Method for unsupervised classification of multiunit neural signal recording under low signal-to-noise ratio

Kyung Hwan Kim, Sung June Kim

Research output: Contribution to journalArticle

28 Citations (Scopus)

Abstract

Neural spike sorting is an indispensable step in the analysis of multiunit extracellular neural signal recording. The applicability of spike sorting systems has been limited, mainly to the recording of sufficiently high signal-to-noise ratios, or to the cases where supervised classification can be utilized. We present a novel unsupervised method that shows satisfactory performance even under high background noise. The system consists of an efficient spike detector, a feature extractor that utilizes projection pursuit based on negentropy maximization (Huber, 1985 and Hyvarinen et al., 1999), and an unsupervised classifier based on probability density modeling using mixture of Gaussians (Jain et al., 2000). Our classifier is based on the mixture model with a roughly approximated number of Gaussians and subsequent mode-seeking. It does not require accurate estimation of the number of units present in the recording and, thus, is better suited for use in fully automated systems. The feature extraction stage leads to better performance than those utilizing principal component analysis and two nonlinear mappings for the recordings from the somatosensory cortex of rat and the abdominal ganglion of Aplysia. The classification method yielded correct classification ratio as high as 95%, for data where it was only 66% when a k-means-type algorithm was used for the classification stage.

Original languageEnglish
Pages (from-to)421-431
Number of pages11
JournalIEEE Transactions on Biomedical Engineering
Volume50
Issue number4
DOIs
Publication statusPublished - 2003 Apr 1

Fingerprint

Signal to noise ratio
Sorting
Classifiers
Principal component analysis
Rats
Feature extraction
Detectors

All Science Journal Classification (ASJC) codes

  • Biomedical Engineering

Cite this

@article{2d1a2678c41342a696d319bd4f7bc63b,
title = "Method for unsupervised classification of multiunit neural signal recording under low signal-to-noise ratio",
abstract = "Neural spike sorting is an indispensable step in the analysis of multiunit extracellular neural signal recording. The applicability of spike sorting systems has been limited, mainly to the recording of sufficiently high signal-to-noise ratios, or to the cases where supervised classification can be utilized. We present a novel unsupervised method that shows satisfactory performance even under high background noise. The system consists of an efficient spike detector, a feature extractor that utilizes projection pursuit based on negentropy maximization (Huber, 1985 and Hyvarinen et al., 1999), and an unsupervised classifier based on probability density modeling using mixture of Gaussians (Jain et al., 2000). Our classifier is based on the mixture model with a roughly approximated number of Gaussians and subsequent mode-seeking. It does not require accurate estimation of the number of units present in the recording and, thus, is better suited for use in fully automated systems. The feature extraction stage leads to better performance than those utilizing principal component analysis and two nonlinear mappings for the recordings from the somatosensory cortex of rat and the abdominal ganglion of Aplysia. The classification method yielded correct classification ratio as high as 95{\%}, for data where it was only 66{\%} when a k-means-type algorithm was used for the classification stage.",
author = "Kim, {Kyung Hwan} and Kim, {Sung June}",
year = "2003",
month = "4",
day = "1",
doi = "10.1109/TBME.2003.809503",
language = "English",
volume = "50",
pages = "421--431",
journal = "IEEE Transactions on Biomedical Engineering",
issn = "0018-9294",
publisher = "IEEE Computer Society",
number = "4",

}

Method for unsupervised classification of multiunit neural signal recording under low signal-to-noise ratio. / Kim, Kyung Hwan; Kim, Sung June.

In: IEEE Transactions on Biomedical Engineering, Vol. 50, No. 4, 01.04.2003, p. 421-431.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Method for unsupervised classification of multiunit neural signal recording under low signal-to-noise ratio

AU - Kim, Kyung Hwan

AU - Kim, Sung June

PY - 2003/4/1

Y1 - 2003/4/1

N2 - Neural spike sorting is an indispensable step in the analysis of multiunit extracellular neural signal recording. The applicability of spike sorting systems has been limited, mainly to the recording of sufficiently high signal-to-noise ratios, or to the cases where supervised classification can be utilized. We present a novel unsupervised method that shows satisfactory performance even under high background noise. The system consists of an efficient spike detector, a feature extractor that utilizes projection pursuit based on negentropy maximization (Huber, 1985 and Hyvarinen et al., 1999), and an unsupervised classifier based on probability density modeling using mixture of Gaussians (Jain et al., 2000). Our classifier is based on the mixture model with a roughly approximated number of Gaussians and subsequent mode-seeking. It does not require accurate estimation of the number of units present in the recording and, thus, is better suited for use in fully automated systems. The feature extraction stage leads to better performance than those utilizing principal component analysis and two nonlinear mappings for the recordings from the somatosensory cortex of rat and the abdominal ganglion of Aplysia. The classification method yielded correct classification ratio as high as 95%, for data where it was only 66% when a k-means-type algorithm was used for the classification stage.

AB - Neural spike sorting is an indispensable step in the analysis of multiunit extracellular neural signal recording. The applicability of spike sorting systems has been limited, mainly to the recording of sufficiently high signal-to-noise ratios, or to the cases where supervised classification can be utilized. We present a novel unsupervised method that shows satisfactory performance even under high background noise. The system consists of an efficient spike detector, a feature extractor that utilizes projection pursuit based on negentropy maximization (Huber, 1985 and Hyvarinen et al., 1999), and an unsupervised classifier based on probability density modeling using mixture of Gaussians (Jain et al., 2000). Our classifier is based on the mixture model with a roughly approximated number of Gaussians and subsequent mode-seeking. It does not require accurate estimation of the number of units present in the recording and, thus, is better suited for use in fully automated systems. The feature extraction stage leads to better performance than those utilizing principal component analysis and two nonlinear mappings for the recordings from the somatosensory cortex of rat and the abdominal ganglion of Aplysia. The classification method yielded correct classification ratio as high as 95%, for data where it was only 66% when a k-means-type algorithm was used for the classification stage.

UR - http://www.scopus.com/inward/record.url?scp=0037388960&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0037388960&partnerID=8YFLogxK

U2 - 10.1109/TBME.2003.809503

DO - 10.1109/TBME.2003.809503

M3 - Article

C2 - 12723053

AN - SCOPUS:0037388960

VL - 50

SP - 421

EP - 431

JO - IEEE Transactions on Biomedical Engineering

JF - IEEE Transactions on Biomedical Engineering

SN - 0018-9294

IS - 4

ER -