Input-output mapping performance of linear and nonlinear models for estimating hand trajectories from cortical neuronal firing patterns
Tóm tắt
Linear and nonlinear (TDNN) models have been shown to estimate hand position using populations of action potentials collected in the pre-motor and motor cortical areas of a primate's brain. One of the applications of this discovery is to restore movement in patients suffering from paralysis. For real-time implementation of this technology, reliable and accurate signal processing models that produce small error variance in the estimated positions are required. In this paper, we compare the mapping performance of the FIR filter, gamma filter and recurrent neural network (RNN) in the peaks of reaching movements. Each approach has strengths and weaknesses that are compared experimentally. The RNN approach shows very accurate peak position estimations with small error variance.
Từ khóa
#Trajectory #Finite impulse response filter #Nonlinear filters #Recurrent neural networks #Neurons #Biological system modeling #Delay effects #Electrodes #Predictive models #Delay estimationTài liệu tham khảo
10.1007/BF02551274
10.1109/81.585959
principe, 2000, Neural and adaptive systems, fundamentals through simulations
10.1038/323533a0
10.1109/5.58337
kolen, 2001, A Field Guide to Dynamical Recurrent Networks
10.1016/S0896-6273(00)80295-0
10.1038/416141a
haykin, 1996, Adaptive Filter Theory
widrow, 1975, Adaptive noise cancelling: principles and applications, Proceedings of the IEEE, 63, 1692, 10.1109/PROC.1975.10036
10.1038/10223
10.1016/S0893-6080(05)80035-8
10.1109/TAC.1967.1098599
haykin, 1994, Neural Networks A Comprehensive Foundation
wessberg, 2000, Real-time prediction of hand trajectory by ensembles of cortical neurons in primates, Nature, 408, 361, 10.1038/35042582
10.1109/5.537107