Neural spike sorting under nearly 0-dB signal-to-noise ratio using nonlinear energy operator and artificial neural-network classifier

Kyung Hwan Kim; Sung June Kim

doi:10.1109/10.871415

Neural spike sorting under nearly 0-dB signal-to-noise ratio using nonlinear energy operator and artificial neural-network classifier

Kyung Hwan Kim, Sung June Kim

Division of Medical Engineering

Research output: Contribution to journal › Article › peer-review

194 Citations (Scopus)

Abstract

We report a result on neural spike sorting under conditions where the signal-to-noise ratio is very low. The use of nonlinear energy operator enables the detection of an action potential, even when the SNR is so poor that a typical amplitude thresholding method cannot be applied. The superior detection ability facilitates the collection of a training set under lower SNR than that of the methods which employ simple amplitude thresholding. Thus, the statistical characteristics of the input vectors can be better represented in the neural-network classifier. The trained neural-network classifiers yield the correct classification ratio higher than 90% when the SNR is as low as 1.2 (0.8 dB) when applied to data obtained from extracellular recording from Aplysia abdominal ganglia using a semiconductor microelectrode array.

Original language	English
Pages (from-to)	1406-1411
Number of pages	6
Journal	IEEE Transactions on Biomedical Engineering
Volume	47
Issue number	10
DOIs	https://doi.org/10.1109/10.871415
Publication status	Published - 2000 Oct

Bibliographical note

Funding Information:
Manuscript received May 3, 1999; revised May 30, 2000. This work was supported by the Ministry of Health and Welfare, Korea, under Grant HMP-98-E-1-0006. Asterisk indicates corresponding author. K. H. Kim is with the School of Electrical Engineering, Seoul National University, Kwanak-gu, Seoul 151–742, Korea (e-mail: khkim@helios.snu.ac.kr). *S. J. Kim is with the School of Electrical Engineering, Seoul National University, San 56–1, Shillim-dong, Kwanak-gu, Seoul 151–742, Korea (e-mail: kim@helios.snu.ac.kr). Publisher Item Identifier S 0018-9294(00)08531-1.

All Science Journal Classification (ASJC) codes

Biomedical Engineering

Access to Document

10.1109/10.871415

Cite this

@article{25269e786d4640f3aa2998f435288a0f,

title = "Neural spike sorting under nearly 0-dB signal-to-noise ratio using nonlinear energy operator and artificial neural-network classifier",

abstract = "We report a result on neural spike sorting under conditions where the signal-to-noise ratio is very low. The use of nonlinear energy operator enables the detection of an action potential, even when the SNR is so poor that a typical amplitude thresholding method cannot be applied. The superior detection ability facilitates the collection of a training set under lower SNR than that of the methods which employ simple amplitude thresholding. Thus, the statistical characteristics of the input vectors can be better represented in the neural-network classifier. The trained neural-network classifiers yield the correct classification ratio higher than 90% when the SNR is as low as 1.2 (0.8 dB) when applied to data obtained from extracellular recording from Aplysia abdominal ganglia using a semiconductor microelectrode array.",

author = "Kim, {Kyung Hwan} and Kim, {Sung June}",

note = "Funding Information: Manuscript received May 3, 1999; revised May 30, 2000. This work was supported by the Ministry of Health and Welfare, Korea, under Grant HMP-98-E-1-0006. Asterisk indicates corresponding author. K. H. Kim is with the School of Electrical Engineering, Seoul National University, Kwanak-gu, Seoul 151–742, Korea (e-mail: khkim@helios.snu.ac.kr). *S. J. Kim is with the School of Electrical Engineering, Seoul National University, San 56–1, Shillim-dong, Kwanak-gu, Seoul 151–742, Korea (e-mail: kim@helios.snu.ac.kr). Publisher Item Identifier S 0018-9294(00)08531-1.",

year = "2000",

month = oct,

doi = "10.1109/10.871415",

language = "English",

volume = "47",

pages = "1406--1411",

journal = "IRE transactions on medical electronics",

issn = "0018-9294",

publisher = "IEEE Computer Society",

number = "10",

}

TY - JOUR

T1 - Neural spike sorting under nearly 0-dB signal-to-noise ratio using nonlinear energy operator and artificial neural-network classifier

AU - Kim, Kyung Hwan

AU - Kim, Sung June

N1 - Funding Information: Manuscript received May 3, 1999; revised May 30, 2000. This work was supported by the Ministry of Health and Welfare, Korea, under Grant HMP-98-E-1-0006. Asterisk indicates corresponding author. K. H. Kim is with the School of Electrical Engineering, Seoul National University, Kwanak-gu, Seoul 151–742, Korea (e-mail: khkim@helios.snu.ac.kr). *S. J. Kim is with the School of Electrical Engineering, Seoul National University, San 56–1, Shillim-dong, Kwanak-gu, Seoul 151–742, Korea (e-mail: kim@helios.snu.ac.kr). Publisher Item Identifier S 0018-9294(00)08531-1.

PY - 2000/10

Y1 - 2000/10

N2 - We report a result on neural spike sorting under conditions where the signal-to-noise ratio is very low. The use of nonlinear energy operator enables the detection of an action potential, even when the SNR is so poor that a typical amplitude thresholding method cannot be applied. The superior detection ability facilitates the collection of a training set under lower SNR than that of the methods which employ simple amplitude thresholding. Thus, the statistical characteristics of the input vectors can be better represented in the neural-network classifier. The trained neural-network classifiers yield the correct classification ratio higher than 90% when the SNR is as low as 1.2 (0.8 dB) when applied to data obtained from extracellular recording from Aplysia abdominal ganglia using a semiconductor microelectrode array.

AB - We report a result on neural spike sorting under conditions where the signal-to-noise ratio is very low. The use of nonlinear energy operator enables the detection of an action potential, even when the SNR is so poor that a typical amplitude thresholding method cannot be applied. The superior detection ability facilitates the collection of a training set under lower SNR than that of the methods which employ simple amplitude thresholding. Thus, the statistical characteristics of the input vectors can be better represented in the neural-network classifier. The trained neural-network classifiers yield the correct classification ratio higher than 90% when the SNR is as low as 1.2 (0.8 dB) when applied to data obtained from extracellular recording from Aplysia abdominal ganglia using a semiconductor microelectrode array.

UR - http://www.scopus.com/inward/record.url?scp=0034306387&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034306387&partnerID=8YFLogxK

U2 - 10.1109/10.871415

DO - 10.1109/10.871415

M3 - Article

C2 - 11059176

AN - SCOPUS:0034306387

SN - 0018-9294

VL - 47

SP - 1406

EP - 1411

JO - IRE transactions on medical electronics

JF - IRE transactions on medical electronics

IS - 10

ER -

Neural spike sorting under nearly 0-dB signal-to-noise ratio using nonlinear energy operator and artificial neural-network classifier

Abstract

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this