检索结果-内蒙古大学图书馆

2023 IEEE International Conference on Real-Time computing and Robotics, RCAR 2023

作者： Dong, Yuanzhe Tang, Xi Jiang, Naifu Xie, Jun Liang, Wenyuan Shang, Peng Li, Guanglin Fang, Peng Chinese Academy of Sciences Cas Key Laboratory of Human-Machine Intelligence-Synergy Systems The Shenzhen Engineering Laboratory of Neural Rehabilitation Technology Shenzhen Institute of Advanced Technology Shenzhen518055 China University of Chinese Academy of Sciences Shenzhen College of Advanced Technology Shenzhen518055 China Xi'an Jiaotong University School of Mechanical Engineering Xi'an710049 China National Research Center for Rehabilitation Technical Aids Beijing100176 China

ISBN: (纸本)9798350327182

Protheses are very useful for limb amputees to restore their lost motor functions. However, most commercially available prostheses lack an intuitive and natural sensory feedback function, which may strongly limit the performance of prosthetic control and lowers the acceptance of amputees. As a non-invasive stimulation method, Transcutaneous Electrical Nerve Stimulation (TENS) has been proven to effectively evoke intuitive and natural sensations, which is practical for upper-limb amputees in clinical applications. In this paper, we explored the relationship between TENS modalities and induced sensory information based on able-bodied subjects by using electroencephalogram (EEG). We computed the Event-related Potential (ERP) and Brain Electrical Activity Mapping (BEAM) to evaluate the performance of sensation evoking. The results demonstrated that the TENS applied on wrist areas with proper parameters could stably induce multiple types of intuitive sensations of different fingers, including touching, vibrating, and flapping, and the mapping relationship between stimulation modality and sensory feedback were objectively verified and evaluated with EEG. This pilot study might provide a support for future researches on restoration of sensory paths and feedback for upper-limb amputees. © 2023 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Micromesh reinforced strain sensor with high stretchability and stability for full-range and periodic human motions monitoring

引用

InfoMat 2024年第4期6卷 124-139页

作者： Haidong Liu Chang Liu Jinan Luo Hao Tang Yuanfang Li Houfang Liu Jingzhi Wu Fei Han Zhiyuan Liu Jianhe Guo Rongwei Tan Tian-Ling Ren Yancong Qiao Jianhua Zhou School of Biomedical Engineering Shenzhen Campus of Sun Yat-sen UniversityShenzhenGuangdongthe People's Republic of China Key Laboratory of Sensing Technology and Biomedical Instruments of Guangdong Province School of Biomedical EngineeringSun Yat-sen UniversityGuangzhouthe People's Republic of China School of Integrated Circuits and Beijing National Research Center for Information Science and Technology(BNRist) Tsinghua UniversityBeijingthe People's Republic of China CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced TechnologyChinese Academy of Sciences(CAS)Shenzhenthe People's Republic of China Guangdong Engineering Technology Research Center of Implantable Medical Polymer Shenzhen Lando Biomaterials Co.Ltd.Shenzhenthe People's Republic of China

The development of strain sensors with high stretchability and stability is an inevitable requirement for achieving full-range and long-term use of wearable electronic ***,a resistive micromesh reinforced strain sensor(MRSS)with high stretchability and stability is prepared,consisting of a laser-scribed graphene(LSG)layer and two styrene-block-poly(ethylene-ran-butylene)-block-poly-styrene micromesh layers embedded in *** micromesh reinforced structure endows the MRSS with combined characteris-tics of a high stretchability(120%),excellent stability(with a repetition error of 0.8%after 11000 cycles),and outstanding sensitivity(gauge factor up to 2692 beyond 100%).Impressively,the MRSS can still be used continauously within the working range without damage,even if stretched to 300%.Furthermore,compared with different structure sensors,the mechanism of the MRSS with high stretchability and stability is ***'s more,a multilayer finite element model,based on the layered structure of the LSG and the morphology of the cracks,is proposed to investigate the strain sensing behavior and failure mechanism of the ***,due to the outstanding performance,the MRSS not only performes well in monitoring full-range human motions,but also achieves intelligent recognitions of various respiratory activities and ges-tures assisted by neural network algorithms(the accuracy up to 94.29%and 100%,respectively).This work provides a new approach for designing high-performance resistive strain sensors and shows great potential in full-range and long-term intelligent health management and human-machine interac-tions applications.

关键词： flexible strain sensor excellent stretchability and stability layered laser-scribed graphene micromesh reinforced structure multilayer finite element model

来源：评论

学校读者我要写书评

暂无评论

Area Intervention for Enhancing Class Activation Maps in Weakly Supervised Semantic Segmentation

Area Intervention for Enhancing Class Activation Maps in Wea...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Xuewei Li Yujie Diao Mei Yu Chenhan Wang Jie Gao Ruiguo Yu College of Intelligence and Computing Tianjin University Tianjin China Tianjin Key Laboratory of Cognitive Computing and Application Tianjin China Tianjin Key Laboratory of Advanced Networking Tianjin China School of Feature Technology Tianjin University Tianjin China OpenBayes (Tianjin) IT Co. Ltd. Tianjin China

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

Generating class activation maps (CAM) as seed regions is a crucial step in weakly supervised semantic segmentation (WSSS). During the training of classification models, instance area information is incorporated into feature vectors and learned by the network. However, during CAM generation, pixel-level prediction scores are solely dependent on features and classifier weights, neglecting the area factor. Such area information becomes a source of bias between training and CAM generation, leading to a significant under-activation (false negatives) of foreground regions. To address this issue, we propose a class area intervention strategy to fine-tune the classification model and rectify this bias. Additionally, we employ a partition activation strategy that can simultaneously consider both under activation and over-activation to generate more precise AICAMs. AICAM is applicable to various WSSS methods based on CAM or its variants. The evaluations on both the PASCAL VOC and MS COCO datasets demonstrate that our method enhances multiple WSSS techniques.

关键词： Training Semantic segmentation Vectors

来源：评论

学校读者我要写书评

暂无评论

Multi-Level Augmentation Consistency Learning and Sample Selection for Semi-Supervised Domain Generalization

Multi-Level Augmentation Consistency Learning and Sample Sel...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Mei Yu Yujian Zhang Xuewei Li Ruixuan Zhang Han Jiang Jie Gao Zhiqiang Liu College of Intelligence and Computing Tianjin University Tianjin China Tianjin Key Laboratory of Cognitive Computing and Application Tianjin China Tianjin Key Laboratory of Advanced Networking Tianjin China School of Future Technology Tianjin University Tianjin China OpenBayes (Tianjin) IT Co. Ltd. Tianjin China

Semi-supervised domain generalization (SSDG) aims to build a domain-generalized model using partially labeled data from source domains. Mainstream SSDG methods follow the augmentation consistency in FixMatch. However, the extraction of domain-invariant features may be challenging due to the absence of feature-based operations, further leading to overfitting of the classifier. To this end, we propose Multi-level Augmentation Consistency Learning (MACMatch), which improves the generalization of feature extractor and classifier through feature-based augmentation consistency. On the other hand, existing methods assume labeled data are class-balanced and domain-balanced, which is easily violated in practice. Based on this, we introduce Representativity and Diversity-based Sample Selection (RDSS), which models data as graphs to evaluate reasonable samples for labeling, relaxing the assumption for labeled data. Experiments on PACS and OfficeHome demonstrate that MACMatch outperforms state-of-the-art SSDG methods. Furthermore, MAC-Match with RDSS achieves competitive results without domain and class priori assumptions. Code is available at https://***/Y-J-Zhang/MACMatch-RDSS.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learning to Imagine: Diversify Memory for Incremental Learning using Unlabeled Data

arXiv

引用

arXiv 2022年

作者： Tang, Yu-Ming Peng, Yi-Xing Zheng, Wei-Shi School of Computer Science and Engineering Sun Yat-Sen University China Peng Cheng Laboratory Shenzhen China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

Deep neural network (DNN) suffers from catastrophic forgetting when learning incrementally, which greatly limits its applications. Although maintaining a handful of samples (called "exemplars") of each task could alleviate forgetting to some extent, existing methods are still limited by the small number of exemplars since these exemplars are too few to carry enough task-specific knowledge, and therefore the forgetting remains. To overcome this problem, we propose to "imagine" diverse counterparts of given exemplars referring to the abundant semantic-irrelevant information from unlabeled data. Specifically, we develop a learnable feature generator to diversify exemplars by adaptively generating diverse counterparts of exemplars based on semantic information from exemplars and semantically-irrelevant information from unlabeled data. We introduce semantic contrastive learning to enforce the generated samples to be semantic consistent with exemplars and perform semantic-decoupling contrastive learning to encourage diversity of generated samples. The diverse generated samples could effectively prevent DNN from forgetting when learning new tasks. Our method does not bring any extra inference cost and outperforms state-of-the-art methods on two benchmarks CIFAR-100 and ImageNet-Subset by a clear margin. Copyright © 2022, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Domain Adaptation Semantic Segmentation on Thyroid Ultrasound Images Based on Task-Oriented Feature Disentanglement

Unsupervised Domain Adaptation Semantic Segmentation on Thyr...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Zijian Zhang Ruiguo Yu Xi Wei Jie Gao Mei Yu Xuewei Li Zhiqiang Liu College of Intelligence and Computing Tianjin University Tianjin China Tianjin Key Laboratory of Cognitive Computing and Application Tianjin China Tianjin Key Laboratory of Advanced Networking Tianjin China School of Feature Technology Tianjin University Tianjin China Tianjin Medical University Cancer Institute and Hospital Tianjin China

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

Unsupervised Domain Adaptation (UDA) methods have become essential for computer-aided diagnostic analysis on medical images due to the advantage of improving the model generalization ability with fewer annotations. The disentanglement-based UDA methods improve the segmentation performance significantly by disentangling the features into domain-specific and domain-invariant components. However, such methods neglect detailed texture in ultrasound images, resulting in inaccurate segmentations of nodules. To address the above problem, we propose a Task-Oriented Feature Disentanglement (TOFD) method to achieve better UDA segmentation on images from different ultrasound machines. TOFD achieves finer-grained disentanglement by the Feature Constraint Module based on maximum entropy. Furthermore, the Domain Label Encoding Module can improve the stability of features by integrating the latent feature of domain bias. Extensive experiments demonstrate that TOFD can effectively enhance the model’s generalization capability and confirm the performance of TOFD on ultrasound images exceeds that of state-of-the-art UDA semantic segmentation.

关键词： Degradation Adaptation models Ultrasonic imaging Semantic segmentation Stability analysis Entropy Encoding

来源：评论

学校读者我要写书评

暂无评论

Balanced And Discriminative Contrastive Learning For Class-Imbalanced Medical Images

Balanced And Discriminative Contrastive Learning For Class-I...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Xuewei Li Yilong Fan Hao Zheng Jie Gao Xi Wei Mei Yu College of Intelligence and Computing Tianjin University Tianjin China Tianjin Key Laboratory of Cognitive Computing and Application Tianjin China Tianjin Key Laboratory of Advanced Networking Tianjin China School of Feature Technology Tianjin University Tianjin China Tianjin Medical University Cancer Institute and Hospital Tianjin China

The class imbalance problem, which is prevalent in medical image datasets, seriously affects the diagnostic effectiveness of deep learning-based network models. Recently, the method based on two-stage learning has produced promising results in solving class imbalance. In two-stage learning, the learning of unbiased classifiers has been well studied, but the representation of imbalanced data is still being explored. In this paper, we focus on the representation learning stage of class-imbalanced and propose a novel balanced and discriminative contrastive learning (BDCL) method. Compared with supervised contrastive learning, BDCL has two improvements: temperature dynamic learning, which balances the gradient contribution of negative samples from different classes; hard example prototypes, which can better learn the feature differences between tail classes. A variety of experimental results on the imbalanced medical image datasets show that BDCL enables the network models to learn representations with desirable balancedness and discriminativeness, effectively solving the class imbalance problem.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Remolding Semantic Focus with Dual Attention Mechanism for Aspect-based Sentiment Analysis 8

Remolding Semantic Focus with Dual Attention Mechanism for A...

引用

8th IEEE International Conference on Cloud computing and intelligence Systems, CCIS 2022

作者： Li, Xingda Bao, Yanwei Hu, Min Ren, Fuji Hefei University of Technology Hefei Anhui230009 China Hefei University of Technology Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine China University of Electronic Science and Technology of China Chengdu Chengdu611730 China

ISBN: (纸本)9781665477352

Aspect-based sentiment analysis (ABSA) is an NLP task that classify fine-grained sentiment towards one specific aspect from the same text. While attention mechanism has achieved great success, attaching aspects to abstract sentiment remains challenging. In this paper, we propose dual attention mechanism, a novel method to re-weight the distribution of attention between stack BERT layers, in prompt learning way with pretrained language model BERT. Specifically, after obtaining the most attractive words, the method raises weight of other possible corresponding words and makes model consider more comprehensively. To introduce more aspect information, we classify the sentiment in improved prompt learning way. Note that the overfitting using BERT on ABSA, we utilize the approach of staged loss that restrict the training not too small. Finally, the experiment results demonstrate the effectiveness and the stability of dual attention and provide a good insight of attention mechanism. © 2022 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Cross-camera Trajectories Help Person Retrieval in a Camera Network

arXiv

引用

arXiv 2022年

作者： Zhang, Xin Xie, Xiaohua Lai, Jianhuang Zheng, Wei-Shi The School of Computer Science and Engineering The Guangdong Province Key Laboratory of Information Security Technology The Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Sun Yat-sen University Guangzhou510006 China

We are concerned with retrieving a query person from multiple videos captured by a non-overlapping camera network. Existing methods often rely on purely visual matching or consider temporal constraints but ignore the spatial information of the camera network. To address this issue, we propose a pedestrian retrieval framework based on cross-camera trajectory generation, which integrates both temporal and spatial information. To obtain pedestrian trajectories, we propose a novel cross-camera spatio-temporal model that integrates pedestrians’ walking habits and the path layout between cameras to form a joint probability distribution. Such a spatio-temporal model among a camera network can be specified using sparsely sampled pedestrian data. Based on the spatio-temporal model, cross-camera trajectories can be extracted by the conditional random field model and further optimized by restricted non-negative matrix factorization. Finally, a trajectory re-ranking technique is proposed to improve the pedestrian retrieval results. To verify the effectiveness of our method, we construct the first cross-camera pedestrian trajectory dataset, the Person Trajectory Dataset, in real surveillance scenarios. Extensive experiments verify the effectiveness and robustness of the proposed method. Copyright © 2022, The Authors. All rights reserved.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

Adversarial Feature Augmentation for Cross-domain Few-shot Classification

arXiv

引用

arXiv 2022年

作者： Hu, Yanxu Ma, Andy J. School of Computer Science and Engineering Sun Yat-sen University China Guangdong Province Key Laboratory of Information Security Technology China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

Few-shot classification is a promising approach to solving the problem of classifying novel classes with only limited annotated data for training. Existing methods based on meta-learning predict novel-class labels for (target domain) testing tasks via meta knowledge learned from (source domain) training tasks of base classes. However, most existing works may fail to generalize to novel classes due to the probably large domain discrepancy across domains. To address this issue, we propose a novel adversarial feature augmentation (AFA) method to bridge the domain gap in few-shot learning. The feature augmentation is designed to simulate distribution variations by maximizing the domain discrepancy. During adversarial training, the domain discriminator is learned by distinguishing the augmented features (unseen domain) from the original ones (seen domain), while the domain discrepancy is minimized to obtain the optimal feature encoder. The proposed method is a plug-and-play module that can be easily integrated into existing few-shot learning methods based on meta-learning. Extensive experiments on nine datasets demonstrate the superiority of our method for cross-domain few-shot classification compared with the state of the art. Code is available at https : //***/youthhoo/AFA For Few shot learning. Copyright © 2022, The Authors. All rights reserved.

关键词： Learning systems

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：