Adaptive Sleep-Wake Discrimination for Wearable Devices

Adaptive Sleep-Wake Discrimination for Wearable Devices. Karlen, W. & Floreano, D. IEEE transactions on bio-medical engineering, 58(4):920-6, 12, 2010.

Paper

Adaptive Sleep-Wake Discrimination for Wearable Devices [link]

Website doi abstract bibtex 3 downloads

Sleep/wake classification systems that rely on physiological signals suffer from inter-subject differences that make accurate classification with a single, subject-independent model difficult. To overcome the limitations of inter-subject variability we suggest a novel on-line adaptation technique that updates the sleep/wake classifier in real-time. The objective of the present study was to evaluate the performance of a newly developed adaptive classification algorithm that was embedded on a wearable sleep/wake classification system called SleePic. The algorithm processed electrocardiogram and respiratory effort signals for the classification task and applied behavioral measurements (obtained from accelerometer and press-button data) for the automatic adaptation task. When trained as a subjectindependent classifier algorithm, the SleePic device was only able to correctly classify 74.94% 6.76 of the human rated sleep/wake data. By using the suggested automatic adaptation method the mean classification accuracy could be significantly improved to 92.98% 3.19. A subject-independent classifier based on activity data only showed a comparable accuracy of 90.44% 3.57. We demonstrated that subject-independent models used for online sleep and wake classification can successfully be adapted to previously unseen subjects without the intervention of human experts or off-line calibration.

@article{
 title = {Adaptive Sleep-Wake Discrimination for Wearable Devices},
 type = {article},
 year = {2010},
 pages = {920-6},
 volume = {58},
 websites = {http://www.ncbi.nlm.nih.gov/pubmed/21172750},
 month = {12},
 id = {cd16a6b6-d19a-365d-bb22-a16a6f9862bd},
 created = {2021-11-19T08:07:18.204Z},
 accessed = {2010-12-30},
 file_attached = {true},
 profile_id = {6d353feb-efe4-367e-84a2-0815eb9ca878},
 last_modified = {2022-09-04T18:12:16.019Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Karlen2010d},
 folder_uuids = {f1f67efc-95a7-4f1a-b181-c3670c667a34,c861438a-f137-4be3-8c86-0f244c523c17},
 private_publication = {false},
 abstract = {Sleep/wake classification systems that rely on physiological signals suffer from inter-subject differences that make accurate classification with a single, subject-independent model difficult. To overcome the limitations of inter-subject variability we suggest a novel on-line adaptation technique that updates the sleep/wake classifier in real-time. The objective of the present study was to evaluate the performance of a newly developed adaptive classification algorithm that was embedded on a wearable sleep/wake classification system called SleePic. The algorithm processed electrocardiogram and respiratory effort signals for the classification task and applied behavioral measurements (obtained from accelerometer and press-button data) for the automatic adaptation task. When trained as a subjectindependent classifier algorithm, the SleePic device was only able to correctly classify 74.94% 6.76 of the human rated sleep/wake data. By using the suggested automatic adaptation method the mean classification accuracy could be significantly improved to 92.98% 3.19. A subject-independent classifier based on activity data only showed a comparable accuracy of 90.44% 3.57. We demonstrated that subject-independent models used for online sleep and wake classification can successfully be adapted to previously unseen subjects without the intervention of human experts or off-line calibration.},
 bibtype = {article},
 author = {Karlen, Walter and Floreano, D},
 doi = {10.1109/TBME.2010.2097261},
 journal = {IEEE transactions on bio-medical engineering},
 number = {4}
}

Downloads: 3