Alertness Staging Based on Improved Self-Organizing Map

In order to classify the alertness status, 19 channels of electroencephalogram（EEG） signals from 5 subjects were acquired during daytime nap. Ten different types of features（including time domain features, frequency domain features and nonlinear features） were extracted from EEG signals, and an impr...

Full description

Saved in:
Bibliographic Details
Published inTransactions of Tianjin University Vol. 19; no. 6; pp. 459 - 462
Main Author 王学民 张翼 李向新 刘雅婷 曹红宝 周鹏 王晓璐 高翔
Format Journal Article
LanguageEnglish
Published Berlin/Heidelberg Springer Berlin Heidelberg 01.12.2013
School of Precision Instruments and Opto-Electronics Engineering, Tianjin University, Tianjin 300072, China%Department of Biomedical Engineering, Tulane University, New Orleans 70112, USA
Subjects
Engineering
Humanities and Social Sciences
Mechanical Engineering
multidisciplinary
Science
分类精度
异构化装置
时域特性
神经网络
脑电信号
自组织映射
非线性特征
频域特性
improved self-organizing map (ISOM)
electroencephalogram (EEG)
alertness staging
Online AccessGet full text
ISSN1006-4982
1995-8196
DOI10.1007/s12209-013-2027-3

Cover

More Information
Summary:In order to classify the alertness status, 19 channels of electroencephalogram（EEG） signals from 5 subjects were acquired during daytime nap. Ten different types of features（including time domain features, frequency domain features and nonlinear features） were extracted from EEG signals, and an improved self-organizing map（ISOM） neuron network was proposed, which successfully identify three different brain status of the subjects： awareness, drowsiness and sleep. Compared with traditional SOM, the experiment results show that the ISOM generates much better classification accuracy, reaching as high as 89.59%.
Bibliography:In order to classify the alertness status, 19 channels of electroencephalogram（EEG） signals from 5 subjects were acquired during daytime nap. Ten different types of features（including time domain features, frequency domain features and nonlinear features） were extracted from EEG signals, and an improved self-organizing map（ISOM） neuron network was proposed, which successfully identify three different brain status of the subjects： awareness, drowsiness and sleep. Compared with traditional SOM, the experiment results show that the ISOM generates much better classification accuracy, reaching as high as 89.59%.
12-1248/T
electroencephalogram（EEG） improved self-organizing map（ISOM） alertness staging
ISSN:1006-4982
1995-8196
DOI:10.1007/s12209-013-2027-3