Type-2 Fuzzy Rule-Based Expert System for Diagnosis of Spinal Cord Disorders

Document Type: Article

Authors

1 Department of Industrial Engineering, Amirkabir University of Technology, Tehran, Iran

2 Knowledge Intelligent System Laboratory, University of Toronto, Toronto, Canada

3 Fayyazbakhsh and Erfan Hospitals, Tehran, Iran

Abstract

The majority of people have experienced pain in their low back or neck in their lives. In this paper a type-2 fuzzy rule based expert system is presented for diagnosing the spinal cord disorders. The interval type-2 fuzzy logic system permits us to handle the high uncertainty of diagnosing the type of disorder and its severity. The spinal cord disorders are studied in five categories using historical data and clinical symptoms of the patients. The main novelty of this paper lies in presentation of the interval type-2 fuzzy hybrid rule-based system, which is a combination of the forward and backward chaining approaches in its inference engine and avoids unnecessary medical questions. Using of parametric operations for fuzzy calculations increases the robustness of the system and the compatibility of the diagnosis with a wide range of physicians’ diagnosis. The outputs of the system are comprised of type of disorder, location and severity as well as the necessity of taking a M.R. Image. A comparison of the performance of the developed system with the expert shows an acceptable accuracy of the system in diagnosing the disorders and determining the necessity of the M.R. Image.

Keywords

Main Subjects

Scientia Iranica

Volume 26, Issue 1
Transactions on Industrial Engineering (E)
January and February 2019
Pages 455-471

Files

Share

How to cite

Statistics