Research on armored vehicle classification based on MFCC and SVM
Authors:
- 1 December 2017
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1938-1941
Abstract
To solve the problem of the passive acoustic recognition for ground battlefield armored vehicle target, in order to improve the recognition rate, a new noise recognition model of armored vehicle is put forward. Which is based on Mel frequency cepstral coefficients (Mel Frequency Cepstrum Coefficient, MFCC) and the support vector machine (Support Vector Machine, SVM). Two representative tanks and two armored vehicle are selected as the recognition object, and the noise of truck and rain are selected as the interference. Extracting MFCC and calculate the average value as the eigenvector, and input it to the SVM whose parameters is optimized by the bat algorithm. Experimental results show that this method has good recognition effect and the recognition rate is above 95%.Keywords
This publication has 4 references indexed in Scilit:
- Choosing Multiple Parameters for Support Vector MachinesMachine Learning, 2002
- The Nature Of Statistical Learning Theory~IEEE Transactions on Neural Networks, 1997
- A training algorithm for optimal margin classifiers1992
- Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentencesIEEE Transactions on Acoustics, Speech, and Signal Processing, 1980