Single trial EEG classification during finger movement task by using hidden Markov models

Conference Proceedings. 2nd International IEEE EMBS Conference on Neural Engineering, 2005. Pub Date : 2005-03-16 DOI:10.1109/CNE.2005.1419702

Yong Li, Guoya Dong, Xiaorong Gao, Shangkai Gao, Manling Ge, Weili Yan

{"title":"Single trial EEG classification during finger movement task by using hidden Markov models","authors":"Yong Li, Guoya Dong, Xiaorong Gao, Shangkai Gao, Manling Ge, Weili Yan","doi":"10.1109/CNE.2005.1419702","DOIUrl":null,"url":null,"abstract":"A new algorithm based on hidden Markov models (HMM) to discriminate single trial electroencephalogram (EEG) between two conditions of finger movement task is proposed. Firstly, multi-channel EEG signals of single trial are filtered in both frequency and spatial domains. The pass bands of the two filters in frequency domain are 0~3 Hz and 8~30 Hz respectively, and the spatial filters are designed by the methods of common spatial subspace decomposition (CSSD). Secondly, two independent features are extracted based on HMM. Finally, the movement tasks are classified into two groups by a perceptron with the extracted features as inputs. With a leave-one out training and testing procedure, an average classification accuracy rate of 93.2% is obtained based on the data from five subjects. The proposed method can be used as an EEG-based brain computer interface (BCI) due to its high recognition rate and insensitivity to noise. In addition, it is suitable for either offline or online EEG analysis","PeriodicalId":113815,"journal":{"name":"Conference Proceedings. 2nd International IEEE EMBS Conference on Neural Engineering, 2005.","volume":"140 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2005-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"7","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Conference Proceedings. 2nd International IEEE EMBS Conference on Neural Engineering, 2005.","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CNE.2005.1419702","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 7

Abstract

A new algorithm based on hidden Markov models (HMM) to discriminate single trial electroencephalogram (EEG) between two conditions of finger movement task is proposed. Firstly, multi-channel EEG signals of single trial are filtered in both frequency and spatial domains. The pass bands of the two filters in frequency domain are 0~3 Hz and 8~30 Hz respectively, and the spatial filters are designed by the methods of common spatial subspace decomposition (CSSD). Secondly, two independent features are extracted based on HMM. Finally, the movement tasks are classified into two groups by a perceptron with the extracted features as inputs. With a leave-one out training and testing procedure, an average classification accuracy rate of 93.2% is obtained based on the data from five subjects. The proposed method can be used as an EEG-based brain computer interface (BCI) due to its high recognition rate and insensitivity to noise. In addition, it is suitable for either offline or online EEG analysis

查看原文本刊更多论文

基于隐马尔可夫模型的手指运动任务单次脑电分类

提出了一种基于隐马尔可夫模型(HMM)的手指运动任务单次试验脑电图鉴别算法。首先，对单次实验的多通道脑电信号进行频率域和空间域滤波;两种滤波器在频域的通频带分别为0~ 3hz和8~ 30hz，空间滤波器采用公共空间子空间分解(CSSD)方法设计。其次，基于HMM提取两个独立的特征;最后，感知器将提取的特征作为输入，将运动任务分为两组。采用“留一”的训练和测试程序，对5个被试的数据进行分类，平均准确率达到93.2%。该方法具有识别率高、对噪声不敏感等优点，可作为基于脑电图的脑机接口(BCI)。此外，它适用于离线或在线脑电图分析

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Conference Proceedings. 2nd International IEEE EMBS Conference on Neural Engineering, 2005.

自引率

0.00%

发文量