Image-Based Learning Approach Applied to Time Series Forecasting
Main Article Content
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.