Neural Network Training on Human Body Core Temperature Data

A multi-layer Adaptive Linear Element neural network computer program was trained with back-propagation on physiological response data from nine subjects walking on a treadmill in two simulated tropical environments. The 100 minute end-point body core temperatures calculated were compared to the measured responses. It was found that although correlation was low and simultaneous high specificity and sensitivity were not displayed, the results were comparable to the predictions from an established human thermal response prediction programme for these subjects. It is concluded that the neural network modelling technique has merit in this field and should be explored further as more data become available.