TY - JOUR
T1 - Alertness staging based on improved self-organizing map
AU - Wang, Xuemin
AU - Zhang, Yi
AU - Li, Xiangxin
AU - Liu, Yating
AU - Cao, Hongbao
AU - Zhou, Peng
AU - Wang, Xiaolu
AU - Gao, Xiang
PY - 2013/12
Y1 - 2013/12
N2 - 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%.
AB - 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%.
KW - alertness staging
KW - electroencephalogram (EEG)
KW - improved self-organizing map (ISOM)
UR - https://www.scopus.com/pages/publications/84891400845
U2 - 10.1007/s12209-013-2027-3
DO - 10.1007/s12209-013-2027-3
M3 - Artículo
AN - SCOPUS:84891400845
SN - 1006-4982
VL - 19
SP - 459
EP - 462
JO - Transactions of Tianjin University
JF - Transactions of Tianjin University
IS - 6
ER -