Abstract
Neural signal decoding is a critical technology in brain machine interface (BMI) to interpret movement intention from multi-neural activity collected from paralyzed patients. As a commonly-used decoding algorithm, the Kalman filter is often applied to derive the movement states from high-dimensional neural firing observation. However, its performance is limited and less effective for noisy nonlinear neural systems with high-dimensional measurements. In this paper, we propose a nonlinear maximum correntropy information filter, aiming at better state estimation in the filtering process for a noisy high-dimensional measurement system. We reconstruct the measurement model between the high-dimensional measurements and low-dimensional states using the neural network, and derive the state estimation using the correntropy criterion to cope with the non-Gaussian noise and eliminate large initial uncertainty. Moreover, analyses of convergence and robustness are given. The effectiveness of the proposed algorithm is evaluated by applying it on multiple segments of neural spiking data from two rats to interpret the movement states when the subjects perform a two-lever discrimination task. Our results demonstrate better and more robust state estimation performance when compared with other filters.
Highlights
IntroductionBrain machine interface (BMI) collects the noisy signals from hundreds of neurons in the brain, and estimates a motor intention from these signals [7,8]
We can see that the curve of nonlinear maximum correntropy information filter (NMCIF) is closer to the ground truth than that of Kalman filter (KF)
The results show that the proposed algorithm is superior to the KF and neural network (NN)
Summary
BMI collects the noisy signals from hundreds of neurons in the brain, and estimates a motor intention from these signals [7,8]. This estimated movement intention can be used to control the robot to assist motor disabled people [9,10,11,12,13,14,15,16,17,18,19]. The implementation of the Kalman filter nicely considers the gradual change of the continuous brain state, and is especially appropriate for the brain control task where the subject continuously adjusts the brain states to control an external robot
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have