FUZZY MODELING AND ANALYTIC HIERARCHY PROCESSING - MEANS TO QUANTIFY RISK LEVELS ASSOCIATED WITH OCCUPATIONAL INJURIES .2. THE DEVELOPMENT OF A FUZZY RULE-BASED MODEL FOR THE PREDICTION OF INJURY

This paper presents the second phase in a two-part research project to develop a fuzzy rule-based expert system for predicting occupational injuries of the forearm and hand. Analytic hierarchy processing (AHP) is used to assign relative weights to the identified risk factors. A f uzzy rule base is constructed with all of the potential combinations f or the given factors. The input parameters are linguistic variables ob tained in the first part of the research. These inputs are fuzzified a nd defuzzified to provide two system outputs: a linguistic value and a numeric value as a prediction of injury. The system provides linguist ic risk levels as well as quantified risks in assessing the overall ri sk of injury. The system evaluation was conducted resulting in calcula tions for Type I and Type II errors. The contributions and limitations of the system are discussed.