A Nonlinear Maximum Correntropy Information Filter for High-Dimensional Neural Decoding

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...

Full description

Bibliographic Details
Main Authors: Xi Liu, Shuhang Chen, Xiang Shen, Xiang Zhang, Yiwen Wang
Format: Article
Language:English
Published: MDPI AG 2021-06-01
Series:Entropy
Subjects:
Online Access:https://www.mdpi.com/1099-4300/23/6/743
_version_ 1797530364005056512
author Xi Liu
Shuhang Chen
Xiang Shen
Xiang Zhang
Yiwen Wang
author_facet Xi Liu
Shuhang Chen
Xiang Shen
Xiang Zhang
Yiwen Wang
author_sort Xi Liu
collection DOAJ
description 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.
first_indexed 2024-03-10T10:27:51Z
format Article
id doaj.art-f1d5508d9a9f484b85883a60b7cdead2
institution Directory Open Access Journal
issn 1099-4300
language English
last_indexed 2024-03-10T10:27:51Z
publishDate 2021-06-01
publisher MDPI AG
record_format Article
series Entropy
spelling doaj.art-f1d5508d9a9f484b85883a60b7cdead22023-11-21T23:55:04ZengMDPI AGEntropy1099-43002021-06-0123674310.3390/e23060743A Nonlinear Maximum Correntropy Information Filter for High-Dimensional Neural DecodingXi Liu0Shuhang Chen1Xiang Shen2Xiang Zhang3Yiwen Wang4Department of Electronic and Computer Engineering, Hong Kong University of Science and Technology, Hong Kong, ChinaDepartment of Chemical and Biological Engineering, Hong Kong University of Science and Technology, Hong Kong, ChinaDepartment of Electronic and Computer Engineering, Hong Kong University of Science and Technology, Hong Kong, ChinaDepartment of Electronic and Computer Engineering, Hong Kong University of Science and Technology, Hong Kong, ChinaDepartment of Electronic and Computer Engineering, Hong Kong University of Science and Technology, Hong Kong, ChinaNeural 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.https://www.mdpi.com/1099-4300/23/6/743state-observation modelhigh-dimensional measurements systemscorrentropy
spellingShingle Xi Liu
Shuhang Chen
Xiang Shen
Xiang Zhang
Yiwen Wang
A Nonlinear Maximum Correntropy Information Filter for High-Dimensional Neural Decoding
Entropy
state-observation model
high-dimensional measurements systems
correntropy
title A Nonlinear Maximum Correntropy Information Filter for High-Dimensional Neural Decoding
title_full A Nonlinear Maximum Correntropy Information Filter for High-Dimensional Neural Decoding
title_fullStr A Nonlinear Maximum Correntropy Information Filter for High-Dimensional Neural Decoding
title_full_unstemmed A Nonlinear Maximum Correntropy Information Filter for High-Dimensional Neural Decoding
title_short A Nonlinear Maximum Correntropy Information Filter for High-Dimensional Neural Decoding
title_sort nonlinear maximum correntropy information filter for high dimensional neural decoding
topic state-observation model
high-dimensional measurements systems
correntropy
url https://www.mdpi.com/1099-4300/23/6/743
work_keys_str_mv AT xiliu anonlinearmaximumcorrentropyinformationfilterforhighdimensionalneuraldecoding
AT shuhangchen anonlinearmaximumcorrentropyinformationfilterforhighdimensionalneuraldecoding
AT xiangshen anonlinearmaximumcorrentropyinformationfilterforhighdimensionalneuraldecoding
AT xiangzhang anonlinearmaximumcorrentropyinformationfilterforhighdimensionalneuraldecoding
AT yiwenwang anonlinearmaximumcorrentropyinformationfilterforhighdimensionalneuraldecoding
AT xiliu nonlinearmaximumcorrentropyinformationfilterforhighdimensionalneuraldecoding
AT shuhangchen nonlinearmaximumcorrentropyinformationfilterforhighdimensionalneuraldecoding
AT xiangshen nonlinearmaximumcorrentropyinformationfilterforhighdimensionalneuraldecoding
AT xiangzhang nonlinearmaximumcorrentropyinformationfilterforhighdimensionalneuraldecoding
AT yiwenwang nonlinearmaximumcorrentropyinformationfilterforhighdimensionalneuraldecoding