Search

Copyright of Journal of Zhengzhou University (Natural Science Edition) is the property of Journal of Zhengzhou University (Natural Science Edition) Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Currently, many smoke recognition algorithms suffer from high false alarm rates, partly due to the fact that most existing convolutional neural networks (CNNs) mainly focus on local information in smoke images during feature extraction, neglecting the global features of smoke images. This bias towards local information processing can easily lead to misjudgments when dealing with variable and complex smoke images. To address this issue, it is necessary to capture the global features of smoke images more accurately, thereby improving the accuracy of smoke recognition algorithms. Therefore, this paper propose a dual-branch smoke recognition method, TCF-Net, which combines the Inception and Transformer structures. This model is improved to enrich feature diversity while reducing channel redundancy. Additionally, the self-attention mechanism from Transformer is introduced, combining its ability to learn global context information with CNN􀆳s capacity to learn local relative position information. During feature extraction, a feature coupling unit (FCU) is embedded to continuously interact the local features and global information in both branches, maximizing the retention of both local and global information and enhancing the performance of the algorithm. The proposed algorithm can classify video frames into three states: black smoke, white smoke, and no smoke. Experimental results show that the improved network can better extract smoke features, reducing the false alarm rate while increasing the accuracy to 97.8%, confirming the excellent performance of the algorithm. [ABSTRACT FROM AUTHOR]

Distant supervision relation extraction faces the problem of data quality, that is, the generated dataset has multiple types of noise, noisy words, noisy sentences and noisy bags. Existing research mainly focuses on the noisy sentences, ignoring the impact of other noise, and cannot completely eliminate the noise. To this end, the paper proposed a distant supervision relation extraction model based on multilevel attention mechanism and dynamic thresholding (MADT). The model firstly used a pre-trained language model to obtain entity-pair semantic representations, then obtained semantic features embedded with keyword information through a bidirectional gated recurrent unit and a self-attention mechanism, and then dealt with the three noise problems sequentially in conjunction with the deep contextual representation of the sentence. In addition, the paper proposed a dynamic thresholding method to further remove noisy sentences, enhance the contribution of positive example sentences to the bag representation, and reduce the impact of noisy bags using a semantic similarity-based attention mechanism. Experiments on the NYT10d and NYT10m datasets show that the MADT model is able to address all levels of noise in distant supervision of relation extraction and effectively improve relation extraction performance. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Remote Sensing is the property of Editorial Office of Journal of Remote Sensing & Science Publishing Co. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Telecommunication Engineering is the property of Telecommunication Engineering and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Graphics is the property of Journal of Graphics Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Graphics is the property of Journal of Graphics Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Chongqing University of Posts & Telecommunications (Natural Science Edition) is the property of Chongqing University of Posts & Telecommunications and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Point of interest (POI) recommendation is one of the most important applications of location-based social networking (LBSN). Existing studies have proposed methods that utilize POI information and spatio-temporal information for recommendation, but the relevant auxiliary information has not been fully utilized, so it can not alleviate the problems of insufficient information and less travel data caused by short track check-in of users. To solve these problems, a friends relationship and selfattention recommendation model ATFR is proposed. The prediction model consists of three parts: Firstly, the representation vector of friend relationship is obtained by graph embedding method and input into the neural network. Secondly, the user interest preference vector is obtained by GRU. Then, the self-attention mechanism is used to model the sequential and social effects of the user check-in sequence and selectively focus on the historical check-in records associated with the check-in sequence. Finally, the future interest points are recommended according to the interest points sorting list. Experimental results on two public datasets show that this model performs better than other algorithms and can be used to improve the quality of personalized interest recommendation services for websites and applications. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Guangxi Normal University - Natural Science Edition is the property of Gai Kan Bian Wei Hui and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Shenzhen University Science & Engineering is the property of Editorial Department of Journal of Shenzhen University Science & Engineering and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Computer-Aided Design & Computer Graphics / Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao is the property of Gai Kan Bian Wei Hui and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Information & Control is the property of Gai Kan Bian Wei Hui and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Test & Measurement Technology is the property of Publishing Center of North University of China and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

ObjectiveNowadays most no contact body size measurement studies are based on point cloud segmentation method, they use a trained point cloud segmentation neural network to segment point cloud of pigs, then locate measurement points based on them. But point cloud segmentation neural network always need a larger graphics processing unit (GPU) memory, moreover, the result of the measurement key point still has room of improvement. This study aims to design a key point generating neural network to extract measurement key points from pig's point cloud. Reducing the GPU memory usage and improve the result of measurement points at the same time, improve both the efficiency and accuracy of the body size measurement.MethodsA neural network model was proposed using improved Transformer attention mechanic called Pig Back Transformer for generating key points and back orientation points which were related to pig body dimensions. In the first part of the network, it was introduced an embedding structure for initial feature extraction and a Transformer encoder structure with edge attention which was a self-attention mechanic improved from Transformer's encoder. The embedding structure using two shared multilayer perceptron (MLP) and a distance embedding algorithm, it takes a set of points from the edge of pig back's point cloud as input and then extract information from the edge points set. In the encoder part, information about the offset distances between edge points and mass point which were their feature that extracted by the embedding structure mentioned before incorporated. Additionally, an extraction algorithm for back edge point was designed for extracting edge points to generate the input of the neural network model. In the second part of the network, it was proposed a Transformer encoder with improved self-attention called back attention. In the design of back attention, it also had an embedding structure before the encoder structure, this embedding structure extracted features from offset values, these offset values were calculated by the points which are none-edge and down sampled by farthest point sampling (FPS) to both the relative centroid point and model generated global key point from the first part that introduced before. Then these offset values were processed with max pooling with attention generated by the extracted features of the points' axis to extract more information that the original Transformer encoder couldn't extract with the same number of parameters. The output part of the model was designed to generate a set of offsets of the key points and points for back direction fitting, than add the set offset to the global key point to get points for pig body measurements. At last, it was introduced the methods for calculating body dimensions which were length, height, shoulder width, abdomen width, hip width, chest circumference and abdomen circumference using key points and back direction fitting points.Results and DiscussionsIn the task of generating key points and points for back direction fitting, the improved Pig Back Transformer performed the best in the accuracy wise in the models tested with the same size of parameters, and the back orientation points generated by the model were evenly distributed which was a good preparation for a better body length calculation. A melting test for edge detection part with two attention mechanic and edge trim method both introduced above had being done, when the edge detection and the attention mechanic got cut off, the result had been highly impact, it made the model couldn't perform as well as before, when the edge trim method of preprocessing part had been cut off, there's a moderate impact on the trained model, but it made the loss of the model more inconsistence while training than before. When comparing the body measurement algorithm with human handy results, the relative error in length was 0.63%, which was an improvement compared to other models. On the other hand, the relative error of shoulder width, abdomen width and hip width had edged other models a little but there was no significant improvement so the performance of these measurement accuracy could be considered negligible, the relative error of chest circumference and abdomen circumference were a little bit behind by the other methods existed, it's because the calculate method of circumferences were not complicated enough to cover the edge case in the dataset which were those point cloud that have big holes in the bottom of abdomen and chest, it impacted the result a lot.ConclusionsThe improved Pig Back Transformer demonstrates higher accuracy in generating key points and is more resource-efficient, enabling the calculation of more accurate pig body measurements. And provides a new perspective for non-contact livestock body size measurements.

To provide drivers with real-time and accurate pedestrian information and reduce traffic accidents, the detection of enhanced YOLOv3-tiny (DOEYT) pedestrian detection algorithm was proposed. The robust feature extraction network was established, and the asymmetric max-pooling was used for down sampling to prevent the loss of lateral pedestrian features due to the increased receptive field. Hardswish was employed as activation function for the convolutional layers to optimize network performance, and the global context (GC) self-attention mechanism was used to capture holistic feature information. In the classification and regression network, the three-scale detection strategy was adopted to improve the accuracy of small-scale pedestrian target detection. The k-means++ algorithm was used to regenerate dataset anchor boxes for enhancing network convergence speed. The pedestrian detection dataset was constructed and divided into training and testing sets to evaluate DOEYT performance. The results show that by the asymmetric max-pooling, Hardswish function and GC self-attention mechanism, AP values are increased by 14.4%, 7.9% and 10.8%, respectively. On the testing set, DOEYT achieves average precision of 91.2% and detection speed of 103 frames per second, which demonstrates that the proposed algorithm can quickly and accurately detect pedestrians for reducing the risk of traffic accidents. [ABSTRACT FROM AUTHOR]

Existing person re-identification (Re-ID) methods often struggle with inaccurate feature extraction and misidentification of person features due to environmental noise. Here, we propose a multi-feature fusion branch network for person Re-ID based on dynamic convolution and attention mechanism. First, considering the uncertainties in illumination, human posture and occlusion, dynamic convolution is proposed to replace static convolution in ResNet50 to obtain a more robust Dy-ResNet50 model. Second, given the great difference in camera perspective and the likelihood of people being occluded by objects, self-attention and cross-attention mechanisms are embedded into the backbone network. Finally, the cross entropy loss function and the hard triplet loss function are used as the model's loss functions, and experiments are carried out on public datasets of DukeMTMC-ReID, Market-1501 and MSMT17. The results show that the proposed model outperforms current mainstream models in Rank-1 (first hit) and mAP (mean Average Precision) on three public datasets, indicating its high identification accuracy. [ABSTRACT FROM AUTHOR]

[Objective]　Nowadays most no contact body size measurement studies are based on point cloud segmentation method, they use a trained point cloud segmentation neural network to segment point cloud of pigs, then locate measurement points based on them. But point cloud segmentation neural network always need a larger graphics processing unit (GPU) memory, moreover, the result of the measurement key point still has room of improvement. This study aims to design a key point generating neural network to extract measurement key points from pig's point cloud. Reducing the GPU memory usage and improve the result of measurement points at the same time, improve both the efficiency and accuracy of the body size measurement. [Methods]　A neural network model was proposed using improved Transformer attention mechanic called Pig Back Transformer for generating key points and back orientation points which were related to pig body dimensions. In the first part of the network, it was introduced an embedding structure for initial feature extraction and a Transformer encoder structure with edge attention which was a self-attention mechanic improved from Transformer's encoder. The embedding structure using two shared multilayer perceptron (MLP) and a distance embedding algorithm, it takes a set of points from the edge of pig back's point cloud as input and then extract information from the edge points set. In the encoder part, information about the offset distances between edge points and mass point which were their feature that extracted by the embedding structure mentioned before incorporated. Additionally, an extraction algorithm for back edge point was designed for extracting edge points to generate the input of the neural network model. In the second part of the network, it was proposed a Transformer encoder with improved self-attention called back attention. In the design of back attention, it also had an embedding structure before the encoder structure, this embedding structure extracted features from offset values, these offset values were calculated by the points which are none-edge and down sampled by farthest point sampling (FPS) to both the relative centroid point and model generated global key point from the first part that introduced before. Then these offset values were processed with max pooling with attention generated by the extracted features of the points' axis to extract more information that the original Transformer encoder couldn't extract with the same number of parameters. The output part of the model was designed to generate a set of offsets of the key points and points for back direction fitting, than add the set offset to the global key point to get points for pig body measurements. At last, it was introduced the methods for calculating body dimensions which were length, height, shoulder width, abdomen width, hip width, chest circumference and abdomen circumference using key points and back direction fitting points. [Results and Discussions]　In the task of generating key points and points for back direction fitting, the improved Pig Back Transformer performed the best in the accuracy wise in the models tested with the same size of parameters, and the back orientation points generated by the model were evenly distributed which was a good preparation for a better body length calculation. A melting test for edge detection part with two attention mechanic and edge trim method both introduced above had being done, when the edge detection and the attention mechanic got cut off, the result had been highly impact, it made the model couldn't perform as well as before, when the edge trim method of preprocessing part had been cut off, there's a moderate impact on the trained model, but it made the loss of the model more inconsistence while training than before. When comparing the body measurement algorithm with human handy results, the relative error in length was 0.63%, which was an improvement compared to other models. On the other hand, the relative error of shoulder width, abdomen width and hip width had edged other models a little but there was no significant improvement so the performance of these measurement accuracy could be considered negligible, the relative error of chest circumference and abdomen circumference were a little bit behind by the other methods existed, it's because the calculate method of circumferences were not complicated enough to cover the edge case in the dataset which were those point cloud that have big holes in the bottom of abdomen and chest, it impacted the result a lot. [Conclusions]　The improved Pig Back Transformer demonstrates higher accuracy in generating key points and is more resource-efficient, enabling the calculation of more accurate pig body measurements. And provides a new perspective for non-contact livestock body size measurements. [ABSTRACT FROM AUTHOR]

vIn the few-shot classification tasks, existing CNN models suffer from insufficient feature extraction, limited feature diversity and weak differentiation between classes in few-shot datasets, leading to low classification accuracy. To address these issues, this paper proposed a few-shot classification model called FMAF. Firstly, this method incorporated multi-granularity thought into the architecture of CNN feature extraction network to enhance feature diversity. Secondly, after the multi-granular feature extraction network, FMAF added a self-attention layer to extract key features from the multi-granular image features, based on the multi-granular attention features, FMAF employed a feature fusion method to combine the information from multiple-granularity attention features, highlighted the crucial features and improved feature representativeness. Finally, this paper utilized two classical few-shot datasets for experimental verification on miniImageNet and tieredImageNet. Experimental results show that FMAF method can effectively improve the accuracy and efficiency of classification. [ABSTRACT FROM AUTHOR]

Domain adaptation, the important branch of transfer learning, aims to solve the problem that the performance of traditional machine learning algorithms drops sharply when the training and test samples obey different data distributions. Transformer is a deep learning framework based on a self-attention mechanism, which has strong global feature extraction ability and modeling ability. In recent years, the combination of Transformer and domain adaptation has also become a research hotspot. Although many relative methods have been published, the review of Transformer application in domain adaptation has not been reported. In order to fill the gap in this field and provide reference for relevant research, this paper summarizes and analyzes some typical domain adaptation methods based on Transformer in recent years. This paper summarizes the concepts related to domain adaptation and the basic structure of the Transformer, sorts out various domain adaptation methods based on Transformer from four applications, i.e. image classification, image semantic segmentation, object detection and medical image analysis and compares the domain adaptation methods in image classification. Finally, the challenges of the current domain adaptation Transformer model are summarized, and the feasible research directions in the future are discussed. [ABSTRACT FROM AUTHOR]

Copyright of Systems Engineering & Electronics is the property of Journal of Systems Engineering & Electronics Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

To reduce the noise of labeled data in the distantly supervised relationship extraction, a distant supervision relationship extraction model integrating entity description and self-attention mechanism is proposed. Based on multi-instance learning, the comprehensive impacts of entity knowledge and position relation are considered, and the splicing vector of word, entity, entity description and relative position are adopted as the model input. A piecewise convolutional neural network is employed as the sentence encoder, which combines with the improved structured self-attention mechanism to capture the internal correlation of features. The difference vector between tail entity and head entity is constructed as the supervision information of attention mechanism to assign weight to each sentence. Experimental results on New York Times dataset show that the model performance indexes of the model reach the maximum values when compared to state-of-the-art models. [ABSTRACT FROM AUTHOR]

Aspect sentiment triple extraction is one of the subtasks of aspect-level sentiment analysis, which aims to extract aspect terms, corresponding opinion terms and sentiment polarity in sentence. Previous studies focus on designing a new paradigm to complete the triplet extraction task in an end-to-end manner. They ignore the role of external knowledge in the model, thus semantic information, part-of-speech information and local context information are not fully explored and utilized. Aiming at the above problems, multi-feature interaction for aspect sentiment triplet extraction (MFI-ASTE) is proposed. Firstly, the bidirectional encoder representation from transformers (BERT) model is used to learn the context semantic feature information, meanwhile, the self-attention mechanism is used to strengthen the semantic feature. Secondly, the semantic feature interacts with the extracted part-of-speech feature and both learn from each other to strengthen the combination ability of the part-of-speech and semantic information. Thirdly, many convolutional neural networks are used to extract multiple local context features of each word, and then multi-point gate mechanism is used to filter these features. Fourthly, three features of external knowledge are fused by two linear layers. Finally, biaffine attention is used for predicting grid tagging and specific decoding schemes are used for decoding triplets. Experimental results show that the proposed model improves the F1 score by 6.83%, 5.60%, 0.54% and 1.22% respectively on four datasets compared with existing mainstream models.

Adrenal vein sampling is required for the staging diagnosis of primary aldosteronism, and the frames in which the adrenal veins are presented are called key frames. Currently, the selection of key frames relies on the doctor's visual judgement which is time-consuming and laborious. This study proposes a key frame recognition algorithm based on deep learning. Firstly, wavelet denoising and multi-scale vessel-enhanced filtering are used to preserve the morphological features of the adrenal veins. Furthermore, by incorporating the self-attention mechanism, an improved recognition model called ResNet50-SA is obtained. Compared with commonly used transfer learning, the new model achieves 97.11% in accuracy, precision, recall, F1, and AUC, which is superior to other models and can help clinicians quickly identify key frames in adrenal veins.

Transformer is a deep learning model based on the self-attention mechanism, showing tremendous potential in computer vision. In image classification tasks, the key challenge lies in efficiently and accurately capturing both local and global features of input images. Traditional approaches rely on convolutional neural networks to extract local features at the lower layers, expanding the receptive field through stacked convolutional layers to obtain global features. However, this strategy aggregates information over relatively short distances, making it difficult to model long-term dependencies. In contrast, the self-attention mechanism of Transformer directly compares features across all spatial positions, capturing long-range dependencies at both local and global levels and exhibiting stronger global modeling capabilities. Therefore, a thorough exploration of the challenges faced by Transformer in image classification tasks is crucial. Taking Vision Transformer as an example, this paper provides a detailed overview of the core principles and architecture of Transformer. It then focuses on image classification tasks, summarizing key issues and recent advancements in visual Transformer research related to performance enhancement, computational costs, and training optimization. Furthermore, applications of Transformer in specific domains such as medical imagery, remote sensing, and agricultural images are summarized, highlighting its versatility and generality. Finally, a comprehensive analysis of the research progress in visual Transformer for image classification is presented, offering insights into future directions for the development of visual Transformer.

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Cotton is one of the most important economic crops in China. It is of great significance to predict the yield of cotton. In this study, the Unmanned Aerial Vehicle (UAV) remote sensing platform was first used to collect some data on the densely planted cotton in Xinjiang, China. Five-point sampling was also utilized in the period of defoliation. A total of five cotton fields were then selected as well. Secondly, each image was divided into multiple sub-images and then enhanced by color space conversion, brightness, noise blurring, flipping and rotating operation. A high-quality dataset was constructed to estimate the cotton yield. Better training was achieved, compared with the original. Eventually, the cotton dataset with the construction site was used to extract the element rate from the cotton images using RCH-UNet (resnet coordinate hardswish UNet). Among them, the UNet was used as a baseline model to construct an improved U-type convolutional neural network. While the IoU (intersection over union), PA (pixel accuracy), and precision were taken as the evaluation metrics. The overall RCH-UNet improved the three metrics by 14.34, 9.85, and 8.68 percentage points, respectively, compared with the original UNet. Specifically, ResNet50 backbone feature extraction network was selected to replace the traditional CBR (convolution batch normalization ReLU) downs sampling structure in UNet; The CA (coordinate attention) mechanism was combined with the UNet; The ReLU activation function in UNet was replaced with the hardswish activation function. The results showed that: 1) The richer semantic information in the ResNet50 was learned through the residual structure, indicating the better feature extraction and expression of the improved model. 2) The CA mechanism was significantly enhanced to learn the detailed features. At the same time, there was an effective reduction in the interference of irrelevant features to the model. 3) The hardswish activation function presented the stronger expression and feature fusion of UNet when performing up-sampling and jump connection. Subsequently, the performance of RCH-UNet was tested with the PSPNet and DeepLabv3 models under the same experimental conditions. The IoU, PA, and precision of RCH-UNet had improved by 9.15, 6.31, and 3.99 percentage points, respectively, compared with the DeepLabv3 model. A prediction model of cotton yield was constructed with the ridge regression from the cotton pixels extracted by the RCH-UNet model. The image texture features were also extracted by GLCM (gray-level co-occurrence matrix). The R² value of the improved model was 0.92, and the average relative error between the predicted and actual yield was 9.254%. The RCH-UNet model was accurately and effectively extracted from the cotton images; Meanwhile, the prediction model of cotton yield was effectively verified using deep learning and image processing. The UAV low-altitude imaging can also be expected to predict the yield of densely planted cotton in Xinjiang, China. [ABSTRACT FROM AUTHOR]

The majority of current machine learning and deep learning solutions for ECG-based emotion recognition utilize fully-supervised learning methods. Several limitations of this approach are that large human-annotated datasets and computing resources are required. Furthermore, the feature representations learned by fully supervised methods tend to be task-specific with limited generalization capability. In response to these issues, this paper proposed an approach based on contrastive lear-ning for ECG-based emotion recognition, which consisted of two steps, such as pre-training and fine-tuning. The goal of pre-training was to learn representations from unlabeled EGG data through contrastive learning. Specifically, it designed two simple and efficient ECG signal augmentation methods, and used these two views to learn robust temporal representations in the time contrastive module, followed by learning discriminative feature representations in the context contrastive module. Fine-tuning used labelled data to learn emotion recognition. Experiments show that the proposed method has reached the maximum accuracy on three public ECG-based emotion recognition datasets. Additionally, the proposed method shows high efficiency under the semi-supervised settings. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Frontiers of Computer Science & Technology is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Electric Power Automation Equipment / Dianli Zidonghua Shebei is the property of Electric Power Automation Equipment Press and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Destination prediction of moving trajectories is an important part of location-based services. The existing prediction methods have two problems: one is that the historical trajectory cannot completely cover all possible query traces (data sparse problem), and the other one is that the difference in the influence of prefix trajectory points on the prediction results is not taken into account (long-term dependence problem). As a result, a trajectory distributed representation method is proposed. Firstly, the trajectory sequence is divided into grids, and the high-dimensional one-hot code vectors representing the location is reduced to generate low-dimensional embedding vectors which contain geographical topological relationships; Secondly, the destinations are clustered, and the cluster centers are used as the labels of the trajectories in the cluster, which reduces the difference of similar trajectories, highlights the characteristics of dissimilar trajectories, and effectively overcomes the problem of data sparseness. In the destination prediction, the self-attention mechanism is introduced into the LSTM network, and a destination prediction model(SATN-LSTM) based on the LSTM network are proposed. Mining the key points from the sequence and assigning weights according to their importance, which solves the longterm dependency problem better. Finally, several experiments are carried out on the real trajectory datasets to verify the effectiveness of our model. Compared with the existing models, it is verified that our model gets higher accuracy. [ABSTRACT FROM AUTHOR]

Copyright of Systems Engineering & Electronics is the property of Journal of Systems Engineering & Electronics Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

For medical image segmentation tasks such as glioma image segmentation with dense prediction, both local and global dependencies were indispensable. To address the problems that convolutional neural networks lacked the ability to establish global dependencies and the self-attention mechanism had insufficient ability to capture local details, a convolutional and deformable attention-based method for glioma image segmentation was proposed. A serial combination module of convolution and deformable attention Transformer was designed, in which convolution was used to extract local features and the immediately following deformable attention. Transformer was used to capture global dependencies to the establishment of local and global dependencies at different resolutions. As a hybrid CNN-Transformer architecture, the method could achieve accurate brain glioma image segmentation without any pretraining. Experiments showed that the average dice score and the average 95% Hausdorff distance on the BraTS2020 glioma image segmentation dataset were 83.56% and 11.30 mm, respectively, achieving comparable segmentation accuracy compared with other methods, while reducing the computational overhead by at least 50% and effectively improving the efficiency of glioma image segmentation. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Data Acquisition & Processing / Shu Ju Cai Ji Yu Chu Li is the property of Editorial Department of Journal of Nanjing University of Aeronautics & Astronautics and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

To solve the difficulty in capturing the changes of emotional intensity between EEG channels and time points, and the difficulty in capturing the emotional similarity of facial features of different subjects, this paper proposes a multimodal continuous emotion recognition model based on EEG and facial videos. A combined model of convolution and bidirectional short-term memory neural network based on spatiotemporal attention (STA-CNNBiLSTM) is used to learn and classify deep emotion related dynamics from the power spectral density (PSD) features of EEG. A pre-training convolutional neural network with self-attention (SA-CNN) is used to learn and classify the deep facial geometric features. We use the decision level fusion algorithm to fuse the above two classification results of EEG and facial geometric features modes to obtain the final results. A large number of comparative verification experiments were carried out on the public MAHNOB-HCI dataset, and the SA-CNN model was pre-trained on the facial geometric features of the FER2013 data set. In the subject-independent experiment, the average binary classification accuracy of the proposed model achieved 75. 00% in valence and 79. 00% in arousal, both of which are better than that in each single mode. Compared with the current popular models SE-CNN and AM-LSTM, the classification performance of the proposed model is also better, which proved that the proposed spatiotemporal attention mechanism can capture more spatiotemporal EEG features, and the self-attention mechanism can focus on the similarity of facial features of different subjects, thus improving the performance of multimodal emotion recognition. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Test & Measurement Technology is the property of Publishing Center of North University of China and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Frontiers of Computer Science & Technology is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Massive multiple-input multiple-output (MIMO) system can provide satisfying gain of spectrum efficiency for 5G and future wireless communication systems.In frequency-division duplex (FDD) mode, downlink channel state information (CSI) needs to be accurately fed back to the base station side to obtain this gain.To improve the feedback accuracy of downlink CSI eigenvector, a self-attention mechanism-based CSI feedback method named SA-CsiNet was proposed.SA-CsiNet respectively deployed self-attention modules at the encoder and the decoder to achieve feature extraction and reconstruction of CSI.Experimental results show that compared with codebook-based and conventional deep learning-based CSI feedback approaches, SA-CsiNet provides higher reconstruction accuracy of CSI.

To enhance the feature representation of region of interest (RoI), which incorporated a spatial context encoding module and soft regression loss, a grid self-attention mechanism 3D object detection method based on raw point cloud, named GT3D, was proposed.The spatial context encoding module was designed to effectively weight the local and spatial features of points through the attention mechanism, considering the contribution of different point cloud features for a more accurate feature representation.The soft regression loss was introduced to address label ambiguity arising during the data annotation phase.Experiments conducted on the public KITTI 3D object detection dataset demonstrate that the proposed method achieves significant improvements in detection accuracy compared to other publicly available point cloud-based 3D object detection methods.The detection results of the test set are submitted to the official KITTI server for public evaluation, achieving detection accuracies of 91.45%, 82.76%, and 79.74% for easy, moderate, and hard difficulty levels in car detection, respectively.

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Data Acquisition & Processing / Shu Ju Cai Ji Yu Chu Li is the property of Editorial Department of Journal of Nanjing University of Aeronautics & Astronautics and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Telecommunication Engineering is the property of Telecommunication Engineering and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Jilin University (Science Edition) / Jilin Daxue Xuebao (Lixue Ban) is the property of Zhongguo Xue shu qi Kan (Guang Pan Ban) Dian zi Za zhi She and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Jilin University (Science Edition) / Jilin Daxue Xuebao (Lixue Ban) is the property of Zhongguo Xue shu qi Kan (Guang Pan Ban) Dian zi Za zhi She and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Guangdong University of Technology is the property of Journal of Guangdong University of Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of East China University of Science & Technology is the property of Journal of East China University of Science & Technology Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)