Abstract
This paper presents on-line unsupervised schemes for de-noising the received signal containing additive multimodal non-Gaussian noise, using concepts of probability density function estimation and dynamic state estimation. Novel on-line probability density estimation techniques, using various unsupervised kernel based methods are presented. The proposed methods are stable, based on simple but flexible representations and are computationally tractable in real time. Various experiments are included to demonstrate that the proposed filters can efficiently denoise sinusoidal and amplitude modulated sinusoidal signals immersed in unimodal as well as multimodal Gaussian-exponential noise with very low signal-to-noise ratio. The proposed filters significantly outperform the popular unscented Kalman filter and handle non-zero mean non-Gaussian multimodal noise in a more effective way. Most importantly, the proposed methods do not need any prior assumption about the nature of noise or signal.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Wan, E., Merwe, R.V.D.: The Unscented Kalman Filter. In: Kalman Filtering and Neural Networks, pp. 221–280. Wiley (2001)
Li, T.H., Song, K.S.: Estimation of the Parameters of Sinusoidal Signals in Non-gaussian Noise. IEEE Trans. Signal Process. 57(1), 62–72 (2009)
Aysal, T., Barner, K.: Hybrid Polynomial Filters for Gaussian and Non-gaussian Noise Environments. IEEE Trans. Signal Process. 54(12), 4644–4661 (2006)
Gordon, N., Salmond, D., Smith, A.: Novel Approach to Nonlinear/non-gaussian Bayesian State Estimation. IEE Pro. F Radar Signal Process. 140(2), 107–113 (1993)
Chen, S., Hong, X., Harris, C.J.: Probability Density Estimation with Tunable Kernels Using Orthogonal forward regression. Trans. SMC-B 40, 1101–1114 (2010)
Richard, C., Bermudez, J., Honeine, P.: Online Prediction of Time Series Data with Kernels. IEEE Trans. Signal Process. 57(3), 1058–1067 (2009)
Behera, L., Sundaram, B.: Stochastic Filtering and Speech Enhancement Using a Recurrent Quantum Neural Network. In: Proceedings of International Conference on Intelligent Sensing and Information Processing, pp. 165–170 (2004)
Behera, L., Kar, I.: Quantum Stochastic Filtering. In: 2005 IEEE International Conference on Systems, Man and Cybernetics, vol. 3, pp. 2161–2167 (2005)
Bishop, C.M.: Pattern Recognition and Machine Learning (Information Science and Statistics), 1st edn (2006); corr. 2nd printing edn. Springer (2007)
Dat, T.H., Takeda, K., Itakura, F.: On-line Gaussian Mixture Modeling in the Log-power Domain for Signal-to-noise Ratio Estimation and Speech Enhancement. Speech Commun. 48(11), 1515–1527 (2006)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Arora, V., Behera, L. (2012). Design of Distribution Independent Noise Filters with Online PDF Estimation. In: Huang, T., Zeng, Z., Li, C., Leung, C.S. (eds) Neural Information Processing. ICONIP 2012. Lecture Notes in Computer Science, vol 7663. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-34475-6_4
Download citation
DOI: https://doi.org/10.1007/978-3-642-34475-6_4
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-34474-9
Online ISBN: 978-3-642-34475-6
eBook Packages: Computer ScienceComputer Science (R0)