The standard approach to integrating heterogeneous information sources is to build a global schema that relates all of the information in the different sources, and to pose queries directly against it. The problem is that schema integration is usually difficult, and as soon as any of the information sources change or a new source is added, the process mayhave to be repeated. The SIMS system uses an alternative approach. A domain model of the application domain is created, establishing a fixed vocabulary for describing data sets in the domain. Using this language, each available information source is described. Queries to SIMS against the collection of available information sources are posed using terms from the domain model, and reformulation operators are employed to dynamically select an appropriate set of information sources and to determine how to integrate the available information to satisfy a query. This approach results in a system that is more flexible than existing ones, more easily scalable, and able to respond dynamically to newly available or unexpectedly missing information sources.

. Data analysis is needed in connection with query processing, to

xi 1 Introduction 1 1.1 Semantic Query Optimization : : : : : : : : : : : : : : : : : : : : : : 3 1.2 High Utility Semantic Knowledge for SQO : : : : : : : : : : : : : : : 6 1.3 Learning Effective and Robust Rules : : : : : : : : : : : : : : : : : : 8 1.4 Closely Related Work : : : : : : : : : : : : : : : : : : : : : : : : : : : 10 1.5 Summary of Contributions : : : : : : : : : : : : : : : : : : : : : : : : 12 1.6 Organization of the Dissertation : : : : : : : : : : : : : : : : : : : : : 13 2 Robustness of Knowledge 15 2.1 Consistency of Rules and Database Changes : : : : : : : : : : : : : : 15 2.2 Definitions of Robustness : : : : : : : : : : : : : : : : : : : : : : : : : 18 2.3 Estimating Robustness : : : : : : : : : : : : : : : : : : : : : : : : : : 19 2.4 Templates for Estimating Robustness : : : : : : : : : : : : : : : : : : 26 2.5 Empirical Demonstration : : : : : : : : : : : : : : : : : : : : : : : : : 27 2.6 Related Uncertainty Measures : : : : : : : : : : : : : : : : : : : ...

and Poster Session. In Section 5.3 we indicate that rule interest measures up to date are not accurate and introduce a necessary condition for interestingness. This work has also been accepted for presentation at the Fifteenth National Conference on Artificial Intelligence (AAAI-98) Student Abstract and Poster Session. In Section 5.4 we introduce the idea of fuzzy metaquery and justify that it can be useful as a integration tool for knowledge discovery systems. This work has been presented at the Sixth IEEE International Conference on Fuzzy Systems (FUZZIEE-97). Finally, in Section 5.5 we explain two components that we are actually developing. 5.1 Distance-Based Discretization Discretization is a process that transforms continuous attributes into discrete ones. Performing this previous step, we can apply discrete classification methods to datasets containing continuous values. We have developed a discretization method, based on the idea of distance between partitions. In this section...

Recent years have seen an explosive growth in the quantity of information that is available. The need for automated techniques to deal with the information overload problem is clear. The ability of users to quickly locate items that meet their own specific needs is crucial. Recommender systems have now been widely and successfully implemented, particularly in e-commerce applications, as a solution to this problem. One of the most

this article is organised as follows. We begin with a discussion of collaborative recommendation and a formalisation of the notions of robustness and the perturbations with which we are concerned (Section 2). We then analyse robustness from both the accuracy and stability perspectives. Regarding accuracy, in Section 3 we formalise robustness in machine learnings terms, and introduce a novel form of class noise that models an interesting suite of attacks. We develop two models that predict the change in accuracy as a function of the number of fake ratings that have been inserted into the customer/product matrix. Regarding stability, we present a framework that describes the stability of a recommendation system subjected to various forms of attack (Section 4). In both cases, we empirically evaluate our predications against several real-world data-sets. We conclude with a description of related work (Section 3.4) and with a summary of our results and a discussion of several open issues (Section 5)