Computational & Technology Resources
an online resource for computational,
engineering & technology publications |
|
Civil-Comp Proceedings
ISSN 1759-3433 CCP: 78
PROCEEDINGS OF THE SEVENTH INTERNATIONAL CONFERENCE ON THE APPLICATION OF ARTIFICIAL INTELLIGENCE TO CIVIL AND STRUCTURAL ENGINEERING Edited by: B.H.V. Topping
Paper 11
Managing Risk through Fuzzy Logic D. Baloi
Department of Civil Engineering, Eduardo Mondlane University, Maputo, Mozambique D. Baloi, "Managing Risk through Fuzzy Logic", in B.H.V. Topping, (Editor), "Proceedings of the Seventh International Conference on the Application of Artificial Intelligence to Civil and Structural Engineering", Civil-Comp Press, Stirlingshire, UK, Paper 11, 2003. doi:10.4203/ccp.78.11
Keywords: decision, fuzzy logic, knowledge-based systems, repertory grid, risk, risk factors, risk management.
Summary
Risk management is a vital project management planning and control tool
and its role has increasingly been recognised as a mechanism for reducing
uncertainty, improving decision making and thus maximising opportunities, [1].
Uncertainty is indeed a major obstacle to effective decision-making in
construction management and efforts must be channeled to the development
of innovative decision models towards its reduction and thus increase the
quality of decisions and project success.
This paper reports initial findings of a research project on the development of a knowledge-based decision support system for risk management within construction organisations. The study focuses on global risk factors affecting construction cost performance. The management of global risk factors affecting cost performance is a typical poorly-structured decision-making problem. Poorly-structured problems are complex because the available information is often imprecise, incomplete and there are no specific algorithms/procedures that can help to derive a solution [2]. The paper presents and discusses the application of Fuzzy Logic technology as a means for handling uncertainty within knowledge-based systems. Several others uncertainty management mechanisms, such as Probability Theory, Dempster-Shafer Theory of Evidence, and Certainty Factors were evaluated. Knowledge-based systems are deemed to have additional capabilities than traditional decision support systems. The knowledge based system incorporates three modules namely analytical models, database modules and knowledge-base modules. Analytical models were derived from management science techniques, the databases were built from data elicited from construction contractors and the knowledge-base was derived through the application of Repertory Grid technique. The process of knowledge acquisition, analysis and representation was largely dealt with through the employment of the Repertory Grid technique. Repertory grid is a technique taken from cognitive psychology and it provides a means to produce a person's mental map on specific topic or domain [3]. The application of Fuzzy Logic is an innovative approach in managing uncertainty in contrast to the traditional Probability Theory. In addition, Repertory Grid technique is a new way of knowledge elicitation compared to the conventional interviews. Both the inputs and outputs of the knowledge based system are qualitative and in natural language, which facilitates its use and understanding. The system can be an important tool for contractors to increase their awareness, identify global risk factors affecting cost performance, assess their impact and likelihood and take appropriate measures in order to reduce their impact on cost performance. Preliminary conclusions drawn from the study indicate that Fuzzy Logic can be used to manage uncertainty in knowledge-based systems. Furthermore, Repertory Grid technique is a powerful technique for eliciting knowledge. Further work is however needed to refine, verify and validate the tools. References
purchase the full-text of this paper (price £20)
go to the previous paper |
|