MILITARY VEHICLE CLASSIFICATION VIA ACOUSTIC AND SEISMIC SIGNALS USING STATISTICAL LEARNING METHODS

Hanguang Xiao (), Congzhong Cai () and Yuzong Chen ()
Additional contact information
Hanguang Xiao: Department of Applied Physics, Chongqing University, Chongqing 400044, P. R. China;
Congzhong Cai: Department of Applied Physics, Chongqing University, Chongqing 400044, P. R. China;
Yuzong Chen: Department of Computational Science, National University of Singapore, Blk SOC1, Level 7, 3 Science Drive 2, Singapore 117543, Singapore

International Journal of Modern Physics C (IJMPC), 2006, vol. 17, issue 02, 197-212

Abstract: It is a difficult and important task to classify the types of military vehicles using the acoustic and seismic signals generated by military vehicles. For improving the classification accuracy and reducing the computing time and memory size, we investigated different pre-processing technology, feature extraction and selection methods. Short Time Fourier Transform (STFT) was employed for feature extraction. Genetic Algorithms (GA) and Principal Component Analysis (PCA) were used for feature selection and extraction further. A new feature vector construction method was proposed by uniting PCA and another feature selection method. K-Nearest Neighbor Classifier (KNN) and Support Vector Machines (SVM) were used for classification. The experimental results showed the accuracies of KNN and SVM were affected obviously by the window size which was used to frame the time series of the acoustic and seismic signals. The classification results indicated the performance of SVM was superior to that of KNN. The comparison of the four feature selection and extraction methods showed the proposed method is a simple, none time-consuming, and reliable technique for feature selection and helps the classifier SVM to achieve more better results than solely using PCA, GA, or combination.

Keywords: Military vehicle; KNN; support vector machine; Short Time Fourier Transform; principal component analysis (search for similar items in EconPapers)
Date: 2006
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.worldscientific.com/doi/abs/10.1142/S0129183106008789
Access to full text is restricted to subscribers

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:wsi:ijmpcx:v:17:y:2006:i:02:n:s0129183106008789

Ordering information: This journal article can be ordered from

DOI: 10.1142/S0129183106008789

Access Statistics for this article

International Journal of Modern Physics C (IJMPC) is currently edited by H. J. Herrmann

More articles in International Journal of Modern Physics C (IJMPC) from World Scientific Publishing Co. Pte. Ltd.
Bibliographic data for series maintained by Tai Tone Lim ().