Adaptive myriad filtering algorithms for removal of nonstationary noise in electrooculograms

Abstract

Suppressing nonstationary noise present in biomedical signals is important to provide high-quality diagnoses. Nonstationary noise is difficult for removing due to its time-varying and previously unknown characteristics. The application of linear filtering to the electrooculograph (EOG) signals leads to the smoothing of diagnostically important rapid changes in a signal caused by saccadic eye movements. In this respect, for processing edges and other discontinuous transitions, nonlinear filters based on robust estimators are more appropriate. The paper introduces novel adaptive algorithms for real-time nonlinear filtering of nonstationary noise in EOG signal with a noise- and signal-dependent filter switching, which is more appropriate for processing a local vicinity of the current input signal sample. One of the algorithms is based on myriad filters and sub-filter weighted FIR (which inite Impulse Responce) myriad hybrid filters. It suggests replacing the median with a myriad operation, calculated by Newton¢s numerical technique with adaptive switching of window length and linearity parameter settings. The other algorithm adaptively switches sub-filter weighted FIR median hybrid and averaging filters with different window lengths, offering simpler calculations and high-speed performance. These algorithms do not require time for filter parameters modification and their exact tuning during real-time signal processing and a prior knowledge of the signal model and noise variance. Numerical simulations were conducted to evaluate the filtering quality based on criteria of mean-square error and signal-to-noise ratio for a model signal under different levels of Gaussian noise. The achieved results show good performance and algorithm high quality for suppression of nonstationary noise in EOG. The myriad type adaptive algorithm prevails over the median in effectiveness but requires a numerical technique for cost function minimization, however, myriad filtering real-time implementation is possible with utilization of high-speed computers. Suggested adaptive algorithms significantly improve the efficiency of nonadaptive filters.