Classification of healthy subjects and insomniac patients based on automated sleep onset detection

C. Dissanayaka, H. Abdullah, Beena Ahmed, T. Penzel, Dean Cvetkovic

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

Abstract

This work aims to investigate new indexes quantitatively differentiate sleep insomnia patients from healthy subjects, in the context of sleep onset fluctuations. Our study included the use of existing PSG dataset, of 20 healthy subjects and 20 insomniac subjects. The differences between normal sleepers and insomniacs was investigated, in terms of dynamics and content of Sleep Onset (SO) process. An automated system was created to achieve this and it consists of six steps: 1) preprocessing of signals 2) feature extraction 3) classification 4) automatic scoring 5) sleep onset detection 6) identification of subject groups. The pre-processing step consisted of the removal of noise and movement artifacts from the signals. The feature extracting step consists of extracting time, frequency and non-linear features of Electroencephalogram (EEG) and Electromyogram (EMG) signals. In the third step, classification was done using ANN (Artificial Neural Networks) classifier. The fourth step consisted of scoring sleep stages (wake, S1, S2, S3 and REM) and produced a hypnogram. In the fifth step, we are detecting sleep onset from our automatic detected hypnogram and identified time of SO reference point and the combination of stages. In the final step we differentiated healthy subjects from insomniac patients based on the parameters calculated in the fifth step.

Original languageEnglish
Title of host publicationInternational Conference for Innovation in Biomedical Engineering and Life Sciences
PublisherSpringer Verlag
Pages188-192
Number of pages5
Volume56
ISBN (Print)9789811002656
DOIs
Publication statusPublished - 2016
EventInternational Conference for Innovation in Biomedical Engineering and Life Sciences, ICIBEL 2015 - Putrajaya, Malaysia
Duration: 6 Dec 20158 Dec 2015

Other

OtherInternational Conference for Innovation in Biomedical Engineering and Life Sciences, ICIBEL 2015
CountryMalaysia
CityPutrajaya
Period6/12/158/12/15

Fingerprint

Electroencephalography
Sleep
Feature extraction
Classifiers
Neural networks
Processing

Keywords

  • ANN
  • EEG
  • EMG
  • Insomnia
  • Sleep Onset

ASJC Scopus subject areas

  • Biomedical Engineering
  • Bioengineering

Cite this

Dissanayaka, C., Abdullah, H., Ahmed, B., Penzel, T., & Cvetkovic, D. (2016). Classification of healthy subjects and insomniac patients based on automated sleep onset detection. In International Conference for Innovation in Biomedical Engineering and Life Sciences (Vol. 56, pp. 188-192). Springer Verlag. https://doi.org/10.1007/978-981-10-0266-3_39

Classification of healthy subjects and insomniac patients based on automated sleep onset detection. / Dissanayaka, C.; Abdullah, H.; Ahmed, Beena; Penzel, T.; Cvetkovic, Dean.

International Conference for Innovation in Biomedical Engineering and Life Sciences. Vol. 56 Springer Verlag, 2016. p. 188-192.

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

Dissanayaka, C, Abdullah, H, Ahmed, B, Penzel, T & Cvetkovic, D 2016, Classification of healthy subjects and insomniac patients based on automated sleep onset detection. in International Conference for Innovation in Biomedical Engineering and Life Sciences. vol. 56, Springer Verlag, pp. 188-192, International Conference for Innovation in Biomedical Engineering and Life Sciences, ICIBEL 2015, Putrajaya, Malaysia, 6/12/15. https://doi.org/10.1007/978-981-10-0266-3_39
Dissanayaka C, Abdullah H, Ahmed B, Penzel T, Cvetkovic D. Classification of healthy subjects and insomniac patients based on automated sleep onset detection. In International Conference for Innovation in Biomedical Engineering and Life Sciences. Vol. 56. Springer Verlag. 2016. p. 188-192 https://doi.org/10.1007/978-981-10-0266-3_39
Dissanayaka, C. ; Abdullah, H. ; Ahmed, Beena ; Penzel, T. ; Cvetkovic, Dean. / Classification of healthy subjects and insomniac patients based on automated sleep onset detection. International Conference for Innovation in Biomedical Engineering and Life Sciences. Vol. 56 Springer Verlag, 2016. pp. 188-192
@inproceedings{2eae3b8ac4454325815aa63f83f19e15,
title = "Classification of healthy subjects and insomniac patients based on automated sleep onset detection",
abstract = "This work aims to investigate new indexes quantitatively differentiate sleep insomnia patients from healthy subjects, in the context of sleep onset fluctuations. Our study included the use of existing PSG dataset, of 20 healthy subjects and 20 insomniac subjects. The differences between normal sleepers and insomniacs was investigated, in terms of dynamics and content of Sleep Onset (SO) process. An automated system was created to achieve this and it consists of six steps: 1) preprocessing of signals 2) feature extraction 3) classification 4) automatic scoring 5) sleep onset detection 6) identification of subject groups. The pre-processing step consisted of the removal of noise and movement artifacts from the signals. The feature extracting step consists of extracting time, frequency and non-linear features of Electroencephalogram (EEG) and Electromyogram (EMG) signals. In the third step, classification was done using ANN (Artificial Neural Networks) classifier. The fourth step consisted of scoring sleep stages (wake, S1, S2, S3 and REM) and produced a hypnogram. In the fifth step, we are detecting sleep onset from our automatic detected hypnogram and identified time of SO reference point and the combination of stages. In the final step we differentiated healthy subjects from insomniac patients based on the parameters calculated in the fifth step.",
keywords = "ANN, EEG, EMG, Insomnia, Sleep Onset",
author = "C. Dissanayaka and H. Abdullah and Beena Ahmed and T. Penzel and Dean Cvetkovic",
year = "2016",
doi = "10.1007/978-981-10-0266-3_39",
language = "English",
isbn = "9789811002656",
volume = "56",
pages = "188--192",
booktitle = "International Conference for Innovation in Biomedical Engineering and Life Sciences",
publisher = "Springer Verlag",

}

TY - GEN

T1 - Classification of healthy subjects and insomniac patients based on automated sleep onset detection

AU - Dissanayaka, C.

AU - Abdullah, H.

AU - Ahmed, Beena

AU - Penzel, T.

AU - Cvetkovic, Dean

PY - 2016

Y1 - 2016

N2 - This work aims to investigate new indexes quantitatively differentiate sleep insomnia patients from healthy subjects, in the context of sleep onset fluctuations. Our study included the use of existing PSG dataset, of 20 healthy subjects and 20 insomniac subjects. The differences between normal sleepers and insomniacs was investigated, in terms of dynamics and content of Sleep Onset (SO) process. An automated system was created to achieve this and it consists of six steps: 1) preprocessing of signals 2) feature extraction 3) classification 4) automatic scoring 5) sleep onset detection 6) identification of subject groups. The pre-processing step consisted of the removal of noise and movement artifacts from the signals. The feature extracting step consists of extracting time, frequency and non-linear features of Electroencephalogram (EEG) and Electromyogram (EMG) signals. In the third step, classification was done using ANN (Artificial Neural Networks) classifier. The fourth step consisted of scoring sleep stages (wake, S1, S2, S3 and REM) and produced a hypnogram. In the fifth step, we are detecting sleep onset from our automatic detected hypnogram and identified time of SO reference point and the combination of stages. In the final step we differentiated healthy subjects from insomniac patients based on the parameters calculated in the fifth step.

AB - This work aims to investigate new indexes quantitatively differentiate sleep insomnia patients from healthy subjects, in the context of sleep onset fluctuations. Our study included the use of existing PSG dataset, of 20 healthy subjects and 20 insomniac subjects. The differences between normal sleepers and insomniacs was investigated, in terms of dynamics and content of Sleep Onset (SO) process. An automated system was created to achieve this and it consists of six steps: 1) preprocessing of signals 2) feature extraction 3) classification 4) automatic scoring 5) sleep onset detection 6) identification of subject groups. The pre-processing step consisted of the removal of noise and movement artifacts from the signals. The feature extracting step consists of extracting time, frequency and non-linear features of Electroencephalogram (EEG) and Electromyogram (EMG) signals. In the third step, classification was done using ANN (Artificial Neural Networks) classifier. The fourth step consisted of scoring sleep stages (wake, S1, S2, S3 and REM) and produced a hypnogram. In the fifth step, we are detecting sleep onset from our automatic detected hypnogram and identified time of SO reference point and the combination of stages. In the final step we differentiated healthy subjects from insomniac patients based on the parameters calculated in the fifth step.

KW - ANN

KW - EEG

KW - EMG

KW - Insomnia

KW - Sleep Onset

UR - http://www.scopus.com/inward/record.url?scp=84952770583&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84952770583&partnerID=8YFLogxK

U2 - 10.1007/978-981-10-0266-3_39

DO - 10.1007/978-981-10-0266-3_39

M3 - Conference contribution

SN - 9789811002656

VL - 56

SP - 188

EP - 192

BT - International Conference for Innovation in Biomedical Engineering and Life Sciences

PB - Springer Verlag

ER -