Computational intelligence: imperfect information representation, integration and optimal querying, and rule based reasoning under uncertainty, incompleteness and inconsistency with multivalued logics

This theme addresses the problem of representing and reasoning with imperfect information using a logical approach based on multivalued logics, as well as the integration and querying of information coming from different sources, in a distributed environment.

Motivation comes from the area of knowledge acquisition, representation, and reasoning based on imperfect knowledge. Indeed, in the real world information may be incomplete or may have a bounded level of certainty and on the other hand contradictions may occur during the process of integrating information coming from various sources as it is the case of collecting knowledge from different experts. In multi-agent systems, different agents may give different answers to the same query. It is then important to be able to process the answers so as to extract the maximum of information on which the various agents agree, or to detect the items on which the agents give conflicting answers. Incompleteness, uncertainty and inconsistency of the information may be treated by using ready to employ hypotheses when information is completely missing, and multivalued logics based on the algebraic concept of bilattice, when information is incomplete, uncertain or inconsistent.

In our framework the information concerns the truth values of information items, and is obtained through queries to the relevant sources. The answers of such queries are combined or integrated using a set of rules. In such a setting, imperfect information i.e. incomplete, uncertain information from a source, or contradictory information coming from different sources, can elegantly be expressed and dealt with using bilattices and an approach of reasoning based on rules whose semantics is natural in these bilattice based multivalued logics.

A connected research direction we tackle concerns the problem of optimal querying of imperfect information. Conventional techniques based on the concept of homomorphism have traditionally been used in database research to study the containment of queries evaluated against conventional data. We have extended and generalized these techniques such that the problem of query containment and equivalence (essential in optimal query evaluation) can be successfully studied in the context of sources containing imperfect information.

Applications in knowledge acquisition and representation, intelligent systems, logic based fuzzy agent systems and imperfect information integration and querying.

Data mining & Machine learning: dimensionality reduction, data sampling and design of new clustering/segmentation techniques

We have introduced an approach to reducing dimensions in data and data clustering inspired from computational models used to evaluate economical parameters. In particular the techniques of dimensionality reduction are based on calculating the highest risk or in other words the lowest return associated with each attribute in the dataset.

Research under development concerns the crystallization, formulation and implementation of new segmentation techniques for large datasets based on three phases that make the process more tractable and insure a good clustering quality. In particular the initial and the final phases make the process scalable since they are optimised for processing large data fragmentally, while the middle phase, whose role is to enhance clustering quality of the result passed from the initial phase, is performed only on data which are wholly resident in main memory, since the middle phase is computationally intensive. These techniques, currently designed for numerical data, need to be extended to nominal and mixed data.

Applications in data pre-processing and segmentation, knowledge discovery in databases.

Back to Daniel Stamate's homepage