Developing Information Granules for Intelligent Data Analysis and Decision-Making Processes

讲座内容：Information granules play a pivotal role in acquiring, representing, processing, and communicating knowledge at a suitable level of abstraction. Designing information granules is central to all pursuits of Granular Computing.

The presentation offers a comprehensive and systematically structured overview of methodologies and algorithms of designing information granules along with a suite of representative applications in data analysis and decision-making. The taxonomy embraces two main categories of data-driven and knowledge-oriented approaches. We introduce and discuss a principle of justifiable granularity, which serves as a key design vehicle facilitating a formation of information granules completed on a basis of available experimental evidence. Recent advances of the principle are discussed including (i) a collaborative version of the principle supporting data analysis carried out in the presence of distributed data, (ii) context-based version of the principle incorporating auxiliary sources of knowledge, and (iii) its hierarchical version facilitating handling experimental evidence being available at several levels of specificity (abstraction). A collection of design scenarios supporting a formation of hierarchies of information granules of higher type and higher order is presented.

In the realm of data analysis, we discuss a collaborative mode of discovery of relationships and a granular summarization of findings quantified in the language of information granules. We advocate the role of information granules ingroup decision-making highlighting a mechanism of calibration of individual decision-making models augmented by a granular knowledge transfer. We discuss matching mechanisms realized through information granules.