FPGA implementation of 4-channel ICA for on-line EEG signal separation

2008 IEEE Biomedical Circuits and Systems Conference Pub Date : 2008-12-01 DOI:10.1109/BIOCAS.2008.4696875

Wei-Chung Huang, S. Hung, Jen-Feng Chung, Meng-Hsiu Chang, Lan-Da Van, Chin-Teng Lin

引用次数: 41

Abstract

Blind source separation of independent sources from their mixtures is a common problem for multi-sensor applications in real world, for example, speech or biomedical signal processing. This paper presents an independent component analysis (ICA) method with information maximization (Infomax) update applied into 4-channel one-line EEG signal separation. This can be implemented on FPGA with a fixed-point number representation, and then the separated signals are transmitted via Bluetooth. As experimental results, the proposed design is faster 56 times than soft performance, and the correlation coefficients at least 80% with the absolute value are compared with off-line processing results. Finally, live demonstration is shown in the DE2 FPGA board, and the design is consisted of 16,605 logic elements.

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

FPGA实现4通道ICA在线脑电信号分离

独立源与混合源的盲分离是现实世界中多传感器应用的常见问题，例如语音或生物医学信号处理。提出了一种信息最大化更新的独立分量分析(ICA)方法，并将其应用于四通道单线脑电信号分离。这可以在FPGA上实现定点数字表示，然后通过蓝牙传输分离的信号。实验结果表明，该设计比软性能快56倍，且与离线处理结果的相关系数与绝对值至少达到80%。最后在DE2 FPGA板上进行了现场演示，该设计由16605个逻辑元件组成。

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分钟内获得全文去求助

来源期刊

2008 IEEE Biomedical Circuits and Systems Conference

自引率

0.00%

发文量

期刊最新文献

A wireless neural interface for chronic recording Development of novel SAW devices in CMOS technology for biosensor applications An efficient wireless power link for high voltage retinal implant FPGA implementation of 4-channel ICA for on-line EEG signal separation Pressure detection and wireless interface for patient bed