Easing Power Consumption of Wearable Activity Monitoring with Change Point Detection

Continuous monitoring of complex activities is valuable for understanding human behavior and providing activity-aware services. At the same time, recognizing these activities requires both movement and location information that can quickly drain batteries on wearable devices. In this paper, we introduce Change Point-based Activity Monitoring (CPAM), an energy-efficient strategy for recognizing and monitoring a range of simple and complex activities in real time. CPAM employs unsupervised change point detection to detect likely activity transition times. By adapting the sampling rate at each change point, CPAM reduces energy consumption by 74.64% while retaining the activity recognition performance of continuous sampling. We validate our approach using smartwatch data collected and labeled by 66 subjects. Results indicate that change point detection techniques can be effective for reducing the energy footprint of sensor-based mobile applications and that automated activity labels can be used to estimate sensor values between sampling periods.

[1]  Diane J. Cook,et al.  A survey of methods for time series change point detection , 2017, Knowledge and Information Systems.

[2]  Munoz-Organero Mario,et al.  Human Activity Recognition Based on Single Sensor Square HV Acceleration Images and Convolutional Neural Networks , 2019, IEEE Sensors Journal.

[3]  R. B. Deshmukh,et al.  A Systematic Review of Compressive Sensing: Concepts, Implementations and Applications , 2018, IEEE Access.

[4]  R. Amutha,et al.  A novel chaotic map based compressive classification scheme for human activity recognition using a tri-axial accelerometer , 2018, Multimedia Tools and Applications.

[5]  Valentina Camomilla,et al.  Trends Supporting the In-Field Use of Wearable Inertial Sensors for Sport Performance Evaluation: A Systematic Review , 2018, Sensors.

[6]  Vigneshwaran Subbaraju,et al.  Energy-Efficient Continuous Activity Recognition on Mobile Phones: An Activity-Adaptive Approach , 2012, 2012 16th International Symposium on Wearable Computers.

[7]  C Leurent,et al.  Digital technologies for cognitive assessment to accelerate drug development in Alzheimer's disease , 2015, Clinical pharmacology and therapeutics.

[8]  Ari Yair Barrera-Animas,et al.  Monitoring Student Activities with Smartwatches: On the Academic Performance Enhancement , 2019, Sensors.

[9]  Yi Wang,et al.  Identifying activity boundaries for activity recognition in smart environments , 2016, 2016 IEEE International Conference on Communications (ICC).

[10]  Minoru Yoshizawa,et al.  Parameter exploration for response time reduction in accelerometer-based activity recognition , 2013, UbiComp.

[11]  Janardhan Rao Doppa,et al.  Learning Activity Predictors from Sensor Data: Algorithms, Evaluation, and Applications , 2017, IEEE Transactions on Knowledge and Data Engineering.

[12]  L. Mathew,et al.  Increasing trend of wearables and multimodal interface for human activity monitoring: A review. , 2017, Biosensors & bioelectronics.

[13]  Mo Li,et al.  Memento: An Emotion Driven Lifelogging System with Wearables , 2017, 2017 26th International Conference on Computer Communication and Networks (ICCCN).

[14]  Christian Haubelt,et al.  Towards energy efficient sensor nodes for online activity recognition , 2017, IECON 2017 - 43rd Annual Conference of the IEEE Industrial Electronics Society.

[15]  Pierre Vandergheynst,et al.  Compressed Sensing for Real-Time Energy-Efficient ECG Compression on Wireless Body Sensor Nodes , 2011, IEEE Transactions on Biomedical Engineering.

[16]  Eamonn J. Keogh,et al.  MDL-based time series clustering , 2012, Knowledge and Information Systems.

[17]  Gabrielle M. Turner-McGrievy,et al.  Choosing between responsive-design websites versus mobile apps for your mobile behavioral intervention: presenting four case studies , 2017, Translational behavioral medicine.

[18]  Hassan Ghasemzadeh,et al.  Toward Ultra-Low-Power Remote Health Monitoring: An Optimal and Adaptive Compressed Sensing Framework for Activity Recognition , 2019, IEEE Transactions on Mobile Computing.

[19]  Abbes Amira,et al.  Compressive Sensing-Based IoT Applications: A Review , 2018, J. Sens. Actuator Networks.

[20]  Mahbub Hassan,et al.  CapSense: Capacitor-based Activity Sensing for Kinetic Energy Harvesting Powered Wearable Devices , 2017, MobiQuitous.

[21]  Davide Anguita,et al.  Transition-Aware Human Activity Recognition Using Smartphones , 2016, Neurocomputing.

[22]  Diane J. Cook,et al.  Automated Detection of Activity Transitions for Prompting , 2015, IEEE Transactions on Human-Machine Systems.

[23]  Zoran A. Salcic,et al.  Adaptive sliding window segmentation for physical activity recognition using a single tri-axial accelerometer , 2017, Pervasive Mob. Comput..

[24]  Carla L Graf,et al.  The Lawton Instrumental Activities of Daily Living Scale , 2008, The American journal of nursing.

[25]  Samaneh Aminikhanghahi,et al.  Real-Time Change Point Detection with Application to Smart Home Time Series Data , 2019, IEEE Transactions on Knowledge and Data Engineering.

[26]  Ian Cleland,et al.  Dynamic detection of window starting positions and its implementation within an activity recognition framework , 2016, J. Biomed. Informatics.

[27]  Kenji Yamanishi,et al.  A unifying framework for detecting outliers and change points from non-stationary time series data , 2002, KDD.

[28]  Paul J. M. Havinga,et al.  SmokeSense: Online Activity Recognition Framework on Smartwatches , 2018, MobiCASE.

[29]  Michèle Basseville,et al.  Detection of abrupt changes: theory and application , 1993 .

[30]  Ümit Y. Ogras,et al.  Online Human Activity Recognition using Low-Power Wearable Devices , 2018, 2018 IEEE/ACM International Conference on Computer-Aided Design (ICCAD).

[31]  Zhetao Li,et al.  Energy-Efficient Dynamic Computation Offloading and Cooperative Task Scheduling in Mobile Cloud Computing , 2019, IEEE Transactions on Mobile Computing.

[32]  Jeongho Kwak,et al.  Proximity-Aware Location Based Collaborative Sensing for Energy-Efficient Mobile Devices , 2019, IEEE Transactions on Mobile Computing.

[33]  Lawrence B. Holder,et al.  Thyme: Improving Smartphone Prompt Timing Through Activity Awareness , 2017, 2017 16th IEEE International Conference on Machine Learning and Applications (ICMLA).

[34]  Yoshihiro Kawahara,et al.  Compressed sensing method for human activity sensing using mobile phone accelerometers , 2012, 2012 Ninth International Conference on Networked Sensing (INSS).

[35]  David Atienza,et al.  A Wireless Body Sensor Network for Activity Monitoring with Low Transmission Overhead , 2014, 2014 12th IEEE International Conference on Embedded and Ubiquitous Computing.

[36]  Diane J. Cook,et al.  Enhancing activity recognition using CPD-based activity segmentation , 2019, Pervasive Mob. Comput..

[37]  Hassan Ghasemzadeh,et al.  Trading Off Power Consumption and Prediction Performance in Wearable Motion Sensors , 2018, ACM Trans. Design Autom. Electr. Syst..

[38]  Sunwoong Choi,et al.  Classification of Various Daily Activities using Convolution Neural Network and Smartwatch , 2018, 2018 IEEE International Conference on Big Data (Big Data).

[39]  Younghee Lee,et al.  Contextual Relationship-based Activity Segmentation on an Event Stream in the IoT Environment with Multi-user Activities , 2016, M4IoT@Middleware.

[40]  Bernt Schiele,et al.  A tutorial on human activity recognition using body-worn inertial sensors , 2014, CSUR.

[41]  Niall Twomey,et al.  On-Board Feature Extraction from Acceleration Data for Activity Recognition , 2018, EWSN.

[42]  Sara Khalifa,et al.  Energy-efficient human activity recognition for self-powered wearable devices , 2017, ACSW.

[43]  Jian Tang,et al.  Energy-efficient collaborative sensing with mobile phones , 2012, 2012 Proceedings IEEE INFOCOM.

[44]  Miguel A. Labrador,et al.  A Survey on Human Activity Recognition using Wearable Sensors , 2013, IEEE Communications Surveys & Tutorials.

[45]  Jay Stewart,et al.  The American Time Use Survey , 2005 .

[46]  Takafumi Kanamori,et al.  A Least-squares Approach to Direct Importance Estimation , 2009, J. Mach. Learn. Res..

[47]  Nirmalya Roy,et al.  A smart segmentation technique towards improved infrequent non-speech gestural activity recognition model , 2017, Pervasive Mob. Comput..

[48]  Hao Ma,et al.  Human Gait Modeling and Analysis Using a Semi-Markov Process With Ground Reaction Forces , 2017, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[49]  Eamonn J. Keogh,et al.  Clustering Time Series Using Unsupervised-Shapelets , 2012, 2012 IEEE 12th International Conference on Data Mining.

[50]  N. Alshurafa,et al.  Battery Optimization in Remote Health Monitoring Systems to Enhance User Adherence , 2014 .

[51]  Maureen Schmitter-Edgecombe,et al.  Technology-Enabled Assessment of Functional Health , 2019, IEEE Reviews in Biomedical Engineering.

[52]  Gabriel Tamura,et al.  Characterizing context-aware recommender systems: A systematic literature review , 2018, Knowl. Based Syst..

[53]  Hassan Ghasemzadeh,et al.  Improving Compliance in Remote Healthcare Systems Through Smartphone Battery Optimization , 2015, IEEE Journal of Biomedical and Health Informatics.

[54]  Majid Sarrafzadeh,et al.  Applying Multivariate Segmentation Methods to Human Activity Recognition From Wearable Sensors’ Data , 2018, JMIR mHealth and uHealth.

[55]  Sajal K. Das,et al.  HuMAn: Complex Activity Recognition with Multi-Modal Multi-Positional Body Sensing , 2019, IEEE Transactions on Mobile Computing.

[56]  Ryan P. Adams,et al.  Bayesian Online Changepoint Detection , 2007, 0710.3742.

[57]  Carl E. Rasmussen,et al.  Gaussian Process Change Point Models , 2010, ICML.

[58]  Le Song,et al.  M-Statistic for Kernel Change-Point Detection , 2015, NIPS.

[59]  Nigel Collier,et al.  Change-Point Detection in Time-Series Data by Relative Density-Ratio Estimation , 2012, Neural Networks.

[60]  Daniel P. Siewiorek,et al.  Selective Sampling Strategies to Conserve Power in Context Aware Devices , 2007, 2007 11th IEEE International Symposium on Wearable Computers.

[61]  Sriram Chellappan,et al.  Watch-Dog: Detecting Self-Harming Activities From Wrist Worn Accelerometers , 2018, IEEE Journal of Biomedical and Health Informatics.

[62]  Michael Beigl,et al.  Energy-Efficient Activity Recognition Using Prediction , 2012, 2012 16th International Symposium on Wearable Computers.

[63]  M. Kawanabe,et al.  Direct importance estimation for covariate shift adaptation , 2008 .

[64]  Tommi Mikkonen,et al.  Early analysis of resource consumption patterns in mobile applications , 2017, Pervasive Mob. Comput..

[65]  Mo Li,et al.  Memento: An Emotion Driven Lifelogging System with Wearables , 2017, 2017 26th International Conference on Computer Communication and Networks (ICCCN).

[66]  Amr Mohamed,et al.  Improving Remote Health Monitoring: A Low-Complexity ECG Compression Approach , 2018, Diagnostics.

[67]  Yoshinobu Kawahara,et al.  Change-Point Detection in Time-Series Data Based on Subspace Identification , 2007, Seventh IEEE International Conference on Data Mining (ICDM 2007).