Design of a neural decoder by sensory prediction and error correction

Junkai Lu, Mo Chen, Young Hwan Chang, Masayoshi Tomizuka, Jose M. Carmena, Claire J. Tomlin

Research output: Contribution to journalArticle

Abstract

Brain-machine interfaces (BMI) hold great potential to improve the quality of life of many patients with disabilities. The neural decoder, which expresses the mapping between the neural signals and the subject's motion, plays an important role in BMI systems. Conventional neural decoders are generally in the form of a kinematic Kalman filter which does not possess an explicit mechanism to deal with the unavoidable mismatch between the biological system and the model of the system used by the decoder. This paper presents a novel design of a neural decoder that uses a one-step model predictive controller to generate a control signal that compensates for the inherent model mismatch. The effectiveness of the proposed decoding algorithm compares favorably to the state-of-the-art Kalman filter in numerical simulations with different degrees of model mismatch.

Original languageEnglish (US)
Article number7040489
Pages (from-to)6999-7004
Number of pages6
JournalUnknown Journal
Volume2015-February
Issue numberFebruary
DOIs
StatePublished - 2014
Externally publishedYes

Fingerprint

Brain-Computer Interfaces
Error correction
Error Correction
Biological Models
Prediction
Biomechanical Phenomena
Kalman filters
Kalman Filter
Brain
Quality of Life
Signal Control
Disability
Biological systems
Biological Systems
Model
Decoding
Kinematics
Express
Controller
Numerical Simulation

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Modeling and Simulation
  • Control and Optimization

Cite this

Lu, J., Chen, M., Chang, Y. H., Tomizuka, M., Carmena, J. M., & Tomlin, C. J. (2014). Design of a neural decoder by sensory prediction and error correction. Unknown Journal, 2015-February(February), 6999-7004. [7040489]. https://doi.org/10.1109/CDC.2014.7040489

Design of a neural decoder by sensory prediction and error correction. / Lu, Junkai; Chen, Mo; Chang, Young Hwan; Tomizuka, Masayoshi; Carmena, Jose M.; Tomlin, Claire J.

In: Unknown Journal, Vol. 2015-February, No. February, 7040489, 2014, p. 6999-7004.

Research output: Contribution to journalArticle

Lu, J, Chen, M, Chang, YH, Tomizuka, M, Carmena, JM & Tomlin, CJ 2014, 'Design of a neural decoder by sensory prediction and error correction', Unknown Journal, vol. 2015-February, no. February, 7040489, pp. 6999-7004. https://doi.org/10.1109/CDC.2014.7040489
Lu J, Chen M, Chang YH, Tomizuka M, Carmena JM, Tomlin CJ. Design of a neural decoder by sensory prediction and error correction. Unknown Journal. 2014;2015-February(February):6999-7004. 7040489. https://doi.org/10.1109/CDC.2014.7040489
Lu, Junkai ; Chen, Mo ; Chang, Young Hwan ; Tomizuka, Masayoshi ; Carmena, Jose M. ; Tomlin, Claire J. / Design of a neural decoder by sensory prediction and error correction. In: Unknown Journal. 2014 ; Vol. 2015-February, No. February. pp. 6999-7004.
@article{f1f5bfbf3f4d487eb2d13b3f696af01e,
title = "Design of a neural decoder by sensory prediction and error correction",
abstract = "Brain-machine interfaces (BMI) hold great potential to improve the quality of life of many patients with disabilities. The neural decoder, which expresses the mapping between the neural signals and the subject's motion, plays an important role in BMI systems. Conventional neural decoders are generally in the form of a kinematic Kalman filter which does not possess an explicit mechanism to deal with the unavoidable mismatch between the biological system and the model of the system used by the decoder. This paper presents a novel design of a neural decoder that uses a one-step model predictive controller to generate a control signal that compensates for the inherent model mismatch. The effectiveness of the proposed decoding algorithm compares favorably to the state-of-the-art Kalman filter in numerical simulations with different degrees of model mismatch.",
author = "Junkai Lu and Mo Chen and Chang, {Young Hwan} and Masayoshi Tomizuka and Carmena, {Jose M.} and Tomlin, {Claire J.}",
year = "2014",
doi = "10.1109/CDC.2014.7040489",
language = "English (US)",
volume = "2015-February",
pages = "6999--7004",
journal = "Indian Journal of Rheumatology",
issn = "0973-3698",
publisher = "Elsevier (Singapore) Pte Ltd",
number = "February",

}

TY - JOUR

T1 - Design of a neural decoder by sensory prediction and error correction

AU - Lu, Junkai

AU - Chen, Mo

AU - Chang, Young Hwan

AU - Tomizuka, Masayoshi

AU - Carmena, Jose M.

AU - Tomlin, Claire J.

PY - 2014

Y1 - 2014

N2 - Brain-machine interfaces (BMI) hold great potential to improve the quality of life of many patients with disabilities. The neural decoder, which expresses the mapping between the neural signals and the subject's motion, plays an important role in BMI systems. Conventional neural decoders are generally in the form of a kinematic Kalman filter which does not possess an explicit mechanism to deal with the unavoidable mismatch between the biological system and the model of the system used by the decoder. This paper presents a novel design of a neural decoder that uses a one-step model predictive controller to generate a control signal that compensates for the inherent model mismatch. The effectiveness of the proposed decoding algorithm compares favorably to the state-of-the-art Kalman filter in numerical simulations with different degrees of model mismatch.

AB - Brain-machine interfaces (BMI) hold great potential to improve the quality of life of many patients with disabilities. The neural decoder, which expresses the mapping between the neural signals and the subject's motion, plays an important role in BMI systems. Conventional neural decoders are generally in the form of a kinematic Kalman filter which does not possess an explicit mechanism to deal with the unavoidable mismatch between the biological system and the model of the system used by the decoder. This paper presents a novel design of a neural decoder that uses a one-step model predictive controller to generate a control signal that compensates for the inherent model mismatch. The effectiveness of the proposed decoding algorithm compares favorably to the state-of-the-art Kalman filter in numerical simulations with different degrees of model mismatch.

UR - http://www.scopus.com/inward/record.url?scp=84988269626&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84988269626&partnerID=8YFLogxK

U2 - 10.1109/CDC.2014.7040489

DO - 10.1109/CDC.2014.7040489

M3 - Article

AN - SCOPUS:84988269626

VL - 2015-February

SP - 6999

EP - 7004

JO - Indian Journal of Rheumatology

JF - Indian Journal of Rheumatology

SN - 0973-3698

IS - February

M1 - 7040489

ER -