检索结果-内蒙古大学图书馆

Federated Motor imagery Classification for Privacy-Preserving Brain-Computer Interfaces

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Jia, Tianwang Meng, Lubin Li, Siyang Liu, Jiajing Wu, Dongrui The Key Laboratory The Ministry of Education for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Shenzhen Huazhong University Science and Technology Research Institute Shenzhen518063 China The School of Civil and Hydraulic Engineering Huazhong University of Science and Technology Wuhan430074 China

Training an accurate classifier for EEG-based brain-computer interface (BCI) requires EEG data from a large number of users, whereas protecting their data privacy is a critical consideration. Federated learning (FL) is a promising solution to this challenge. This paper proposes Federated classification with local Batch-specific batch normalization and Sharpness-aware minimization (FedBS) for privacy protection in EEG-based motor imagery (MI) classification. FedBS utilizes local batch-specific batch normalization to reduce data discrepancies among different clients, and sharpness-aware minimization optimizer in local training to improve model generalization. Experiments on three public MI datasets using three popular deep learning models demonstrated that FedBS outperformed six state-of-the-art FL approaches. Remarkably, it also outperformed centralized training, which does not consider privacy protection at all. In summary, FedBS protects user EEG data privacy, enabling multiple BCI users to participate in large-scale machine learning model training, which in turn improves the BCI decoding accuracy. © 2024, CC BY.

关键词： Federated learning

Learning Probabilistic Coordinate Fields for Robust Correspondences

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhao, Weiyue Lu, Hao Ye, Xinyi Cao, Zhiguo Li, Xin Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China The Lane Department of Computer Science and Electrical Engineering West Virginia University MorgantownWV26506-6109 United States

We introduce Probabilistic Coordinate Fields (PCFs), a novel geometric-invariant coordinate representation for image correspondence problems. In contrast to standard Cartesian coordinates, PCFs encode coordinates in correspondence-specific barycentric coordinate systems (BCS) with affine invariance. To know when and where to trust the encoded coordinates, we implement PCFs in a probabilistic network termed PCF-Net, which parameterizes the distribution of coordinate fields as Gaussian mixture models. By jointly optimizing coordinate fields and their confidence conditioned on dense flows, PCF-Net can work with various feature descriptors when quantifying the reliability of PCFs by confidence maps. An interesting observation of this work is that the learned confidence map converges to geometrically coherent and semantically consistent regions, which facilitates robust coordinate representation. By delivering the confident coordinates to keypoint/feature descriptors, we show that PCF-Net can be used as a plug-in to existing correspondence-dependent approaches. Extensive experiments on both indoor and outdoor datasets suggest that accurate geometric invariant coordinates help to achieve the state of the art in several correspondence problems, such as sparse feature matching, dense image registration, camera pose estimation, and consistency filtering. Further, the interpretable confidence map predicted by PCF-Net can also be leveraged to other novel applications from texture transfer to multi-homography classification. Copyright © 2023, The Authors. All rights reserved.

关键词： Textures

A2B: Anchor to Barycentric Coordinate for Robust Correspondence

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhao, Weiyue Lu, Hao Cao, Zhiguo Li, Xin The Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Lane Department of Computer Science and Electrical Engineering West Virginia University Commonwealth of Virginia Morgantown 15461 United States

There is a long-standing problem of repeated patterns in correspondence problems, where mismatches frequently occur because of inherent ambiguity. The unique position information associated with repeated patterns makes coordinate representations a useful supplement to appearance representations for improving feature correspondences. However, the issue of appropriate coordinate representation has remained unresolved. In this study, we demonstrate that geometric-invariant coordinate representations, such as barycentric coordinates, can significantly reduce mismatches between features. The first step is to establish a theoretical foundation for geometrically invariant coordinates. We present a seed matching and filtering network (SMFNet) that combines feature matching and consistency filtering with a coarse-to-fine matching strategy in order to acquire reliable sparse correspondences. We then introduce DEGREE, a novel anchor-to-barycentric (A2B) coordinate encoding approach, which generates multiple affine-invariant correspondence coordinates from paired images. DEGREE can be used as a plug-in with standard descriptors, feature matchers, and consistency filters to improve the matching quality. Extensive experiments in synthesized indoor and outdoor datasets demonstrate that DEGREE alleviates the problem of repeated patterns and helps achieve state-of-the-art performance. Furthermore, DEGREE also reports competitive performance in the third image Matching Challenge at CVPR 2021. This approach offers a new perspective to alleviate the problem of repeated patterns and emphasizes the importance of choosing coordinate representations for feature correspondences. Copyright © 2023, The Authors. All rights reserved.

关键词：

Relative-Posture-Fixed Model Predictive Human-Following control with Visibility Constraints in Obstacle Environments

学校读者我要写书评

暂无评论

Relative-Posture-Fixed Model Predictive Human-Following Cont...

International Conference on Advanced Robotics and Mechatronics (ICARM)

作者： Yikun Zhang Jian Huang Jinqi Yu Yaonan Zhu Yasuhisa Hasegawa Key Laboratory for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Shenzhen Huazhong University of Science and Technology Research Institute ShenZhen China Department of Micronano Mechanical Science and Engineering Nagoya University Nagoya Japan

The relative-posture-fixed human following is critical for the human-robot interaction and cooperation in daily scenes such as domestic service and healthcare. However, few of previous researches have discussed the difficulties faced by mobile robots in the real world, including the limitation of sensing range and hindrance from obstacles. For practicality, in this paper we investigate the relative-posture-fixed following control with collision avoidance and visibility constraints. The control task is formulated as a receding-horizon optimization problem and solved under the Nonlinear Model Predictive control (NMPC) framework, while an Extended Kalman Filter (EKF) based human trajectory predict algorithm is integrated into the robot controller. The effectiveness of the proposed algorithm is verified in a simulation, and the results demonstrate a promising performance of our controller for the human-following task in complicated environments.

关键词：

CPTNet: Cascade Pose Transform Network for Single image Talking Head Animation 15th

学校读者我要写书评

暂无评论

CPTNet: Cascade Pose Transform Network for Single Image Talk...

15th Asian Conference on Computer Vision, ACCV 2020

作者： Zhang, Jiale Xian, Ke Liu, Chengxin Chen, Yinpeng Cao, Zhiguo Zhong, Weicai Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Huawei CBG Consumer Cloud Service Search Product and Big Data Platform Department Xi’an China

ISBN: (纸本)9783030695378

We study the problem of talking head animation from a single image. Most of the existing methods focus on generating talking heads for human. However, little attention has been paid to the creation of talking head anime. In this paper, our goal is to synthesize vivid talking heads from a single anime image. To this end, we propose cascade pose transform network, termed CPTNet, that consists of a face pose transform network and a head pose transform network. Specifically, we introduce a mask generator to animate facial expression (e.g., close eyes and open mouth) and a grid generator for head movement animation, followed by a fusion module to generate talking heads. In order to handle large motion and obtain more accurate results, we design a pose vector decomposition and cascaded refinement strategy. In addition, we create an anime talking head dataset, that includes various anime characters and poses, to train our model. Extensive experiments on our dataset demonstrate that our model outperforms other methods, generating more accurate and vivid talking heads from a single anime image. © 2021, Springer Nature Switzerland AG.

关键词： Animation

Lite-HRNet: A lightweight high-resolution network

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Yu, Changqian Xiao, Bin Gao, Changxin Yuan, Lu Zhang, Lei Sang, Nong Wang, Jingdong Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Microsoft

We present an efficient high-resolution network, Lite-HRNet, for human pose estimation. We start by simply applying the efficient shuffle block in ShuffleNet to HRNet (high-resolution network), yielding stronger performance over popular lightweight networks, such as MobileNet, ShuffleNet, and Small HRNet. We find that the heavily-used pointwise (1 × 1) convolutions in shuffle blocks become the computational bottleneck. We introduce a lightweight unit, conditional channel weighting, to replace costly pointwise (1 × 1) convolutions in shuffle blocks. The complexity of channel weighting is linear w.r.t the number of channels and lower than the quadratic time complexity for pointwise convolutions. Our solution learns the weights from all the channels and over multiple resolutions that are readily available in the parallel branches in HRNet. It uses the weights as the bridge to exchange information across channels and resolutions, compensating the role played by the pointwise (1 × 1) convolution. Lite-HRNet demonstrates superior results on human pose estimation over popular lightweight networks. Moreover, Lite-HRNet can be easily applied to semantic segmentation task in the same lightweight manner. The code and models have been publicly available at https://***/HRNet/Lite-HRNet. © 2021, CC BY.

关键词： Convolution

Isoform Function Prediction Based on Heterogeneous Graph Attention Networks

学校读者我要写书评

暂无评论

Isoform Function Prediction Based on Heterogeneous Graph Att...

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Kuo Guo Yifan Li Hao Chen Hong-Bin Shen Yang Yang Department of Computer Science and Engineering Shanghai Jiao Tong University and Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai China Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University and Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China Computational Biology Department School of Computer Science Carnegie Mellon University Pittsburgh PA USA

Isoforms refer to different mRNA molecules transcribed from the same gene, which can be translated into proteins with varying structures and functions. Predicting the functions of isoforms is an essential topic in bioinformatics as it can provide valuable insights into the intricate mechanisms of gene regulation and biological processes. Conventionally, gene function labels are standardized in Gene Ontology (GO) terms. However, traditional methods for predicting isoform function are largely limited by the absence of isoform-specific labels, sparse annotations, and the vast number of GO terms. To address these issues, we propose HANIso, a deep learning-based method for isoform function prediction. HANIso leverages a pretrained protein language model to extract features from protein sequences. It also integrates heterogeneous information, such as isoform sequence features, GO annotations, and isoform interaction data, using a Heterogeneous Graph Attention Network (HAN). This allows the model to learn the importance of different sources of information and their semantic relationships through the attention mechanism. Our method can predict function labels at both the gene level and isoform level. We conduct experiments on two species datasets, and the results demonstrate that our method outperforms existing methods on both AUROC and AUPRC. HANIso has the potential to overcome the limitations of traditional methods and provide a more accurate and comprehensive understanding of isoform function.

关键词：

Adversarial attacks and defenses in physiological computing:a systematic review

学校读者我要写书评

暂无评论

National Science Open 2023年第1期2卷 62-90页

作者： Dongrui Wu Jiaxin Xu Weili Fang Yi Zhang Liuqing Yang Xiaodong Xu Hanbin Luo Xiang Yu Ministry of Education Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and AutomationHuazhong University of Science and TechnologyWuhan 430074China Zhejiang Lab Hangzhou 311121China School of Civil and Hydraulic Engineering Huazhong University of Science and TechnologyWuhan 430074China College of Public Administration Huazhong University of Science and TechnologyWuhan 430074China Electrical Engineering and Computer Science Department University of MichiganAnn Arbor MI 48109USA School of Management and Sino-European Institute for Intellectual Property Huazhong University of Science and TechnologyWuhan 430074China

Physiological computing uses human physiological data as system inputs in real *** includes,or significantly overlaps with,brain-computer interfaces,affective computing,adaptive automation,health informatics,and physiological signal based *** computing increases the communication bandwidth from the user to the computer,but is also subject to various types of adversarial attacks,in which the attacker deliberately manipulates the training and/or test examples to hijack the machine learning algorithm output,leading to possible user confusion,frustration,injury,or even ***,the vulnerability of physiological computing systems has not been paid enough attention to,and there does not exist a comprehensive review on adversarial attacks to *** study fills this gap,by providing a systematic review on the main research areas of physiological computing,different types of adversarial attacks and their applications to physiological computing,and the corresponding defense *** hope this review will attract more research interests on the vulnerability of physiological computing systems,and more importantly,defense strategies to make them more secure.

关键词： physiological computing brain-computer interfaces health informatics biometrics machine learning adversarial attack

EMPIRICAL STUDIES ON THE PROPERTIES OF LINEAR REGIONS IN DEEP NEURAL NETWORKS 8

学校读者我要写书评

暂无评论

EMPIRICAL STUDIES ON THE PROPERTIES OF LINEAR REGIONS IN DEE...

8th International Conference on Learning Representations, ICLR 2020

作者： Zhang, Xiao Wu, Dongrui Ministry of Education Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

A deep neural network (DNN) with piecewise linear activations can partition the input space into numerous small linear regions, where different linear functions are fitted. It is believed that the number of these regions represents the expressivity of the DNN. This paper provides a novel and meticulous perspective to look into DNNs: Instead of just counting the number of the linear regions, we study their local properties, such as the inspheres, the directions of the corresponding hyperplanes, the decision boundaries, and the relevance of the surrounding regions. We empirically observed that different optimization techniques lead to completely different linear regions, even though they result in similar classification accuracies. We hope our study can inspire the design of novel optimization techniques, and help discover and analyze the behaviors of DNNs. © 2020 8th International Conference on Learning Representations, ICLR 2020. All rights reserved.

关键词： Deep neural networks