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

Research output: Contribution to journalArticlepeer-review

184 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 languageEnglish
Pages (from-to)1406-1411
Number of pages6
JournalIEEE Transactions on Biomedical Engineering
Volume47
Issue number10
DOIs
Publication statusPublished - 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

Fingerprint

Dive into the research topics of 'Neural spike sorting under nearly 0-dB signal-to-noise ratio using nonlinear energy operator and artificial neural-network classifier'. Together they form a unique fingerprint.

Cite this