A voting and predictive neural network system for use in a new artificial larynx

M. J. Russell, D. M. Rubin, T. Marwala, B. Wigdorowitz

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Citation (Scopus)

Abstract

A new artificial Larynx is currently under development at the University of the Witwatersrand, Johannesburg. This device uses dynamic tongue movement from a palatometer system to infer what the user is trying to say. Feature selection algorithms extract information from the palatometer data and are then used as input to a Multi-Layer Perceptron Neural Network. This paper deals with improving the success rate of the Neural Networks by using a voting system as well as a word prediction system. By using a voting system unknown non-rejected input words were correctly identified 93.5% of the time, while the system has a rejection rate of 17.36%. A set of grammar rules were developed for the word set and this improved the number of correct unknown, non-rejected words to 94.14% but increased the rejection rate to 17.74%.

Original languageEnglish
Title of host publication2nd International Conference on Biomedical and Pharmaceutical Engineering, ICBPE 2009 - Conference Proceedings
DOIs
Publication statusPublished - 2009
Externally publishedYes
Event2nd International Conference on Biomedical and Pharmaceutical Engineering, ICBPE 2009 - Singapore, Singapore
Duration: 2 Dec 20094 Dec 2009

Publication series

Name2nd International Conference on Biomedical and Pharmaceutical Engineering, ICBPE 2009 - Conference Proceedings

Conference

Conference2nd International Conference on Biomedical and Pharmaceutical Engineering, ICBPE 2009
Country/TerritorySingapore
CitySingapore
Period2/12/094/12/09

ASJC Scopus subject areas

  • Biomedical Engineering
  • General Medicine

Fingerprint

Dive into the research topics of 'A voting and predictive neural network system for use in a new artificial larynx'. Together they form a unique fingerprint.

Cite this