Decision making using neural networks

doi:10.1016/0925-2312(94)90070-1

Neurocomputing

Volume 6, Issue 3, June 1994, Pages 363-374

https://doi.org/10.1016/0925-2312(94)90070-1 Get rights and content

Abstract

This paper presents an application of neural networks in decision making. The problem considered in this paper is the evaluation of the relative contribution of various pollution sources to the pollution of a certain ecosystem. The neural network is trained using the data collected by checking every day the ecosystem for the existence of chemical pollutants exceeding a normal threshold. The response of the trained network to some appropriately selected inputs provides the relative effect of the pollution sources on the pollution of the ecosystem. The reliability of the resulting system is tested and evaluated through experimental results.

References (18)

N.B. Karayiannis et al.
Fast learning algorithms for neural networks
E.B. Baum et al.
What size net gives valid generalization?
Neural Computation
(1989)
H.D. Block et al.
Determination and detection of features in patterns
H. Boulard et al.
Auto-association by multilayer perceptrons and singular value decomposition
Biol. Cybernet.
(1988)
D.J. Burr
Experiments on neural net recognition of spoken and written text
IEEE Trans. Acoustics Speech and Signal Processing
(1988)
G.W. Cottrell et al.
Learning internal representations from gray-scale images: An example of extensional programming
G. Cybenko
Approximation by superpositions of sigmoid functions
Math. Control Signals Syst.
(1989)
R.P. Gorman et al.
Learned classification of sonar targets using a massively parallel network
IEEE Trans. Acoustics Speech Signal Processing
(1988)
D.H. Graf et al.
A neural controller for collision-free movement of general robot manipulators

There are more references available in the full text version of this article.

Cited by (6)

Logic-oriented model of artificial neural networks
1997, Information Sciences
This paper addresses the problem of logical interpretation of neural nodes, which are basically computational elements. We will look at generic models of neurons viewed as computing units carrying out logic operations on input signals. The mapping of the inherent logical background of the problem at hand, given in the form of an artificial neural network (ANN), onto the logic-oriented network can be realized by choosing appropriate logic-based neurons. Introducing “a simple type” of logical function in the form NofM, we concluded that it is possible to model ANN behavior with these functions without ad hoc approximations. During the modeling process, it is more important to take into account the range and relations between weight factors in ANN than their absolute values. Based on this analysis, we developed an algorithm for logical interpretation of a neuron's computational model based on the generalized logical function NofM. Also, we present in this paper the methodology and some experimental results concerning logical interpretation of ANN. Experiments provide a better understanding of ANN behavior, particularly multiple-layered perceptrons (MLPs), and the meaning of the related concepts: robustness, redundancy, pruning, etc.
On-line expert system for odor complaints in a refinery
1996, Computers and Chemical Engineering
On-line capabilities of modern expert systems are of special interest due to the possibility of real-time environmental monitoring and detection of possible rules violations in their early phase of development. One of the most difficult environmental problem for some refineries located in fairly populated areas are released refinery odors. In an attempt to solve this problem, an odor expert system is proposed in this paper. It includes a historical data base with all available odor complaints, real-time monitoring of weather data and selected process variables, a detailed map, and rules. The rules are based on the developed methodology for quantitavely correlating process variables with odor complaints. The methodology includes threshold values calculations for selected variables at the Waste Water Treatment Plant and their correlation with process variables in different units inside the refinery. The proposed expert system has been implemented in the GENSYM G2 software environment at StarEnterprise refinery in Delaware City, Delaware, USA.
Visualization of neural-network gaps based on error analysis
1999, IEEE Transactions on Neural Networks
Neural network modeling and simulation of the synthesis of CuInS<inf>2</inf>/ZnS quantum dots
2020, Engineering Reports
Decision support system for innovation with a special emphasis on pollution
2007, International Journal of Environment and Pollution
Engineering neural models of cognitive planning, emotion and volition
2005, Neural Network World

^∗

Nicolaos B. Karayiannis was born in Greece, on January 1, 1960. He received the Diploma degree in Electrical Engineering from the National Technical University of Athens in 1983, and the M.A.Sc. and Ph.D. degrees in Electrical Engineering from the University of Toronto in 1987 and 1991, respectively.

He is currently an Assistant Professor in the Department of Electrical Engineering, University of Houston. From 1984 to 1991 he worked as a Research and Teaching Assistant at the University of Toronto. From 1983 to 1984 he was a Research Assistant at the Nuclear Research Center ‘Democritos’, Athens, Greece, where he was engaged in research on multidimensional signal processing. His current research interests include supervised and unsupervised learning and applications of artificial neural networks in image processing and analysis.

Dr. Karayiannis is a member of the Institute of Electrical and Electronics Engineers (IEEE), the International Neural Network Society (INNS) and the Technical Chamber of Greece.

^∗∗

Anastasios N. Venetsanopoulos received the B.S. degree from the National Technical University of Athens (NTU), Greece, in 1965, and the M.S., M. Phil., and Ph.D., degrees in electrical engineering all from Yale University, in 1966, 1968, and 1969, respectively. He joined the University of Toronto, Canada, in September 1968, where he is now Professor in the Department of Electrical Engineering. He also served as Chairman of the Communications Group (1974 to 1978 and 1981 to 1986), and Associate Chairman of the Department of Electrical Engineering (1978 to 1979). He was on research leave at the Swiss Federal Institute of Technology, the University of Florence, the Federal University of Rio de Janeiro, the National Technical University of Athens, and the Imperial College of Sciences and Technology, and was Adjunct Professor at Concordia University. He served as Lecturer of numerous short courses to industry and continuing education programs: he is a contributor to eleven books and has published over 400 papers in digital signal and image processing, and digital communications: he also served as consultant to several organizations, and as Editor of the Canadian Electrical Engineering Journal (1981 to 1983).

Dr. Venetsanopoulos was President of the Canadian Society for Electrical Engineering and Vice-President of the Engineering Institute of Canada (1983–1984). He was a Fulbright Scholar, A, F. Schmitt Scholar, and recipient of the J. Vakis Award. He is a member of the New York Academy of Sciences, Sigma Xi, the Institute of Electrical and Electronics Engineers, the International Society for Optical Engineering, and the Technical Chamber of Greece: he is a Registered Professional Engineer in Ontario and Greece, and a Fellow of the Engineering Institute of Canada.

View full text

PaperDecision making using neural networks

Abstract

What size net gives valid generalization?

Neural Computation

Determination and detection of features in patterns

Auto-association by multilayer perceptrons and singular value decomposition

Biol. Cybernet.

Experiments on neural net recognition of spoken and written text

IEEE Trans. Acoustics Speech and Signal Processing

Learning internal representations from gray-scale images: An example of extensional programming

Approximation by superpositions of sigmoid functions

Math. Control Signals Syst.

Learned classification of sonar targets using a massively parallel network

IEEE Trans. Acoustics Speech Signal Processing

A neural controller for collision-free movement of general robot manipulators

Paper
Decision making using neural networks