| 基于判别混合高斯模型的信息积累方法及在脑机接口中的应用 |
| |
| 引用本文： | 朱晓源,吴健康,程义民.基于判别混合高斯模型的信息积累方法及在脑机接口中的应用[J].北京生物医学工程,2007,26(5):480-484. |
| |
| 作者姓名： | 朱晓源 吴健康 程义民 |
| |
| 作者单位： | 中国科学与技术大学电子科学与技术系,合肥,230027;资讯通信研究院,新加坡,119613 |
| |
| 摘 要： | 设计有效的学习算法快速准确地对脑电信号(eelectroencephalogram,EEG)进行连续预测是脑机接口(brain-computer interface,BCI)研究的关键之一.本文提出了一种新颖的基于判别混合高斯模型(discriminative gaussian mixture model,DGMM)的信息积累方法.该方法通过区分度权值对分类器在各时段的输出进行积累,从而达到提高脑电信号分类精度的作用.在两个运动想象数据集上的实验结果表明该方法能够提高BCI系统的性能,具有较好的实用性.
|
| 关 键 词： | 脑机接口 脑电信号 连续预测 判别混合高斯模型 |
| 文章编号： | 1002-3208（2007）05-0480-05 |
| 收稿时间： | 2006-09-17 |
| 修稿时间： | 2006-12-27 |
Accumulate information based on DGMM for brain-computer interface |
| |
| ZHU Xiaoyuan,WU Jiankang,CHENG Yimin.Accumulate information based on DGMM for brain-computer interface[J].Beijing Biomedical Engineering,2007,26(5):480-484. |
| |
| Authors: | ZHU Xiaoyuan WU Jiankang CHENG Yimin |
| |
| Institution: | 1. Department of Electronic Science and Technology, University of Science and Technology of China, Hefei 230027 ; 2 Institute for Infocomm Research, 21 Heng Mui Keng Terrace, Singapore 119613 |
| |
| Abstract: | Developing effective learning algorithms for fast and accurate continuous prediction using Eelectroen- cephalogram (EEG) signal is a key issue in brain-computer interface (BCI).This paper proposes a novel statistical ap- proach based on discriminative gaussian mixture models (DGMM) to classify the EEG trials by combining the predictions of segments according to the discriminative powers at individual time intervals during a trial.The experimental results on two motor imagery datasets show that the proposed method improves the performance of BCI system and is suitable for online ap- plication. |
| |
| Keywords: | brain-computer interface EEG continuous prediction DGMM |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
