Data handling in data fusion: Methodologies and applications

The use of data fusion methodologies has increased at the same rhythm as the capability of modern analytical laboratories of measuring sample from multiple sources. Almost all data fusion strategies can be grouped into three levels, they fuse the data differently with the sole aim of obtaining a better response (qualitative or quantitative) than that obtained by the instruments individually. One of the major key points for the data fusion methodologies to succeed is the understanding of the data structure obtained from a particular instrument. This point is not exhaustively commented in the literature focused on data fusion, sometimes paying too much attention to the algorithms instead. This manuscript explains data fusion from the structure of the different data obtained by different analytical platforms. Special attention will be given to the nature of the data and the relationships between the samples and the variables, as well as within the variables.