Clustering of human motions based on feature-level fusion of multiple body sensor data

Human joints and muscles are the crucial biomechanical factors that control and drive body movements. Hence, assessing the role of joint movements and muscular activities is important for analyzing human motions. This quantification of integrated biomechanical kinematics with electrophysiology is useful for gait and posture analysis, prosthetic design and other orthopedic applications. We study the effect of integrating multiple body sensor data on the clustering of human motions by fusing their corresponding relevant features extracted from the raw data. In this paper, our objective is to perform cluster analysis on human motions based on the fused feature vectors that underline the joint relationship between body movements and muscular activity.

[1]  Susana Nascimento.  Fuzzy Clustering Via Proportional Membership Model , 2005 .

[2]  F. K. Lam,et al.  Fuzzy EMG classification for prosthesis control. , 2000, IEEE transactions on rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society.

[3]  Zhoujun Li,et al.  A novel unsupervised feature selection method for bioinformatics data sets through feature clustering , 2008, 2008 IEEE International Conference on Granular Computing.

[4]  William M. Rand,et al.  Objective Criteria for the Evaluation of Clustering Methods , 1971 .

[5]  Arun Ross,et al.  Information fusion in biometrics , 2003, Pattern Recognit. Lett..

[6]  F. Mohd-Yasin,et al.  Techniques of EMG signal analysis: detection, processing, classification and applications , 2006, Biological Procedures Online.

[7]  T. Kuo,et al.  A comparative analysis of various EMG pattern recognition methods. , 1996, Medical engineering & physics.

[8]  B. Prabhakaran,et al.  Indexing of variable length multi-attribute motion data , 2004, MMDB '04.

[9]  Cyrus Shahabi,et al.  A multilevel distance-based index structure for multivariate time series , 2005, 12th International Symposium on Temporal Representation and Reasoning (TIME'05).

[10]  Gholamreza Anbarjafari,et al.  Data Fusion Boosted Face Recognition Based on Probability Distribution Functions in Different Colour Channels , 2009, EURASIP J. Adv. Signal Process..

[11]  N. P. Reddy,et al.  Fractal analysis of surface EMG signals from the biceps. , 1997, International journal of medical informatics.

[12]  R.N. Scott,et al.  A new strategy for multifunction myoelectric control , 1993, IEEE Transactions on Biomedical Engineering.

[13]  D Graupe,et al.  Multifunctional prosthesis and orthosis control via microcomputer identification of temporal pattern differences in single-site myoelectric signals. , 1982, Journal of biomedical engineering.

[14]  B. Prabhakaran,et al.  A similarity measure for motion stream segmentation and recognition , 2005, MDM '05.

[15]  L. D. de Souza,et al.  A comparison of the timing of muscle activity during sitting down compared to standing up. , 2000, Physiotherapy research international : the journal for researchers and clinicians in physical therapy.

[16]  Dimitrios Gunopulos,et al.  Indexing Large Human-Motion Databases , 2004, VLDB.

[17]  Feng Liu,et al.  3D motion retrieval with motion index tree , 2003, Comput. Vis. Image Underst..

[18]  P. Derambure,et al.  Effect of age on anticipatory postural adjustments in unilateral arm movement. , 2006, Gait & posture.

[19]  Bruce C. Wheeler,et al.  EMG feature evaluation for movement control of upper extremity prostheses , 1995 .

[20]  C. A. Murthy,et al.  Unsupervised Feature Selection Using Feature Similarity , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[21]  Donald W. Bouldin,et al.  A Cluster Separation Measure , 1979, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[22]  B. Prabhakaran,et al.  Integration of Motion Capture and EMG data for Classifying the Human Motions , 2007, 2007 IEEE 23rd International Conference on Data Engineering Workshop.

[23]  Chih-Yi Chiu,et al.  Content-based retrieval for human motion data , 2004, J. Vis. Commun. Image Represent..

[24]  Jeffrey M. Hausdorff,et al.  Multiscale entropy analysis of human gait dynamics. , 2003, Physica A.

[25]  Adrian Del Boca.  Myoelectric signal recognition using artificial neural networks in real time , 1993 .

[26]  Beng Chin Ooi,et al.  Indexing the Distance: An Efficient Method to KNN Processing , 2001, VLDB.

[27]  B. Prabhakaran,et al.  Hierarchical Indexing Structure for 3D Human Motions , 2007, MMM.

[28]  Martin Vetterli,et al.  Fast Fourier transforms: a tutorial review and a state of the art , 1990 .

[29]  Tido Röder,et al.  Efficient content-based retrieval of motion capture data , 2005, SIGGRAPH 2005.