Advantage of support vector machine for neural spike train decoding under spike sorting errors

Kyunghwan Kim, Sung Shin Kim, Sung June Kim

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

5 Citations (Scopus)

Abstract

Decoding of kinematic variables from neuronal spike trains is important for neuroprosthetic devices. The spike trains from single units must be extracted from extracellular neural signals and thus spike detection and sorting procedure is essential. Since the spike detection and sorting procedure may yield considerable errors, decoding algorithm should be robust against spike train errors. Here we showed that the spike train decoding algorithms employing a nonlinear mapping, especially support vector machine (SVM), may be more advantageous contrary to conventional belief that linear filter is sufficient. The advantage became more conspicuous with erroneous spike trains. Using the SVM, satisfactory performance could be obtained much more easily, compared to the case of using multilayer perceptron, which was employed for previous studies. The results suggests the possibility of neuroprosthetic device with a low-quality spike sorting preprocessor.

Original languageEnglish
Title of host publicationProceedings of the 2005 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE-EMBS 2005
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages5280-5283
Number of pages4
Volume7 VOLS
ISBN (Print)0780387406, 9780780387409
Publication statusPublished - 2005 Jan 1
Event2005 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE-EMBS 2005 - Shanghai, China
Duration: 2005 Sep 12005 Sep 4

Other

Other2005 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE-EMBS 2005
CountryChina
CityShanghai
Period05/9/105/9/4

Fingerprint

Sorting
Support vector machines
Decoding
Equipment and Supplies
Neural Networks (Computer)
Biomechanical Phenomena
Multilayer neural networks
Kinematics
Support Vector Machine

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Biomedical Engineering
  • Computer Vision and Pattern Recognition
  • Health Informatics

Cite this

Kim, K., Kim, S. S., & Kim, S. J. (2005). Advantage of support vector machine for neural spike train decoding under spike sorting errors. In Proceedings of the 2005 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE-EMBS 2005 (Vol. 7 VOLS, pp. 5280-5283). [1615671] Institute of Electrical and Electronics Engineers Inc..
Kim, Kyunghwan ; Kim, Sung Shin ; Kim, Sung June. / Advantage of support vector machine for neural spike train decoding under spike sorting errors. Proceedings of the 2005 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE-EMBS 2005. Vol. 7 VOLS Institute of Electrical and Electronics Engineers Inc., 2005. pp. 5280-5283
@inproceedings{e3a0a239a6f1424783a12026d5ae37ef,
title = "Advantage of support vector machine for neural spike train decoding under spike sorting errors",
abstract = "Decoding of kinematic variables from neuronal spike trains is important for neuroprosthetic devices. The spike trains from single units must be extracted from extracellular neural signals and thus spike detection and sorting procedure is essential. Since the spike detection and sorting procedure may yield considerable errors, decoding algorithm should be robust against spike train errors. Here we showed that the spike train decoding algorithms employing a nonlinear mapping, especially support vector machine (SVM), may be more advantageous contrary to conventional belief that linear filter is sufficient. The advantage became more conspicuous with erroneous spike trains. Using the SVM, satisfactory performance could be obtained much more easily, compared to the case of using multilayer perceptron, which was employed for previous studies. The results suggests the possibility of neuroprosthetic device with a low-quality spike sorting preprocessor.",
author = "Kyunghwan Kim and Kim, {Sung Shin} and Kim, {Sung June}",
year = "2005",
month = "1",
day = "1",
language = "English",
isbn = "0780387406",
volume = "7 VOLS",
pages = "5280--5283",
booktitle = "Proceedings of the 2005 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE-EMBS 2005",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

Kim, K, Kim, SS & Kim, SJ 2005, Advantage of support vector machine for neural spike train decoding under spike sorting errors. in Proceedings of the 2005 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE-EMBS 2005. vol. 7 VOLS, 1615671, Institute of Electrical and Electronics Engineers Inc., pp. 5280-5283, 2005 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE-EMBS 2005, Shanghai, China, 05/9/1.

Advantage of support vector machine for neural spike train decoding under spike sorting errors. / Kim, Kyunghwan; Kim, Sung Shin; Kim, Sung June.

Proceedings of the 2005 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE-EMBS 2005. Vol. 7 VOLS Institute of Electrical and Electronics Engineers Inc., 2005. p. 5280-5283 1615671.

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

TY - GEN

T1 - Advantage of support vector machine for neural spike train decoding under spike sorting errors

AU - Kim, Kyunghwan

AU - Kim, Sung Shin

AU - Kim, Sung June

PY - 2005/1/1

Y1 - 2005/1/1

N2 - Decoding of kinematic variables from neuronal spike trains is important for neuroprosthetic devices. The spike trains from single units must be extracted from extracellular neural signals and thus spike detection and sorting procedure is essential. Since the spike detection and sorting procedure may yield considerable errors, decoding algorithm should be robust against spike train errors. Here we showed that the spike train decoding algorithms employing a nonlinear mapping, especially support vector machine (SVM), may be more advantageous contrary to conventional belief that linear filter is sufficient. The advantage became more conspicuous with erroneous spike trains. Using the SVM, satisfactory performance could be obtained much more easily, compared to the case of using multilayer perceptron, which was employed for previous studies. The results suggests the possibility of neuroprosthetic device with a low-quality spike sorting preprocessor.

AB - Decoding of kinematic variables from neuronal spike trains is important for neuroprosthetic devices. The spike trains from single units must be extracted from extracellular neural signals and thus spike detection and sorting procedure is essential. Since the spike detection and sorting procedure may yield considerable errors, decoding algorithm should be robust against spike train errors. Here we showed that the spike train decoding algorithms employing a nonlinear mapping, especially support vector machine (SVM), may be more advantageous contrary to conventional belief that linear filter is sufficient. The advantage became more conspicuous with erroneous spike trains. Using the SVM, satisfactory performance could be obtained much more easily, compared to the case of using multilayer perceptron, which was employed for previous studies. The results suggests the possibility of neuroprosthetic device with a low-quality spike sorting preprocessor.

UR - http://www.scopus.com/inward/record.url?scp=33846916903&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33846916903&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:33846916903

SN - 0780387406

SN - 9780780387409

VL - 7 VOLS

SP - 5280

EP - 5283

BT - Proceedings of the 2005 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE-EMBS 2005

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Kim K, Kim SS, Kim SJ. Advantage of support vector machine for neural spike train decoding under spike sorting errors. In Proceedings of the 2005 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE-EMBS 2005. Vol. 7 VOLS. Institute of Electrical and Electronics Engineers Inc. 2005. p. 5280-5283. 1615671