An Approach to the Development of Hybrid Architecture of Expert Systems
The knowledge acquisition process is a crucial stage in the technology of expert systems. However, this process is not well defined. One of the promising structured source of learning can be found in the recent work on neural network technology. Neural network can serve as a knowledge base of exp...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Language: | English English |
| Published: |
1999
|
| Subjects: | |
| Online Access: | http://psasir.upm.edu.my/id/eprint/9629/1/FSKTM_1999_3_IR.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The knowledge acquisition process is a crucial stage in the technology of expert
systems. However, this process is not well defined. One of the promising structured
source of learning can be found in the recent work on neural network technology.
Neural network can serve as a knowledge base of expert system that does
classification tasks. The combination of these two technologies emerges new
systems called neural expert systems. Neural expert systems allow us to generate a
knowledge base automatically from training examples. Also, they have an ability to
handle partial and noisy data. Despite the advances of these systems, debugging
their knowledge bases is still a big problem. Neural networks still have some
problems such as providing explanation facilities, managing the architecture of
network and accelerating the training time. The concept of a rough set bas been proposed as a new mathematical tool to deal
with uncertain and imprecise data. Using this tool to approach the problem of data
reduction and data dependency has emerged as a powerful technique in applications
of expert systems, decision support systems, machine learning, and pattern
recognition. Two methods based on rough set analysis were developed and merged
with the development of neural expert systems forming a new hybrid architecture of
expert systems called a rough neural expert system. The first method works as a preprocessor
for neural network. within the architecture, and it is called a pre-processing
rough engine, while the second one was added to the architecture for building a new
structure of inference engine called a rough neural inference engine. Consequently, a
new architecture of knowledge base was designed. This new architecture was based
on the connectionist of neural network and the reduction of rough set analysis.
The proposed design was implemented using an environment of object-oriented
programming. Four objects and three modules were developed using C++
programming language. The performance of the proposed system was evaluated by
an application to the field of medical diagnosis using a real example of hepatitis
diseases. Data for this application was obtained from researchers working on a
related study. Also, the proposed work. was compared with some related works. The
comparing results indicate that the new methods have improved the inference
procedures of the expert systems. The findings from this study have showed that this
new architecture has some properties over the conventional architectures of expert
systems. |
|---|