Hurst exponents based detection of wake-sleep - A pilot study

N. Sriraam, B. R. Purnima, K. Uma, T. K. Padmashri

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

Detection of Sleep onset is one of complex processes in the area of sleep medicine. The transition from wake state to sleep is termed as sleep onset and is identified using distinct markers like behavioural features, physiological features and changes in EEC Extraction of appropriate features from EEG recordings helps in automated recognition and classification of wake-sleep transition. This research study proposes the introduction of Hurst exponent (HE) to indicate the transition between wake and sleep derived from EEG recordings. Being the non-linear chaotic parameter, Hurst exponent quantifies correlation among the time series data and this property has been exploited for sleep EEGs. Two typical channels O1 and O2 were used for the study and Hurst exponents were estimated for the EEG segments followed by classification using two linear classifiers, LDA and KNN. The statistical analysis confirms that the mean value of HE is lower for sleep than wake. The preliminary study reveals a classification accuracy of 99.96% with HE features with KNN classifier. The procedure needs to be tested with larger datasets.

Original languageEnglish
Title of host publicationProceedings of International Conference on Circuits, Communication, Control and Computing, I4C 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages118-121
Number of pages4
ISBN (Electronic)9781479965465
DOIs
Publication statusPublished - 10-03-2014
Externally publishedYes
Event2014 International Conference on Circuits, Communication, Control and Computing, I4C 2014 - Bangalore, India
Duration: 21-11-201422-11-2014

Conference

Conference2014 International Conference on Circuits, Communication, Control and Computing, I4C 2014
CountryIndia
CityBangalore
Period21-11-1422-11-14

Fingerprint

Electroencephalography
Classifiers
Sleep
Time series
Statistical methods

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Electrical and Electronic Engineering

Cite this

Sriraam, N., Purnima, B. R., Uma, K., & Padmashri, T. K. (2014). Hurst exponents based detection of wake-sleep - A pilot study. In Proceedings of International Conference on Circuits, Communication, Control and Computing, I4C 2014 (pp. 118-121). [7057771] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CIMCA.2014.7057771
Sriraam, N. ; Purnima, B. R. ; Uma, K. ; Padmashri, T. K. / Hurst exponents based detection of wake-sleep - A pilot study. Proceedings of International Conference on Circuits, Communication, Control and Computing, I4C 2014. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 118-121
@inproceedings{f08f44e565d247a69215e49812fc607d,
title = "Hurst exponents based detection of wake-sleep - A pilot study",
abstract = "Detection of Sleep onset is one of complex processes in the area of sleep medicine. The transition from wake state to sleep is termed as sleep onset and is identified using distinct markers like behavioural features, physiological features and changes in EEC Extraction of appropriate features from EEG recordings helps in automated recognition and classification of wake-sleep transition. This research study proposes the introduction of Hurst exponent (HE) to indicate the transition between wake and sleep derived from EEG recordings. Being the non-linear chaotic parameter, Hurst exponent quantifies correlation among the time series data and this property has been exploited for sleep EEGs. Two typical channels O1 and O2 were used for the study and Hurst exponents were estimated for the EEG segments followed by classification using two linear classifiers, LDA and KNN. The statistical analysis confirms that the mean value of HE is lower for sleep than wake. The preliminary study reveals a classification accuracy of 99.96{\%} with HE features with KNN classifier. The procedure needs to be tested with larger datasets.",
author = "N. Sriraam and Purnima, {B. R.} and K. Uma and Padmashri, {T. K.}",
year = "2014",
month = "3",
day = "10",
doi = "10.1109/CIMCA.2014.7057771",
language = "English",
pages = "118--121",
booktitle = "Proceedings of International Conference on Circuits, Communication, Control and Computing, I4C 2014",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

Sriraam, N, Purnima, BR, Uma, K & Padmashri, TK 2014, Hurst exponents based detection of wake-sleep - A pilot study. in Proceedings of International Conference on Circuits, Communication, Control and Computing, I4C 2014., 7057771, Institute of Electrical and Electronics Engineers Inc., pp. 118-121, 2014 International Conference on Circuits, Communication, Control and Computing, I4C 2014, Bangalore, India, 21-11-14. https://doi.org/10.1109/CIMCA.2014.7057771

Hurst exponents based detection of wake-sleep - A pilot study. / Sriraam, N.; Purnima, B. R.; Uma, K.; Padmashri, T. K.

Proceedings of International Conference on Circuits, Communication, Control and Computing, I4C 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 118-121 7057771.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Hurst exponents based detection of wake-sleep - A pilot study

AU - Sriraam, N.

AU - Purnima, B. R.

AU - Uma, K.

AU - Padmashri, T. K.

PY - 2014/3/10

Y1 - 2014/3/10

N2 - Detection of Sleep onset is one of complex processes in the area of sleep medicine. The transition from wake state to sleep is termed as sleep onset and is identified using distinct markers like behavioural features, physiological features and changes in EEC Extraction of appropriate features from EEG recordings helps in automated recognition and classification of wake-sleep transition. This research study proposes the introduction of Hurst exponent (HE) to indicate the transition between wake and sleep derived from EEG recordings. Being the non-linear chaotic parameter, Hurst exponent quantifies correlation among the time series data and this property has been exploited for sleep EEGs. Two typical channels O1 and O2 were used for the study and Hurst exponents were estimated for the EEG segments followed by classification using two linear classifiers, LDA and KNN. The statistical analysis confirms that the mean value of HE is lower for sleep than wake. The preliminary study reveals a classification accuracy of 99.96% with HE features with KNN classifier. The procedure needs to be tested with larger datasets.

AB - Detection of Sleep onset is one of complex processes in the area of sleep medicine. The transition from wake state to sleep is termed as sleep onset and is identified using distinct markers like behavioural features, physiological features and changes in EEC Extraction of appropriate features from EEG recordings helps in automated recognition and classification of wake-sleep transition. This research study proposes the introduction of Hurst exponent (HE) to indicate the transition between wake and sleep derived from EEG recordings. Being the non-linear chaotic parameter, Hurst exponent quantifies correlation among the time series data and this property has been exploited for sleep EEGs. Two typical channels O1 and O2 were used for the study and Hurst exponents were estimated for the EEG segments followed by classification using two linear classifiers, LDA and KNN. The statistical analysis confirms that the mean value of HE is lower for sleep than wake. The preliminary study reveals a classification accuracy of 99.96% with HE features with KNN classifier. The procedure needs to be tested with larger datasets.

UR - http://www.scopus.com/inward/record.url?scp=84946689595&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84946689595&partnerID=8YFLogxK

U2 - 10.1109/CIMCA.2014.7057771

DO - 10.1109/CIMCA.2014.7057771

M3 - Conference contribution

AN - SCOPUS:84946689595

SP - 118

EP - 121

BT - Proceedings of International Conference on Circuits, Communication, Control and Computing, I4C 2014

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Sriraam N, Purnima BR, Uma K, Padmashri TK. Hurst exponents based detection of wake-sleep - A pilot study. In Proceedings of International Conference on Circuits, Communication, Control and Computing, I4C 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 118-121. 7057771 https://doi.org/10.1109/CIMCA.2014.7057771