Assessing Human Performance Influencing Factors through LINMAP and Bayesian Belief Networks

This study aims at identifying and ranking the performance influencing factors (PIFs) that cause error in human operations. The failure weight rate for tasks carried out by each operator were investigated. Assessing these reduces error, hence increasing safety, efficiency job satisfaction. methods of linear programming technique multidimensional analysis preference (LINMAP) Bayesian Belief Networks used to investigate an aircraft tire manufacturing industry. All operators workshops evaluated. Based on data analysis, weighted potential task was obtained. PIFs workshop ranked prioritized so having most influence can be easily distinguished where have highest failure, identified. probability obtained a predictive model, it determined when occurs, which are influential its occurrence. method utilized does not include copious pairwise, exhausting times confusing comparisons operators.