Neural networks based approach to estimate body fat (%BF)

The amount of fat in human body compositi n relative to total body weight (%BF) is considered a determinant factor to a healt ier and longer life. In this paper a neural network approach, that overcomes some of the current limitations of assessing %BF through skinfold thickness measurement with cal liper devices, is presented. Neural networks recognised capabilities in modelling nonli near problems can provide a valuable tool to deal with the inherent nonlinear behaviour f body tissues. The approach was tested on a sample of elder individuals, men and wo men, showing better performance when compared with two available alternative method ol gies.