检索结果-内蒙古大学图书馆

International Winter Workshop on brain-computer interface (BCI)

作者： Gege Zhan Haolong Su Pengchao Wang Lan Niu Jianxiong Bin Wei Mu Xueze Zhang Haifeng Jiang Lihua Zhang Xiaoyang Kang Shanghai Engineering Research Center of AI & Robotics MOE Frontiers Center for Brain Science State Key Laboratory of Medical Neurobiology Laboratory for Neural Interface and Brain Computer Interface Engineering Research Center of AI & Robotics Ministry of Education Institute of AI & Robotics Institute of Meta-Medical Academy for Engineering & Technology Fudan University Shanghai China Ji Hua Laboratory Foshan Guangdong Province China Shanghai Mental Center Shanghai Jiao Tong University School of Medicine Shanghai China Chinese Academy of Sciences CAS Center for Excellence in Brain Science and Intelligence Technology (CEBSIT) Shanghai China Yiwu Research Institute of Fudan University Chengbei Road Yiwu City Zhejiang China Zhejiang Lab Research Center for Intelligent Sensing Hangzhou China

EEG signal contains a wealth of information about brain activity, but the recording process is inevitably contaminated by EOG artifacts. An effective method to remove EOG artifacts can provide a guarantee for subsequent EEG analysis. In this paper, we compare the performance of four ICA algorithms in removing EOG artifacts from EEG signals of methamphetamine addicts. From the perspective of time domain and power spectral density, all the four algorithms can effectively remove the EOG artifacts without obvious difference. In terms of PSNR, MI and processing speed, FastICA algorithm can achieve higher processing speed and reconstruct signals better than the other three algorithms.

关键词： Electrooculography brain Electroencephalography brain-computer interfaces Recording Time-domain analysis

来源：评论

学校读者我要写书评

暂无评论

Effects of Input Neuron Mapping Coordinates in Spiking neural Network on the Motor Imagery EEG Signals Classification

Effects of Input Neuron Mapping Coordinates in Spiking Neura...

引用

International Winter Workshop on brain-computer interface (BCI)

作者： Gege Zhan Haolong Su Pengchao Wang Lan Niu Jianxiong Bin Wei Mu Xueze Zhang Haifeng Jiang Lihua Zhang Xiaoyang Kang Shanghai Engineering Research Center of AI & Robotics MOE Frontiers Center for Brain Science State Key Laboratory of Medical Neurobiology Institute of AI & Robotics Laboratory for Neural Interface and Brain Computer Interface Engineering Research Center of AI & Robotics Ministry of Education Institute of Meta-Medical Academy for Engineering & Technology Fudan University Shanghai China Ji Hua Laboratory Foshan Guangdong Province China Shanghai Mental Center Shanghai Jiao Tong University School of Medicine Shanghai China CAS Center for Excellence in Brain Science and Intelligence Technology (CEBSIT) Chinese Academy of Sciences Shanghai China Yiwu Research Institute of Fudan University Chengbei Road Yiwu City Zhejiang China Research Center for Intelligent Sensing Zhejiang Lab Hangzhou China

Spiking neural network (SNN), the third generation of the artificial neural network, uses the same computational principles as Spatio-temporal brain data (STBD) generation, so it can be used as an effective tool to learn and understand STBD. When using SNN to process STBD, mapping of input neurons is a problem to be considered. This paper investigates the influence of changing the mapping coordinates of input neurons on motor imagery EEG signal classification. The results show that the coordinate change affects the interaction between the input neuron and its neighboring neurons, and causes the classification accuracy to change, but the impact mechanism is unknown.

关键词： Neurons Pattern classification Artificial neural networks Electroencephalography brain-computer interfaces Biological neural networks

来源：评论

学校读者我要写书评

暂无评论

VQCNIR: Clearer Night Image Restoration with Vector-Quantized Codebook

arXiv

引用

arXiv 2023年

作者： Zou, Wenbin Gao, Hongxia Ye, Tian Chen, Liang Yang, Weipeng Huang, Shasha Chen, Hongshen Chen, Sixiang The School of Automation Science and Engineering South China University of Technology China Research Center for Brain-Computer Interface Pazhou Laboratory Guangzhou China The Hong Kong University of Science and Technology Guangzhou China College of Photonic and Electronic Engineering Fujian Normal University China

Night photography often struggles with challenges like low light and blurring, stemming from dark environments and prolonged exposures. Current methods either disregard priors and directly fitting end-to-end networks, leading to inconsistent illumination, or rely on unreliable handcrafted priors to constrain the network, thereby bringing the greater error to the final result. We believe in the strength of data-driven high-quality priors and strive to offer a reliable and consistent prior, circumventing the restrictions of manual priors. In this paper, we propose Clearer Night Image Restoration with Vector-Quantized Codebook (VQCNIR) to achieve remarkable and consistent restoration outcomes on real-world and synthetic benchmarks. To ensure the faithful restoration of details and illumination, we propose the incorporation of two essential modules: the Adaptive Illumination Enhancement Module (AIEM) and the Deformable Bi-directional Cross-Attention (DBCA) module. The AIEM leverages the inter-channel correlation of features to dynamically maintain illumination consistency between degraded features and high-quality codebook features. Meanwhile, the DBCA module effectively integrates texture and structural information through bi-directional cross-attention and deformable convolution, resulting in enhanced fine-grained detail and structural fidelity across parallel decoders. Extensive experiments validate the remarkable benefits of VQCNIR in enhancing image quality under low-light conditions, showcasing its state-of-the-art performance on both synthetic and real-world datasets. The code is available at https://***/AlexZou14/VQCNIR. © 2023, CC BY.

关键词： Restoration

来源：评论

学校读者我要写书评

暂无评论

A High-Performance Classification Method Based on CNN for Interventional EEG Data

A High-Performance Classification Method Based on CNN for In...

引用

International Symposium on Autonomous Systems (ISAS)

作者： Sining Li Gan Liu Fan Feng Dongdong Wu Yudong Ma Feng Duan Tianjin Key Laboratory of Interventional Brain-Computer Interface and Intelligent Rehabilitation Nankai University Tianjin China Department of Biomedical Engineering School of Medicine Tsinghua University Beijing China Department of Neurosurgery General Hospital of the People’s Liberation Army Beijing China Department of Neurosurgery Air Force Medical University Beijing China

ISBN: (数字)9798350363173

ISBN: (纸本)9798350363180

Interventional brain-computer interfaces (BCI) have been developed for many years and are capable of collecting electroencephalogram (EEG) signals. However, research on interventional EEG signals is just beginning. In this paper. We present a new deep learning network for intentional classification of interventional EEG in a monkey. Electrodes are placed on the inner walls of the vessels in the superior sagittal sinus to collect signals in four states. Then, we construct a Convolutional neural Networks (CNN) model to extract features and classify the states. In the experiments, we recognize the interventional EEG signals of the monkey in the four states, and the average recognition accuracy of its EEG signals in each state is more than 90% for the whole dataset, and 70% for the validation set. The experimental results show that the method in this paper can effectively recognize and classify interventional EEG signals in different states. Our work advances the application of interventional BCIs and paves the way for the future development of more versatile and responsive interventional EEG interfaces.

关键词： Electrodes Deep learning brain modeling Feature extraction Electroencephalography Data models brain-computer interfaces

来源：评论

学校读者我要写书评

暂无评论

Ultra-high field MRI compatible electrical and optical neural interface

引用

Sensors and Actuators A: Physical 2025年 393卷

作者： Yuan Zhang Song Le Aiping Wang Gege Zhan Xiaoyong Zhang Lihua Zhang Zhongxue Gan Xiaoyang Kang Laboratory for Neural Interface and Brain Computer Interface MOE Frontiers Center for Brain Science State Key Laboratory of Brain Function and Disorders Institute of AI & Robotics Institute of Meta-Medical Academy for Engineering & Technology College of Intelligent Robotics and Advanced Manufacturing Fudan University Shanghai 200433 China Yiwu Research Institute of Fudan University Yiwu City Zhejiang 322000 China

neural electrical interfaces are important tools for local neural stimulation and recording, while magnetic resonance imaging (MRI) is one of the effective and non-invasive techniques for recording whole-brain signals. MRI-compatible neural interfaces combine two approaches to neural activity and is of great importance for the understanding of brain function. Therefore, it makes both requests on the magnetic and electronic performance of neural interfaces. Here, we developed MRI-compatible flexible neural interfaces based on the highly conductive metal film, for the first time. Our approach is significantly different from the traditional carbon materials or conductive polymers based neural interfaces in that the non-metal film have reduced conductivity compared with the highly conductive metal film. This approach addresses the challenges encountered while using traditional metal-based conductive film in the MRI environment by the magnetron co-sputtering of the noble metal Au-Pt film with the opposite susceptibility. As a result, our MRI-compatible flexible neural interfaces achieve the highest integration density of electrodes. The highly conductive metal based neural interfaces were tested to be functionable, and showed little artifacts in an ultra-high field 11.7 T MRI scanner, which provide the possibility to multimodal neural recording and stimulation.

关键词： Bioelectronics Magnetic resonance imaging (MRI) compatible neural interface neural optrode Susceptibility

来源：评论

学校读者我要写书评

暂无评论

T-TIME: Test-Time Information Maximization Ensemble for Plug-and-Play BCIs

arXiv

引用

arXiv 2024年

作者： Li, Siyang Wang, Ziwei Luo, Hanbin Ding, Lieyun 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 Wuhan430074 China Shenzhen Huazhong University of Science and Technology Research Institute Shenzhen China Henan Key Laboratory of Brain Science and Brain Computer Interface Technology School of Electrical and Information Engineering Zhengzhou University China School of Civil and Hydraulic Engineering Huazhong University of Science and Technology Wuhan430074 China

Objective: An electroencephalogram (EEG)-based brain-computer interface (BCI) enables direct communication between the human brain and a computer. Due to individual differences and non-stationarity of EEG signals, such BCIs usually require a subject-specific calibration session before each use, which is time-consuming and user-unfriendly. Transfer learning (TL) has been proposed to shorten or eliminate this calibration, but existing TL approaches mainly consider offline settings, where all unlabeled EEG trials from the new user are available. Methods: This paper proposes Test-Time Information Maximization Ensemble (T-TIME) to accommodate the most challenging online TL scenario, where unlabeled EEG data from the new user arrive in a stream, and immediate classification is performed. T-TIME initializes multiple classifiers from the aligned source data. When an unlabeled test EEG trial arrives, T-TIME first predicts its labels using ensemble learning, and then updates each classifier by conditional entropy minimization and adaptive marginal distribution regularization. Our code is publicized. Results: Extensive experiments on three public motor imagery based BCI datasets demonstrated that T-TIME outperformed about 20 classical and state-of-the-art TL approaches. Significance: To our knowledge, this is the first work on test time adaptation for calibration-free EEG-based BCIs, making plug-and-play BCIs possible. © 2024, CC BY.

关键词： Calibration

来源：评论

学校读者我要写书评

暂无评论

Biomolecular condensates and disease pathogenesis

引用

Science China(Life Sciences) 2024年第9期67卷 1792-1832页

作者： Ke Ruan Ge Bai Yanshan Fang Dan Li Tingting Li Xingguo Liu Boxun Lu Qing Lu Zhou Songyang Shuguo Sun Zheng Wang Xin Zhang Wen Zhou Hong Zhang The First Affiliated Hospital&School of Life Sciences Ministry of Education Key Laboratory for Membrane-less Organelles&Cellular DynamicsHefei National Research Center for Interdisciplinary Sciences at the MicroscaleCenter for Advanced Interdisciplinary Science and Biomedicine of IHMDivision of Life Sciences and MedicineUniversity of Science and Technology of ChinaHefei 230027China Nanhu Brain-computer Interface Institute Hangzhou 311100China Department of Neurology of Second Affiliated Hospital and School of Brain Science and Brain Medicine Zhejiang University School of MedicineHangzhou 310058China Interdisciplinary Research Center on Biology and Chemistry Shanghai Institute of Organic ChemistryChinese Academy of SciencesShanghai 201210China University of Chinese Academy of Sciences Beijing 100049China Bio-X Institutes Key Laboratory for the Genetics of Developmental and Neuropsychiatric Disorders(Ministry of Education)Shanghai Jiao Tong UniversityShanghai 200030China Department of Biomedical Informatics School of Basic Medical SciencesPeking University Health Science CenterBeijing 100191China CAS Key Laboratory of Regenerative Biology Joint School of Life SciencesGuangzhou Institutes of Biomedicine and HealthChinese Academy of SciencesGuangzhou 510530China Joint School of Life Sciences Guangzhou Medical UniversityGuangzhou 510000China Neurology Department at Huashan Hospital State Key Laboratory of Medical Neurobiology and MOE Frontiers Center for Brain ScienceInstitutes of Brain ScienceSchool of Life SciencesFudan UniversityShanghai 200433 China Key Laboratory for the Genetics of Developmental and Neuropsychiatric Disorders Ministry of EducationBio-X InstitutesShanghai Jiao Tong UniversityShanghai 200030China State Key Laboratory of Biocontrol MOE Key Laboratory of Gene Function and Regulation and Guangzhou Key Laboratory of Healthy Aging ResearchSchool of Life SciencesSun Yat-sen Memorial HospitalSun Yat-sen UniversityGuangzhou 510275China Department of Human Anatomy Hist

Biomolecular condensates or membraneless organelles(MLOs)formed by liquid-liquid phase separation(LLPS)divide intracellular spaces into discrete compartments for specific *** of LLPS or aberrant phase transition that disturbs the formation or material states of MLOs is closely correlated with neurodegeneration,tumorigenesis,and many other pathological ***,we summarize the recent progress in development of methods to monitor phase separation and we discuss the biogenesis and function of MLOs formed through phase *** then present emerging proof-of-concept examples regarding the disruption of phase separation homeostasis in a diverse array of clinical conditions including neurodegenerative disorders,hearing loss,cancers,and immunological ***,we describe the emerging discovery of chemical modulators of phase separation.

关键词： liquid-liquid phase separation biomolecular condensate membraneless organelle

来源：评论

学校读者我要写书评

暂无评论

Hand Gesture Recognition Using Surface Electromyography and 3d Self-Organizing Map Network with Switching States

SSRN

引用

SSRN 2024年

作者： Duan, Yahan Li, Wenyu Solé-Casals, Jordi Liu, Zhongxin Duan, Feng College of Artificial Intelligence Nankai University 38 Tongyan Road Jinnan District Tianjin300350 China Tianjin Key Laboratory of Interventional Brain-Computer Interface and Intelligent Rehabilitation 38 Tongyan Road Jinnan District Tianjin300350 China Data and Signal Processing Group University of Vic Central University of Catalonia Vic Catalonia08500 Spain

Surface electromyography (sEMG) is widely utilized in rehabilitation therapy. However, existing gesture recognition methods predominantly concentrate on rigid static gestures, overlooking the importance of dynamic switching in practical tasks and the associated dynamic features for natural hand control. This neglect limits the consideration of hand gesture dexterity and diversity. In response, this work proposes a novel paradigm for hand gesture recognition, in which the switching state between two gestures is treated equally as a static pattern for downstream feature extraction and classification. A 3-dimensional self-organizing mapping neural network is investigated to fully characterize the high-dimensional sEMG signals. Due to the sequential feature of hand gesture variation, the prior switching probability is further applied to reduce ambiguity and computational consumption. The proposed paradigm and algorithm are tested and verified through five-fold cross-validation with multiple subjects. The experimental results show that the average accuracy of the 3D self-organizing mapping method is 78.74% while considering switching states, which is at least 6.97% higher than some traditional learning-based algorithms: long short-term memory and wavelet neural network. This work suggests the potential for achieving dexterous control in prosthetics. © 2024, The Authors. All rights reserved.

关键词： Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

Exploiting the Intrinsic Neighborhood Semantic Structure for Domain Adaptation in EEG-based Emotion Recognition

引用

IEEE Transactions on Affective Computing 2025年

作者： Yang, Yi Wang, Ze Song, Yu Jia, Ziyu Wang, Boyu Jung, Tzyy-Ping Wan, Feng Macau University of Science and Technology Macao Centre for Mathematical Sciences Respiratory Disease AI Laboratory on Epidemic Intelligence and Medical Big Data Instrument Applications Faculty of Innovation Engineering 999078 China Tianjin University of Technology School of Electrical Engineering and Automation Tianjin Key Laboratory of New Energy Power Conversion Transmission and Intelligent Control Tianjin300384 China Chinese Academy of Sciences Beijing Key Laboratory of Brainnetome and Brain-Computer Interface and Brainnetome Center Institute of Automation Beijing100045 China Western University Department of Computer Science Brain Mind Institute LondonONN6A 3K7 Canada University of California at San Diego Swartz Center for Computational Neuroscience Institute for Neural Computation La Jolla CA92093 United States University of Macau Department of Electrical and Computer Engineering Faculty of Science and Technology China University of Macau Centre for Cognitive and Brain Sciences Centre for Artificial Intelligence and Robotics Institute of Collaborative Innovation 999078 China

Due to the inherent non-stationarity and individual differences present in electroencephalogram (EEG) signals, developing a generalizable model that performs well on new subjects is challenging in EEG-based emotion recognition. Most existing domain adaptation (DA) methods typically mitigate these discrepancies by aligning the marginal distributions of domain feature representations. However, when there is a significant difference in the class-conditional distribution between domain features and labels, the domain-invariant features learned by aligning marginal distributions may have limited discriminative ability for unlabeled target instances or even prove counterproductive. To address this issue, we propose a Neighborhood Semantic Aware Learning-based Dynamic Graph Attention Convolution (NSAL-DGAT) approach that learns target semantic information by considering the inter-domain semantic topological structure, thereby improving classifier adaptation for target instances. Specifically, the proposed NSAL framework is designed to capitalize on the insight that after domain feature alignment, some target samples and their neighboring source samples exhibit similar semantics. By leveraging the neighborhood topological structure, we extract and incorporate semantic target features to train a more transferable classifier. Besides, we implement an entropy weighting mechanism to emphasize representative target semantic information, encouraging target instances to prioritize high-confidence individuals within the source neighborhood. We have conducted extensive experiments on the public SEED dataset and our collected the Hearing-Impaired EEG Dataset (HIED). The experimental results underscore the efficacy of our proposed NSAL-DGAT approach, showcasing state-of-the-art accuracy in subject-dependent as well as subject-independent scenarios. The source code is available at https://***/YYingDL/NSAL-DGAT. © 2010-2012 IEEE.

关键词： Speech analysis

来源：评论

学校读者我要写书评

暂无评论

Family history, inflammation, and cerebellum in major depression: a combined VBM and dynamic functional connectivity study

引用

Translational Psychiatry 2025年第1期15卷 1-7页

作者： Pang, Jianyue Xu, Jiaying Chen, Long Teng, Huimin Su, Chenxiao Zhang, Zhiyuan Gao, Lingyun Zhang, Rui Liu, Gang Chen, Yuan He, Jin Pang, Yajing Li, Hengfen Department of Psychiatry The First Affiliated Hospital of Zhengzhou University Zhengzhou China Henan Key Laboratory of Brain Science and Brain-Computer Interface Technology School of Electrical and Information Engineering Zhengzhou University Zhengzhou China Department of Neurosurgery Zhengzhou Central Hospital Affiliated to Zhengzhou University Zhengzhou China Department of Magnetic Resonance Imaging The First Affiliated Hospital of Zhengzhou University Zhengzhou China

A family history (FH) of depression significantly influences the progress of major depressive disorder (MDD). However, the underlying neural mechanism of FH remains unclear. This study examined the association between brain structural and connectivity alterations, inflammation, and FH in MDD. A total of 134 MDD patients with (FH group, n = 43) and without (NFH group, n = 91) first-degree FH and 96 demographic-matched healthy controls (HCs) were recruited. Voxel-based morphometry (VBM) and sliding-window dynamic functional connectivity (dFC) analyses were performed, and inflammatory biomarkers (C-reactive protein (CRP) and interleukin-6 (IL-6)) were detected. Compared with HCs, FH and NFH groups showed decreased gray matter volume (GMV) in the left cerebellum posterior lobe and increased dFC between this region and the left inferior parietal lobule. The FH group showed increased dFC between the cerebellum region and medial prefrontal cortex (mPFC) compared to NFH and HCs. The combination of these brain measurements further differentiated between FH and NFH. Moreover, the GMV of the cerebellum was positively correlated with CRP in the NFH group, while the dFC between the cerebellum and mPFC was positively correlated with IL-6 in the FH group. The present findings indicate that cerebellar structure and dynamic function vary according to FH of MDD and are related to inflammatory factors, potentially offering novel insights into the underlying pathogenic mechanisms of MDD. © The Author(s) 2025.

关键词：

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：