The IRMA Community
Newsletters
Research IRM
Click a keyword to search titles using our InfoSci-OnDemand powered search:
|
Recognition of Emotions in Gait Patterns Using Discrete Wavelet Transform
|
|
Author(s): N. M. Khair (School of Mechatronic Engineering, Universiti Malaysia Perlis, Arau, Malaysia), Hariharan Muthusamy (School of Mechatronic Engineering, Universiti Malaysia Perlis, Arau, Malaysia), S. Yaacob (School of Mechatronic Engineering, Universiti Malaysia Perlis, Arau, Malaysia)and S. N. Basah (School of Mechatronic Engineering, Universiti Malaysia Perlis, Arau, Malaysia)
Copyright: 2012
Volume: 1
Issue: 1
Pages: 8
Source title:
International Journal of Biomedical and Clinical Engineering (IJBCE)
Editor(s)-in-Chief: Natarajan Sriraam (M.S. Ramaiah Institute of Technology, India)
DOI: 10.4018/ijbce.2012010107
Purchase
|
Abstract
Emotion is a natural instinctive state of mind deriving from one’s circumstances, mood, or relationships with others. Emotion can be characterized primarily by the psycho-physiological expressions, biological reactions, body interaction, and mental states. The emotional component is to be important for social interaction to serve the communication, response, and conveying information. The problem in controlling and maintaining human emotion can lead to emotional disorder. According to the National Institute of Mental Health (NIMH), approximation of 10-15% of the children tend to have an emotional and behavioral disorder. In this paper, discrete wavelet transform (DWT) was proposed to recognize human emotions in gait patterns. Four discrete categories of emotion such as fear, happy, normal, and sad were analyzed. Data was extracted from a single stride of gait. Daubechies wavelet of order 1 and order 4 was utilized to investigate their performance in recognizing emotional expression in gait patterns. Six statistical features namely mean, maximum, minimum, standard deviation, skewness, and kurtosis were derived from both approximation and detail coefficients at every level of decomposition. The discrete emotion was classified using kNN and fkNN classifier. The maximum classification accuracy of 96.07% was obtained at the first level of decomposition using kNN.
Related Content
|
Srinivasa M. G., Pandian P. S..
© 2022.
20 pages.
|
|
Sindhu P. Menon.
© 2022.
16 pages.
|
|
Sameena Naaz, Arooj Hussain, Farheen Siddiqui.
© 2022.
19 pages.
|
|
Dabbu Suman, Malini Mudigonda, B. Ram Reddy, Yashwanth Vyza.
© 2022.
27 pages.
|
|
Mohankrishna Potnuru, B. Suribabu Naick.
© 2022.
17 pages.
|
|
Sapna Singh Kshatri, Deepak Singh, Mukesh Kumar Chandrakar, G. R. Sinha.
© 2022.
17 pages.
|
|
Shashank Srivastava, Shipra Prakash, Suresh Bhalla, Alok Madan, Sunil Sharma, H. S. Chhabra, Jitesh S. Manghwani.
© 2022.
12 pages.
|
|
|