文章基本信息

标题：A Study on Visualizing Feature Extracted from Deep Restricted Boltzmann Machine using PCA
本地全文：下载
作者：Koki Kawasaki ; Tomohiro Yoshikawa ; Takeshi Furuhashi 等
期刊名称：International Journal of Computer Information Systems and Industrial Management Applications
印刷版ISSN：2150-7988
电子版ISSN：2150-7988
出版年度：2016
卷号：8
页码：067-076
出版社：Machine Intelligence Research Labs (MIR Labs)
摘要：P300 speller is a system that allows users to input letters using only electroencephalogram (EEG). A componen- t called P300 is used to interpret the EEG in P300 speller. In order to achieve high performance in P300 speller, achieving high performance of P300 detection is essential. However, EEG waveforms are strongly dependent on the conditions of subject and/or environment, so it is not easy to detect P300 precisely. In this study, deep neural network using restricted boltzmann ma- chine, which became famous by its high performance, is used to detect P300. It is expected that it also shows high perfor- mance for complex EEG waveforms. The experimental result shows that deep neural network was able to detect P300 better than the existing method (stepwise linear discriminant analy- sis). Furthermore, this study refers to the learned feature by deep restricted boltzmann machine. We can see that deep re- stricted boltzmann machine learns the feature extracted from the EEG waveforms correctly to detect P300 which led to the high performance.
关键词：Restricted boltzmann machine; Deep neural network; ; P300 detection; Feature extraction; Visualizing feature; Principal ; component analysis