Abstract
This paper presents a nonlinear method---total variation denoising (TVD) method, for impulse signals denoising. The basic idea of TVD is to solve a total variation function optimization problem. Experimental results suggest that the mean squared error (MSE) can not distinguish the results with some falsely identified impulses. Thus, a dual assessment criterion incorporating both MSE and false identification power (fid) is proposed. Numerical experiments have shown that the proposed approach outperforms the traditional wavelet denoising (WD) by using the dual assessment criterion.
Keyword: Denoise; total variation; impulse signals.
References
1. Y. S. Fan, and G. T. Zheng, “Research of high-resolution vibration signal detection technique and application to mechanical fault diagnosis,” Mechanical Systems and Signal Processing, 21, 2007, pp. 678-687.
2. S. Chen, B. Yu, and M. Vetterli, “Adaptive wavelet thresholding for image denoising and compression,” IEEE Transactions on Image Processing, 9, 2000, pp. 1532-1546.
.
3. S. Chen, B. Yu, and M. Vetterli, “Spatially adaptive wavelet thresholding with context modeling for image denoising,” IEEE Transactions on Image Processing, 9, 2000, pp. 1522-1531.
4. J. Lin, M. Zuo, and K. Fyfe, “Mechanical fault detection based on the wavelet denoising technique,” ASME Journal of Vibration and Acoustics, 126, 2004, pp. 9-16.
5. A. Hyvarinen, “Sparse code shrinkage denoising of non-Gaussian data by maximum likelihood estimation,” Neural Computation, 11, 1999, pp. 739-1768.
6. Q. Xu, and Z. Li, “Recognition of wear mode using multi-variable synthesis approach based on wavelet packet and improved three-line method,” Mechanical Systems and Signal Processing, 21, 2007, pp. 3146-3166.
7. H. Hong, and M. Liang, “K-Hybrid: A kurtosis-based hybrid thresholding method for mechanical signal denoising,” Transactions of the ASME, 129, 2007, pp. 458-470.
8. L. I. Rudin, S. Osher, and E. Fatemi, “Nonlinear total variation based noise removal algorithms,” Physica D, 60, 1992, pp. 259-268.
9. D. C. Dobson, and C. R. Vogel, “Convergence of an iterative method for total variation denoising,” SIAM Journal on Numerical Analysis, 34, 1997, pp. 1779-1791.
10. Z. Xie, and J. Feng, “Blind source separation of continuous-time chaotic signals based on fast random search algorithm,” IEEE Transactions on Circuits and Systems II: Express Briefs, 57, 2010, pp. 461-465.
11. J. Nocedal, “Updating Quasi-Newton Matrices with Limited Storage,” Mathematics of Computation, 35, 1980, pp. 773-782.
12. D. C. Liu, and J. Nocedal, “On the limited memory BFGS method for large scale optimization,” Mathematical Programming, 45, 1989, pp. 503-528.
13. M. V. Wickerhauser, Adapted Wavelet Analysis from Theory to Software Algorithms, New York, A.K. Peters, 1994.
作者简介:
谢宗伯，博士，华南理工大学副研究员，IEEE/IEICE会员，主要研究方向为信号处理与机器学习。先后主持国家和省部级项目多项，在国际高水平期刊发表论文多篇。
冯久超，教授，博导，华南理工大学教授，IEEE会员，广东省“珠江学者”特聘教授，主要研究方向为非线性系统理论。
