{"title":"BPNN Based Processing for End Effects of HHT","authors":"Chun-Yao Lee, Yao-chen Lee","volume":48,"journal":"International Journal of Electrical and Computer Engineering","pagesStart":1719,"pagesEnd":1722,"ISSN":"1307-6892","URL":"https:\/\/publications.waset.org\/pdf\/11909","abstract":"This paper describes a method of signal process applied\r\non an end effects of Hilbert-Huang transform (HHT) to provide an\r\nimprovement in the reality of spectrum. The method is based on\r\nback-propagation network (BPN). To improve the effect, the end\r\nextension of the original signal is obtained by back-propagation\r\nnetwork. A full waveform including origin and its extension is\r\ndecomposed by using empirical mode decomposition (EMD) to obtain\r\nintrinsic mode functions (IMFs) of the waveform. Then, the Hilbert\r\ntransform (HT) is applied to the IMFs to obtain the Hilbert spectrum of\r\nthe waveform. As a result, the method is superiority of the processing\r\nof end effect of HHT to obtain the real frequency spectrum of signals.","references":"[1] Huang, N., Z. Shen, S. Long, M. Wu, H. Shih, Q. Zheng, N. Yen, C.C.\r\nTung and H. Liu, \" The empirical mode decomposition and the Hilbert\r\nspectrum for nonlinear, nonstationary time series analysis,\" 1998 Proc. R.\r\nSoc. Lond. Vol. A454, pp. 903-995.\r\n[2] Y.Deng, W.Wang, C.Qian, Z.Wang, D.Dai, \"Boundary-processingtechnique\r\nin EMD method and Hilbert transform,\" 2001 Chinese Science\r\nBulletin Vol. 46, pp. 954-960.\r\n[3] D.E.Rumelhart, G.E.Hinton, and R.J.Willia, \"Learning representations by\r\nback-propagation errors,\" 1986 Nature Vol. 323, pp. 533-536.\r\n[4] Plaut,D. C., Nowlan,S. J. and Hinton,G. E., \"Experiments on Learning by\r\nBack Propagation,\" 1986 Technical Report CMU-CS-86-126.","publisher":"World Academy of Science, Engineering and Technology","index":"Open Science Index 48, 2010"}