Use this URL to cite or link to this record in EThOS:
Title: Multi criteria decision making methodology for fuzzy rule based systems and networks using TOPSIS
Author: Yaakob, Abdul Malek Bin
ISNI:       0000 0004 7224 133X
Awarding Body: University of Portsmouth
Current Institution: University of Portsmouth
Date of Award: 2017
Availability of Full Text:
Access from EThOS:
Access from Institution:
Fuzzy systems and networks are vital within the armoury of fuzzy tools and applicable to real life decision making environments. Three types of fuzzy systems introduced in literatures which are systems with single rule base, systems with multiple rule bases and system with networked rule bases. This research introduces novel extension of the Technique of Ordering of Preference by Similarity to Ideal Solution (TOPSIS) methods and uses fuzzy systems and networks to solve multi-criteria decision making problems where both benefit and cost are presented as subsystems. In conjunction, the implementation of fuzzy sets type-1, type-2 and Z-number of proposed approaches is also presented. Furthermore, literatures have observed that tracking the performance of criteria is crucial by controlling the estimation of uncertainty of the criteria. Thus, the decision maker evaluates the performance of each alternative and further observes the performance for both benefit and cost criteria. This research improves significantly the transparency of the TOPSIS methods while ensuring higher effectiveness in comparison to established approaches. Ensuring the practicality and the effectiveness of proposed methods in a realistic scenario, the problem of ranking traded stock is studied. This case study is conducted based on stocks traded in a developing financial market such as Kuala Lumpur Stock Exchange. The ranking based on proposed methods is validated comparatively using performance indicators such as Spearman Rho correlation, Kendall Tau correlation, Root Mean Square Errror and Average Absolute Distance by assuming ranking based on return on investment as a benchmarking. Based on the case study, the proposed methods outperform the established TOPSIS methods in term of average rank position.
Supervisor: Gegov, Alexander Emilov ; Bader-El-Den, Mohamed ; Chlebikova, Janka Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID:  DOI: Not available