An adaptive neuro-fuzzy inference system for sleep spindle detection

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

doi:10.1109/iFUZZY.2012.6409733

An adaptive neuro-fuzzy inference system for sleep spindle detection

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

Department of Computer Science and Information Engineering

Research output: Contribution to conference › Paper › peer-review

4 Citations (Scopus)

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.

Original language	English
Pages	369-373
Number of pages	5
DOIs	https://doi.org/10.1109/iFUZZY.2012.6409733
Publication status	Published - 2012
Event	2012 International Conference on Fuzzy Theory and Its Applications, iFUZZY 2012 - Taichung, Taiwan Duration: 2012 Nov 16 → 2012 Nov 18

Other

Other	2012 International Conference on Fuzzy Theory and Its Applications, iFUZZY 2012
Country/Territory	Taiwan
City	Taichung
Period	12-11-16 → 12-11-18

All Science Journal Classification (ASJC) codes

Logic

Access to Document

10.1109/iFUZZY.2012.6409733

Cite this

@conference{ce2d1b050cb6431b9d08706bfbcc0030,

title = "An adaptive neuro-fuzzy inference system for sleep spindle detection",

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.",

author = "Liang, {Sheng Fu} and Kuo, {Chih En} and Hu, {Yu Han} and Chen, {Chun Yu} and Li, {Yu Hung}",

year = "2012",

doi = "10.1109/iFUZZY.2012.6409733",

language = "English",

pages = "369--373",

note = "2012 International Conference on Fuzzy Theory and Its Applications, iFUZZY 2012 ; Conference date: 16-11-2012 Through 18-11-2012",

}

TY - CONF

T1 - An adaptive neuro-fuzzy inference system for sleep spindle detection

AU - Liang, Sheng Fu

AU - Kuo, Chih En

AU - Hu, Yu Han

AU - Chen, Chun Yu

AU - Li, Yu Hung

PY - 2012

Y1 - 2012

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=84874066051&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84874066051&partnerID=8YFLogxK

U2 - 10.1109/iFUZZY.2012.6409733

DO - 10.1109/iFUZZY.2012.6409733

M3 - Paper

AN - SCOPUS:84874066051

SP - 369

EP - 373

T2 - 2012 International Conference on Fuzzy Theory and Its Applications, iFUZZY 2012

Y2 - 16 November 2012 through 18 November 2012

ER -

An adaptive neuro-fuzzy inference system for sleep spindle detection

Abstract

Other

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this