Image-Based learning approach applied to time series forecasting

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.