Abstract
This paper presents an effective detection algorithm for wrist motions based on an improved SVM (support vector machine) classifier. Firstly, a novel windowing method is proposed to enhance the consistency of sampled motion. After extracting characteristic features in both time and frequency domains, a feature scaling process is applied and a C-SVC (C-Support Vector Classifier) is trained by a threshold-based grid-search with cross-validation, to achieve higher accuracy and faster convergence. The experiments demonstrate that the proposed algorithm outperforms the traditional SVM in accuracy and convergence.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Hsieh, S.L., Chen, C.C., Wu, S.H., Yue, T.W.: A wrist-worn fall detection system using accelerometers and gyroscopes. IEEE Tran. Networking Sens. Control 11, 518–523 (2014)
Fuentes, D., Gonzalez-Abril, L., Angulo, C., Ortega.: Online motion recognition using an accelerometer in a mobile device. Expert. Syst. Appl. 39(3), 2461–2465 (2012)
Cortes, V.: Support-vector network. Mach. Learn. 20, 273–297 (1995)
Yang, J.Y., Wang, J.S., Chen, Y.P.: Using acceleration measurements for activity recognition: an effective learning algorithm for constructing neural classifiers. Pattern Recogn. Lett. 29(16), 2213–2220 (2008)
Lugade, V., Fortune, E., Morrow, M., Kaufman, K.: Validity of using tri-axial accelerometers to measure human movement Part I: posture and movement detection. Med. Eng. Phys. 36(2), 169–176 (2014)
Bakshi, A., Kopparapu, S.K., Pawar, S., Nema, S.: Novel windowing technique of MFCC for speaker identification with modified polynomial classifiers. IEEE Tran. Confluence 5, 292–297 (2014)
Parhi, K., Ayinala, M.: Low-complexity welch power spectral density computation. IEEE Tran. Circ. Syst. I Regul. Pap. 61(1), 172–182 (2014)
Xiao, P., Qu, W., Qi, H., Li, Z.: Detecting DDoS attacks against data center with correlation analysis. Comput. Commun. 67, 66–74 (2015)
Grandvalet, Y., Canu, S.: Adaptive scaling for feature selection in SVMs. Adva. Neur. Info. Proc. Syst. 11, 553–560 (2002)
Li, Q., Salman, R., Test, E., Strack, R., Kecman, V.: Parallel multitask cross validation for support vector machine using GPU. J. Parallel. Distr. Com. 73(3), 293–302 (2013)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer Science+Business Media Singapore
About this paper
Cite this paper
Wu, XK., Yang, XG., Cai, ZG., Luo, SS. (2016). An Improved SVM-Based Motion Detection Algorithm Using an Accelerometer. In: Hussain, A. (eds) Electronics, Communications and Networks V. Lecture Notes in Electrical Engineering, vol 382. Springer, Singapore. https://doi.org/10.1007/978-981-10-0740-8_13
Download citation
DOI: https://doi.org/10.1007/978-981-10-0740-8_13
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-0738-5
Online ISBN: 978-981-10-0740-8
eBook Packages: EngineeringEngineering (R0)