Application of bioelectrical impedance sensing techniques for dengue infection with non-linear autoregressive model

Abstract

This paper discussed novel system identification for bioelectrical impedance measurement parameter for monitoring dengue infections by using nonlinear AR (NAR) based on Artificial Neural Network (ANN). Bioelectrical impedance measurement indicate the volume of Hb of the subjects and NAR model with regularized approach yields better accuracy by 80.60% for bioelectrical impedance sensing method. In building the model, three parameter were considered; the final prediction error (FPE), Akaike’s Information Criteria (AIC), and Lipschitz number.