PREDICTING PEAK PINCH STRENGTH - ARTIFICIAL NEURAL NETWORKS VS REGRESSION

Cumulative trauma disorders (CTDs) of the upper extremities are one of the major ergonomics areas of research. Pinching is a common risk fac tor associated with the development of hand/wrist CTDs. The capacity s tandards of peak pinch strength for various postures are needed to des ign the tasks in harmony with the workers. This paper describes the fo rmulation, building and comparison of pinch strength prediction models that were obtained using two approaches: Statistical and artificial n eural networks (ANN). Statistical and ANN models were developed to pre dict the peak chuck pinch strength as a function of different combinat ions of five elbow and seven shoulder flexion angles, and several anth ropometric and physiological variables. The two modeling approaches we re compared. The results indicate ANN models to provide more accurate predictions over the standard statistical models. Relevance to industr y The proposed ANN approach to prediction modeling, as an alternative to traditional statistical modeling approach for predicting peak pinch strength, increases prediction accuracy, and thus improves the effect iveness of task and workplace designers, toward the prevention of occu pational CTDs.