Pattern Recognition and Machine Learning (Information Science and Statistics)
Pattern Recognition and Machine Learning (Information Science and Statistics)
Estimation of the parameters of sinusoidal signals in non-Gaussian noise
IEEE Transactions on Signal Processing
Online prediction of time series data with kernels
IEEE Transactions on Signal Processing
Probability density estimation with tunable kernels using orthogonal forward regression
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics - Special issue on gait analysis
Hybrid Polynomial Filters for Gaussian and Non-Gaussian Noise Environments
IEEE Transactions on Signal Processing
| Hi-index | 0.00 |
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.