Alertness staging based on improved self-organizing map

Xuemin Wang, Yi Zhang, Xiangxin Li, Yating Liu, Hongbao Cao, Peng Zhou, Xiaolu Wang, Xiang Gao

Research output: Contribution to journalArticlepeer-review

1 Scopus citations

Abstract

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%.

Original languageEnglish
Pages (from-to)459-462
Number of pages4
JournalTransactions of Tianjin University
Volume19
Issue number6
DOIs
StatePublished - Dec 2013
Externally publishedYes

Keywords

  • alertness staging
  • electroencephalogram (EEG)
  • improved self-organizing map (ISOM)

Fingerprint

Dive into the research topics of 'Alertness staging based on improved self-organizing map'. Together they form a unique fingerprint.

Cite this