Dealing with the Effects of Sensor Displacement in Wearable Activity Recognition

Most wearable activity recognition systems assume a predefined sensor deployment that remains unchanged during runtime. However, this assumption does not reflect real-life conditions. During the normal use of such systems, users may place the sensors in a position different from the predefined sensor placement. Also, sensors may move from their original location to a different one, due to a loose attachment. Activity recognition systems trained on activity patterns characteristic of a given sensor deployment may likely fail due to sensor displacements. In this work, we innovatively explore the effects of sensor displacement induced by both the intentional misplacement of sensors and self-placement by the user. The effects of sensor displacement are analyzed for standard activity recognition techniques, as well as for an alternate robust sensor fusion method proposed in a previous work. While classical recognition models show little tolerance to sensor displacement, the proposed method is proven to have notable capabilities to assimilate the changes introduced in the sensor position due to self-placement and provides considerable improvements for large misplacements.

[1]  H.J. Stam,et al.  Automated estimation of initial and terminal contact timing using accelerometers; development and validation in transtibial amputees and controls , 2005, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

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

[3]  Bernt Schiele,et al.  Dead reckoning from the pocket - An experimental study , 2010, 2010 IEEE International Conference on Pervasive Computing and Communications (PerCom).

[4]  Klaus-Robert Müller,et al.  Covariate Shift Adaptation by Importance Weighted Cross Validation , 2007, J. Mach. Learn. Res..

[5]  Patrick Robertson,et al.  Bayesian recognition of motion related activities with inertial sensors , 2010, UbiComp '10 Adjunct.

[6]  Ilias Tachtsidis,et al.  Estimating a modified Grubb's exponent in healthy human brains with near infrared spectroscopy and transcranial Doppler , 2009, Physiological measurement.

[7]  Gregory J. Pottie,et al.  Self-calibration of sensor misplacement based on motion signatures , 2013, 2013 IEEE International Conference on Body Sensor Networks.

[8]  Héctor Pomares,et al.  Kinect=IMU? Learning MIMO Signal Mappings to Automatically Translate Activity Recognition Systems across Sensor Modalities , 2012, 2012 16th International Symposium on Wearable Computers.

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

[10]  M. Stone Asymptotics for and against cross-validation , 1977 .

[11]  Daniel Roggen,et al.  Designing and sharing activity recognition systems across platforms , 2011 .

[12]  Ricardo Chavarriaga,et al.  Unsupervised Adaptation to On-body Sensor Displacement in Acceleration-Based Activity Recognition , 2011, 2011 15th Annual International Symposium on Wearable Computers.

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

[14]  Didier Stricker,et al.  Creating and benchmarking a new dataset for physical activity monitoring , 2012, PETRA '12.

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

[16]  Héctor Pomares,et al.  Human activity recognition based on a sensor weighting hierarchical classifier , 2013, Soft Comput..

[17]  Peter E. Hart,et al.  Nearest neighbor pattern classification , 1967, IEEE Trans. Inf. Theory.

[18]  Ricardo Chavarriaga,et al.  Unsupervised adaptation for acceleration-based activity recognition: robustness to sensor displacement and rotation , 2011, Personal and Ubiquitous Computing.

[19]  Andrea Mannini,et al.  Activity recognition using a single accelerometer placed at the wrist or ankle. , 2013, Medicine and science in sports and exercise.

[20]  Daniel Roggen,et al.  On the Issue of Variability in Labels and Sensor Configurations in Activity Recognition Systems , 2010, Pervasive 2010.

[21]  Merryn J Mathie,et al.  Accelerometry: providing an integrated, practical method for long-term, ambulatory monitoring of human movement , 2004, Physiological measurement.

[22]  Kamiar Aminian,et al.  Ambulatory system for human motion analysis using a kinematic sensor: monitoring of daily physical activity in the elderly , 2003, IEEE Transactions on Biomedical Engineering.

[23]  Lei Gao,et al.  A system for activity recognition using multi-sensor fusion , 2011, 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[24]  Philip J Peyton,et al.  A new method for measurement of gas exchange during anaesthesia using an extractable marker gas. , 2004, Physiological measurement.

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

[26]  Guang-Zhong Yang,et al.  Sensor Positioning for Activity Recognition Using Wearable Accelerometers , 2011, IEEE Transactions on Biomedical Circuits and Systems.

[27]  Gerhard Tröster,et al.  Unsupervised Classifier Self-Calibration through Repeated Context Occurences: Is there Robustness against Sensor Displacement to Gain? , 2009, 2009 International Symposium on Wearable Computers.

[28]  Daniel P. Siewiorek,et al.  Activity recognition and monitoring using multiple sensors on different body positions , 2006, International Workshop on Wearable and Implantable Body Sensor Networks (BSN'06).

[29]  Tapio Seppänen,et al.  Recognizing human motion with multiple acceleration sensors , 2001, 2001 IEEE International Conference on Systems, Man and Cybernetics. e-Systems and e-Man for Cybernetics in Cyberspace (Cat.No.01CH37236).

[30]  Paul Lukowicz,et al.  Rapid Prototyping of Activity Recognition Applications , 2008, IEEE Pervasive Computing.

[31]  Héctor Pomares,et al.  Window Size Impact in Human Activity Recognition , 2014, Sensors.

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

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

[34]  Reza Lotfian,et al.  Impact of sensor misplacement on dynamic time warping based human activity recognition using wearable computers , 2012, Wireless Health.

[35]  Paul Lukowicz,et al.  Wearable Activity Tracking in Car Manufacturing , 2008, IEEE Pervasive Computing.

[36]  Héctor Pomares,et al.  A benchmark dataset to evaluate sensor displacement in activity recognition , 2012, UbiComp.

[37]  L. Benini,et al.  Activity recognition from on-body sensors by classifier fusion: sensor scalability and robustness , 2007, 2007 3rd International Conference on Intelligent Sensors, Sensor Networks and Information.

[38]  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).

[39]  Lianwen Jin,et al.  A naturalistic 3D acceleration-based activity dataset & benchmark evaluations , 2010, 2010 IEEE International Conference on Systems, Man and Cybernetics.

[40]  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.

[41]  B. Ripley,et al.  Pattern Recognition , 1968, Nature.

[42]  Albrecht Schmidt,et al.  Multi-sensor Activity Context Detection for Wearable Computing , 2003, EUSAI.

[43]  Ilkka Korhonen,et al.  Detection of Daily Activities and Sports With Wearable Sensors in Controlled and Uncontrolled Conditions , 2008, IEEE Transactions on Information Technology in Biomedicine.

[44]  Yun Fu,et al.  Multiple feature fusion by subspace learning , 2008, CIVR '08.

[45]  Paul Lukowicz,et al.  Dealing with sensor displacement in motion-based onbody activity recognition systems , 2008, UbiComp.

[46]  Héctor Pomares,et al.  Daily living activity recognition based on statistical feature quality group selection , 2012, Expert Syst. Appl..

[47]  Kenneth Meijer,et al.  Activity identification using body-mounted sensors—a review of classification techniques , 2009, Physiological measurement.

[48]  Hongnian Yu,et al.  Activity classification using a single wrist-worn accelerometer , 2011, 2011 5th International Conference on Software, Knowledge Information, Industrial Management and Applications (SKIMA) Proceedings.

[49]  Shigeo Abe DrEng Pattern Classification , 2001, Springer London.

[50]  O. Amft,et al.  Influence of a loose-fitting sensing garment on posture recognition in rehabilitation , 2008, 2008 IEEE Biomedical Circuits and Systems Conference.

[51]  Tatsuo Nakajima,et al.  Feature Selection and Activity Recognition from Wearable Sensors , 2006, UCS.

[52]  Jessica K. Hodgins,et al.  Guide to the Carnegie Mellon University Multimodal Activity (CMU-MMAC) Database , 2008 .