< Back to previous page

Publication

A Framework for Low-Level Data Fusion

Book Contribution - Chapter

© 2019 Elsevier B.V. Modern empirical science relies more and more on acquiring data. This has been accelerated by the developments in instrumental measurement methods allowing for collecting data in a high-throughput and relatively cheap way. Although this development has certainly created a big advantage for science, it has also created a big challenge: how to analyze such data? When multiple data blocks are measured on the same system, then it is worthwhile to analyze those data blocks simultaneously to arrive at a global view of that system. This problem analyzing multiple related data blocks simultaneously has already a long history in data analysis with many proposed methods but has experienced a revival in the last decade because of the reasons mentioned earlier. Depending on the specific field of data analysis, the methods to deal with this problem are called multiset methods, multiblock methods, data integration, or data fusion methods, to name a few. In this chapter, we present two frameworks for data fusion. The first framework includes a generic account of an important subset of the class of so-called low-level model-based data fusion methods. The second framework focuses on a subset of the methods subsumed by the first framework to separate the variation in multiblock data in common and distinct parts. We illustrate both frameworks with real-life examples from metabolomics.
Book: Data Fusion Methodology and Applications
Pages: 27 - 50
ISBN:0444639845
Publication year:2019
Accessibility:Closed