Auditory brainstem response classification using modular neural networks

Han Wen, Ozcan Ozdamar

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

2 Citations (Scopus)

Abstract

A modular artificial neural-network system composed of two levels of modules has been developed for the classification of auditory brainstem response (ABR) to be used in electrophysiologic hearing-threshold determination. The first level consists of four neural-network modules, each of which is trained to recognize one of four basic ABR waveforms (high, mid, low and, no response). The final classifications (response, no response, and cannot determine) are decided by a second-level neural network or a rule-base system. The performance of the system was evaluated by computing Bayesian boundaries obtained by the nearest neighbor method. The results show that the modular system is trained faster than previous nonmodular networks and yields higher recognition rates. Eliminating stimulus and muscle artifacts by limiting input window further improves the recognition rate.

Original languageEnglish
Title of host publicationProceedings of the Annual Conference on Engineering in Medicine and Biology
Place of PublicationPiscataway, NJ, United States
PublisherPubl by IEEE
Pages1879-1880
Number of pages2
Volume13
Editionpt 4
ISBN (Print)0780302168
StatePublished - Dec 1 1991
Externally publishedYes
EventProceedings of the 13th Annual International Conference of the IEEE Engineering in Medicine and Biology Society - Orlando, FL, USA
Duration: Oct 31 1991Nov 3 1991

Other

OtherProceedings of the 13th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
CityOrlando, FL, USA
Period10/31/9111/3/91

Fingerprint

Neural networks
Audition
Muscle

ASJC Scopus subject areas

  • Bioengineering

Cite this

Wen, H., & Ozdamar, O. (1991). Auditory brainstem response classification using modular neural networks. In Proceedings of the Annual Conference on Engineering in Medicine and Biology (pt 4 ed., Vol. 13, pp. 1879-1880). Piscataway, NJ, United States: Publ by IEEE.

Auditory brainstem response classification using modular neural networks. / Wen, Han; Ozdamar, Ozcan.

Proceedings of the Annual Conference on Engineering in Medicine and Biology. Vol. 13 pt 4. ed. Piscataway, NJ, United States : Publ by IEEE, 1991. p. 1879-1880.

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

Wen, H & Ozdamar, O 1991, Auditory brainstem response classification using modular neural networks. in Proceedings of the Annual Conference on Engineering in Medicine and Biology. pt 4 edn, vol. 13, Publ by IEEE, Piscataway, NJ, United States, pp. 1879-1880, Proceedings of the 13th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Orlando, FL, USA, 10/31/91.
Wen H, Ozdamar O. Auditory brainstem response classification using modular neural networks. In Proceedings of the Annual Conference on Engineering in Medicine and Biology. pt 4 ed. Vol. 13. Piscataway, NJ, United States: Publ by IEEE. 1991. p. 1879-1880
Wen, Han ; Ozdamar, Ozcan. / Auditory brainstem response classification using modular neural networks. Proceedings of the Annual Conference on Engineering in Medicine and Biology. Vol. 13 pt 4. ed. Piscataway, NJ, United States : Publ by IEEE, 1991. pp. 1879-1880
@inproceedings{63478ecef2c3478b84795765b5d31ebc,
title = "Auditory brainstem response classification using modular neural networks",
abstract = "A modular artificial neural-network system composed of two levels of modules has been developed for the classification of auditory brainstem response (ABR) to be used in electrophysiologic hearing-threshold determination. The first level consists of four neural-network modules, each of which is trained to recognize one of four basic ABR waveforms (high, mid, low and, no response). The final classifications (response, no response, and cannot determine) are decided by a second-level neural network or a rule-base system. The performance of the system was evaluated by computing Bayesian boundaries obtained by the nearest neighbor method. The results show that the modular system is trained faster than previous nonmodular networks and yields higher recognition rates. Eliminating stimulus and muscle artifacts by limiting input window further improves the recognition rate.",
author = "Han Wen and Ozcan Ozdamar",
year = "1991",
month = "12",
day = "1",
language = "English",
isbn = "0780302168",
volume = "13",
pages = "1879--1880",
booktitle = "Proceedings of the Annual Conference on Engineering in Medicine and Biology",
publisher = "Publ by IEEE",
edition = "pt 4",

}

TY - GEN

T1 - Auditory brainstem response classification using modular neural networks

AU - Wen, Han

AU - Ozdamar, Ozcan

PY - 1991/12/1

Y1 - 1991/12/1

N2 - A modular artificial neural-network system composed of two levels of modules has been developed for the classification of auditory brainstem response (ABR) to be used in electrophysiologic hearing-threshold determination. The first level consists of four neural-network modules, each of which is trained to recognize one of four basic ABR waveforms (high, mid, low and, no response). The final classifications (response, no response, and cannot determine) are decided by a second-level neural network or a rule-base system. The performance of the system was evaluated by computing Bayesian boundaries obtained by the nearest neighbor method. The results show that the modular system is trained faster than previous nonmodular networks and yields higher recognition rates. Eliminating stimulus and muscle artifacts by limiting input window further improves the recognition rate.

AB - A modular artificial neural-network system composed of two levels of modules has been developed for the classification of auditory brainstem response (ABR) to be used in electrophysiologic hearing-threshold determination. The first level consists of four neural-network modules, each of which is trained to recognize one of four basic ABR waveforms (high, mid, low and, no response). The final classifications (response, no response, and cannot determine) are decided by a second-level neural network or a rule-base system. The performance of the system was evaluated by computing Bayesian boundaries obtained by the nearest neighbor method. The results show that the modular system is trained faster than previous nonmodular networks and yields higher recognition rates. Eliminating stimulus and muscle artifacts by limiting input window further improves the recognition rate.

UR - http://www.scopus.com/inward/record.url?scp=0026310314&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0026310314&partnerID=8YFLogxK

M3 - Conference contribution

SN - 0780302168

VL - 13

SP - 1879

EP - 1880

BT - Proceedings of the Annual Conference on Engineering in Medicine and Biology

PB - Publ by IEEE

CY - Piscataway, NJ, United States

ER -