检索结果-内蒙古大学图书馆

A deep learning strategy for automatic congestive heart failure detection using novel bottleneck attention module

APPLIED INTELLIGENCE 2024年第17-18期54卷 8120-8131页

作者： Wang, Jibin Guo, Xingtian Anhui Sci & Technol Univ Dept Network Engn Fengyang 233100 Peoples R China Anhui Med Univ Clin Coll Hefei 230031 Peoples R China

Congestive heart failure (CHF) is a sort of common cardiovascular disease. Artificial vision inspection on electrocardiogram (ECG) has turned into the mainstream diagnosis strategy for CHF detection, however it is strenuous and challenging. Motivated from bottleneck attention module (BAM), we construct an efficient architecture based on naive bidirectional gate recurrent unit (BGRU) for automatic CHF detection called BAM-BGRU. BAM-BGRU can refine the attention maps from both pathways: Channel attention and Spatial attention to enhance feature representation ability. To evaluate the effectiveness, we leverage naive GRU, BGRU and BAM as control groups with BIDMC congestive heart failure database (BCHFD) and congestive heart failure RR intervals database (CHFRID). The results achieve an obvious performance improvement than control groups and existing algorithms with an accuracy of 99.1% and 98.8%. Besides, we implement visualization analysis for multilevel derivative gradient flows of ECG episodes to strengthen model interpretability. To our knowledge, we first reformulate naive BGRU framework for consistent performance improvements showing promising potentials in diverse CNN backbones.

关键词： Electrocardiogram Congestive heart failure Bidirectional gate recurrent unit attention mechanism bottleneck attention module

来源：评论

学校读者我要写书评

暂无评论

Facial Expression Recognition Using a Semantic-Based bottleneck attention module

引用

INTERNATIONAL JOURNAL ON SEMANTIC WEB AND INFORMATION SYSTEMS 2024年第1期20卷 1页

作者： Zhang, Shengfu Xiao, Zhongjie Qinghai Minzu Univ Xining Qinghai Peoples R China

Facial expression recognition (FER) is of great value in affective computing. Currently, many FER models have difficulty distinguishing between primary and secondary features. To this end, we propose a FER model based on the semantic bottleneck attention module (BAM). The improvement is that the input image is processed through two branches. BAM uses spatial attention to construct feature maps that can highlight important feature areas and suppress secondary features. The moving flipped bottleneck convolution (MBConv) module introduces random depth, reducing training time and improving model performance. Random depth enables the model to reduce the risk of overfitting during training by randomly skipping some layers. Global average pooling replaces the fully connected layer and compresses the entire feature map (FM) into numerical values to obtain high-purity image features. Through experiments on Extended Cohn-Kanade, Static Facial Expressions in the Wild, and Real-world Affective Faces Database CK+, SFEW, and RAFDB databases, the accuracy of our model reaches 98.33%, 61.14%, and 89.43% respectively, which is better than the other three advanced comparison methods.

关键词： Facial Expression Recognition Semantic Feature Extraction bottleneck attention module Mobile Flip bottleneck Convolution Global Average Pooling Channel attention module

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach Based on Multi-Level bottleneck attention modules Using Self-Guided Dropblock for Person Re-Identification

引用

IEEE ACCESS 2022年 10卷 123160-123176页

作者： Yaseen, Muhammad Usman Nasralla, Moustafa M. Aslam, Faiza Ali, Syed Sohaib Khattak, Sohaib Bin Altaf COMSATS Univ Islamabad Dept Comp Sci Islamabad 45550 Pakistan Prince Sultan Univ Dept Commun & Networks Engn Riyadh 12435 Saudi Arabia CGG Serv UK Ltd Crawley RH10 9QN England

Person re-identification has inspired a lot of interest due to its significance in intelligent video surveillance. It is a difficult task due to the presence of critical challenges such as changes in appearance, misalignment, occlusion and background noise. Batch drop block layer (BDB) has been used recently in person re-identification by exploiting the feature erasing procedure. However, BDB drops a block of features randomly, resulting in the loss of contextual information, which makes the model difficult to train. Also, due to the random dropping of features, large area of discriminative information may lose during training, resulting in low efficiency and performance. To address this problem and to improve the model representation power, we propose a novel, lightweight, self-adaptive bottleneck attention module with a self-attention branch to improve the model performance by reducing the parameter overhead with negligible computation cost. The proposed approach entails bottleneck attention module (BAM) which is incorporated between ResNet layers to remove the background noise and to nominate the high-level semantic part. Further, dilated convolutions with batch normalization are used to tackle the contextual information loss problem and to avoid overfitting. In addition, an informative global branch is used which captures the global representation of the network, and the attention branch entails the multiscale local salient information. Two types of loss functions including softmax and batch hard triplet are used in the training process for each branch, forcing the network to encapsulate the common attribute within the similar identity and to maintain distance between distinct individuals. Compared with BDB, our network improves the mAp to 88.1%, and Rank-1 gets 96.3% for the market-1501 dataset. The results on Cuhk-03-Detected dataset showed 79.2% mAp score, with 81.4 %, Rank-1, whereas on Cuhk-03-labelled dataset, a mAP score of 81.3% and a Rank-1 score of 83.

关键词： Feature extraction Measurement Cameras Semantics Deep learning Training Multiscale feature extraction lightweight self-attention bottleneck attention module

来源：评论

学校读者我要写书评

暂无评论

Research on person re-identification based on multi-level attention model

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2024年第40期83卷 87459-87477页

作者： Wei, Dan Liang, Danyang Wu, Longfei Wang, Xiaolan Jiang, Lei Luo, Suyun Shanghai Univ Engn Sci Shanghai Peoples R China

Person Re-identification (ReID) is an important research direction in the field of pattern recognition, which aims to retrieve the same pedestrian in different cameras. The combination of deep learning and attention mechanism greatly improves the accuracy of image retrieval, but previous researchers usually use on-channel or spatial convolution to learn attention, ignoring the connection between attention feature nodes. In this article, we first improve a bottleneck attention module (BAM) to make the learned attention map faster. Secondly, to capture the relevance of each feature node in the global attentional feature map, we design a self-relevant attention module (SRA), which models the global scope structure information and is used to capture the connection between the feature node positions to make the obtained attentional map more robust. Finally, we propose a method to strengthen the attention features, so that the higher attention features around the position also get higher feature values, so that the obtained feature map is more robust. The effectiveness of the model is confirmed in several mainstream pedestrian re-identification datasets, and the proposed model outperforms most state-of-the-art methods.

关键词： Person re-identification bottleneck attention module Self-relevant attention module Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Bi-attention DoubleUNet: A deep learning approach for carotid artery segmentation in transverse view images for non-invasive stenosis diagnosis

引用

BIOMEDICAL SIGNAL PROCESSING AND CONTROL 2024年 94卷

作者： Ottakath, Najmath Akbari, Younes Al-Maadeed, Somaya Ali Bouridane, Ahmed Zughaier, Susu M. Chowdhury, Muhammad E. H. Qatar Univ Dept Comp Sci & Engn Doha Qatar Univ Sharjah Ctr Data Analyt & Cybersecur Sharjah U Arab Emirates Qatar Univ Coll Med QU Hlth Doha Qatar Qatar Univ Dept Elect Engn Doha Qatar

The carotid artery is a vital blood vessel that supplies oxygenated blood to the brain. Blockages in this artery can lead to life-threatening illnesses, making accurate diagnosis essential. While ultrasound (US) imaging is the primary diagnostic tool, evaluations by trained operators can be subjective and imprecise. An automated approach can provide a more reliable and accurate evaluation of the carotid artery's condition. To achieve this, the artery must first be identified and isolated from US images. This paper proposes an automated segmentation method for the carotid artery in transverse B-mode ultrasound images, using a Bi-attention DoubleUnet architecture which incorporates spatial attention and channel wise attention using bottleneck attention module. The method is evaluated on a dataset of transverse images acquired from two devices. The obtained results exhibit higher performance than existing methods with a dice index of 95.96%, IoU of 97.92%, Precision of 98.35% and recall of 97.57% on combined dataset. Another variant of doubleUnet with SE layer and without ASPP (Artous Spatial Pyramidal Pooling) is presented where the modified DoubleUnet with SE realized an average IoU of 92.805%, Dice of 96.215%, precision of 98.82%, and recall of 93.84% representing average results across datasets. These approaches can significantly improve the efficiency and accuracy of carotid artery disease diagnosis and treatment, ultimately improving patient outcomes.

关键词： Carotid artery segmentation Transverse mode attention network DoubleUnet bottleneck attention module

来源：评论

学校读者我要写书评

暂无评论

DSBAV-Net: Depthwise Separable bottleneck attention V-Shaped Network with Hybrid Convolution for Left Atrium Segmentation

引用

ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING 2025年第2期50卷 1097-1108页

作者： Ocal, Hakan Bartin Univ Fac Engn Architecture & Design Comp Engn TR-74100 Bartin Turkiye

Accurate and precise segmentation of the left atrium (LA) is crucial in the early diagnosis and treatment of atrial fibrillation (AF), which is the most common heart rhythm disease in cases. The size of fibrotic tissue in patients with AF is based on manual examination of images obtained from the gadolinium-enhanced cardiac magnetic resonance imaging (MRI) technique. However, manual examination of the acquired images is time-consuming and has many difficulties, such as LA thickness between observers and resolution according to MR devices. To overcome the challenges of manual segmentation of images obtained from MRI devices, end-to-end, fully automated deep learning-based segmentation architectures have become extremely important today. In this study, an encoder-decoder-based V-shaped deep learning architecture is proposed for precise segmentation of LA. In the proposed architecture, standard convolution and depthwise separable convolution are used together. Thus, sparsely connected blocks with fewer parameters and deeply separable convolutions learn the feature representations better, increasing the robustness of the model. In addition, the bottleneck attention module has been added to each encoder layer, allowing the network to learn which features to focus on and which features to suppress in images by attention mapping channel and spatially. The proposed architecture obtained 0.915 dice and 0.844 Jaccard scores in the STACOM 2018 challenge dataset. The obtained results draw attention to the robustness of the model.

关键词： Left atrium segmentation DSBAV-Net bottleneck attention module Layer-based hybrid convolution Fusion loss

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Prediction of Freezing of Gait in Parkinson's Disease With the Ensemble Channel Selection Approach

引用

BRAIN AND BEHAVIOR 2025年第1期15卷 e70206页

作者： Abbasi, Sara Rezaee, Khosro Islamic Azad Univ Mashhad Dept Biomed Engn Mashhad Iran Meybod Univ Dept Biomed Engn Meybod Iran

Purpose A debilitating and poorly understood symptom of Parkinson's disease (PD) is freezing of gait (FoG), which increases the risk of falling. Clinical evaluations of FoG, relying on patients' subjective reports and manual examinations by specialists, are unreliable, and most detection methods are influenced by subject-specific factors. Method To address this, we developed a novel algorithm for detecting FoG events based on movement signals. To enhance efficiency, we propose a novel architecture integrating a bottleneck attention module into a standard bidirectional long short-term memory network (BiLSTM). This architecture, adaptable to a convolution bottleneck attention-BiLSTM (CBA-BiLSTM), classifies signals using data from ankle, leg, and trunk sensors. Finding Given three movement directions from three locations, we reduce computational complexity in two phases: selecting optimal channels through ensemble learning followed by feature reduction using attention mapping. In FoG event detection tests, performance improved significantly compared to control groups and existing methods, achieving 99.88% accuracy with only two channels. Conclusion The reduced computational complexity enables real-time monitoring. Our approach demonstrates substantial improvements in classification results compared to traditional deep learning methods.

关键词： bidirectional long short-term memory bottleneck attention module channel selection ensembling freezing of gait Parkinson's disease

来源：评论

学校读者我要写书评

暂无评论

Face Super-Resolution via Hierarchical Multi-Scale Residual Fusion Network

引用

IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES 2021年第9期E104A卷 1365-1369页

作者： Wang, Yu Lu, Tao Wu, Zhihao Wu, Yuntao Zhang, Yanduo Wuhan Inst Technol Sch Comp Sci & Engn Hubei Key Lab Intelligent Robot Wuhan 430073 Peoples R China

Exploring the structural information as prior to facial images is a key issue of face super-resolution (SR). Although deep convolutional neural networks (CNNs) own powerful representation ability, how to accurately use facial structural information remains challenges. In this paper, we proposed a new residual fusion network to utilize the multi-scale structural information for face SR. Different from the existing methods of increasing network depth, the bottleneck attention module is introduced to extract fine facial structural features by exploring correlation from feature maps. Finally, hierarchical scales of structural information is fused for generating a high-resolution (HR) facial image. Experimental results show the proposed network outperforms some existing state-of-the-art CNNs based face SR algorithms.

关键词： multi-scale residual bottleneck attention module face super-resolution

来源：评论

学校读者我要写书评

暂无评论

SUPRAVENTRICULAR TACHYCARDIA CLASSIFICATION USING attention-BASED RESIDUAL NETWORKS

引用

JOURNAL OF MECHANICS IN MEDICINE AND BIOLOGY 2021年第5期21卷

作者： Zhang, Jiayu Qian, Li Hou, Xingyu Zhu, Honglei Wu, Xiaomei Fudan Univ Sch Informat Sci & Technol Shanghai 200433 Peoples R China Fudan Univ Sch Informat Sci & Technol Dept Elect Engn Shanghai 200433 Peoples R China

Atrioventricular nodal reentrant tachycardia (AVNRT) and atrioventricular reentrant tachycardia (AVRT) are two common arrhythmias with high similarity. Automatic electrocardiogram (ECG) detection using machine learning and neural networks has replaced manual detection, but few studies distinguishing AVNRT from AVRT have been reported. This study proposed a classification algorithm using bottleneck attention module (BAM)-based deep residual network (ResNet) through two-lead ECG records. Specifically, ResNet possessed sufficient network depth to extract abundant features, and BAM was introduced to optimize weight assignment of feature maps by fusing together channel and spatial information. Seven types of ECG signals from four public databases were used to pretrain the proposed classification model, which was then fine-tuned using the experimental dataset. The AVNRT and AVRT detection precisions were 98.95% and 87.47%, sensitivities were 87.52% and 98.58%, and the Fl-scores were 92.82% and 92.68%, respectively. These findings showed that our proposed classification model achieved excellent inter-patient classification performance and can assist doctors in the diagnosis of AVNRT and AVRT.

关键词： Atrioventricular node reentrant tachycardia atrioventricular reentrant tachycardia residual network bottleneck attention module electrocardiogram transfer learning

来源：评论

学校读者我要写书评

暂无评论

Crack BASNet:Building Surface Crack Detection Network Based On Improved BASNet

Crack BASNet:Building Surface Crack Detection Network Based ...

引用

第34届中国控制与决策会议

作者： Wencai Cao Jin Wu Lei Zhu School of Information Science and Engineering Wuhan University of Science and Technology Engineering Research Center for Metallurgical Automation and Measurement Technology Ministry of Education

In order to slove the problems of interference in the detection results,the imbalance ratio of different samples,low detection accuracy,and blurry boundaries on building surface crack detection,this paper proposes a new crack detection network based on improved BASNet(Crack BASNet).In Crack BASNet,the bottleneck attention module(BAM) is embedded in the coding stage to extract complementary crack features and suppress irrelevant background features from the two dimensions of channel and *** activation function in the network adopts PReLU to alleviate the problem that the neuron weight cannot be *** a new hybrid loss function of using Focal loss,SSIM loss and Dice loss is designed to solve the problem of the imbalance ratio of positive and negative samples,difficult and easy ***,this paper makes comparative experiments on the Crack BASNet to the BASNet,the classical image segmentation networks,and other crack detection networks to evaluate the performance of proposed network *** experimental results show that precision,recall,F-measure and relax F-measure value of Crack BASNet are 0.881,0.853,0.867 and 0.837,which are 0.8%,3.5%,2.2% and 3.2% higher than BASNet,and the detection boundaries of fine cracks are more clear and continuous than *** addition,Crack BASNet outperforms the classic image segmentation networks such as FCN,PSPNet,etc,and crack detection networks such as Crack FCN,RFCN,etc,both in terms of detection accuracy and boundary quality.

关键词： Crack Detection Crack BASNet bottleneck attention module PReLU Hybrid Loss Model Evaluation

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：