James F. Peters (U of Manitoba, Canada)

TITLE: Near Sets: A New Approach to Perceptual Object Recognition

DATE: May 14, 11:20am-12:10pm

ABSTRACT: The problem considered in this paper is how to approximate sets of objects that are qualitatively but not necessarily spatially near each other. The term qualitatively near is used here to mean closeness of descriptions or distinctive characteristics of objects. The solution to this problem is inspired by the work of Zdzislaw Pawlak during the early 1980s on the classification of objects by means of their attributes. In working toward a solution of the problem of the approximation of sets that are qualitatively near each other, this article considers an extension of the basic model for approximation spaces. The basic approach is to consider a link relation, which is defined relative to measurements associated with features shared by objects independent of their spatial relations. The proposed approach to approximation of sets of objects is a straightforward extension of the rough set approach, where approximation can be considered in the context of families of information granules (neighborhoods). A byproduct of the proposed approximation method is what we call a near set. It should also be observed that what is presented in this paper is considered a special (not a general) theory about nearness of objects. The contribution of this article is an approach to nearness as a vague concept which can be approximated from sample objects and domain knowledge.

Chengqi Zhang (U of Technology, Sydney, Australia)

TITLE: Activity Mining to Strengthen Debt Prevention

DATE: May 14, 12:10pm-1:00pm

ABSTRACT: Activity data accumulated in real life, e.g. in terrorist activities and fraudulent customer contacts, presents special structural and semantic complexities. However, it may lead to or be associated with significant business impacts. For instance, a series of terrorist activities may trigger a disaster to the society; large amounts of fraudulent activities in social security program may result in huge government customer debt. Mining such data challenges the existing KDD research in aspects such as unbalanced data distribution and impact-targeted pattern mining. This talk investigates the characteristics of activity data and the methodologies of activity mining. Activity mining aims to discover impact-targeted activity patterns in huge volumes of unbalanced activity transactions. Activity patterns identified can prevent disastrous events or improve business decision making and processes. We illustrate issues and prospects in mining governmental customer contacts to strengthen debt prevention.

Bernhard Ganter (TU Dresden, Germany)

TITLE: Computing with Formal Concepts

DATE: May 14, 3:00pm-3:50pm

ABSTRACT: Formal Concept Analysis is a mathematical theory that offers a formalization of "concept" and "conceptual hierarchy". It has a rich methodology, based on the algebraic theory of complete lattices. It also has a tradition of applications in many areas. One of its strong sides is that it offers solid mathematical tools also for non-numerical data. Another one is that its visualizations are intuitive even for those users who have not studied the theoretical background. The author focuses on questions of knowledge exploration. A key issue here is how to design a compact, correct and complete representation of certain well limited areas of knowledge. For the simplest case of implicational attribute logic there is a popular result guaranteeing the existence of a minimal base of information. This result can, with some loss of elegance, widely be generalized and thereby be made more useful for applications. Examples will be indicated. The generalized versions can be made practical, since there are algorithms and implementations available. However, some basic theoretical problems (such as complexity problems) remain unsolved.