Recognition and Classification of Human Activity by Posture Sensing and Machine Learning

Abstract:

This paper describes how to use a posture sensor to validate human daily activity and by machine learning algorithm - Support Vector Machine (SVM) an outstanding model is built. The optimal parameter σ and c of RBF kernel SVM were obtained by searching automatically. Those kinematic data was carried out through three major steps: wavelet transformation, Principle Component Analysis (PCA) -based dimensionality reduction and k-fold cross-validation, followed by implementing a best classifier to distinguish 6 difference actions. As an activity classifier, the SVM (Support Vector Machine) algorithm is used, and we have achieved over 94.5% of mean accuracy in detecting differential actions. It shows that the verification approach based on the recognition of human activity detection is valuable and will be further explored in the near future.

• Periodical: Advanced Materials Research (Volumes 468-471)
• Pages: 2916-2919
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.468-471.2916
• Online since: February 2012
• Authors: Fan Yang, Yu Chuan Wu
• Keywords: Activity Recognition, K-Fold Cross Validation, Principal Component Analysis (PCA), Wavelet

References

[1] Altun, K. and B. Barshan, Human activity recognition using inertial/magnetic sensor units. 2010. pp.38-51.

DOI: 10.1007/978-3-642-14715-9_5

[2] Maulik, U. and D. Chakraborty, A self-trained ensemble with semisupervised SVM: An application to pixel classification of remote sensing imagery. Pattern Recognition, 2011. 44(3): pp.615-623.

DOI: 10.1016/j.patcog.2010.09.021

[3] Rabiner, L.R., Tutorial on hidden Markov models and selected applications in speech recognition. Proceedings of the Ieee, 1989. 77(2): pp.257-286.

DOI: 10.1109/5.18626

[4] Kung, H.Y., et al. Efficient movement detection for human actions using triaxial accelerometer. 2010.

[5] Altun, K., B. Barshan, and O. Tunçel, Comparative study on classifying human activities with miniature inertial and magnetic sensors. Pattern Recognition, 2010. 43(10): pp.3605-3620.

DOI: 10.1016/j.patcog.2010.04.019

[6] Kubo, H., T. Mori, and T. Sato. Detection and measurement of human motion and respiration with microwave Doppler sensor. 2010.

[7] Kangas, M., et al., Comparison of low-complexity fall detection algorithms for body attached accelerometers. Gait and Posture, 2008. 28(2): pp.285-291.

DOI: 10.1016/j.gaitpost.2008.01.003

[8] Shahbudin, S., et al. Analysis of PCA based feature vectors for SVM posture classification. 2010.

[9] Kandaswamy, A., et al., Neural classification of lung sounds using wavelet coefficients. Computers in Biology and Medicine, 2004. 34(6): pp.523-537.

DOI: 10.1016/s0010-4825(03)00092-1

[10] Lau, H.Y., K.Y. Tong, and H. Zhu, Support vector machine for classification of walking conditions using miniature kinematic sensors. Medical and Biological Engineering and Computing, 2008. 46(6): pp.563-573.

DOI: 10.1007/s11517-008-0327-x

[11] Fukuchi, R.K., et al., Support vector machines for detecting age-related changes in running kinematics. Journal of Biomechanics, 2011. 44(3): pp.540-542.

DOI: 10.1016/j.jbiomech.2010.09.031