The nature of statistical learning theory
The nature of statistical learning theory
Support Vector Machines: Theory and Applications (Studies in Fuzziness and Soft Computing)
Support Vector Machines: Theory and Applications (Studies in Fuzziness and Soft Computing)
Hi-index | 0.00 |
In order to make effective recognition of radiated noises of ships, on the basis of the auditory Patterson-Holdsworth cochlear model and Meddis' Inner Hair Cell (IHC) model, a feature extraction of radiated noises of ships model simulating the partial auditory system is set up to obtain the average firing rate. Then an algorithm (One-Against-All: OAA) of multi-class Support Vector Machines (SVMs) is defined. Finally, the extracted feature vectors are used to classify three different classes of targets using SVMs, BP Neural Network (BPNN) and K-Nearest Neighbor (KNN) methods. At the same time we compare the recognition performance of average firing rate feature with general power spectrum feature. Results show that the statistical recognition corrective rate of average firing rate feature exceeds 96.5% using SVMs.