期刊名称：International Journal of Advanced Research in Computer Engineering & Technology (IJARCET)
印刷版ISSN：2278-1323
出版年度：2013
卷号：2
期号：2
页码：812-816
出版社：Shri Pannalal Research Institute of Technolgy
摘要：This paper presents a new approach for classification of various non-stationary power signal waveforms using modified Gaussian windowing technique. In comparison to the earlier Gaussian window, the modified Gaussian window is found to provide excellent normalized frequency contours of the power signal disturbances suitable for accurate visual localization, detection and classification. Various non-stationary power signals are processed through S-Transform with modified Gaussian window to generate time-frequency contours for extracting optimal feature vectors for automatic pattern classification. The extracted features are clustered using Fuzzy C-means algorithm. From simulation results, it is shown that the proposed Fuzzy C-means algorithm reveal very encouraging results in terms of the quality of solution found, the average no of function evaluations and processing time required. The average classification accuracy of the disturbances is 94.37%
