A Reliable and Reconfigurable Signal Processing Framework for Estimation of Metabolic Equivalent of Task in Wearable Sensors

Wearable motion sensors are widely used to estimate metabolic equivalent of task (MET) values associated with physical activities. However, one major obstacle in widespread adoption of current wearables is that any changes in configuration of the network requires new data collection and re-training of the underlying signal processing algorithms. For any wearable-based MET estimation framework to be considered a viable platform, it needs to be reconfigurable, reliable, and power-efficient. In this paper, we aim to address the issues of sensor misplacement, power efficiency, and new sensor addition and propose a reliable and reconfigurable MET estimation framework. We introduce a power-aware sensor localization approach that allows users to wear the sensors on different body locations without need for adhering to a specific installation protocol. Furthermore, we propose a novel transductive transfer learning approach, which gives end-users the ability to add new sensors to the network without need for collecting new training data. This is accomplished by transferring the knowledge of already trained sensors to the untrained sensors in real-time. Our experiments demonstrate that our sensor localization algorithm achieves an accuracy of 90.8% in detecting location of the wearable sensors. The integrated model of sensor localization and MET calculation achieves an R2 of 0.8 in estimating MET values using a regression-based model. Furthermore, our transfer learning algorithm improves the R2 value of MET estimation up to 60%.

[1]  Franco Turini,et al.  Time-Annotated Sequences for Medical Data Mining , 2007 .

[2]  E. Silerova,et al.  Knowledge and information systems , 2018 .

[3]  Bo Dong,et al.  Metabolic energy expenditure estimation using a position-agnostic wearable sensor system , 2014, 2014 IEEE Healthcare Innovation Conference (HIC).

[4]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[5]  Matt Brzycki,et al.  A Practical Approach To Strength Training , 1990 .

[6]  Paul Lukowicz,et al.  Using acceleration signatures from everyday activities for on-body device location , 2007, 2007 11th IEEE International Symposium on Wearable Computers.

[7]  Hassan Ghasemzadeh,et al.  A machine learning approach for medication adherence monitoring using body-worn sensors , 2016, 2016 Design, Automation & Test in Europe Conference & Exhibition (DATE).

[8]  Yoshihiro Kawahara,et al.  Monitoring Daily Energy Expenditure using a 3-Axis Accelerometer with a Low-Power Microprocessor , 2009, e Minds Int. J. Hum. Comput. Interact..

[9]  Hassan Ghasemzadeh,et al.  An Energy-Efficient Computational Model for Uncertainty Management in Dynamically Changing Networked Wearables , 2016, ISLPED.

[10]  Héctor Pomares,et al.  On the Use of Sensor Fusion to Reduce the Impact of Rotational and Additive Noise in Human Activity Recognition , 2012, Sensors.

[11]  Timothy Kwok,et al.  Effect of age and gender on energy expenditure in common activities of daily living in a Chinese population , 2007, Disability and rehabilitation.

[12]  Majid Sarrafzadeh,et al.  Unsupervised techniques for time series mining and information extraction in medical informatics , 2010 .

[13]  Paul Lukowicz,et al.  Where am I: Recognizing On-body Positions of Wearable Sensors , 2005, LoCA.

[14]  Diane J. Cook,et al.  Toward personalized and context-aware prompting for smartphone-based intervention , 2016, 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[15]  Bo Dong,et al.  Comparing metabolic energy expenditure estimation using wearable multi-sensor network and single accelerometer , 2013, 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[16]  Yoshua Bengio,et al.  Deep Learning of Representations for Unsupervised and Transfer Learning , 2011, ICML Unsupervised and Transfer Learning.

[17]  G. Cawley,et al.  Efficient approximate leave-one-out cross-validation for kernel logistic regression , 2008, Machine Learning.

[18]  Héctor Pomares,et al.  Dealing with the Effects of Sensor Displacement in Wearable Activity Recognition , 2014, Sensors.

[19]  Hassan Ghasemzadeh,et al.  Power-Aware Computing in Wearable Sensor Networks: An Optimal Feature Selection , 2015, IEEE Transactions on Mobile Computing.

[20]  Hassan Ghasemzadeh,et al.  A Hardware-Assisted Energy-Efficient Processing Model for Activity Recognition Using Wearables , 2016, TODE.

[21]  Jun Huan,et al.  Large margin transductive transfer learning , 2009, CIKM.

[22]  Murat Dundar,et al.  Bayesian multiple instance learning: automatic feature selection and inductive transfer , 2008, ICML '08.

[23]  Majid Sarrafzadeh,et al.  Accelerometer-based on-body sensor localization for health and medical monitoring applications , 2011, Pervasive Mob. Comput..

[24]  Hassan Ghasemzadeh,et al.  Toward robust and platform-agnostic gait analysis , 2015, 2015 IEEE 12th International Conference on Wearable and Implantable Body Sensor Networks (BSN).

[25]  Luca Benini,et al.  Network-Level Power-Performance Trade-Off in Wearable Activity Recognition: A Dynamic Sensor Selection Approach , 2012, TECS.

[26]  Hongyi Li,et al.  A method to deal with installation errors of wearable accelerometers for human activity recognition , 2011, Physiological measurement.

[27]  Ramesh Nallapati,et al.  A Comparative Study of Methods for Transductive Transfer Learning , 2007, Seventh IEEE International Conference on Data Mining Workshops (ICDMW 2007).

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

[29]  Majid Sarrafzadeh,et al.  On-body device localization for health and medical monitoring applications , 2011, 2011 IEEE International Conference on Pervasive Computing and Communications (PerCom).

[30]  Yan Liu,et al.  A general framework for scalable transductive transfer learning , 2013, Knowledge and Information Systems.

[31]  Majid Sarrafzadeh,et al.  MET calculations from on-body accelerometers for exergaming movements , 2013, 2013 IEEE International Conference on Body Sensor Networks.

[32]  J F Sallis,et al.  Compendium of physical activities: classification of energy costs of human physical activities. , 1993, Medicine and science in sports and exercise.

[33]  David R Bassett,et al.  2011 Compendium of Physical Activities: a second update of codes and MET values. , 2011, Medicine and science in sports and exercise.

[34]  Hassan Ghasemzadeh,et al.  Toward seamless wearable sensing: Automatic on-body sensor localization for physical activity monitoring , 2014, 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[35]  Maurice Bruynooghe,et al.  Learning Relational Options for Inductive Transfer in Relational Reinforcement Learning , 2007, ILP.

[36]  Susmita Sur-Kolay,et al.  Energy-Efficient Long-term Continuous Personal Health Monitoring , 2015, IEEE Transactions on Multi-Scale Computing Systems.

[37]  Paul Lukowicz,et al.  Sensor Placement Variations in Wearable Activity Recognition , 2014, IEEE Pervasive Computing.

[38]  Hassan Ghasemzadeh,et al.  Impact of sensor misplacement on estimating metabolic equivalent of task with wearables , 2015, 2015 IEEE 12th International Conference on Wearable and Implantable Body Sensor Networks (BSN).

[39]  D. Warburton,et al.  Health benefits of physical activity: the evidence , 2006, Canadian Medical Association Journal.

[40]  Julien Penders,et al.  Estimating Energy Expenditure Using Body-Worn Accelerometers: A Comparison of Methods, Sensors Number and Positioning , 2015, IEEE Journal of Biomedical and Health Informatics.

[41]  Ricardo Chavarriaga,et al.  On-line anomaly detection and resilience in classifier ensembles , 2013, Pattern Recognit. Lett..

[42]  Daniel Olgu ´ õn,et al.  Human Activity Recognition: Accuracy across Common Locations for Wearable Sensors , 2006 .

[43]  Hassan Ghasemzadeh,et al.  Cost-sensitive feature selection for on-body sensor localization , 2014, UbiComp Adjunct.

[44]  Rajat Raina,et al.  Self-taught learning: transfer learning from unlabeled data , 2007, ICML '07.

[45]  Hassan Ghasemzadeh,et al.  Patient-centric on-body sensor localization in smart health systems , 2014, 2014 48th Asilomar Conference on Signals, Systems and Computers.

[46]  Chris A. Glasbey,et al.  An Analysis of Histogram-Based Thresholding Algorithms , 1993, CVGIP Graph. Model. Image Process..

[47]  Yoshua Bengio,et al.  Unsupervised and Transfer Learning Challenge: a Deep Learning Approach , 2011, ICML Unsupervised and Transfer Learning.

[48]  B E Ainsworth,et al.  Compendium of physical activities: an update of activity codes and MET intensities. , 2000, Medicine and science in sports and exercise.

[49]  G. Troster,et al.  Evolving discriminative features robust to sensor displacement for activity recognition in body area sensor networks , 2009, 2009 International Conference on Intelligent Sensors, Sensor Networks and Information Processing (ISSNIP).