DEVICE AND METHOD FOR GENERATING ARTIFICIAL NEURAL NETWORK-BASED PREDICTION MODEL

摘要

The present invention relates to an artificial neural network-based prediction model generation device comprising: an input data conversion unit for converting L (L is a natural number) dimensional array input data into normalized vector data so as to input the same into a modeling unit; the modeling unit, which models an artificial neural network-based prediction model for learning the inputted vector data, and outputs a prediction value through modeling; and an adjusting unit for calculating an error value by comparing, with an actual measurement value, the prediction value by means of the modeling unit, and adjusting a learning parameter of an artificial neural network through a back propagation algorithm by using the error value.