Please use this identifier to cite or link to this item:
|Title:||Military vehicle classification via acoustic and seismic signals using statistical learning methods||Authors:||Xiao, H.
Principal component analysis
Short Time Fourier Transform
Support vector machine
|Issue Date:||Feb-2006||Citation:||Xiao, H., Cai, C., Chen, Y. (2006-02). Military vehicle classification via acoustic and seismic signals using statistical learning methods. International Journal of Modern Physics C 17 (2) : 197-212. ScholarBank@NUS Repository. https://doi.org/10.1142/S0129183106008789||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. © World Scientific Publishing Company.||Source Title:||International Journal of Modern Physics C||URI:||http://scholarbank.nus.edu.sg/handle/10635/106151||ISSN:||01291831||DOI:||10.1142/S0129183106008789|
|Appears in Collections:||Staff Publications|
Show full item record
Files in This Item:
There are no files associated with this item.
checked on Nov 30, 2020
WEB OF SCIENCETM
checked on Nov 30, 2020
checked on Nov 29, 2020
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.