The state of a plant affects its chlorophyll content, which in turn, affects the way the plant reflects light. Consequently, the characteristics of the reflected light can be used to determine the health of a plant. This raises the possibility of monitoring large areas of vegetation by analyzing the reflectance of the plants in the area. This paper discusses the use of neural networks for analy...

This paper outlines an algorithm for incrementally growing Artificial Neural Networks. The algorithm allows the network to expand by adding new sub-networks or modules to an existing structure; the modules are trained using an Evolutionary Algorithm. Only the latest module added to the network is trained, the previous structure remains fixed. The algorithm allows information from different data...

In this paper, we propose a new method for decomposing pattern classification problems based on the class relations among training data. By using this method, we can divide a K-class classification problem into a series of ((2)(K)) two-class problems. These two-class problems are to discriminate class Ci from class Cj for i=1, ..., K and j = i+1, while the existence of the training data belongi...

It is important to detect the leakage of the gas to be flammable or poisonous from the cracks in pipes of petroleum refining plants or chemical plants. We examined the application of modular neural networks to the acoustic diagnosis technique for the leakage sound. The modular neural network has the ability to adapt its structure according to the environment. Experiments were performed for an a...

This paper describes a neural ore grade estimation system developed at the AIMS Research Unit of the University of Nottingham. GEMNET II is a modular neural network system designed to receive drillhole information from an orebody and perform ore grade estimation on a block model basis. The aims of the system are to provide a valid alternative to conventional grade estimation techniques while re...

In this paper we derive an upper bound for the average-case generalization error of the mixture of experts modular neural network, based on an average-case generalization error bound for an isolated neural network. By doing this we also generalize a previous bound for this architecture that was restricted to special problems. We also present a correction factor for the original average generali...

iii Abstract In this project a new modular neural network is proposed The basic building blocks of the architecture are small multilayer feedforward networks trained using the Backpropagation algorithm The structure of the modular system is similar to architectures known from logical neural networks The new network is not fully connected and therefore the number of weight connections is much le...

Paying attention to realistic systems in the actual engineering fields, we must very often treat their systems as stochastic systems with non-Gaussian, nonlinear and/or non-stationary properties. In this paper, a regression analysis method for such stochastic systems is proposed by introducing reasonably a modular structured neural network. The proposed modular structured neural network is cons...