Neural Network Aided Adaptive Minimum L1-Norm Filter for EP Estimation

Guo Wenqiang, Qiu Tianshuang, and Li Fan 1. Dalian University of Technology, Dalian , China , 116024 2. Xinjiang Institute of Finance and Economics, Urumchi 830012,China Tel: +86-0411-84706009-3038 Summary: Evoked potentials (EPs) have been widely used to quantify neurological system properties. Traditional EP analyses are developed under the condition that the background noises in EP are Gaussian distributed. Alpha stable distribution, a generalization of Gaussian, is better for modeling impulsive noises than Gaussian distribution in biomedical signal processing. This paper presents a new minimum L1-norm filter algorithm for EP estimation based on neural network. Simulation results show that the new algorithm is very effective under both Gaussian and lower order alpha stable noise condition and is closer to optimal fashion in EP signal estimation compared with traditional methods.