Recognizing Sleep Stages with Wearable Sensors in Everyday Settings

The paper presents results from the SmartSleep project which aims at developing a smartphone app that gives users individual advice on how to change their behaviour to improve their sleep. The advice is generated by identifying correlations between behaviour during the day and sleep architecture. To this end, the project addresses two sub-tasks: detecting a user’s daytime behaviour and recognising sleep stages in an everyday setting. The focus of the paper is on the second task. Various sensor devices from the consumer market were used in addition to the usual PSG sensors in a sleep lab. An expert assigned a sleep stage for every 30 seconds. Subsequently, a sleep stage classifier was learned from the resulting sensor data streams segmented into labelled sleep stages of 30 seconds each. Apart from handcrafted features we also experimented with unsupervised feature learning based on the deep learning paradigm. Our best results for correctly classified sleep stages are in the range of 90 to 91% for Wake, REM and N3, while the best recognition rate for N2 is 83%. The classification results for N1 turned out to be much worse, N1 being mostly confused with N2.

[1]  Mannes Poel,et al.  Comparison of feature and classifier algorithms for online automatic sleep staging based on a single EEG signal , 2014, 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[2]  Geoffrey E. Hinton.  Training Products of Experts by Minimizing Contrastive Divergence , 2002, Neural Computation.

[3]  Christos Panagiotou,et al.  A comparative study between SVM and fuzzy inference system for the automatic prediction of sleep stages and the assessment of sleep quality , 2015, 2015 9th International Conference on Pervasive Computing Technologies for Healthcare (PervasiveHealth).

[4]  Ulrich Reimer,et al.  Mobile Stress Recognition and Relaxation Support with SmartCoping: User-Adaptive Interpretation of Physiological Stress Parameters , 2017, HICSS.

[5]  Philipp Scholl,et al.  Towards Benchmarked Sleep Detection with Wrist-Worn Sensing Units , 2014, 2014 IEEE International Conference on Healthcare Informatics.

[6]  Alberto Guillén,et al.  Combination of Heterogeneous EEG Feature Extraction Methods and stacked Sequential Learning for Sleep Stage Classification , 2013, Int. J. Neural Syst..

[7]  Gary M. Weiss,et al.  Activity recognition using cell phone accelerometers , 2011, SKDD.

[8]  Ulrich Reimer,et al.  An Application Framework for Personalised and Adaptive Behavioural Change Support Systems , 2016, ICT4AgeingWell.

[9]  Xiao Liu,et al.  Multi-channel EEG-based sleep stage classification with joint collaborative representation and multiple kernel learning , 2015, Journal of Neuroscience Methods.

[10]  João S. Domingos,et al.  A review of current sleep screening applications for smartphones , 2013, Physiological measurement.

[11]  Yunhao Liu,et al.  Intelligent sleep stage mining service with smartphones , 2014, UbiComp.

[12]  Peter Sommerlad,et al.  Pattern-Oriented Software Architecture , 1996 .

[13]  H. Landolt,et al.  Schlafgewohnheiten, Schlafqualität und Schlafmittelkonsum der Schweizer Bevölkerung – Ergebnisse aus einer neuen Umfrage bei einer repräsentativen Stichprobe , 2014 .

[14]  Miguel Á. Carreira-Perpiñán,et al.  On Contrastive Divergence Learning , 2005, AISTATS.

[15]  S. Surani,et al.  The NAMES assessment: a novel combined-modality screening tool for obstructive sleep apnea , 2011, Sleep and Breathing.

[16]  Kai Spiegelhalder,et al.  Insomnia as a predictor of depression: a meta-analytic evaluation of longitudinal epidemiological studies. , 2011, Journal of affective disorders.

[17]  Mohammad Ali Keyvanrad,et al.  A brief survey on deep belief networks and introducing a new object oriented toolbox ( DeeBNet V 3 . 0 ) , 2016 .

[18]  Yosuke Kurihara,et al.  Sleep-Stage Decision Algorithm by Using Heartbeat and Body-Movement Signals , 2012, IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans.

[19]  Geoffrey E. Hinton.  A Practical Guide to Training Restricted Boltzmann Machines , 2012, Neural Networks: Tricks of the Trade.

[20]  A. Avidan,et al.  Review of sleep disorders. , 1990, Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society.

[21]  Amy Loutfi,et al.  Sleep Stage Classification Using Unsupervised Feature Learning , 2012, Adv. Artif. Neural Syst..

[22]  Thomas Penzel,et al.  A comparison of radio-frequency biomotion sensors and actigraphy versus polysomnography for the assessment of sleep in normal subjects , 2015, Sleep and Breathing.

[23]  B. Kolla,et al.  Consumer sleep tracking devices: a review of mechanisms, validity and utility , 2016, Expert review of medical devices.

[24]  Pascal Vincent,et al.  Unsupervised Feature Learning and Deep Learning: A Review and New Perspectives , 2012, ArXiv.

[25]  C. Shapiro,et al.  The Prevalence, Cost Implications, and Management of Sleep Disorders: An Overview , 2002, Sleep & breathing = Schlaf & Atmung.

[26]  Hwee Pink Tan,et al.  Deep Activity Recognition Models with Triaxial Accelerometers , 2015, AAAI Workshop: Artificial Intelligence Applied to Assistive Technologies and Smart Environments.

[27]  Shwetak N. Patel,et al.  DoppleSleep: a contactless unobtrusive sleep sensing system using short-range Doppler radar , 2015, UbiComp.