Professor Ngoc Thanh Nguyen
Ph.D., D.Sc., ACM Distinguished Scientist
Head of Knowledge Management Systems Division
Institute of Informatics
Wroclaw University of Technology, Poland
Editor-in-Chief of Transactions on Computational Collective Intelligence - Springer 
Email: Ngoc-Thanh.Nguyen@pwr.edu.pl
Homepage: http://www.ii.pwr.wroc.pl/~nguyen/




Computational Collective Intelligence and Knowledge Inconsistency in Multi-agents Environments
Computational Collective Intelligence (CCI) is understood as an AI sub-field dealing with soft computing methods which enable making group decisions or processing knowledge among autonomous units acting
in distributed environments. Web-based systems, social networks and multi-agent systems very often need these tools for working out consistent knowledge states, resolving conflicts and making decisions. In
this talk I will present several aspects related to the answers of the following questions: Is the intelligence of a collective larger than the intelligence of its members? How to determine the knowledge of a collective on the basis of the knowledge of its members? How to evaluate the quality of the collective knowledge? Many examples show that the knowledge of a collective is not a usual union of the knowledge of its
members. For multi-agent environments, in case of some conflict between agents referring to the proper knowledge of a real world, CCI tools may be very useful for reconciling the inconsistency and processing the knowledge of agents.

Rough Classification: Algorithms and Applications
Rough classification methods, in general, serve to determining a set of attributes which generate an approximate classification referring to a given classification. In the Pawlak’s concept of rough classification for a given classification C of set U of objects a rough classification is the approximation of C. Assume that classification C is generated by set B of attributes, then the approximation of C is based on determining a
proper subset B’ of B such that the classification generated by B’ differs “a little” from C. The small difference between these classifications is illustrated by the difference of their accuracy measures which
should not be larger than some threshold. In our approach we consider other problem of rough classification: For a given classification of set U which is generated by set A of attributes, one should determine such minimal set B of attributes from A that the distance between the classification generated by attributes from B and the given classification is minimal. In this talk an approach for using rough classification methods to perform recommendation processes in intelligent e-learning systems is
presented. Rough classification in this case is related to inconsistency aspect of knowledge of the system. The inconsistency here appears in two aspects: In the first aspect inconsistency refers to difference of the
passed scenarios of similar learners (belonging to the same class of the classification). In this case to determine an opening scenario for a new learner it is needed to calculate the consensus of the passed scenarios of the members of the class. The second aspect of inconsistency refers to the fact that assumed to be similar learners (belonging to the same class of the classification) may have very miscellaneous passed scenarios. This, in turn, may cause a lack of efficiency of the procedure proposed for the first
aspect. Here we propose to use a rough classification based method to redefine the criterion for classification. Apart from the application in e-learning systems, another application of the rough classification methods will be also presented referring to designing adaptive user interfaces.

How to Use Inconsistency of Knowledge in Determining Knowledge of a Collective?
There are two aspects of knowledge inconsistency: Centralization aspect and Distribution aspect. The first of them is based on inconsistency of different elements of the same knowledge base, and the second is
related to inconsistency of different knowledge bases referring to a common subject. The focused point of this talk concerns the second aspect. The subject of this speech is included in Computational Collective
Intelligence (CCI) which is understood as an AI sub-field dealing with soft computing methods which enable making group decisions or processing knowledge among autonomous units acting in distributed environments. Web-based systems, social networks and multi-agent systems very often need these tools for working out consistent knowledge states, resolving conflicts and making decisions. In this talk several aspects related to the answers of the following questions will be presented: Is the knowledge of a
collective more proper than the knowledge of its members? How to determine the knowledge of a collective on the basis of the knowledge of its members? How to evaluate the quality of the collective knowledge? Many examples show that the knowledge of a collective is not a usual union of the knowledge of its members. It turned out that the inconsistency degree of the knowledge of collective’s members can have essential influence on the knowledge of this collective.