Neural networks can detect patterns in information that they receive and have been used successfully in many classification problems. The research discussed in this paper was pursued to determine if neural networks could be successfully used for alarm classification for security systems operating in unstructured environments. The project investigated the usefulness of various types of neural networks for this application. The results from the research exceeded the original goals, promising sound application to security systems in unstructured environments.
Get full access to this article
View all access options for this article.
References
1.
Barron, R.L., A.N. Mucciardi, F.J. Cook, J.N. Craig and A.R. Barron.1984. 'Adaptive Learning Networks: Development and Application in the United States of Algorithms Related to GMDH", Self-Organizing Methods in Modelmg, GMDH-Type Algorithms , S. J. Farlow, ed., Marcell Dekker, Inc., pp. 25-65.
2.
Eberhart, R.C. and R.W. Dobbins.1990. Neural Network PC Tools: A Practical Guide , San Diego: Academic Press.
3.
Lippmann, R.P.1989. "Pattern Classification Using Neural Networks" , IEEE Communications Magazine, pp. 47-64.
4.
NeuralWare, Inc.1991. Neural Computing, Pittsburgh: NeuralWare, Inc.
5.
Simpson, P.K.1990. Artificial Neural Systems, New York: Pergamon Press.
