Automatic Detection of Deviations in Human Movements Using HMM: Discrete vs Continuous

Automatic detection of correct performance of movements in humans is the core of coaching and rehabilitation applications. Human movement can be studied in terms of sequential data by using different sensor technologies. This representation makes it possible to use models that use sequential data to determine if executions of a certain activity are close enough to the specification or if they must be considered to be erroneous. One of the most widely used approaches for characterization of sequential data are Hidden Markov Models (HMM). They have the advantage of being able to model processes based on data from noisy sources. In this work we explore the use of both discrete and continuous HMMs to label movement sequences as either according to a specification or deviated from it. The results show that the majority of sequences are correctly labeled by the technique, with an advantage for continuous HMM.

[1]  Chen Wang,et al.  Trajectory-based multi-dimensional outlier detection in wireless sensor networks using Hidden Markov Models , 2014, Wirel. Networks.

[2]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[3]  Jaime S. Cardoso,et al.  Outlier detection in 802.11 wireless access points using Hidden Markov Models , 2014, 2014 7th IFIP Wireless and Mobile Networking Conference (WMNC).

[4]  Hans-Werner Gellersen,et al.  MotionMA: motion modelling and analysis by demonstration , 2013, CHI.

[5]  Yingfeng Cai,et al.  Trajectory-based anomalous behaviour detection for intelligent traffic surveillance , 2015 .

[6]  Jesús Francisco Vargas-Bonilla,et al.  HMM Based Evaluation of Physical Therapy Movements Using Kinect Tracking , 2015, ISVC.

[7]  Wenbing Zhao,et al.  Rule based realtime motion assessment for rehabilitation exercises , 2014, 2014 IEEE Symposium on Computational Intelligence in Healthcare and e-health (CICARE).

[8]  Hichem Sahli,et al.  Continuous Change Detection and Classification Using Hidden Markov Model: A Case Study for Monitoring Urban Encroachment onto Farmland in Beijing , 2015, Remote. Sens..

[9]  Su Yang,et al.  Anomaly Detection on Collective Moving Patterns: A Hidden Markov Model Based Solution , 2011, 2011 International Conference on Internet of Things and 4th International Conference on Cyber, Physical and Social Computing.

[10]  Padhraic Smyth,et al.  Markov monitoring with unknown states , 1994, IEEE J. Sel. Areas Commun..

[11]  Majid Mirmehdi,et al.  Online quality assessment of human motion from skeleton data , 2014, BMVC.

[12]  Hugo Fuks,et al.  Qualitative activity recognition of weight lifting exercises , 2013, AH.

[13]  Manuel P. Cuéllar,et al.  An Approach for the Evaluation of Human Activities in Physical Therapy Scenarios , 2014, MONAMI.

[14]  Zhiqiang Ge,et al.  HMM-Driven Robust Probabilistic Principal Component Analyzer for Dynamic Process Fault Classification , 2015, IEEE Transactions on Industrial Electronics.