Adaptive Sleep/Wake Classification Based on Cardiorespiratory Signals for Wearable Devices. Karlen, W., Mattiussi, C., & Floreano, D. In 2007 IEEE Biomedical Circuits and Systems Conference, pages 203-6, 11, 2007. IEEE. ![Adaptive Sleep/Wake Classification Based on Cardiorespiratory Signals for Wearable Devices [link]](https://bibbase.org/img/filetypes/link.svg "link")
Website abstract bibtex 1 download In this paper we describe a method to classify online sleep/wake states of humans based on cardiorespiratory signals for wearable applications. The method is designed to be embedded in a portable microcontroller device and to cope with the resulting tight power restrictions. The method uses a Fast Fourier Transform as the main feature extraction method and an adaptive feed-forward Artificial Neural Network as a classifier. Results show that when the network is trained on a single user, it can correctly classify on average 95.4% of unseen data from the same user. The accuracy of the method in multi-user conditions is lower (89.4%). This is still comparable to actigraphy methods, but our method classifies wake periods considerably better.
@inProceedings{
title = {Adaptive Sleep/Wake Classification Based on Cardiorespiratory Signals for Wearable Devices},
type = {inProceedings},
year = {2007},
identifiers = {[object Object]},
keywords = {EMG,EOG,actigraphy,adaptive feed-forward network,adaptive sleep-wake classification,artificial neural network,biomedical electronics,biomedical equipment,biomedical signal analysis,cardiorespiratory signal,classification,electro-oculography,electrocardiography,electromyography,fast Fourier transform,fast Fourier transforms,feature extraction,feedforward neural nets,medical signal processing,microcontrollers,neural classifier,neurophysiology,pneumodynamics,portable microcontroller device,respiratory effort,signal classification,signal classifier,sleep and wake,sleepECG,wearable computing,wearable device},
pages = {203-6},
websites = {http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=4463344},
month = {11},
publisher = {IEEE},
id = {9a9b4f27-e94d-3338-a96a-49e8d5b646c9},
created = {2009-05-29T19:40:42.000Z},
accessed = {2012-11-21},
file_attached = {true},
profile_id = {6d353feb-efe4-367e-84a2-0815eb9ca878},
last_modified = {2014-11-28T11:16:47.000Z},
read = {true},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {Karlen2007},
source_type = {article},
abstract = {In this paper we describe a method to classify online sleep/wake states of humans based on cardiorespiratory signals for wearable applications. The method is designed to be embedded in a portable microcontroller device and to cope with the resulting tight power restrictions. The method uses a Fast Fourier Transform as the main feature extraction method and an adaptive feed-forward Artificial Neural Network as a classifier. Results show that when the network is trained on a single user, it can correctly classify on average 95.4% of unseen data from the same user. The accuracy of the method in multi-user conditions is lower (89.4%). This is still comparable to actigraphy methods, but our method classifies wake periods considerably better.},
bibtype = {inProceedings},
author = {Karlen, Walter and Mattiussi, Claudio and Floreano, Dario},
booktitle = {2007 IEEE Biomedical Circuits and Systems Conference}
}
Downloads: 1
{"_id":{"_str":"53421a16ecd21cdc070002c4"},"__v":3,"authorIDs":["5456ef428b01c8193000007c"],"author_short":["Karlen, W.","Mattiussi, C.","Floreano, D."],"bibbaseid":"karlen-mattiussi-floreano-adaptivesleepwakeclassificationbasedoncardiorespiratorysignalsforwearabledevices-2007","bibdata":{"title":"Adaptive Sleep/Wake Classification Based on Cardiorespiratory Signals for Wearable Devices","type":"inProceedings","year":"2007","identifiers":"[object Object]","keywords":"EMG,EOG,actigraphy,adaptive feed-forward network,adaptive sleep-wake classification,artificial neural network,biomedical electronics,biomedical equipment,biomedical signal analysis,cardiorespiratory signal,classification,electro-oculography,electrocardiography,electromyography,fast Fourier transform,fast Fourier transforms,feature extraction,feedforward neural nets,medical signal processing,microcontrollers,neural classifier,neurophysiology,pneumodynamics,portable microcontroller device,respiratory effort,signal classification,signal classifier,sleep and wake,sleepECG,wearable computing,wearable device","pages":"203-6","websites":"http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=4463344","month":"11","publisher":"IEEE","id":"9a9b4f27-e94d-3338-a96a-49e8d5b646c9","created":"2009-05-29T19:40:42.000Z","accessed":"2012-11-21","file_attached":"true","profile_id":"6d353feb-efe4-367e-84a2-0815eb9ca878","last_modified":"2014-11-28T11:16:47.000Z","read":"true","starred":false,"authored":"true","confirmed":"true","hidden":false,"citation_key":"Karlen2007","source_type":"article","abstract":"In this paper we describe a method to classify online sleep/wake states of humans based on cardiorespiratory signals for wearable applications. The method is designed to be embedded in a portable microcontroller device and to cope with the resulting tight power restrictions. The method uses a Fast Fourier Transform as the main feature extraction method and an adaptive feed-forward Artificial Neural Network as a classifier. Results show that when the network is trained on a single user, it can correctly classify on average 95.4% of unseen data from the same user. The accuracy of the method in multi-user conditions is lower (89.4%). This is still comparable to actigraphy methods, but our method classifies wake periods considerably better.","bibtype":"inProceedings","author":"Karlen, Walter and Mattiussi, Claudio and Floreano, Dario","booktitle":"2007 IEEE Biomedical Circuits and Systems Conference","bibtex":"@inProceedings{\n title = {Adaptive Sleep/Wake Classification Based on Cardiorespiratory Signals for Wearable Devices},\n type = {inProceedings},\n year = {2007},\n identifiers = {[object Object]},\n keywords = {EMG,EOG,actigraphy,adaptive feed-forward network,adaptive sleep-wake classification,artificial neural network,biomedical electronics,biomedical equipment,biomedical signal analysis,cardiorespiratory signal,classification,electro-oculography,electrocardiography,electromyography,fast Fourier transform,fast Fourier transforms,feature extraction,feedforward neural nets,medical signal processing,microcontrollers,neural classifier,neurophysiology,pneumodynamics,portable microcontroller device,respiratory effort,signal classification,signal classifier,sleep and wake,sleepECG,wearable computing,wearable device},\n pages = {203-6},\n websites = {http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=4463344},\n month = {11},\n publisher = {IEEE},\n id = {9a9b4f27-e94d-3338-a96a-49e8d5b646c9},\n created = {2009-05-29T19:40:42.000Z},\n accessed = {2012-11-21},\n file_attached = {true},\n profile_id = {6d353feb-efe4-367e-84a2-0815eb9ca878},\n last_modified = {2014-11-28T11:16:47.000Z},\n read = {true},\n starred = {false},\n authored = {true},\n confirmed = {true},\n hidden = {false},\n citation_key = {Karlen2007},\n source_type = {article},\n abstract = {In this paper we describe a method to classify online sleep/wake states of humans based on cardiorespiratory signals for wearable applications. The method is designed to be embedded in a portable microcontroller device and to cope with the resulting tight power restrictions. The method uses a Fast Fourier Transform as the main feature extraction method and an adaptive feed-forward Artificial Neural Network as a classifier. Results show that when the network is trained on a single user, it can correctly classify on average 95.4% of unseen data from the same user. The accuracy of the method in multi-user conditions is lower (89.4%). This is still comparable to actigraphy methods, but our method classifies wake periods considerably better.},\n bibtype = {inProceedings},\n author = {Karlen, Walter and Mattiussi, Claudio and Floreano, Dario},\n booktitle = {2007 IEEE Biomedical Circuits and Systems Conference}\n}","author_short":["Karlen, W.","Mattiussi, C.","Floreano, D."],"urls":{"Website":"http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=4463344"},"bibbaseid":"karlen-mattiussi-floreano-adaptivesleepwakeclassificationbasedoncardiorespiratorysignalsforwearabledevices-2007","role":"author","keyword":["EMG","EOG","actigraphy","adaptive feed-forward network","adaptive sleep-wake classification","artificial neural network","biomedical electronics","biomedical equipment","biomedical signal analysis","cardiorespiratory signal","classification","electro-oculography","electrocardiography","electromyography","fast Fourier transform","fast Fourier transforms","feature extraction","feedforward neural nets","medical signal processing","microcontrollers","neural classifier","neurophysiology","pneumodynamics","portable microcontroller device","respiratory effort","signal classification","signal classifier","sleep and wake","sleepECG","wearable computing","wearable device"],"downloads":1},"bibtype":"inProceedings","biburl":null,"downloads":1,"keywords":["emg","eog","actigraphy","adaptive feed-forward network","adaptive sleep-wake classification","artificial neural network","biomedical electronics","biomedical equipment","biomedical signal analysis","cardiorespiratory signal","classification","electro-oculography","electrocardiography","electromyography","fast fourier transform","fast fourier transforms","feature extraction","feedforward neural nets","medical signal processing","microcontrollers","neural classifier","neurophysiology","pneumodynamics","portable microcontroller device","respiratory effort","signal classification","signal classifier","sleep and wake","sleepecg","wearable computing","wearable device"],"search_terms":["adaptive","sleep","wake","classification","based","cardiorespiratory","signals","wearable","devices","karlen","mattiussi","floreano"],"title":"Adaptive Sleep/Wake Classification Based on Cardiorespiratory Signals for Wearable Devices","year":2007}