Image-Based Learning Approach Applied to Time Series Forecasting

Abstract

In this paper, a new learning approach based on time-series image information is presented. In order to implement

this new learning technique, a novel time-series input data representation is also defined. This input data

representation is based on information obtained by image axis division into boxes. The difference between this new

input data representation and the classical is that this technique is not time-dependent. This new information is

implemented in the new Image-Based Learning Approach (IBLA) and by means of a probabilistic mechanism this

learning technique is applied to the interesting problem of time series forecasting. The experimental results indicate

that by using the methodology proposed in this article, it is possible to obtain better results than with the classical

techniques such as artificial neuronal networks and support vector machines.