The Sort-One-Versus-All for Improving Human Activity Classification with Multi-Class Support Vector Machine
Keywords:
Sort-One-Versus-All (SOVA), One-Versus-All (SOVA), Human Activity Classification, Multi-Class Support Vector MachineAbstract
The One-Versus-All (OVA) method has effectively been applied to data classification using multi-class support vector machine method. As far as human activities are concerned, however, there are some similar gestures and movement activities, which may cause wrong classification when the OVA method with a multi-class support vector machine is used. This study therefore proposed the Sort-One-Versus-All (SOVA) method to improve the efficiency of human activity classification via the use of the multi-class support vector machine method. The SOVA method uses the test rates in multiple groups for sequencing the use of the classification model in the testing process. The result of the classification is the class, in which the class is first classified from the test process. Our experimental data revealed that the SOVA method had an accuracy of human activity classification of 95.36%, which was higher than those of the OVA and One-Versus-One (OVO) methods. In terms of data classification speed, the SOVA method was 1.79 times faster than the OVA method and 6.84 times faster than the OVO method. The proposed method is expected to be capable of classifying data in other applications as well.
References
Yin, J., Yang, Q. and Pan, J.J., 2008, “Sensor-Based Abnormal Human-Activity Detection,” IEEE Transactions on Knowledge and Data Engineering, 20 (8), pp. 1082-1090.
Visutarrom, T., Mongkolnam, P. and Chan, J.H., 2014, “Multiple-Stage Classification of Human Poses while Watching Television,” Proceedings of the 2nd International Symposium on Computational and Business Intelligence, New Delhi, India, pp. 10-16.
Chen, H., Qian, G. and James, J., 2005, “An Autonomous Dance Scoring System Using Marker-based Motion Capture,” Proceedings of the 2005 IEEE 7th Workshop on Multimedia Signal Processing, Shanghai, China. pp. 1-4.
Ranasinghe, S., Machot, F.A. and Mayr, H.C., 2016, “A Review on Applications of Activity Recognition Systems with Regard to Performance and Evaluation,” International Journal of Distributed Sensor Networks, 12 (8), pp. 1-22.
Ann, O.C. and Theng, L.B., 2014, “Human Activity Recognition: A Review,” 2014 IEEE International Conference on Control System, Computing and Engineering, Batu Ferringhi, Malaysia. pp. 389-393.
Kumada, K., Usui, Y. and Kondo, K., 2013, “Golf Swing Tracking and Evaluation using Kinect Sensor and Particle Filter,” Proceedings of the International Symposium on Intelligent Signal Processing and Communication Systems, Naha, Okinawa, Japan, pp. 698-703.
Alexiadis, D.S., Kelly, P., Daras, P., O'Connor, N.E., Boubekeur, T. and Moussa, M. B., 2011, “Evaluating a Dancer's Performance using Kinect-based Skeleton Tracking,” Proceedings of the 19th ACM International Conference on Multimedia, New York, USA, pp. 659-662.
Marquardt, Z., Beira, J., Em, N., Paiva, I. and Kox, S., 2012, “Super Mirror: a Kinect Interface for Ballet Dancers,” Proceedings of the ACM Annual Conference Extended Abstracts on Human Factors in Computing Systems, Texas, USA, pp. 1619-1624.
Yu, X., Wu, L., Liu, Q. and Zhou, H., 2011, “Children Tantrum Behaviour Analysis based on Kinect Sensor,” Proceedings of the Third Chinese Conference on Intelligent Visual Surveillance, Beijing, China, pp. 49-52.
Paliyawan, P., Nukoolkit, C. and Mongkolnam, P., 2014, “Office Workers Syndrome Monitoring using Kinect,” Proceedings of the 20th Asia-Pacific Conference on Communication, Pattaya, Thailand, pp. 58-63.
Cippitelli, E., Gasparrini, S., Gambi, E. and Spinsante, S., 2016, “A Human Activity Recognition System Using Skeleton Data from RGBD Sensors,” Computational Intelligence and Neuroscience, p. 21.
Sung, J., Ponce, C., Selman, B. and Saxena, A., 2011, “Human Activity Detection from RGBD Images,” AAAIWS'11-16 Proceedings of the 16th AAAI Conference on Plan, Activity, and Intent Recognition, AAAI Press, pp. 47-55.
Chaaraouia, A.A., Padilla-López, J. R., Climent-Pérez, P. and Flórez-Revuelta, F., 2014, “Evolutionary Joint Selection to Improve Human Action Recognition with RGB-D Devices,” Expert Systems with Applications, 41 (3), pp. 786-794.
Ong, W., Palafox, L. and Koseki, T., 2013, “Investigation of Feature Extraction for Unsupervised Learning in Human Activity Detection,” Bulletin of Networking, Computing, Systems, and Software, 2 (1), pp. 30-35.
Cortes, C. and Vapnik, V., 1995, “Support-vector Networks,” Machine Learning, 20 (3), pp. 273-297.
Hearst, M.A., Dumais, S.T., Osuna, E., Platt, J. and Scholkopf, B., 1998, “Support vector machines,” IEEE Intelligent Systems and their Applications, 13 (4), pp. 18-28.
Jetpipattanapong, D., 2018, “Feature Selection for Human Activity Classification from Skeleton Data using Two-Level Selection Technique,” KMUTT Research and Development Journal, 41 (4), pp. 401-420. (In Thai)
Taha, A., Zayed, H.H., Khalifa, M.E., and El-Horbaty, E.M., 2015, “Skeleton-based Human Activity Recognition for Video Surveillance,” International Journal of Scientific and Engineering Research, 6 (1), pp. 993-1003.
Baum, L.E., Petrie, T., Soules, G., and Weiss, N., 1970, “A Maximization Technique Occurring in the Statistical Analysis of Probabilistic Functions of Markov Chains,” The Annals of Mathematical Statistics, 41 (1), pp. 164-171.
Romero E. and Toppo D., 2007, “Comparing Support Vector Machines and Feedforward Neural Networks With Similar Hidden-Layer Weights,” IEEE Transactions on Neural Networks, 18 (3), pp. 959-963.
Korba, K.A. and Arbaoui F., 2018, “SVM Multi-Classification of Induction Machine's Bearings Defects using Vibratory Analysis based on Empirical Mode Decomposition,” International Journal of Applied Engineering Research, 13 (9), pp. 6579-6586.
Vapnip, V.N., 1999, “An Overview of Statistical Learning Theory,” IEEE Transactions on Neural Networks, 10 (5), pp. 988-999.
Hastie, T. and Tibshirani, R., 1998, “Classification by Pairwise Coupling,” Annals of Statistics, 26 (2), pp. 451-471.
Kantavat, P., Kijsirikul, B., Songsiri, P., Fukui, K. and Numao, M., 2018, “Efficient Decision Trees for Multi–Class Support Vector Machines Using Entropy and Generalization Error Estimation,” International Journal of Applied Mathematics and Computer Science, 28 (4), pp. 705–717.
Hsu, C. and Lin, C., 2002, “A Comparison of Methods for Multiclass Support Vector Machines,” IEEE Transactions on Neural Networks, 13 (2), pp. 415-425.
Haykin, S., 1998, Neural Networks: A Comprehensive Foundation, 2nd ed., Prentice-Hall, New Jersey, pp. 318-350.
Friedman, J., 1996, “Another Approach to Polychotomous Classification,” Technical Report, Department of Statistics, Stanford University.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2021 King Mongkut's University of Technology Thonburi
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Any form of contents contained in an article published in Science and Engineering Connect, including text, equations, formula, tables, figures and other forms of illustrations are copyrights of King Mongkut's University of Technology Thonburi. Reproduction of these contents in any format for commercial purpose requires a prior written consent of the Editor of the Journal.
