Fuzzy neural networks (FuNN) in the Palm environment
Moyle, Sam A; Watts, Mike
This document is prepared with two purposes in mind. The first is to introduce the roof maintenance problem and the proposed solutions. The second is to describe its implementation for the Palm platform. The first section comprises a fairly comprehensive description of the roof maintenance problem and expected outcomes, as described by a roof maintenance expert. The purpose is not to train any individual to be come a roof maintenance expert, rather to demonstrate that the decision made by such an expert can be broken down into realistic components and subsequently acted upon. Because they can be broken down, it is possible to replicate and create an expert system able to make decision (at least in part) based on the values immediately available. The second section concentrates on actual implementation. Firstly a prototype using desktop resources is described, then the re-development for Palm devices. Within this section, the decision process and steps taken are described – which will hopefully prevent others making some of the errors made in getting this far. Section 3 describes the outcomes and directions that may be taken in the future. There are many things that can be done to improve interface design and make things easier for the end user– the roof maintenance expert.
Publisher: University of Otago
Research Type: Other