Sleep behavior assessment via smartwatch and stigmergic receptive fields

Sleep behavior is a key factor in maintaining good physiological and psychological health. A well-known approach to monitor sleep is polysomnography. However, it is costly and intrusive, which may disturb sleep. Consequently, polysomnography is not suitable for sleep behavior analysis. Other approaches are based on actigraphy and sleep diary. Although being a good source of information for sleep quality assessment, sleep diaries can be affected by cognitive bias related to subject’s sleep perception, while actigraphy overestimates sleep periods and night-time disturbance compared to sleep diaries. Machine learning techniques can improve the objectivity and reliability of the observations. However, since signal morphology vary widely between people, conventional machine learning is complex to set up. In this regard, we present an adaptive, reliable, and innovative computational approach to provide per-night assessment of sleep behavior to the end-user. We exploit heartbeat rate and wrist acceleration data, gathered via smartwatch, in order to identify subject’s sleep behavioral pattern. More specifically, heartbeat rate and wrist motion samples are processed via computational stigmergy, a bio-inspired scalar and temporal aggregation of samples. Stigmergy associates each sample to a digital pheromone deposit (mark) defined in a mono-dimensional space and characterized by evaporation over time. As a consequence, samples close in terms of time and intensity are aggregated into functional structures called trails. The stigmergic trails allow to compute the similarity between time series on different temporal scales, to support classification or clustering processes. The overall computing schema includes a parametric optimization for adapting the structural parameters to individual sleep dynamics. The outcome is a similarity between sleep nights of the same subject, to generate clusters of nights with different quality levels. Experimental results are shown for three real-world subjects. The resulting similarity is also compared with the dynamic time warping, a popular similarity measure for time series.

[1]  Sonia Ancoli-Israel,et al.  Comparison of sleep parameters from actigraphy and polysomnography in older women: the SOF study. , 2008, Sleep.

[2]  Sharon L. Oviatt,et al.  Toward Adaptive Information Fusion in Multimodal Systems , 2005, MLMI.

[3]  C. Guilleminault,et al.  Meta-analysis of quantitative sleep parameters from childhood to old age in healthy individuals: developing normative sleep values across the human lifespan. , 2004, Sleep.

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

[5]  N. Ansari,et al.  Adaptive fusion by reinforcement learning for distributed detection systems , 1996, IEEE Transactions on Aerospace and Electronic Systems.

[6]  Keith G Wilson,et al.  Daily diary and ambulatory activity monitoring of sleep in patients with insomnia associated with chronic musculoskeletal pain , 1998, Pain.

[7]  F. Snyder,et al.  Recorded and reported sleep in chronic primary insomnia. , 1976, Archives of general psychiatry.

[8]  Jasper Snoek,et al.  Practical Bayesian Optimization of Machine Learning Algorithms , 2012, NIPS.

[9]  Eva Ceulemans,et al.  Proceedings of COMPSTAT'2010 , 2010 .

[10]  Jiaqi Liu,et al.  A novel clustering method on time series data , 2011, Expert Syst. Appl..

[11]  Andrea Domenici,et al.  Using Smartwatch Sensors to Support the Acquisition of Sleep Quality Data for Supervised Machine Learning , 2016, MobiHealth.

[12]  D. Kripke,et al.  The role of actigraphy in the evaluation of sleep disorders. , 1995, Sleep.

[13]  Rudolf Mathar,et al.  Kernel-based learning of decision fusion in wireless sensor networks , 2008, 2008 11th International Conference on Information Fusion.

[14]  Stefano Chessa,et al.  GP-m: Mobile middleware infrastructure for Ambient Assisted Living , 2014, 2014 IEEE Symposium on Computers and Communications (ISCC).

[15]  Marco Di Rienzo,et al.  Wearable monitoring: A project for the unobtrusive investigation of sleep physiology aboard the International Space Station , 2015, 2015 Computing in Cardiology Conference (CinC).

[16]  Michael T. Heath,et al.  Scientific Computing , 2018 .

[17]  Claudio Gallicchio,et al.  Human activity recognition using multisensor data fusion based on Reservoir Computing , 2016, J. Ambient Intell. Smart Environ..

[18]  Job G. Godino,et al.  Measures of sleep and cardiac functioning during sleep using a multi-sensory commercially-available wristband in adolescents , 2016, Physiology & Behavior.

[19]  Vangelis Metsis,et al.  Non-invasive analysis of sleep patterns via multimodal sensor input , 2012, Personal and Ubiquitous Computing.

[20]  Marco Avvenuti,et al.  MARS, a Multi-Agent System for Assessing Rowers' Coordination via Motion-Based Stigmergy , 2013, Sensors.

[21]  Ian H. Witten,et al.  The WEKA data mining software: an update , 2009, SKDD.

[22]  Soon Ju Kang,et al.  A wearable device platform for the estimation of sleep quality using simultaneously motion tracking and pulse oximetry , 2016, 2016 IEEE International Conference on Consumer Electronics (ICCE).

[23]  M. Littner,et al.  Practice parameters for the indications for polysomnography and related procedures: an update for 2005. , 2005, Sleep.

[24]  Giulio Sandini,et al.  A Survey of Artificial Cognitive Systems: Implications for the Autonomous Development of Mental Capabilities in Computational Agents , 2007, IEEE Transactions on Evolutionary Computation.

[25]  Ron Kohavi,et al.  The Power of Decision Tables , 1995, ECML.

[26]  Pradeep K. Atrey,et al.  Learning Multisensor Confidence Using a Reward-and-Punishment Mechanism , 2009, IEEE Transactions on Instrumentation and Measurement.

[27]  D. Skene,et al.  Comparison between subjective and actigraphic measurement of sleep and sleep rhythms , 1999, Journal of sleep research.

[28]  Andrew Chesson,et al.  Practice parameters for the use of actigraphy in the clinical assessment of sleep disorders. American Sleep Disorders Association. , 1995, Sleep.

[29]  Guang-Zhong Yang,et al.  An On-Node Processing Approach for Anomaly Detection in Gait , 2015, IEEE Sensors Journal.

[30]  Hui Ding,et al.  Querying and mining of time series data: experimental comparison of representations and distance measures , 2008, Proc. VLDB Endow..

[31]  Gregory D. Hager.  Task-Directed Sensor Fusion and Planning: A Computational Approach , 1990 .

[32]  Léon Bottou,et al.  Large-Scale Machine Learning with Stochastic Gradient Descent , 2010, COMPSTAT.

[33]  Daniel J Buysse,et al.  Measuring sleep habits without using a diary: the sleep timing questionnaire. , 2003, Sleep.

[34]  A. Sadeh.  The role and validity of actigraphy in sleep medicine: an update. , 2011, Sleep medicine reviews.

[35]  P.D. Mannheimer,et al.  Wavelength selection for low-saturation pulse oximetry , 1997, IEEE Transactions on Biomedical Engineering.

[36]  Young-Sik Jeong,et al.  Sleeping situation monitoring system in ubiquitous environments , 2012, Personal and Ubiquitous Computing.

[37]  Zilu Liang,et al.  SleepExplorer: a visualization tool to make sense of correlations between personal sleep data and contextual factors , 2016, Personal and Ubiquitous Computing.

[38]  Michael T. Heath,et al.  Scientific Computing: An Introductory Survey , 1996 .

[39]  Neil D. Lawrence,et al.  International workshop on machine learning for multimodal interaction , 2007 .

[40]  Gigliola Vaglini,et al.  Measuring Physical Activity of Older Adults via Smartwatch and Stigmergic Receptive Fields , 2017, ICPRAM.

[41]  Pubudu N. Pathirana,et al.  Smartwatch: Performance evaluation for long-term heart rate monitoring , 2015, 2015 International Symposium on Bioelectronics and Bioinformatics (ISBB).

[42]  C. Espie,et al.  Use of the Sleep Assessment Device (Kelley and Lichstein, 1980) to validate insomniacs' self-report of sleep pattern , 1989 .

[43]  Nuno Constantino Castro,et al.  Time Series Data Mining , 2009, Encyclopedia of Database Systems.

[44]  Paolo Barsocchi,et al.  EMS@CNR: An Energy monitoring sensor network infrastructure for in-building location-based services , 2014, 2014 International Conference on High Performance Computing & Simulation (HPCS).

[45]  Massimiliano de Zambotti,et al.  Evaluation of a consumer fitness-tracking device to assess sleep in adults , 2015, Chronobiology international.

[46]  Paolo Barsocchi,et al.  Monitoring elderly behavior via indoor position-based stigmergy , 2015, Pervasive Mob. Comput..

[47]  H. Miwa,et al.  Roll-over Detection and Sleep Quality Measurement using a Wearable Sensor , 2007, 2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[48]  Fanglin Chen,et al.  Unobtrusive sleep monitoring using smartphones , 2013, 2013 7th International Conference on Pervasive Computing Technologies for Healthcare and Workshops.

[49]  Derek K. Shaeffer,et al.  MEMS inertial sensors: A tutorial overview , 2013, IEEE Communications Magazine.

[50]  J. Hobson,et al.  The Role of Sleep in Learning and Memory , 2014 .

[51]  Alessio Vecchio,et al.  Gait-based authentication using a wrist-worn device , 2016, MobiQuitous.

[52]  Yoram Singer,et al.  Pegasos: primal estimated sub-gradient solver for SVM , 2011, Math. Program..

[53]  Marian Haescher,et al.  SmartMove: a smartwatch algorithm to distinguish between high- and low-amplitude motions as well as doffed-states by utilizing noise and sleep , 2016, iWOAR.

[54]  M. Johns,et al.  A new method for measuring daytime sleepiness: the Epworth sleepiness scale. , 1991, Sleep.

[55]  Lars Widmer,et al.  Stress and sleep quality estimation from a smart wearable sensor , 2010, 5th International Conference on Pervasive Computing and Applications.

[56]  T. Åkerstedt,et al.  The meaning of good sleep: a longitudinal study of polysomnography and subjective sleep quality , 1994, Journal of sleep research.

[57]  J. Ross Quinlan,et al.  Induction of Decision Trees , 1986, Machine Learning.

[58]  M. B. Gillespie,et al.  Overview of smartphone applications for sleep analysis , 2016, World journal of otorhinolaryngology - head and neck surgery.

[59]  John Allen.  Photoplethysmography and its application in clinical physiological measurement , 2007, Physiological measurement.

[60]  Diogo R. Ferreira,et al.  Preprocessing techniques for context recognition from accelerometer data , 2010, Personal and Ubiquitous Computing.

[61]  Matjaz Gams,et al.  How Accurately Can Your Wrist Device Recognize Daily Activities and Detect Falls? , 2016, Sensors.

[62]  Gregory F. Cooper,et al.  A Bayesian method for the induction of probabilistic networks from data , 1992, Machine Learning.

[63]  Filippo Palumbo,et al.  Taking Arduino to the Internet of Things: The ASIP programming model , 2016, Comput. Commun..

[64]  M. Littner,et al.  The indications for polysomnography and related procedures. , 1997, Sleep.

[65]  David Howard,et al.  A Comparison of Feature Extraction Methods for the Classification of Dynamic Activities From Accelerometer Data , 2009, IEEE Transactions on Biomedical Engineering.

[66]  Gigliola Vaglini,et al.  Improving the Analysis of Context-Aware Information via Marker-Based Stigmergy and Differential Evolution , 2015, ICAISC.

[67]  Beatrice Lazzerini,et al.  A novel approach to fuzzy clustering based on a dissimilarity relation extracted from data using a TS system , 2006, Pattern Recognit..

[68]  Fakhri Karray,et al.  Multisensor data fusion: A review of the state-of-the-art , 2013, Inf. Fusion.

[69]  I Oswald,et al.  Assessment of insomnia. , 1981, British medical journal.