A Monte Carlo sequential estimation of point process optimum filtering for brain machine interfaces

Yiwen Wang, António R C Paiva, José C. Príncipe, Justin C. Sanchez

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

The previous decoding algorithms for Brain Machine Interfaces are normally utilized to estimate animal's movement from binned spike rates, which loses spike timing resolution and may exclude rich neural dynamics due to single spikes. Based on recently proposed Monte Carlo sequential estimation algorithm on point process, we present a decoding framework to reconstruct the kinematic states directly from the multi-channel spike trains. Starting with analysis on the differences between the simulation and real BMI data, neural tuning properties are modeled to encode the movement information of the experimental primate as the pre-knowledge for Monte-Carlo sequential estimation for BMI. The preliminary kinematics reconstruction shows better results when compared with Kalman filter.

Original languageEnglish
Title of host publicationIEEE International Conference on Neural Networks - Conference Proceedings
Pages2250-2255
Number of pages6
DOIs
StatePublished - Dec 1 2007
Externally publishedYes
Event2007 International Joint Conference on Neural Networks, IJCNN 2007 - Orlando, FL, United States
Duration: Aug 12 2007Aug 17 2007

Other

Other2007 International Joint Conference on Neural Networks, IJCNN 2007
CountryUnited States
CityOrlando, FL
Period8/12/078/17/07

Fingerprint

Decoding
Brain
Kinematics
Kalman filters
Animals
Tuning
Primates

ASJC Scopus subject areas

  • Software

Cite this

Wang, Y., Paiva, A. R. C., Príncipe, J. C., & Sanchez, J. C. (2007). A Monte Carlo sequential estimation of point process optimum filtering for brain machine interfaces. In IEEE International Conference on Neural Networks - Conference Proceedings (pp. 2250-2255). [4371308] https://doi.org/10.1109/IJCNN.2007.4371308

A Monte Carlo sequential estimation of point process optimum filtering for brain machine interfaces. / Wang, Yiwen; Paiva, António R C; Príncipe, José C.; Sanchez, Justin C.

IEEE International Conference on Neural Networks - Conference Proceedings. 2007. p. 2250-2255 4371308.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Wang, Y, Paiva, ARC, Príncipe, JC & Sanchez, JC 2007, A Monte Carlo sequential estimation of point process optimum filtering for brain machine interfaces. in IEEE International Conference on Neural Networks - Conference Proceedings., 4371308, pp. 2250-2255, 2007 International Joint Conference on Neural Networks, IJCNN 2007, Orlando, FL, United States, 8/12/07. https://doi.org/10.1109/IJCNN.2007.4371308
Wang Y, Paiva ARC, Príncipe JC, Sanchez JC. A Monte Carlo sequential estimation of point process optimum filtering for brain machine interfaces. In IEEE International Conference on Neural Networks - Conference Proceedings. 2007. p. 2250-2255. 4371308 https://doi.org/10.1109/IJCNN.2007.4371308
Wang, Yiwen ; Paiva, António R C ; Príncipe, José C. ; Sanchez, Justin C. / A Monte Carlo sequential estimation of point process optimum filtering for brain machine interfaces. IEEE International Conference on Neural Networks - Conference Proceedings. 2007. pp. 2250-2255
@inproceedings{e96e8f5f00a94c5b96cf39d27438b135,
title = "A Monte Carlo sequential estimation of point process optimum filtering for brain machine interfaces",
abstract = "The previous decoding algorithms for Brain Machine Interfaces are normally utilized to estimate animal's movement from binned spike rates, which loses spike timing resolution and may exclude rich neural dynamics due to single spikes. Based on recently proposed Monte Carlo sequential estimation algorithm on point process, we present a decoding framework to reconstruct the kinematic states directly from the multi-channel spike trains. Starting with analysis on the differences between the simulation and real BMI data, neural tuning properties are modeled to encode the movement information of the experimental primate as the pre-knowledge for Monte-Carlo sequential estimation for BMI. The preliminary kinematics reconstruction shows better results when compared with Kalman filter.",
author = "Yiwen Wang and Paiva, {Ant{\'o}nio R C} and Pr{\'i}ncipe, {Jos{\'e} C.} and Sanchez, {Justin C.}",
year = "2007",
month = "12",
day = "1",
doi = "10.1109/IJCNN.2007.4371308",
language = "English",
isbn = "142441380X",
pages = "2250--2255",
booktitle = "IEEE International Conference on Neural Networks - Conference Proceedings",

}

TY - GEN

T1 - A Monte Carlo sequential estimation of point process optimum filtering for brain machine interfaces

AU - Wang, Yiwen

AU - Paiva, António R C

AU - Príncipe, José C.

AU - Sanchez, Justin C.

PY - 2007/12/1

Y1 - 2007/12/1

N2 - The previous decoding algorithms for Brain Machine Interfaces are normally utilized to estimate animal's movement from binned spike rates, which loses spike timing resolution and may exclude rich neural dynamics due to single spikes. Based on recently proposed Monte Carlo sequential estimation algorithm on point process, we present a decoding framework to reconstruct the kinematic states directly from the multi-channel spike trains. Starting with analysis on the differences between the simulation and real BMI data, neural tuning properties are modeled to encode the movement information of the experimental primate as the pre-knowledge for Monte-Carlo sequential estimation for BMI. The preliminary kinematics reconstruction shows better results when compared with Kalman filter.

AB - The previous decoding algorithms for Brain Machine Interfaces are normally utilized to estimate animal's movement from binned spike rates, which loses spike timing resolution and may exclude rich neural dynamics due to single spikes. Based on recently proposed Monte Carlo sequential estimation algorithm on point process, we present a decoding framework to reconstruct the kinematic states directly from the multi-channel spike trains. Starting with analysis on the differences between the simulation and real BMI data, neural tuning properties are modeled to encode the movement information of the experimental primate as the pre-knowledge for Monte-Carlo sequential estimation for BMI. The preliminary kinematics reconstruction shows better results when compared with Kalman filter.

UR - http://www.scopus.com/inward/record.url?scp=51749083487&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=51749083487&partnerID=8YFLogxK

U2 - 10.1109/IJCNN.2007.4371308

DO - 10.1109/IJCNN.2007.4371308

M3 - Conference contribution

SN - 142441380X

SN - 9781424413805

SP - 2250

EP - 2255

BT - IEEE International Conference on Neural Networks - Conference Proceedings

ER -