An adaptive neuro-fuzzy inference system for sleep spindle detection

Author

Sheng-Fu Liang ; Chih-En Kuo ; Yu-Han Hu ; Chun-Yu Chen ; Yu-Hung Li

Author_Institution

Dept. of Comput. Sci. & Inf., Nat. Cheng Kung Univ., Tainan, Taiwan

fYear

2012

fDate

16-18 Nov. 2012

Firstpage

369

Lastpage

373

Abstract

In this paper, an adaptive neuro-fuzzy inference system (ANFIS) for sleep spindle detection was developed. Two input variables including teager energy operator (TEO) and sigma index analyses of the EEG signals were extracted. 1180 training samples (0.5 s) of 15 subjects were used to ANFIS training, include 397 spindle and 783 non-spindle waveform. Then the 1519 epochs (30s) of other 15 subjects were used to evaluate the performance of ANFIS. The overall sensitivity and specificity of the ANFIS are 94.09% and 96.76%, respectively. Although the overall false positive rate is 38.58%, spindle and non-spindle successful detection rate could almost reach 90% for each subject. This method can integrate with various PSG systems for sleep monitoring in cognitive enhancements or sleep efficiency.

Keywords

cognition; electroencephalography; fuzzy neural nets; fuzzy reasoning; medical signal processing; sleep; ANFIS; EEG signals; PSG systems; TEO; adaptive neuro-fuzzy inference system; cognitive enhancements; nonspindle successful detection rate; sigma index analyses; sleep efficiency; sleep monitoring; sleep spindle detection; teager energy operator; Adaptive systems; Electroencephalography; Feature extraction; Indexes; Sleep; Training; Training data; Adaptive neuro-fuzzy inference system; Automatic sleep spindle detection; EEG;

fLanguage

English

Publisher

ieee

Conference_Titel

Fuzzy Theory and it's Applications (iFUZZY), 2012 International Conference on

Conference_Location

Taichung

Print_ISBN

978-1-4673-2057-3

Type

conf

DOI

10.1109/iFUZZY.2012.6409733

Filename

6409733