Analytical space for data representation and interactive analysis
Computer Science Journal of Moldova, 10 (1):
59--80 (2002)Abstract
In the article the notion of analytical space is introduced and its application to data representation and interactive analysis is studied. Analytical space is defined through membership relation among its elements where each element is characterised by its extensional and intensional. All data element properties are derived from this fundamental relation. Inference in analytical space is thought of as finding mapping from one subspace into another and is carried out through propagation of information by means of deaggregation and aggregation operations. The general goal of data analysis is defined to be simplifying the form of representation with simultaneous retaining most of the data semantics. An interactive data analysis procedure is proposed, which is based on selecting interesting subspaces in analytical space, finding mapping from this space into the range of values by means of inference and finally visualising this mapping in an appropriate form.