Two States Mapping Based Time Series Neural NetworkModel for Compensation Prediction Residual Error

摘要

The objective of this paper was to design a model of human bio signal data prediction system for decreasing ofprediction error using two states mapping based time series neural network BP (back-propagation) model. Normally, a lotof the industry has been applied neural network model by training them in a supervised manner with the error back-propagation algorithm for time series prediction systems. However, it still has got a residual error between real value andprediction result. Therefore, we designed two states of neural network model for compensation residual error which ispossible to use in the prevention of sudden death and metabolic syndrome disease such as hypertension disease andobesity. We determined that most of the simulation cases were satisfied by the two states mapping based time seriesprediction model. In particular, small sample size of times series were more accurate than the standard MLP model.