检索结果-内蒙古大学图书馆

International Winter Workshop on brain-computer interface (BCI)

作者： Bo Wen Jing Zhang Minjie Wang Lusheng Liu Yuan Zhang Aiping Wang Lu Wang 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 Yiwu Research Institute of Fudan University Chengbei Road Yiwu City Zhejiang China Research Center for Intelligent Sensing Zhejiang Lab Hangzhou China

The implantable brain-computer interface is a kind of brain-computer interaction device. The electrode array implanted in the deep surface of the brain is used to study neural function and medical rehabilitation. Nowadays, the implanted type usually has different degrees of damage to the brain, and the intravascular electrode, as the best technology, has the advantage of no need to drill holes in the brain, and the EEG signal collected is also strong, so it has become a very promising direction. This paper mainly discusses the intravascular use of vascular stent as a carrier, the attachment of the electrode array to the vascular stent, and the multi-physical field simulation of the array in the superior sagittal sinus. By discussing the layout of different electrode arrays and the discussion of grounding electrodes, this paper summarizes a relatively reasonable electrode array layout and a relatively reasonable selection of grounding electrodes.

关键词： Electrodes Electric potential Minimally invasive surgery Grounding Layout Interference Electrical stimulation

来源：评论

学校读者我要写书评

暂无评论

A Channel Selection Method for Motor Imagery EEG Based on Fisher Score of OVR-CSP

A Channel Selection Method for Motor Imagery EEG Based on Fi...

引用

International Winter Workshop on brain-computer interface (BCI)

作者： Wei Mu Junkongshuai Wang Lu Wang Pengchao Wang Jiaguan Han Lan Niu Jianxiong Bin Lusheng Liu Jing Zhang Jie Jia 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 Institute of Meta-Medical Academy for Engineering & Technology Fudan University Shanghai China Ji Hua Laboratory Foshan Guangdong Province China Department of Rehabilitation Medicine Huashan Hospital Fudan University Shanghai China Yiwu Research Institute of Fudan University Chengbei Road Yiwu City Zhejiang China Research Center for Intelligent Sensing Zhejiang Lab Hangzhou China

EEG is widely used in the field of brain computer interfaces. It has the advantages of being non-invasive, easy acquisition, and so on. However, multi-channel EEG signals will bring noise interference and redundant information while improving the resolution, and channel selection can reduce noise signals to obtain more real signals. Therefore, appropriate channel selection is very necessary for BCI system application. This paper proposes a Fisher score calculation method based on OVR-CSP features for channel selection and uses a transformer to classify. The experimental results show that the proposed method achieves 85.54% accuracy in selecting 16.55 channels on the public dataset BCI IV IIa.

关键词： Electrodes Interference Transformers Feature extraction Electroencephalography brain-computer interfaces Physiology

来源：评论

学校读者我要写书评

暂无评论

Generative Adversarial Networks for Electroencephalogram Signal Analysis: A Mini Review

Generative Adversarial Networks for Electroencephalogram Sig...

引用

International Winter Workshop on brain-computer interface (BCI)

作者： Junkongshuai Wang Wei Mu Aiping Wang Lu Wang Jiaguan Han Pengchao Wang Lan Niu Jianxiong Bin 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 Yiwu Research Institute of Fudan University Chengbei Road Yiwu City Zhejiang China Research Center for Intelligent Sensing Zhejiang Lab Hangzhou China

brain-computer interface (BCI) technology based on electroencephalography (EEG) signals is growing rapidly and attracting widespread attention. However, due to the EEG acquisition methods, the quality and quantity of EEG signals are not able to be guaranteed. To alleviate the problems caused by the lack of data, in this paper, we introduce the applications of EEG signals using generative adversarial networks (GANs) which have shown great performance in image data augmentation and other time series data and then discuss their performance.

关键词： Time series analysis Generative adversarial networks Electroencephalography brain-computer interfaces Signal analysis

来源：评论

学校读者我要写书评

暂无评论

Enhancing Motor Imagery EEG Signal Classification with Simplified GoogLeNet

Enhancing Motor Imagery EEG Signal Classification with Simpl...

引用

International Winter Workshop on brain-computer interface (BCI)

作者： Lu Wang Junkongshuai Wang Bo Wen Wei Mu Lusheng Liu Jiaguan Han Lihua Zhang Jie Jia Xiaoyang Kang Shanghai Engineering Research Center of AI & Robotics MOE Frontiers Center for Brain Science State Key Laboratory of Medical NeurobiologyAcademy for Engineering & Technology Laboratory for Neural Interface and Brain Computer Interface Engineering Research Center of AI & Robotics Ministry of Education Institute of AI & Robotics Institute of Meta-MedicalFudan University Shanghai China Ji Hua Laboratory Guangdong Province Foshan China Yiwu Research Institute of Fudan University Chengbei Road Yiwu City Zhejiang China Department of Rehabilitation Medicine Huashan Hospital Fudan University Shanghai China Research Center for Intelligent Sensing Zhejiang Lab Hangzhou China

The brain-computer interface is a novel tool for interaction between the brain and external devices, and is an important tool at the forefront of international brain science research. Motor imagery does not require external stimulation and is one of the most widely used BCI paradigms, and is now widely used to address the treatment of neurological impairments such as paralysis, stroke, and acromegaly. Electrophysiological source imaging is a technique based on the observation of electromagnetic signals from the cerebral cortex, reflecting the electrophysiological activity of brain nerve cells on the scalp surface of the brain. The wavelet transform, on the other hand, is commonly used for the processing of non-smooth signals and aims to extract excellent signal features. This paper combines these two algorithms as feature extraction methods. In recent years, deep learning has been increasingly combined with MI-EEG-based BCI. GoogLeNet is one of the most classical convolutional neural networks and has made a splash in ImageNet image recognition. However, using GoogLeNet to train the BCI public dataset BCI IV IIa and dataset HGD has shown problems such as long training time, overfitting, and gradient disappearance. In response, this paper proposes an improved and streamlined version of GoogLeNet for training based on this dataset to achieve an overall improvement in accuracy, training time, number of parameters, and other indicators. It is useful for the realistic application of MI-based BCI systems.

关键词： Training Wavelet transforms Surface waves Scalp Pattern classification Electrophysiology Streaming media

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

Removing EOG Artifacts from the Resting State EEG Signal of Methamphetamine Addicts by ICA Algorithms

Removing EOG Artifacts from the Resting State EEG Signal of ...

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 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

Light Radiation Simulation of Micro-LED Array for the Optical neural interface Targeted Cerebral Cortex in Rhesus Monkey

Light Radiation Simulation of Micro-LED Array for the Optica...

引用

International Winter Workshop on brain-computer interface (BCI)

作者： Lusheng Liu Wenlei Zhang Bo Wen Minjie Wang Aiping Wang Jing Zhang Yuan Zhang Song Le Haifeng Jiang Rongwei Zhai 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 Yiwu Research Institute of Fudan University Chengbei Road Yiwu City Zhejiang China Research Center for Intelligent Sensing Zhejiang Lab Hangzhou China Shanghai Mental Health Center Shanghai China Jiao Tong University School of Medicine Shanghai China Lingang Laboratory Shanghai China

The advanced technology of optogenetics has greatly promoted the development of neuroscience. To further optimize the optical neural interface, understanding the propagation process of light in neural tissues is essential for neuroscience research on the application of LED in optogenetics. In this work, we use TracePro software to build geometric models and simulate LED devices. The Rhesus monkey brain model is established to simulate the neural tissue to analyze the irradiance distribution at a specific location, to obtain the effective lighting range. In addition, we analyzed the influencing factors of the illumination range of the implanted light source device. We believe that the distance between devices should be $1.1 \sim1.2$ times of the light range of the simulation result when the devices fit the brain.

关键词： Neuroscience Shape Simulation Lighting Implants Light emitting diodes Optogenetics

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

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：

来源：评论

学校读者我要写书评

暂无评论

Historical perspectives, challenges, and future directions of implantable brain-computer interfaces for sensorimotor applications

引用

Bioelectronic Medicine 2021年第1期7卷 1-11页

作者： Chandrasekaran, Santosh Fifer, Matthew Bickel, Stephan Osborn, Luke Herrero, Jose Christie, Breanne Xu, Junqian Murphy, Rory K. J. Singh, Sandeep Glasser, Matthew F. Collinger, Jennifer L. Gaunt, Robert Mehta, Ashesh D. Schwartz, Andrew Bouton, Chad E. Neural Bypass and Brain Computer Interface Laboratory Feinstein Institutes for Medical Research Northwell Health ManhassetNY United States Research and Exploratory Development Department Johns Hopkins University Applied Physics Laboratory LaurelMD United States The Human Brain Mapping Laboratory Feinstein Institutes for Medical Research Northwell Health ManhassetNY United States Department of Neurosurgery Barbara Zucker School of Medicine at Hofstra/Northwell ManhassetNY United States Department of Neurology Donald and Barbara Zucker School of Medicine at Hofstra/Northwell ManhassetNY United States Departments of Radiology and Psychiatry Baylor College of Medicine HoustonTX United States Department of Neurosurgery Barrow Neurological Institute St. Joseph’s Hospital and Medical Center PhoenixAZ United States Good Shepherd Rehabilitation Hospital AllentownPA United States Departments of Radiology and Neuroscience Washington University in St Louis Saint LouisMO United States Rehabilitation Neural Engineering Labs University of Pittsburgh PittsburghPA United States Department of Physical Medicine and Rehabilitation University of Pittsburgh PittsburghPA United States Department of Bioengineering University of Pittsburgh PittsburghPA United States Center for the Neural Basis of Cognition University of Pittsburgh PittsburghPA United States McGowan Institute of Regenerative Medicine University of Pittsburgh PittsburghPA United States Department of Molecular Medicine Donald and Barbara Zucker School of Medicine at Hofstra/Northwell ManhassetNY United States

Almost 100 years ago experiments involving electrically stimulating and recording from the brain and the body launched new discoveries and debates on how electricity, movement, and thoughts are related. Decades later the development of brain-computer interface technology began, which now targets a wide range of applications. Potential uses include augmentative communication for locked-in patients and restoring sensorimotor function in those who are battling disease or have suffered traumatic injury. Technical and surgical challenges still surround the development of brain-computer technology, however, before it can be widely deployed. In this review we explore these challenges, historical perspectives, and the remarkable achievements of clinical study participants who have bravely forged new paths for future beneficiaries. © 2021, The Author(s).

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：