detection accuracy, and variable environmental conditions, in this paper, we propose a ship detection algorithm CSD-YOLO (Context guided block module, Slim-neck, Deformable large kernel attention-You Only Look Once) based on the deformable large kernel attention (D-LKA) mechanism, which was improved based on YOLOv8 to enhance its performance. This approach integrates several innovations to bolster its performance. Initially, the utilization of the Context Guided Block module (CG block) enhanced the c2f module of the backbone network, thereby augmenting the feature extraction capabilities and enabling a more precise capture of the key image information. Subsequently, the introduction of a novel neck architecture and the incorporation of the slim-neck module facilitated more effective feature fusion, thereby enhancing both the accuracy and efficiency of detection. Furthermore, the algorithm incorporates a D-LKA mechanism to dynamically adjust the convolution kernel shape and size, thereby enhancing the model's adaptability to varying ship target shapes and sizes. To address data scarcity in complex marine environments, the experiments utilized a fused dataset comprising the SeaShips dataset and a proprietary dataset. The experimental results demonstrate that the CSD-YOLO algorithm outperformed the YOLOv8n algorithm across all model evaluation metrics. Specifically, the precision rate (precision) was 91.5%, the recall rate (recall) was 89.5%, and the mean accuracy (mAP) was 91.5%. Compared to the benchmark algorithm, the Recall was improved by 0.7% and the mAP was improved by 0.4%. These results indicate that the CSD-YOLO algorithm can effectively meet the requirements for ship target recognition and tracking in complex marine environments. [ABSTRACT FROM AUTHOR]

In this paper, we present a novel paradigm for disease detection. We build an artificial intelligence based system where various biomedical data are retrieved from distributed and homogeneous sensors. We use different deep learning architectures (VGG16, RESNET, and DenseNet) with ensemble learning and attention mechanisms to study the interactions between different biomedical data to detect and diagnose diseases. We conduct extensive testing on biomedical data. The results show the benefits of using deep learning technologies in the field of artificial intelligence of medical things to diagnose diseases in the healthcare decision‐making process. For example, the disease detection rate using the proposed methodology achieves 92%, which is greatly improved compared to the higher‐level disease detection models. [ABSTRACT FROM AUTHOR]

As an enhanced version of standard CAN, the Controller Area Network with Flexible Data (CAN-FD) rate is vulnerable to attacks due to its lack of information security measures. However, although anomaly detection is an effective method to prevent attacks, the accuracy of detection needs further improvement. In this paper, we propose a novel intrusion detection model for the CAN-FD bus, comprising two sub-models: Anomaly Data Detection Model (ADDM) for spotting anomalies and Anomaly Classification Detection Model (ACDM) for identifying and classifying anomaly types. ADDM employs Long Short-Term Memory (LSTM) layers to capture the long-range dependencies and temporal patterns within CAN-FD frame data, thus identifying frames that deviate from established norms. ACDM is enhanced with the attention mechanism that weights LSTM outputs, further improving the identification of sequence-based relationships and facilitating multi-attack classification. The method is evaluated on two datasets: a real-vehicle dataset including frames designed by us based on known attack patterns, and the CAN-FD Intrusion Dataset, developed by the Hacking and Countermeasure Research Lab. Our method offers broader applicability and more refined classification in anomaly detection. Compared with existing advanced LSTM-based and CNN-LSTM-based methods, our method exhibits superior performance in detection, achieving an improvement in accuracy of 1.44% and 1.01%, respectively. [ABSTRACT FROM AUTHOR]

Interactive devices such as touch screens have gained widespread usage in daily life; this has directed the attention of researchers to the quality of screen glass. Consequently, defect detection in screen glass is essential for improving the quality of smartphone screens. In recent years, defect detection methods based on deep learning have played a crucial role in improving detection accuracy and robustness. However, challenges have arisen in achieving high-performance detection due to the small size, irregular shapes and low contrast of defects. To address these challenges, this paper proposes CE-SGNet, a Context-Enhanced Network with a Spatial-aware Graph, for smartphone screen defect detection. It consists of two novel components: the Adaptive Receptive Field Attention Module (ARFAM) and the Spatial-aware Graph Reasoning Module (SGRM). The ARFAM enhances defect features by adaptively extracting contextual information to capture the most relevant contextual region of defect features. The SGRM constructs a region-to-region graph and encodes region features with spatial relationships. The connections among defect regions are enhanced during the propagation process through a graph attention network. By enriching the feature representations of defect regions, the CE-SGNet can accurately identify and locate defects of various shapes and scales. Experimental results demonstrate that the CE-SGNet achieves outstanding performance on two public datasets. [ABSTRACT FROM AUTHOR]

Dongba characters are ancient ideographic scripts with abstract expressions that differ greatly from modern Chinese characters; directly applying existing methods cannot achieve the font style transfer of Dongba characters. This paper proposes an Attention-based Font style transfer Generative Adversarial Network (AFGAN) method. Based on the characteristics of Dongba character images, two core modules are set up in the proposed AFGAN, namely void constraint and font stroke constraint. In addition, in order to enhance the feature learning ability of the network and improve the style transfer effect, the Convolutional Block Attention Module (CBAM) mechanism is added in the down-sampling stage to help the network better adapt to input font images with different styles. The quantitative and qualitative analyses of the generated font and the real font were conducted by consulting with professional artists based on the newly built small seal script, slender gold script, and Dongba character dataset, and the styles of the small seal script and slender gold script were transferred to Dongba characters. The results indicate that the proposed AFGAN method has advantages in evaluation indexes and visual quality compared to existing networks. At the same time, this method can effectively learn the style features of small seal script and slender gold script, and transfer them to Dongba characters, indicating the effectiveness of this method. [ABSTRACT FROM AUTHOR]

Structural health monitoring for roads is an important task that supports inspection of transportation infrastructure. This paper explores deep learning techniques for crack detection in road images and proposes an automatic pixel-level semantic road crack image segmentation method based on a Swin transformer. This method employs Swin-T as the backbone network to extract feature information from crack images at various levels and utilizes the texture unit to extract the texture and edge characteristic information of cracks. The refinement attention module (RAM) and panoramic feature module (PFM) then merge these diverse features, ultimately refining the segmentation results. This method is called FetNet. We collect four public real-world datasets and conduct extensive experiments, comparing FetNet with various deep-learning methods. FetNet achieves the highest precision of 90.4%, a recall of 85.3%, an F1 score of 87.9%, and a mean intersection over union of 78.6% on the Crack500 dataset. The experimental results show that the FetNet approach surpasses other advanced models in terms of crack segmentation accuracy and exhibits excellent generalizability for use in complex scenes. [ABSTRACT FROM AUTHOR]

The application of neural networks in wheat ear detection and counting in smart agriculture holds significant value, showcasing how artificial intelligence technology brings innovation and improvement to the agricultural sector. However, due to the high density, variety, and complex growth cycles of wheat ears, as well as the influence of complex backgrounds during detection, issues such as false positives, false negatives, and low detection rates may arise. Addressing these challenges, this paper proposes a wheat ear detection solution based on the FasterCANet-YOLOv8s algorithm. Firstly, the FasterCANet Block is introduced to enhance the speed of wheat detection. Secondly, an efficient network structure, the QAFPN model, is proposed to strengthen the Neck network, achieving a balance between speed and accuracy in wheat detection. Finally, to better capture the features of small targets, the RFB Block is introduced to improve the SPPF layer. The improved algorithm achieves an mAP@0.5 of 94.4%, surpassing existing technologies. Our model can accurately and quickly locate targets, holding tremendous potential in the wheat cultivation domain and providing efficient and precise support for agricultural production. [ABSTRACT FROM AUTHOR]

This paper presents a novel multi-scale attention residual network (MAResNet) for diagnosing patients with pulmonary tuberculosis (PTB) by computed tomography (CT) images. First, a three-dimensional (3D) network structure is applied in MAResNet based on the continuity and correlation of nodal features on different slices of CT images. Secondly, MAResNet incorporates the residual module and Convolutional Block Attention Module (CBAM) to reuse the shallow features of CT images and focus on key features to enhance the feature distinguishability of images. In addition, multi-scale inputs can increase the global receptive field of the network, extract the location information of PTB, and capture the local details of nodules. The expression ability of both high-level and low-level semantic information in the network can also be enhanced. The proposed MAResNet shows excellent results, with overall 94% accuracy in PTB classification. MAResNet based on 3D CT images can assist doctors make more accurate diagnosis of PTB and alleviate the burden of manual screening. In the experiment, a called Grad-CAM was employed to enhance the class activation mapping (CAM) technique for analyzing the model's output, which can identify lesions in important parts of the lungs and make transparent decisions. [ABSTRACT FROM AUTHOR]

Assessing the strength of complex networks is crucial for evaluating their functionality and monitoring system security. Two primary perspectives for measuring network robustness are connectivity and controllability, which quantify how well a network maintains connectivity and controllability after experiencing complete attacks. However, conventional robustness calculation methods that use simulation attacks can be impractical for large-scale networks. Recent research has explored the use of deep learning methods for network robustness prediction, including PCR (short for predictor of controllability robustness), which uses a VGG (short for visual geometry group)-based convolutional neural network (CNN) and a linear filter. However, PCR has limitations, including inaccurate edge importance differentiation and fluctuating output curves. This paper presents ATTRP, an attention-based robustness predictor, which addresses these limitations. ATTRP uses a novel convolutional neural network with channel and spatial attention mechanisms to improve prediction accuracy and a robustness filter based on Savitzky–Golay smoothing to rectify the robustness curve. Experimental studies demonstrate that ATTRP outperforms other predictors, with much lower errors, while its computational speed is far superior to that of traditional attacking simulation. Overall, our research provides a more effective and efficient means of predicting network robustness, with potential applications in monitoring system security. [ABSTRACT FROM AUTHOR]

To address the low segmentation accuracy of multifidus muscle lesion sites in MRI images of patients with lumbar disc herniation, this paper proposes a new model to improve the U2-Net network with the goal that the encoding and decoding subnetworks are interconnected by a series of nested jump paths. To reduce the semantic missing of feature maps in the encoding and decoding subnetworks, the jump connections in the middle of RSU-7,RSU-6,RSU-5,and RSU-4 in the U2-Net model are redesigned, while the RSU-4F part remains unchanged. In addition, the channel attention module is added to enable the net to focus on channels of higher contribution to task, thus extract high quality multifractal muscle features. The experiments on the multifidus muscle MRI image dataset show that the improved U2-Net outperforms U-Net,U2-Net and U-Net++ network in indicators of Dice, HD and MIoU. It can be concluded that the proposed approach has good performance on MRI image segmentation of multifidus muscle, which can assist doctors to make diagnosis. [ABSTRACT FROM AUTHOR]

Transportation mode recognition is an important and challenging problem in intelligent transportation systems. For decades, many data mining and deep learning methods have been proposed, but all these methods have some deficiencies and do not fully use temporal and spatial information hidden in raw GPS trajectory data. In this paper, we presented a new deep learning model called TSANET, which designs an attention mechanism to combine global and local spatiotemporal features. The input of the model is seven kinematic features, derived from the GPS trajectories and covers all information hidden in the GPS points. The model adopts TCN and ST-Block to extract global and local spatiotemporal features, respectively. In ST-Block, BiGRU is used to capture temporal features and DenseNet is applied to capture spatial features. In TCN, convolution operations are applied to obtain temporal and spatial information. Moreover, a dual-layer attention mechanism is developed to integrate and reconstruct these features by assigning different weights to global and local spatiotemporal features caught by TCN and ST-Block. By comprehensively considering global and local features, the model can greatly improve classification performance and recognition granularity, and with the further introduction of the attention mechanism, it can identify all transportation modes in a fine-grained manner. At last, the experiments have been conducted on the Geo1 and Geo2 datasets used by many researchers. The experimental results show that our model cannot only achieve the highest accuracy of 94.34 % among all recent methods but also identify all seven transportation modes clearly, thus verifying the advantages and effectiveness of the model. [ABSTRACT FROM AUTHOR]

Traditional fish farming methods suffer from backward production, low efficiency, low yield, and environmental pollution. As a result of thorough research using deep learning technology, the industrial aquaculture model has experienced gradual maturation. A variety of complex factors makes it difficult to extract effective features, which results in less-than-good model performance. This paper proposes a fish detection method that combines a triple attention mechanism with a You Only Look Once (TAM-YOLO)model. In order to enhance the speed of model training, the process of data encapsulation incorporates positive sample matching. An exponential moving average (EMA) is incorporated into the training process to make the model more robust, and coordinate attention (CA) and a convolutional block attention module are integrated into the YOLOv5s backbone to enhance the feature extraction of channels and spatial locations. The extracted feature maps are input to the PANet path aggregation network, and the underlying information is stacked with the feature maps. The method improves the detection accuracy of underwater blurred and distorted fish images. Experimental results show that the proposed TAM-YOLO model outperforms YOLOv3, YOLOv4, YOLOv5s, YOLOv5m, and SSD, with a mAP value of 95.88%, thus providing a new strategy for fish detection. [ABSTRACT FROM AUTHOR]

It is of great significance to accurately grasp ground-level ozone concentration on a wide scale in order to cope with the increasingly serious ground-level ozone pollution problem. Currently, satellite technology can be used to monitor ground-level ozone concentration on a wide scale, but there is the problem of insufficient spatial resolution. The use of ground monitoring stations to detect ground-level ozone concentration can obtain more accurate ozone concentration around the station, but there are problems of limited number of stations and sparse distribution. Therefore, it is still a challenge to accurately grasp the ground-level ozone concentration at a large scale and high spatial resolution. To address this issue, this paper proposes a ground-level ozone concentration inversion algorithm based on deep learning methods, incorporating data from remote sensing satellites, ground monitoring stations, meteorological conditions, geography, and land use. Taking Yunnan Province in China as the experimental region and utilizing five-fold cross-validation, the model's Mean Square Error (MSE) reached 340.45 and Root Mean Square Error (RMSE) reached 18.45. Compared to machine learning models, the error decreased by 14.53%, outperforming Random Forest models, Convolution Neural Networks, and Vision Transformers. This study offers a referential approach for accurately capturing ground-level ozone concentrations at a large scale with high spatial resolution. [ABSTRACT FROM AUTHOR]

Time series data are prevalent in the real world, particularly playing a crucial role in key domains such as meteorology, electricity, and finance. Comprising observations at historical time points, these data, when subjected to in-depth analysis and modeling, enable researchers to predict future trends and patterns, providing support for decision making. In current research, especially in the analysis of long time series, effectively extracting and integrating long-term dependencies with short-term features remains a significant challenge. Long-term dependencies refer to the correlation between data points spaced far apart in a time series, while short-term features focus on more recent changes. Understanding and combining these two features correctly are crucial for constructing accurate and reliable predictive models. To efficiently extract and integrate long-term dependencies and short-term features in long time series, this paper proposes a pyramid attention structure model based on multi-scale feature extraction, referred to as the MSFformer model. Initially, a coarser-scale construction module is designed to obtain coarse-grained information. A pyramid data structure is constructed through feature convolution, with the bottom layer representing the original data and each subsequent layer containing feature information extracted across different time step lengths. As a result, nodes higher up in the pyramid integrate information from more time points, such as every Monday or the beginning of each month, while nodes lower down retain their individual information. Additionally, a Skip-PAM is introduced, where a node only calculates attention with its neighboring nodes, parent node, and child nodes, effectively reducing the model's time complexity to some extent. Notably, the child nodes refer to nodes selected from the next layer by skipping specific time steps. In this study, we not only propose an innovative time series prediction model but also validate the effectiveness of these methods through a series of comprehensive experiments. To comprehensively evaluate the performance of the designed model, we conducted comparative experiments with baseline models, ablation experiments, and hyperparameter studies. The experimental results demonstrate that the MSFformer model improves by 35.87% and 42.6% on the MAE and MSE indicators, respectively, compared to traditional Transformer models. These results highlight the outstanding performance of our proposed deep learning model in handling complex time series data, particularly in capturing long-term dependencies and integrating short-term features. [ABSTRACT FROM AUTHOR]

Surface defects on the permanent magnetic ferrite magnet rotor are the primary cause for the decline in performance and safety hazards in permanent magnet motors. Machine-vision methods offer the possibility to identify defects automatically. In response to the challenges in the permanent magnetic ferrite magnet rotor, this study proposes an improved You Only Look Once (YOLO) algorithm named SAB-YOLOv5. Utilizing a line-scan camera, images capturing the complete surface of a general object are obtained, and a dataset containing surface defects is constructed. Simultaneously, an improved YOLOv5-based surface defect algorithm is introduced. Firstly, the algorithm enhances the capability to extract features at different scales by incorporating the Atrous Spatial Pyramid Pooling (ASPP) structure. Then, the fusion of features is improved by combining the tensor concatenation operation of the feature-melting network with the Bidirectional Feature Pyramid Network (BiFPN) structure. Finally, the introduction of the spatial pyramid dilated (SPD) convolutional structure into the backbone network and output end enhances the detection performance for minute defects on the target surface. In the study, the SAB-YOlOv5 algorithm shows an obvious increase from 84.2% to 98.3% in the mean average precision (mAP) compared to that of the original YOLOv5 algorithm. The results demonstrate that the data acquisition method and detection algorithm designed in this paper effectively enhance the efficiency of defect detection permanent magnetic ferrite magnet rotors. [ABSTRACT FROM AUTHOR]

The image outpainting based on deep learning shows good performance and has a wide range of applications in many fields. The previous image outpainting methods mostly used a single image as input. In this paper, we use the left and right images as input images, and expand the unknown region in the middle to generate an image that connects the left and right images to form a complete semantically smooth image. A cascaded refinement residual attention model for image outpainting is proposed. The Residual Channel-Spatial Attention (RCSA) module is designed to effectively learn image information about known regions. The Cascaded Dilated-conv (CDC) module is used to capture deep features, and more semantic information is obtained through dilated convolutions of different rates. The Refine on Features Aggregation (RFA) module connects the encoder and decoder to refine the result image for generating it clearer and smoother. Experimental results show that the proposed model is able to hallucinate more meaningful structures and vivid textures and achieve satisfactory results. [ABSTRACT FROM AUTHOR]

This paper suggests a text emotion analysis approach built on the BMCBMA model for use in an online education environment aiming at the issues of poor text utilization, challenge in effective information extraction, and a failure to effectively recognize word polysemy in existing text emotion analysis task research. Initially, a language model is constructed using Bidirectional Encoder Representations from Transformers (BERT) pre-training. The word vector trained by BERT pre-training is selected to supplant the word vector trained in the conventional manner, and the semantic vector is generated dynamically using the context of the word. Second, the Bi-directional Long Short-Term Memory (BiLSTM) model is employed to record semantic information by simultaneously integrating both positive and negative orientations to assess the emotional polarity information for every text in its entirety. The Multi-channel Convolutional Neural Networks (CNN) model is then utilized to derive textual local feature information of text. Lastly, the attention mechanism is used to cause all types of features to interact and to derive a deeper semantic association within the context. Experiments indicate that the suggested method has accuracy, F1, recall, and precision values of 0.915, 0.911, 0.915 and 0.908, correspondingly. The suggested approach performs significantly better in text emotion analysis than the comparison method. [ABSTRACT FROM AUTHOR]

Accurately forecasting short-term traffic flow is essential for intelligent transportation systems. However, current methods often struggle to fully exploit implicit variation patterns and heterogeneous correlations in traffic flow data, and can be sensitive to non-Gaussian noise. In this paper, we propose a novel noise-immune and attention-based multi-modal model (NIAMNet) for short-term traffic flow forecasting. Inspired by the success of computer vision techniques, NIAMNet transforms one-dimensional traffic flow into images and embeds residual dual-attention blocks (RDB) to extract in-deep features. Besides, we introduce a dynamic noise-immune loss to address the impact of noise and outliers on model performance. Experimental results on four real-world benchmark datasets demonstrate the superiority of NIAMNet over existing methods, achieving the lowest MAPE (10.43, 9.79, 10.51, and 11.01) and RMSE (247.13, 192.36, 208.40, and 150.01). Additional ablation experiments are carried out to provide insight into the significance of each component. Our approach contributes to the development of more accurate and robust short-term traffic flow forecasting models. [ABSTRACT FROM AUTHOR]

Dynamic monitoring of cropland using high spatial resolution remote sensing images is a powerful means to protect cropland resources. However, when a change detection method based on a convolutional neural network employs a large number of convolution and pooling operations to mine the deep features of cropland, the accumulation of irrelevant features and the loss of key features will lead to poor detection results. To effectively solve this problem, a novel cropland change detection network (CroplandCDNet) is proposed in this paper; this network combines an adaptive receptive field and multiscale feature transmission fusion to achieve accurate detection of cropland change information. CroplandCDNet first effectively extracts the multiscale features of cropland from bitemporal remote sensing images through the feature extraction module and subsequently embeds the receptive field adaptive SK attention (SKA) module to emphasize cropland change. Moreover, the SKA module effectively uses spatial context information for the dynamic adjustment of the convolution kernel size of cropland features at different scales. Finally, multiscale features and difference features are transmitted and fused layer by layer to obtain the content of cropland change. In the experiments, the proposed method is compared with six advanced change detection methods using the cropland change detection dataset (CLCD). The experimental results show that CroplandCDNet achieves the best F1 and OA at 76.04% and 94.47%, respectively. Its precision and recall are second best of all models at 76.46% and 75.63%, respectively. Moreover, a generalization experiment was carried out using the Jilin-1 dataset, which effectively verified the reliability of CroplandCDNet in cropland change detection. [ABSTRACT FROM AUTHOR]

The recognition of steel microstructure images plays a crucial role in the metallographic analysis process. Although some progress has been made through the application of artificial intelligence algorithms, several challenges remain. First, existing algorithms exhibit weak nonlinear feature extraction capabilities and noticeable limitations. Second, they overlook the intrinsic noise and redundant interference present in microscopic images. To address these issues, this paper investigates the automatic recognition of metallographic tissues by leveraging residual structures in deep neural networks. An enhanced residual network model based on transfer learning is proposed, which utilizes the pre-trained weights from the ImageNet dataset to facilitate learning with small sample data. This network offers higher classification accuracy and higher F1 scores. In addition, a deep residual shrinkage network model based on an attention mechanism is proposed. This model incorporates an attention sub-network into the original residual module and employs a soft threshold function to eliminate redundant features, including noise. The proposed algorithms are evaluated against various convolutional neural networks using 20 types of metallographic test sets. The experimental results showed that both methods have high accuracy rates of 95% and 94.44%, respectively, and F1 scores of 0.9464 and 0.9419. While maintaining the complexity of the model, there has been a significant improvement in accuracy, and the models exhibit strong generalization capabilities. Our research contributes to enhancing production efficiency, strengthening quality control, and improving material performance through computer vision technology. [ABSTRACT FROM AUTHOR]

This paper presents a novel U-Net model incorporating a hybrid attention mechanism for automating the segmentation of sub-retinal layers in Optical Coherence Tomography (OCT) images. OCT is an ophthalmology tool that provides detailed insights into retinal structures. Manual segmentation of these layers is time-consuming and subjective, calling for automated solutions. Our proposed model combines edge and spatial attention mechanisms with the U-Net architecture to improve segmentation accuracy. By leveraging attention mechanisms, the U-Net focuses selectively on image features. Extensive evaluations using datasets demonstrate that our model outperforms existing approaches, making it a valuable tool for medical professionals. The study also highlights the model's robustness through performance metrics such as an average Dice score of 94.99%, Adjusted Rand Index (ARI) of 97.00%, and Strength of Agreement (SOA) classifications like "Almost Perfect", "Excellent", and "Very Strong". This advanced predictive model shows promise in expediting processes and enhancing the precision of ocular imaging in real-world applications. [ABSTRACT FROM AUTHOR]

Enhancers play an important role in the process of gene expression regulation. In DNA sequence abundance or absence of enhancers and irregularities in the strength of enhancers affects gene expression process that leads to the initiation and propagation of diverse types of genetic diseases such as hemophilia, bladder cancer, diabetes and congenital disorders. Enhancer identification and strength prediction through experimental approaches is expensive, time-consuming and error-prone. To accelerate and expedite the research related to enhancers identification and strength prediction, around 19 computational frameworks have been proposed. These frameworks used machine and deep learning methods that take raw DNA sequences and predict enhancer's presence and strength. However, these frameworks still lack in performance and are not useful in real time analysis. This paper presents a novel deep learning framework that uses language modeling strategies for transforming DNA sequences into statistical feature space. It applies transfer learning by training a language model in an unsupervised fashion by predicting a group of nucleotides also known as k-mers based on the context of existing k-mers in a sequence. At the classification stage, it presents a novel classifier that reaps the benefits of two different architectures: convolutional neural network and attention mechanism. The proposed framework is evaluated over the enhancer identification benchmark dataset where it outperforms the existing best-performing framework by 5%, and 9% in terms of accuracy and MCC. Similarly, when evaluated over the enhancer strength prediction benchmark dataset, it outperforms the existing best-performing framework by 4%, and 7% in terms of accuracy and MCC. [ABSTRACT FROM AUTHOR]

Rare antinuclear antibody (ANA) pattern recognition has been a widely applied technology for routine ANA screening in clinical laboratories. In recent years, the application of deep learning methods in recognizing ANA patterns has witnessed remarkable advancements. However, the majority of studies in this field have primarily focused on the classification of the most common ANA patterns, while another subset has concentrated on the detection of mitotic metaphase cells. To date, no prior research has been specifically dedicated to the identification of rare ANA patterns. In the present paper, we introduce a novel attention-based enhancement framework, which was designed for the recognition of rare ANA patterns in ANA-indirect immunofluorescence images. More specifically, we selected the algorithm with the best performance as our target detection network by conducting comparative experiments. We then further developed and enhanced the chosen algorithm through a series of optimizations. Then, attention mechanism was introduced to facilitate neural networks in expediting the learning process, extracting more essential and distinctive features for the target features that belong to the specific patterns. The proposed approach has helped to obtained high precision rate of 86.40%, 82.75% recall, 84.24% F1 score and 84.64% mean average precision for a 9-category rare ANA pattern detection task on our dataset. Finally, we evaluated the potential of the model as medical technologist assistant and observed that the technologist's performance improved after referring to the results of the model prediction. These promising results highlighted its potential as an efficient and reliable tool to assist medical technologists in their clinical practice. [ABSTRACT FROM AUTHOR]

In recent years, deep learning techniques have been increasingly utilized to automate and reduce human errors in leukocyte classification. However, reliability and accuracy issues remain a challenge. This paper proposes CAB‐Net, an end‐to‐end deep learning‐based model that integrates a convolutional neural network with an attention mechanism and BLSTM. The model uses a stack of convolutional and pooling layers to extract initial features from input images, which are then fed into the attention block to generate class‐specific discriminative features and BLSTM employed to model deterministic class correlations between highlighted discriminative features and labels. Experimental results show that CAB‐Net outperforms state‐of‐the‐art methods in term of accuracy, precision, recall, F1‐Score, and AUC‐ROC. In addition, the CAB‐Net model demonstrates good performance even with low‐resolution images. Consequently, CAB‐Net can be considered as the current state‐of‐the‐art prediction model for improving leukocyte classification in clinical environments. [ABSTRACT FROM AUTHOR]

Deep learning shows great potential in low-light image enhancement, which can improve image brightness and contrast while keeping image natural. However, due to the lack of prior knowledge extracted manually or excessive amplification of noise, these methods result in poor quality of enhanced images. To solve these challenging problems, this paper proposes a dual-branch grayscale image enhancement network based on dense residual and attention mechanism. Low-light grayscale image is used as input. Firstly, features that fuse deep and shallow information are extracted through dense residual convolution branch network; secondly, texture features are extracted through U-Net branch network combined with attention mechanism; then the extracted features are integrated, and finally luminance is adjusted by a brightness adjustment module to output an enhanced grayscale image. In addition, a joint loss function is designed to measure the network training loss from brightness, texture, contrast and noise. A large number of quantitative and qualitative experiments on LOL and VE-LOL datasets show that the proposed method improves Peak Signal to Noise Ratio Index and Structural Similarity Index by 19.65 - 59.76% and 5.61 - 85.53%, respectively, compared with EnlightenGAN, KinD++, RUAS, LLFlow, etc. The proposed method is superior to the most famous methods, thanks to the deep feature extraction and fusion capability of dense residual convolutional network and texture extraction capability of U-Net network combined with attention mechanism. [ABSTRACT FROM AUTHOR]

In videos, anomaly detection is challenging due to its diverse nature in different application domains. Reconstruction and prediction-based methods have been widely employed to detect anomalies. Due to the generalization capability of a deep neural network, sometimes, it recreates irregular patterns along with regular ones. This paper presents a novel autoencoder-based framework called deep multiplicative attention-based autoencoder (DeMAAE) to detect anomalies in a video sequence. The global attention mechanism is used at the decoder side of DeMAAE for better feature learning during the decoding phase. An attention map is created by taking the dot product between all encoder's hidden states and the previously generated decoder's hidden state. After that, the final output of the decoder is determined by the context vector. The context vector is computed using the weighted summation of all encoder's hidden states and attention weight. DeMAAE delivers an improved runtime of 0.015 s (∼ 67 fps) for detecting anomalies during testing. Extensive experiments have been performed on the two diversified and widely used datasets (UCSD Pedestrian and CUHK Avenue) to compare the efficacy of DeMAAE with different state-of-the-art methods. [ABSTRACT FROM AUTHOR]

In recent years, deep learning networks have achieved prominent success in the field of multi-exposure image fusion. However, it is still challenging to prevent color distortion and blurry edges which leads to bad visual effects. In this paper, we present a multi-scale attention-guided network for multi-exposure image fusion in a coarse-to-fine manner. The network generates multi-scale enhanced attention weight maps of images in different sizes which possess vital details and can emphasize essential regions of interest from both sides. The multi-scale structure can extract features on different scales, and the bilayer structure can extract features from different image sizes. Moreover, we designed a coarse-to-fine attention module to finally generate the weight maps; the module combines channel attention with spatial attention. Fused results will be generated under the guidance of the weight maps. Qualitative and quantitative experiments are performed on a publicly available dataset which shows our method outperforms the state-of-the-art methods in visual effect and objective analysis. Also, ablation experiments prove each part of our method has a great advantage in generating images with significant details, prominent targets, and faithful color. [ABSTRACT FROM AUTHOR]

Multi-exposure fusion (MEF) is widely researched and applied to high dynamic range (HDR) imaging, where one of the most challenging problems is the artifacts caused by the motion of objects between input images. Recently, deep learning methods have been widely applied for HDR imaging with excellent results, showing significant advantages. However, many methods cannot avoid artifacts due to inaccurate alignment before merging HDR images. In this paper, we propose an end-to-end network (C-ED-GMNET) with a channel and spatial attention network, an encoder–decoder network and a gradual merging network for generating artifact-free HDR images in dynamic scenes. The attention module consists of two submodules to identify useful features and exclude harmful components in inputs from both channel and spatial dimensions, respectively. The attention-guided feature maps are sent to the encoders for further feature extraction, and then, the outputs are sent to a gradual merging module consisting of two steps to generate deep features progressively. Besides, the differences between the merged image and the original images are identified by applying global residual learning with all the inputs, and the merged image feature is recovered by the decoder to obtain the final HDR image. Quantitative and qualitative experiments on two public datasets show that the proposed C-ED-GMNET produces better results than existing state-of-the-art methods and significantly reduces the runtime due to the encoders which reduce the amount of computation. [ABSTRACT FROM AUTHOR]

The recognition of steel microstructure images plays a crucial role in the metallographic analysis process. Although some progress has been made through the application of artificial intelligence algorithms, several challenges remain. First, existing algorithms exhibit weak nonlinear feature extraction capabilities and noticeable limitations. Second, they overlook the intrinsic noise and redundant interference present in microscopic images. To address these issues, this paper investigates the automatic recognition of metallographic tissues by leveraging residual structures in deep neural networks. An enhanced residual network model based on transfer learning is proposed, which utilizes the pre-trained weights from the ImageNet dataset to facilitate learning with small sample data. This network offers higher classification accuracy and higher F1 scores. In addition, a deep residual shrinkage network model based on an attention mechanism is proposed. This model incorporates an attention sub-network into the original residual module and employs a soft threshold function to eliminate redundant features, including noise. The proposed algorithms are evaluated against various convolutional neural networks using 20 types of metallographic test sets. The experimental results showed that both methods have high accuracy rates of 95% and 94.44%, respectively, and F1 scores of 0.9464 and 0.9419. While maintaining the complexity of the model, there has been a significant improvement in accuracy, and the models exhibit strong generalization capabilities. Our research contributes to enhancing production efficiency, strengthening quality control, and improving material performance through computer vision technology. [ABSTRACT FROM AUTHOR]

Pipe jacking is a trenchless technology used to install buried pipelines, such as sewer lines in wastewater management systems. Existing mechanistic approaches based on geomaterial strength parameters (i.e., friction angle and apparent cohesion) can provide an estimation of the potential jacking forces during construction. However, extracting intact rock cores for strength characterisation is challenging when dealing with highly weathered 'soft rocks' which exhibit RQD values of zero. Such was the case for a pipe jacking drive traversing the highly weathered lithology underlying Kuching City, Malaysia. Furthermore, mechanistic approaches face limitations during construction when jacking forces are dependent on operation parameters, such as jacking speed and lubrication. To address these knowledge gaps, the primary objectives of this study are the development of rock strength parameters based on in situ pressuremeter testing for the purpose of estimating jacking forces. Furthermore, this study investigates the influence of various pipe jacking operation parameters, with a particular focus on their impact on jacking forces in weathered 'soft rocks'. To achieve this, a novel deep learning model with an attention mechanism is introduced. The proposed methods of rock strength parameters derived from pressuremeter testing and the utilisation of deep learning will help to provide insights into the key factors affecting the development of jacking forces. This paper successfully shows the use of in situ pressuremeter testing in developing Mohr–Coulomb (MC) parameters directly from the site. In addition, the developed deep learning model with an attention mechanism successfully highlights the significance of pipe jacking operation parameters with an accuracy of 88% in predicting the jacking forces. [ABSTRACT FROM AUTHOR]

In the domain of AI-driven healthcare, deep learning models have markedly advanced pneumonia diagnosis through X-ray image analysis, thus indicating a significant stride in the efficacy of medical decision systems. This paper presents a novel approach utilizing a deep convolutional neural network that effectively amalgamates the strengths of EfficientNetB0 and DenseNet121, and it is enhanced by a suite of attention mechanisms for refined pneumonia image classification. Leveraging pre-trained models, our network employs multi-head, self-attention modules for meticulous feature extraction from X-ray images. The model's integration and processing efficiency are further augmented by a channel-attention-based feature fusion strategy, one that is complemented by a residual block and an attention-augmented feature enhancement and dynamic pooling strategy. Our used dataset, which comprises a comprehensive collection of chest X-ray images, represents both healthy individuals and those affected by pneumonia, and it serves as the foundation for this research. This study delves deep into the algorithms, architectural details, and operational intricacies of the proposed model. The empirical outcomes of our model are noteworthy, with an exceptional performance marked by an accuracy of 95.19%, a precision of 98.38%, a recall of 93.84%, an F1 score of 96.06%, a specificity of 97.43%, and an AUC of 0.9564 on the test dataset. These results not only affirm the model's high diagnostic accuracy, but also highlight its promising potential for real-world clinical deployment. [ABSTRACT FROM AUTHOR]

Video-based peripheral oxygen saturation (SpO2) estimation, utilizing solely RGB cameras, offers a non-contact approach to measuring blood oxygen levels. Previous studies set a stable and unchanging environment as the premise for non-contact blood oxygen estimation. Additionally, they utilized a small amount of labeled data for system training and learning. However, it is challenging to train optimal model parameters with a small dataset. The accuracy of blood oxygen detection is easily affected by ambient light and subject movement. To address these issues, this paper proposes a contrastive learning spatiotemporal attention network (CL-SPO2Net), an innovative semi-supervised network for video-based SpO2 estimation. Spatiotemporal similarities in remote photoplethysmography (rPPG) signals were found in video segments containing facial or hand regions. Subsequently, integrating deep neural networks with machine learning expertise enabled the estimation of SpO2. The method had good feasibility in the case of small-scale labeled datasets, with the mean absolute error between the camera and the reference pulse oximeter of 0.85% in the stable environment, 1.13% with lighting fluctuations, and 1.20% in the facial rotation situation. [ABSTRACT FROM AUTHOR]

Semantic relatedness is one of the most significant aspects of natural language processing. It has been identified as a critical technology for developing intelligent systems like Siri, Microsoft Ice, Cortana, and Xiaoai. In 2014, SemEval ranked SR as the top task. While many existing studies have focused on analyzing the entailment of single phrases, advancements in deep learning have made it possible to analyze complete sentences or texts. While the natural parallelism of membrane computing has shown promise for data processing, harnessing this potential to advance semantic relatedness remains an open problem yet to be tackled. This paper proposes a novel Siamese Manhattan LSTM-SNP approach (SiMaLSTM-SNP) for the SR problem. The approach uses a collaborative Word2vec and 10-Layer Attention strategy to represent and extract sentence pairs and a Siamese LSTM-SNP structure to calculate the hidden states of sentences. The multi-head self-attention layer identifies text associations and redistributes hidden state weights. The last hidden state is extracted, and the relatedness score is calculated using the Manhattan distance. The experiments demonstrate that SiMaLSTM-SNP outperforms 17 classical SR baselines and 7 novel approaches on the standard datasets SICK and STS in terms of mean square error performance. This indicates that SiMaLSTM-SNP can accurately capture the semantic distinction between two sentences and effectively preserve their semantic information. [ABSTRACT FROM AUTHOR]

With the gradual growth of deep learning in machine vision, efficient extraction of 3D point clouds becomes significant. The raw data of the 3D point cloud are sparse, disordered, and immersed in noise, which makes it difficult to classify and segment. Whether 3D point clouds can be classified and segmented or not, the local feature is an essential ingredient. Therefore, this paper proposes a GateNet-based PointNet++ network (G-PointNet++). G-PointNet++ extracts local features more accurately than PointNet++ by suppressing irrelevant features and emphasizing important features. Meanwhile, it refines the feature adaptively. Besides, the SENet and attention mechanism are introduced into PointNet++. G-PointNet++ was evaluated on the public ModelNet dataset, ShapeNet dataset, and S3DIS dataset, and its effectiveness in classification and segmentation tasks was verified. In the classification task, G-PointNet++ achieves an overall classification accuracy (OA) of 95.5% on ModelNet10 and 93.3% on ModelNet40. In the segmentation task, the mIoU of G-PointNet++ reaches 85.5% on ShapeNet. These experiments show that G-PointNet++ achieves better performance and saves more time than PointNet++, and its overall accuracy is higher than that of PCT network on ModeNet40. [ABSTRACT FROM AUTHOR]