Online segmentation with multi-layer SVM for knee osteoarthritis rehabilitation monitoring

Rehabilitation exercise is one of the most important parts in knee osteoarthritis therapy. A good rehabilitation monitoring method provides physiotherapists with performance metrics that are greatly helpful in recovery progress. One of the main difficulties of monitoring and analysis is performing accurate online segmentation of motion sections due to the high degree of freedom (DoF) of human motion. This paper proposes an approach for initial posture classification and online segmentation of rehabilitation exercise data acquired with body-worn inertial sensors. Specifically, we introduce a threshold-based algorithm for initial posture classification and a multi-layer Support Vector Machine (SVM) model for online segmentation. The proposed approach is capable of accurate online segmentation and classification of exercise data. The approach is verified on 10 subjects performing common rehabilitation exercises for knee osteoarthritis, giving initial posture classification accuracy of 97.9% and segmentation accuracy of 90.6% on layer-1 SVM and 92.7% on layer-2 SVM.

[1]  M G Pandy,et al.  Computer modeling and simulation of human movement. , 2001, Annual review of biomedical engineering.

[2]  Liu Zhi.  Parameter selection in SVM with RBF kernel function , 2007 .

[3]  Yu-Chee Tseng,et al.  A Wireless Human Motion Capturing System for Home Rehabilitation , 2009, 2009 Tenth International Conference on Mobile Data Management: Systems, Services and Middleware.

[4]  Dan Schonfeld,et al.  HMM-based motion recognition system using segmented PCA , 2005, IEEE International Conference on Image Processing 2005.

[5]  Ichiro Takeuchi,et al.  Safe Screening of Non-Support Vectors in Pathwise SVM Computation , 2013, ICML.

[6]  J. Satheesh Kumar,et al.  Support Vector Machine Technique for EEG Signals , 2013 .

[7]  Ying Wu,et al.  Signal Classification Method Based on Support Vector Machine and High-Order Cumulants , 2010, Wirel. Sens. Netw..

[8]  Han Meng,et al.  Parameter selection in SVM with RBF kernel function , 2012, World Automation Congress 2012.

[9]  Jonathan Feng-Shun Lin,et al.  Online Segmentation of Human Motion for Automated Rehabilitation Exercise Analysis , 2014, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[10]  Ramakant Nevatia,et al.  Recognition and Segmentation of 3-D Human Action Using HMM and Multi-class AdaBoost , 2006, ECCV.

[11]  Huosheng Hu,et al.  Applications of wearable inertial sensors in estimation of upper limb movements , 2006, Biomed. Signal Process. Control..

[12]  Takeo Kanade,et al.  Classifying human motion quality for knee osteoarthritis using accelerometers , 2010, 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology.

[13]  Cheng-Lung Huang,et al.  A distributed PSO-SVM hybrid system with feature selection and parameter optimization , 2008, Appl. Soft Comput..

[14]  Shyamal Patel,et al.  Mercury: a wearable sensor network platform for high-fidelity motion analysis , 2009, SenSys '09.

[15]  J Perry,et al.  Electromyographic analysis of knee rehabilitation exercises. , 1994, The Journal of orthopaedic and sports physical therapy.

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