Heterogeneous Multi-Classifiers for Moving Vehicle Noise Classification using Bootstrap Method
N. Abdul Rahim1, Paulraj M P2, A.H. Adom3
1N. Abdul Rahim, School of Mechatronic Engineering, Universiti Malaysia Perlis, Malaysia.
2Paulraj M P, School of Mechatronic Engineering, Universiti Malaysia Perlis, Malaysia.
3A. H. Adom, School of Mechatronic Engineering, Universiti Malaysia Perlis, Malaysia.
Manuscript received on March 22, 2013. | Revised Manuscript received on April 15, 2013. | Manuscript published on April 30, 2013. | PP: 435-439 | Volume-2, Issue-4, April 2013. | Retrieval Number: D1485042413/2013©BEIESP
Open Access | Ethics and Policies | Cite
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: In this paper, a simple system has been proposed to identify the type and distance of a moving vehicle using multi-classifier system (MCS). One-third octave filter bank approach has been used for extracting the significant feature from the noise emanated by the moving vehicle. The extracted features were associated with the type and distance of the moving vehicle and the heterogeneous multi-classifier system (HTMCS) based on multilayer Perceptron (MLP), K-nearest neighbor (KNN) and support vector machines (SVM) has been developed. Bootstrap sampling method based HTMCS was developed and the developed model has yielded a higher classification accuracy when compared to the individual base classifier models.
Keywords: Bootstrap, Heterogeneous, Moving Vehicle, Multi-Classifier System, One-Third-Octave.