Data fusion is crucial in almost every application of artificial intelligence. Classification, image processing, decision-making, big data or deep learning require collecting data and fusing them in appropriate ways in order to solve specific problems. For this reason, a huge effort is devoted to the developments and analysis of data fusion methods.
Aggregation functions are one of the most widely used methods in this sense. They are defined as monotone functions with appropriate boundary conditions and include, among others, most of the means or functions such as the product, the minimum or the maximum. However, in recent years it has been shown that the concept of aggregation function can be too restrictive, as it does not cover some examples which can provide good results in particular applications, as it is the case of the mode. Furthermore, some data fusion functions more general than aggregations, the so called pre-aggregation functions, have been proposed to deal with problems ranging from classification to the computational brain, with very promising results.