Can Smartwatches Replace Smartphones for Posture Tracking?

This paper introduces a human posture tracking platform to identify the human postures of sitting, standing or lying down, based on a smartwatch. This work develops such a system as a proof-of-concept study to investigate a smartwatch’s ability to be used in future remote health monitoring systems and applications. This work validates the smartwatches’ ability to track the posture of users accurately in a laboratory setting while reducing the sampling rate to potentially improve battery life, the first steps in verifying that such a system would work in future clinical settings. The algorithm developed classifies the transitions between three posture states of sitting, standing and lying down, by identifying these transition movements, as well as other movements that might be mistaken for these transitions. The system is trained and developed on a Samsung Galaxy Gear smartwatch, and the algorithm was validated through a leave-one-subject-out cross-validation of 20 subjects. The system can identify the appropriate transitions at only 10 Hz with an F-score of 0.930, indicating its ability to effectively replace smart phones, if needed.

[1]  Majid Sarrafzadeh,et al.  Anti-Cheating: Detecting Self-Inflicted and Impersonator Cheaters for Remote Health Monitoring Systems with Wearable Sensors , 2014, 2014 11th International Conference on Wearable and Implantable Body Sensor Networks.

[2]  Jeen-Shing Wang,et al.  Using acceleration measurements for activity recognition: An effective learning algorithm for constructing neural classifiers , 2008, Pattern Recognit. Lett..

[3]  Mary Beth Rosson,et al.  Use and Adoption Challenges of Wearable Activity Trackers , 2015 .

[4]  Majid Sarrafzadeh,et al.  Battery optimization in smartphones for remote health monitoring systems to enhance user adherence , 2014, PETRA '14.

[5]  Katarzyna Wac,et al.  Getting closer: an empirical investigation of the proximity of user to their smart phones , 2011, UbiComp '11.

[6]  J. Wiens,et al.  Learning Evolving Patient Risk Processes for C. Diff Colonization , 2012 .

[7]  Fausto Giunchiglia,et al.  Multi-device activity logging , 2014, UbiComp Adjunct.

[8]  L. Buydens,et al.  Facilitating the application of Support Vector Regression by using a universal Pearson VII function based kernel , 2006 .

[9]  H. Krumholz,et al.  Telemonitoring for patients with chronic heart failure: a systematic review. , 2007, Journal of cardiac failure.

[10]  Marian Haescher,et al.  Sensor requirements for activity recognition on smart watches , 2013, PETRA '13.

[11]  Ho-Jin Choi,et al.  A watch-type human activity detector for the aged care , 2012, 2012 14th International Conference on Advanced Communication Technology (ICACT).

[12]  Kristof Van Laerhoven,et al.  A typology of wearable activity recognition and interaction , 2015, iWOAR.

[13]  Hassan Ghasemzadeh,et al.  Remote patient monitoring: what impact can data analytics have on cost? , 2013, Wireless Health.

[14]  Dongkyoo Shin,et al.  Smart Watch and Monitoring System for Dementia Patients , 2013, GPC.

[15]  Katarzyna Wac,et al.  UbiqLog: a generic mobile phone-based life-log framework , 2013, Personal and Ubiquitous Computing.

[16]  Majid Sarrafzadeh,et al.  Determining the Single Best Axis for Exercise Repetition Recognition and Counting on SmartWatches , 2014, 2014 11th International Conference on Wearable and Implantable Body Sensor Networks.

[17]  H. Krumholz,et al.  Telemonitoring in patients with heart failure. , 2010, The New England journal of medicine.

[18]  Martin Tomitsch,et al.  Energy-Efficient Integration of Continuous Context Sensing and Prediction into Smartwatches , 2015, Sensors.

[19]  T. Vasankari,et al.  A universal, accurate intensity‐based classification of different physical activities using raw data of accelerometer , 2015, Clinical physiology and functional imaging.

[20]  Majid Sarrafzadeh,et al.  Robust human intensity-varying activity recognition using Stochastic Approximation in wearable sensors , 2013, 2013 IEEE International Conference on Body Sensor Networks.

[21]  H. Ghasemzadeh,et al.  Wireless Medical-Embedded Systems: A Review of Signal-Processing Techniques for Classification , 2013, IEEE Sensors Journal.

[22]  Simon Mayer,et al.  User Interface Beaming -- Seamless Interaction with Smart Things Using Personal Wearable Computers , 2014, 2014 11th International Conference on Wearable and Implantable Body Sensor Networks Workshops.

[23]  Thomas Kirste,et al.  Ambient interaction by smart watches , 2012, PETRA '12.

[24]  Majid Sarrafzadeh,et al.  A Remote Patient Monitoring System for Congestive Heart Failure , 2011, Journal of Medical Systems.

[25]  S. Cessie,et al.  Predictive value of geriatric assessment for patients older than 70 years, treated with chemotherapy. , 2006, Critical reviews in oncology/hematology.

[26]  Mark L. Fowler,et al.  Indoor Localization, Tracking and Fall Detection for Assistive Healthcare Based on Spatial Sparsity and Wireless Sensor Network , 2013, Int. J. Monit. Surveillance Technol. Res..

[27]  Michael L. Littman,et al.  Activity Recognition from Accelerometer Data , 2005, AAAI.

[28]  Mi Zhang,et al.  A feature selection-based framework for human activity recognition using wearable multimodal sensors , 2011, BODYNETS.

[29]  Guy Lapalme,et al.  A systematic analysis of performance measures for classification tasks , 2009, Inf. Process. Manag..

[30]  Hassan Ghasemzadeh,et al.  WANDA: an end-to-end remote health monitoring and analytics system for heart failure patients , 2012, Wireless Health.

[31]  Ling Bao,et al.  Activity Recognition from User-Annotated Acceleration Data , 2004, Pervasive.

[32]  D. De Rossi,et al.  Wearable kinesthetic systems for capturing and classifying body posture and gesture , 2005, 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference.

[33]  Majid Sarrafzadeh,et al.  Multiple model recognition for near-realistic exergaming , 2015, 2015 IEEE International Conference on Pervasive Computing and Communications (PerCom).

[34]  Kristof Van Laerhoven,et al.  ISWC 2013-Wearables Are Here to Stay , 2014, IEEE Pervasive Comput..

[35]  Hugo Fuks,et al.  Wearable Computing: Accelerometers' Data Classification of Body Postures and Movements , 2012, SBIA.

[36]  Kristof Van Laerhoven,et al.  Wear is Your Mobile? Investigating Phone Carrying and Use Habits with a Wearable Device , 2015, Front. ICT.

[37]  Blaine A. Price,et al.  Wearables: has the age of smartwatches finally arrived? , 2015, Commun. ACM.

[38]  Archan Misra,et al.  The challenge of continuous mobile context sensing , 2014, 2014 Sixth International Conference on Communication Systems and Networks (COMSNETS).

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

[40]  Debjyoti Chowdhury,et al.  A Real Time Gesture Recognition with Wrist Mounted Accelerometer , 2015 .

[41]  Samanwoy Ghosh Dastidar,et al.  Classification of Traumatic Brain Injury Severity Using Informed Data Reduction in a Series of Binary Classifier Algorithms , 2012, IEEE Transactions on Neural Systems and Rehabilitation Engineering.