Title :
Prediction of human static and dynamic strengths by modified basic GMDH algorithm
Author_Institution :
Dept. of Mech. & Ind. Eng., Cincinnati Univ., OH, USA
Abstract :
The basic group method of data handling (GMDH), with some modifications, is applied to predict human static and dynamic strengths as a function of body size. It is indicated by a comparison between GMDH models (not time-series models) and traditional regression models that GMDH improves strength prediction accuracy while using relatively fewer predictors (body size parameters). Employee screening and placement procedures for jobs requiring exertion of physical strength are simplified by this method.
Keywords :
biomechanics; forecasting theory; physiological models; GMDH algorithm; accuracy; body size; dynamic strengths; employee screening; group method of data handling; human; physical strength; prediction; static strength; Circuit faults; Humans; Inspection; Polynomials; Predictive models; Printed circuits; Visualization;
Journal_Title :
Systems, Man and Cybernetics, IEEE Transactions on
DOI :
10.1109/TSMC.1984.6313301