位置：成果数据库 > 期刊 > 期刊详情页
基于马尔科夫切换过程的运动想象信号分类
  • ISSN号：0258-8021
  • 期刊名称：中国生物医学工程学报
  • 时间：2014.12.20
  • 页码：666-672
  • 分类：TP391.4[自动化与计算机技术—计算机应用技术;自动化与计算机技术—计算机科学与技术]
  • 作者机构：[1]华南理工大学自动化科学与工程学院,广州510640, [2]国家电网湖北电力公司黄石供电公司,黄石435000
  • 相关基金：广东省自然科学基金（$2012020010945）;国家自然科学基金（61105121,61175114,91120305）
  • 相关项目：基于凸分析与优化的fMRI脑功能定位与神经解码研究
作者： 杨雅|俞祝良|顾正晖|李远清|
关键词： 运动想象, 脑机接口, 马尔科夫切换, AR模型, 信号分类, motor imagery, brain computer interface （BCI）, Markov switching processes, AR model, signal classification
中文摘要：

隐马尔科夫模型（HMM）在脑机接口（BCI）领域中已经得到很好的应用,尤其是在运动想象（MI）信号的分类中.但是,很多传统的方法只是利用隐马尔科夫模型描述信号的动态特性,再根据观测数据求得模型参数,然后进行信号分类.由于脑电信号低信噪比、高维数和状态复杂的特点,在研究中先用分层Dirichlet过程（HDP）描述MI信号,利用HDP自聚类特性,然后使用AR模型描述MI信号的时间特性,最后结合马尔科夫切换过程（MSP）描述MI信号的动态特性,以此来充分地描述MI信号.随后对实验室采集的数据和2003年BCI国际大赛的部分数据,使用HDP-AR-HMM模型对MI信号分类,获得很好的分类效果,准确率分别是99.00％、92.00％和72.46％.实验结果表明,所提出的方法可以取得更好的运动想象信号分类.

英文摘要：

Hidden Markov model （HMM） is well applied in brain computer interface, especially in the classification of motor imagery（MI） electroencephalogram （EEG） signal. Conventional methods use HMM to model EEG signal, then use the observed signal under controlled state to estimate the HMM parameters and finally classify the EEG signal through the trained HMMs. However, due to the characteristics of low signal-to- noise ratio （ SNR ）, high dimensionality and complexity of motor imagery EEG signal, HMM cannot fully describe the dynamic property of motor imagery EEG signal. In this paper, we use hierarchical Dirichlet process （HDP） with self-clustering ability to describe MI signals and then use AR/VAR model to highlight the time property of MI signal. Finally we combine them with Markov switching processing （MSP） so that we can get more information of MI signal. In order to verify this method, we tested the algorithm on our in-house data and some of the 2003 BCI international competition data sets. High accuracy on classification of MI is obtained.

同期刊论文项目
双向多维脑机接口关键技术及其应用研究
期刊论文 75 会议论文 34 获奖 6
小训练集下的在线脑机接口算法与实验研究
期刊论文 16 会议论文 3
基于凸分析与优化的fMRI脑功能定位与神经解码研究
期刊论文 18 会议论文 4
同项目期刊论文
A template-matching method for optical power monitoring
？Voxel Selection and Neural Decoding of fMRI Data Based on Robust Sparse Programming with Multi-dime
A comparison study of two P300 speller paradigms for brain--computer interface
Linear aperiodic array synthesis using an improved genetic algorithm
Analysis of fMRI data based on sparsity of source components in signal dictionary
Grouped Automatic Relevance Determination and Its Application in Channel Selection for P300 BCIs.
An efficient implementation of modified regularized sparse recovery for real-time optical power moni
A Real-timeObject Tracking System based on Kalman Filter and MB-LBP Feature Matching
Energy-Efficient ECG Compression on Wireless Biosensors via Minimal Coherence Sensing and Weighted l
Effect of errors in partially known support on the recoverability of modified compressive sensing
STRAPS: A Fully Data-Driven Spatio-TemporallyRegularized Algorithm for M/EEG Patch Source Imaging
Design principles of the sparse coding network and the role of "sister cells" in t
A Hybrid Brain-Computer Interface-Based Mail Client
Simple methods for property protection in video surveillance
Detecting number processing and mental calculation in patients with disorders of consciousness using
Control of a Wheelchair in an Indoor Environment Based on a Brain-Computer Interface and Automated N
Grouped Automatic Relevance Determination and Its Application in Channel Selection for P300 BCIs
Channel selection by Rayleigh coefficient maximization based genetic algorithm for classifying singl
Sparse Representation for Brain Signal Processing
Multilinear and nonlinear generalizations of partial least squares: an overview of recent advances
Detecting awareness in patients with disorders of consciousness using a hybrid brain–computer interf
Spectral–Spatial Classification of Hyperspectral Images via Spatial Translation-Invariant Wavelet-B
A tensor-based scheme for stroke patients’ motor imagery EEG analysis in BCI-FES rehabilitation trai
Energy-Efficient ECG Compression on Wireless Biosensors via Minimal Coherence Sensing and Weighted M
Kernelization of Tensor-Based Models for Multiway Data Analysis
Higher Order Partial Least Squares (HOPLS): A Generalized Multilinear Regression Method
Feature learning from incomplete EEG with denoising autoencoder
Multimodal BCIs: TargetDetection, Multi-dimensional Control, and Awareness Evaluation in Patients wi
Selective AudiovisualSemantic Integration Enabled by Feature-Selective Attention
A Boosting-Based Spatial-Spectral Model forStroke Patients' EEG Analysis in Rehabilitation T
Enhanced Motor Imagery Training Using a Hybrid BCI With Feedback
RSTFC: A Novel Algorithm for Spatio-Temporal Filtering and Classification of Single-Trial EEG
Uncorrelated Multiway Discriminant Analysis of EEG Motor Imagery Classification
A brain computer interface-based explorer
Bayesian estimation of ERP components from multicondition and multichannel EEG
STRAPS: A Fully Data-Driven Spatio-Temporally Regularized Algorithm for M/EEG Patch Source Imaging
Neurophysiological substrates of stroke patients with motor imagery-based Brain-Computer Interface t
Statistically Adaptive Image Denoising Based on Overcomplete Topographic Sparse Coding
Semisupervised Sparse Multilinear Discriminant Analysis
A Novel Audiovisual Brain-Computer Interface and Its Application in Awareness Detection
Content Based Image Search for Clothing Recommendations in E-Commerce
Probabilistic common spatial patterns for multichannel EEG analysis
A comparison study of two P300 speller paradigms for brain-computer interface
A Hybrid BCI System Combining P300 and SSVEP and Its Application to Wheelchair Control
Higher-Order Partial Least Squares (HOPLS): A Generalized Multi-Linear Regression Method
Active training paradigm for motor imagery BCI
An Online Semi-supervised Brain-Computer Interface
A Sparse Representation-Based Algorithm for Pattern Localization in Brain Imaging Data Analysis
Sparse Representation for Brain Signal Processing [A tutorial on methods and applications
Recoverability Analysis for Modified Compressive Sensing with Partially Known Support
Detecting awareness in patients with disorders of consciousness using a hybrid brain-computer interf
Bayesian Robust Tensor Factorization forIncomplete Multiway Data
Discriminative Analysis of Parkinson's Disease Based on Whole-Brain Functional Connectivity
基于事件关联电位脑机接口的电视遥控异步系统
经皮神经电刺激在脑卒中后肩手综合征的应用
运动想象结合任务导向训练对慢性期脑卒中患者上肢功能影响的随机对照研究
经颅直流电刺激结合任务导向性训练改善脑卒中患者上肢运动功能的静息态fMRI研究
基于镜像神经元理论的动作观察在脑卒中后肩手综合征疼痛康复中的应用
基于FAST和BRIEF的图像匹配算法
室内环境中脑控轮椅的路径跟踪控制
经颅直流电刺激结合任务导向性训练对慢性期脑卒中患者上肢及手功能障碍的影响
Discrimination Between Control and Idle States in Asynchronous SSVEP-Based Brain Switches: A Pseudo-
Voxel selection and neural decoding of fMRI data based on robust sparse programming with multi-dimen
Sparse Representation for Brain Signal Processing [A tutorial on methods and applications]
基于P300的交互式字符输入脑机接口系统
Long-tail distribution based multiscale-multiband autoregressive detection for hyperspectral imagery
Target selection with hybrid feature for BCI-based 2-D cursor control
期刊信息
  • 《中国生物医学工程学报》
  • 中国科技核心期刊
  • 主管单位:中国科学技术协会
  • 主办单位:中国生物医学工程学会
  • 主编：刘德培
  • 地址：北京东单三条9号
  • 邮编：100730
  • 邮箱：cjbmecjbme@163.com
  • 电话：010-65248786
  • 国际标准刊号：ISSN：0258-8021
  • 国内统一刊号：ISSN：11-2057/R
  • 邮发代号:82-73
  • 获奖情况:
  • 国内外数据库收录:
  • 被引量:8917