Predicting peak pinch strength: Artificial neural networks vs. regression
Proceedings of the 1995 10th Annual International Industrial Ergonomics and Safety Conference, Seattle, WA, USA, 01 Haziran 1995, cilt.18, ss.431-441, (Tam Metin Bildiri)
- Yayın Türü: Bildiri / Tam Metin Bildiri
- Cilt numarası: 18
- Doi Numarası: 10.1016/0169-8141(95)00106-9
- Basıldığı Şehir: Seattle, WA, USA
- Sayfa Sayıları: ss.431-441
- Anahtar Kelimeler: Artificial neural networks (ANN), Cumulative trauma disorders (CTDs), Ergonomic intervention, Modeling, Pinch strength, Predictive models
- Boğaziçi Üniversitesi Adresli: Hayır
Özet
Cumulative trauma disorders (CTDs) of the upper extremities are one of the major ergonomics areas of research. Pinching is a common risk factor associated with the development of hand/wrist CTDs. The capacity standards of peak pinch strength for various postures are needed to design the tasks in harmony with the workers. This paper describes the formulation, building and comparison of pinch strength prediction models that were obtained using two approaches: Statistical and artificial neural networks (ANN). Statistical and ANN models were developed to predict the peak chuck pinch strength as a function of different combinations of five elbow and seven shoulder flexion angles, and several anthropometric and physiolgical variables. The two modeling approaches were compared. The results indicate ANN models to provide more accurate predictions over the standard statistical models. Relevance to industry. 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 effectiveness of task and workplace designers, toward the prevention of occupational CTDs. Cumulative trauma disorders (CTDs) of the upper extremities are one of the major ergonomics areas of research. Pinching is a common risk factor associated with the development of hand/wrist CTDs. The capacity standards of peak pinch strength for various postures are needed to design the tasks in harmony with the workers. This paper describes the formulation, building and comparison of pinch strength prediction models that were obtained using two approaches: Statistical and artificial neural networks (ANN). Statistical and ANN models were developed to predict the peak chuck pinch strength as a function of different combinations of five elbow and seven shoulder flexion angles, and several anthropometric and physiological variables. The two modeling approaches were compared. The results indicate ANN models to provide more accurate predictions over the standard statistical models.