Catálogo de publicaciones - libros

The describes a biological network or system that facilitates detoxification and removal from the body of harmful xenobiotic and endobiotic compounds. While life scientists have developed a relatively comprehensive understanding of this system, many mechanistic details are yet to be discovered. Critical mechanisms are those which are likely to significantly further our understanding of the fundamental components and the interaction patterns that govern this systems gene expression and the identification of potential regulatory nodes. Our working assumption is that a creative information exploration of available bile acid and xenobiotic system information could support the development (and testing) of novel hypotheses about this system. To explore this we have set up an information space consisting of information from biology and finance, which we consider to be two semantically distant knowledge domains and therefore have a high potential for interesting bisociations. Using a cross-context clustering approach and outlier detection, we identify bisociations and evaluate their value in terms of their potential as novel biological hypotheses.

Bisociative knowledge discovery - finding useful, previously unknown links between concepts - is a vital tool in unlocking the economic and social value of the vast range of networked data and services that is now available. An important application for bisociative knowledge discovery is business process analysis, where bisociation could lead to improvements in one domain being disseminated to other domains. We identify two forms of bisociation, based on structural similarity, that are applicable to business processes, and present examples using real-world data to show how bisociative reasoning can be applied.

Surprising a user with unexpected and fortunate recommendations is a key challenge for recommender systems. Motivated by the concept of bisociations, we propose ways to create an environment where such serendipitous recommendations become more likely. As application domain we focus on music recommendation using MusicGalaxy, an adaptive user-interface for exploring music collections. It leverages a non-linear multi-focus distortion technique that adaptively highlights related music tracks in a projection-based collection visualization depending on the current region of interest. While originally developed to alleviate the impact of inevitable projection errors, it can also adapt according to user-preferences. We discuss how using this technique beyond its original purpose can create distortions of the visualization that facilitate bisociative music discovery.