Improvement of spike train decoder under spike detection and classification errors using support vector machine

Kyunghwan Kim, Sung Shin Kim, Sung June Kim

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

The successful decoding of kinematic variables from spike trains of motor cortical neurons is essential for cortical neural prosthesis. Spike trains from each single unit must be extracted from extracellular neural signals and, thus, spike detection and sorting procedure is indispensable but the detection and sorting may involve considerable error. Thus, a decoding algorithm should be robust with respect to spike train errors. Here, we show that spike train decoding algorithms employing nonlinear mapping, especially a support vector machine (SVM), may be more advantageous contrary to previous results which showed that an optimal linear filter is sufficient. The advantage became more conspicuous in the case of erroneous spike trains. Using the SVM, satisfactory training of the decoder could be achieved much more easily, compared to the case of using a multilayer perceptron, which has been employed in previous studies. Tests were performed on simulated spike trains from primary motor cortical neurons with a realistic distribution of preferred direction. The results suggest the possibility that a neuroprosthetic device with a low-quality spike sorting preprocessor can be achieved by adopting a spike train decoder that is robust to spike sorting errors.

Original languageEnglish
Pages (from-to)124-130
Number of pages7
JournalMedical and Biological Engineering and Computing
Volume44
Issue number1-2
DOIs
Publication statusPublished - 2006 Mar 1

Fingerprint

Sorting
Support vector machines
Decoding
Neurons
Neural prostheses
Multilayer neural networks
Kinematics

All Science Journal Classification (ASJC) codes

  • Biomedical Engineering
  • Computer Science Applications

Cite this

@article{01688f4f4e3049acac42a4083f7d6585,
title = "Improvement of spike train decoder under spike detection and classification errors using support vector machine",
abstract = "The successful decoding of kinematic variables from spike trains of motor cortical neurons is essential for cortical neural prosthesis. Spike trains from each single unit must be extracted from extracellular neural signals and, thus, spike detection and sorting procedure is indispensable but the detection and sorting may involve considerable error. Thus, a decoding algorithm should be robust with respect to spike train errors. Here, we show that spike train decoding algorithms employing nonlinear mapping, especially a support vector machine (SVM), may be more advantageous contrary to previous results which showed that an optimal linear filter is sufficient. The advantage became more conspicuous in the case of erroneous spike trains. Using the SVM, satisfactory training of the decoder could be achieved much more easily, compared to the case of using a multilayer perceptron, which has been employed in previous studies. Tests were performed on simulated spike trains from primary motor cortical neurons with a realistic distribution of preferred direction. The results suggest the possibility that a neuroprosthetic device with a low-quality spike sorting preprocessor can be achieved by adopting a spike train decoder that is robust to spike sorting errors.",
author = "Kyunghwan Kim and Kim, {Sung Shin} and Kim, {Sung June}",
year = "2006",
month = "3",
day = "1",
doi = "10.1007/s11517-005-0009-x",
language = "English",
volume = "44",
pages = "124--130",
journal = "Medical and Biological Engineering and Computing",
issn = "0140-0118",
publisher = "Springer Verlag",
number = "1-2",

}

Improvement of spike train decoder under spike detection and classification errors using support vector machine. / Kim, Kyunghwan; Kim, Sung Shin; Kim, Sung June.

In: Medical and Biological Engineering and Computing, Vol. 44, No. 1-2, 01.03.2006, p. 124-130.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Improvement of spike train decoder under spike detection and classification errors using support vector machine

AU - Kim, Kyunghwan

AU - Kim, Sung Shin

AU - Kim, Sung June

PY - 2006/3/1

Y1 - 2006/3/1

N2 - The successful decoding of kinematic variables from spike trains of motor cortical neurons is essential for cortical neural prosthesis. Spike trains from each single unit must be extracted from extracellular neural signals and, thus, spike detection and sorting procedure is indispensable but the detection and sorting may involve considerable error. Thus, a decoding algorithm should be robust with respect to spike train errors. Here, we show that spike train decoding algorithms employing nonlinear mapping, especially a support vector machine (SVM), may be more advantageous contrary to previous results which showed that an optimal linear filter is sufficient. The advantage became more conspicuous in the case of erroneous spike trains. Using the SVM, satisfactory training of the decoder could be achieved much more easily, compared to the case of using a multilayer perceptron, which has been employed in previous studies. Tests were performed on simulated spike trains from primary motor cortical neurons with a realistic distribution of preferred direction. The results suggest the possibility that a neuroprosthetic device with a low-quality spike sorting preprocessor can be achieved by adopting a spike train decoder that is robust to spike sorting errors.

AB - The successful decoding of kinematic variables from spike trains of motor cortical neurons is essential for cortical neural prosthesis. Spike trains from each single unit must be extracted from extracellular neural signals and, thus, spike detection and sorting procedure is indispensable but the detection and sorting may involve considerable error. Thus, a decoding algorithm should be robust with respect to spike train errors. Here, we show that spike train decoding algorithms employing nonlinear mapping, especially a support vector machine (SVM), may be more advantageous contrary to previous results which showed that an optimal linear filter is sufficient. The advantage became more conspicuous in the case of erroneous spike trains. Using the SVM, satisfactory training of the decoder could be achieved much more easily, compared to the case of using a multilayer perceptron, which has been employed in previous studies. Tests were performed on simulated spike trains from primary motor cortical neurons with a realistic distribution of preferred direction. The results suggest the possibility that a neuroprosthetic device with a low-quality spike sorting preprocessor can be achieved by adopting a spike train decoder that is robust to spike sorting errors.

UR - http://www.scopus.com/inward/record.url?scp=33745479321&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33745479321&partnerID=8YFLogxK

U2 - 10.1007/s11517-005-0009-x

DO - 10.1007/s11517-005-0009-x

M3 - Article

C2 - 16929930

AN - SCOPUS:33745479321

VL - 44

SP - 124

EP - 130

JO - Medical and Biological Engineering and Computing

JF - Medical and Biological Engineering and Computing

SN - 0140-0118

IS - 1-2

ER -