Riadh Ben Messaoud

X-warehousing: an XML-based approach for warehousing complex data

XML is suitable for structuring complex data coming from different sources and supported by heterogeneous formats. It allows a flexible formalism capable to represent and store different types of data. Therefore, the importance of integrating XML documents in data warehouses is becoming increasingly high. In this paper, we propose an XML-based methodology, named X-Warehousing, which designs warehouses at a logical level, and populates them with XML documents at a physical level. Our approach is mainly oriented to users analysis objectives expressed according to an XML Schema and merged with XML data sources. The resulted XML Schema represents the logical model of a data warehouse. Whereas, XML documents validated against the analysis objectives populate the physical model of the data warehouse, called the XML cube.

Enhanced mining of association rules from data cubes

On-line analytical processing (OLAP) provides tools to explore and navigate into data cubes in order to extract interesting information. Nevertheless, OLAP is not capable of explaining relationships that could exist in a data cube. Association rules are one kind of data mining techniques which finds associations among data. In this paper, we propose a framework for mining inter-dimensional association rules from data cubes according to a sum-based aggregate measure more general than simple frequencies provided by the traditional COUNT measure. Our mining process is guided by a meta-rule context driven by analysis objectives and exploits aggregate measures to revisit the definition of support and confidence. We also evaluate the interestingness of mined association rules according to Lift and Loevinger criteria and propose an efficient algorithm for mining inter-dimensional association rules directly from a multidimensional data.

A new OLAP aggregation based on the AHC technique

Nowadays, decision support systems are evolving in order to handle complex data. Some recent works have shown the interest of combining on-line analysis processing (OLAP) and data mining. We think that coupling OLAP and data mining would provide excellent solutions to treat complex data. To do that, we propose an enhanced OLAP operator based on the agglomerative hierarchical clustering (AHC). The here proposed operator, called <i>OpAC</i> (Operator for Aggregation by Clustering) is able to provide significant aggregates of facts refereed to complex objects. We complete this operator with a tool allowing the user to evaluate the best partition from the AHC results corresponding to the most interesting aggregates of facts.

Efficient multidimensional data representations based on multiple correspondence analysis

In the On Line Analytical Processing (OLAP) context, exploration of huge and sparse data cubes is a tedious task which does not always lead to efficient results. In this paper, we couple OLAP with the Multiple Correspondence Analysis (MCA) in order to enhance visual representations of data cubes and thus, facilitate their interpretations and analysis. We also provide a quality criterion to measure the relevance of obtained representations. The criterion is based on a geometric neighborhood concept and a similarity metric between cells of a data cube. Experimental results on real data proved the interest and the efficiency of our approach.

A Data Mining-Based OLAP Aggregation of Complex Data: Application on XML Documents

Nowadays, most organizations deal with complex data that have different formats and come from different sources. The XML formalism is evolving and becoming a promising solution for modeling and warehousing these data in decision support systems. Nevertheless, classical OLAP tools still are not capable of analyzing such data. In this article, we associate OLAP and data mining to cope with advanced analysis on complex data. We provide a generalized OLAP operator, called OpAC, based on the AHC. OpAC is adapted for all types of data, since it deals with data cubes modeled within XML. Our operator enables significant aggregates of facts expressing semantic similarities. Evaluation criteria of aggregates’ partitions are proposed in order to assist the choice of the best partition. Furthermore, we developed a Web application for our operator. We also provide performance experiments and drive a case study on XML documents dealing with the breast cancer research domain.

Mining Association Rules in OLAP Cubes

On-line analytical processing (OLAP) provides tools to explore data cubes in order to extract interesting information. Nevertheless, OLAP is not capable of explaining relationships that could exist within data. Association rules are one kind of data mining techniques which finds associations among data. In this paper, we propose a framework for mining association rules from data cubes according to a sum-based aggregate measure which is more general than frequencies provided by the count measure. Our mining process is guided by a meta-rule context driven by analysis objectives and exploits aggregate measures to revisit the definition of support and confidence. We also evaluate the interestingness of mined association rules according to Lift and Loevinger criteria and propose an algorithm for mining inter-dimensional association rules directly from a multidimensional structure of data

Evaluation of a MCA-based approach to organize data cubes

In the OLAP context, exploration of huge and sparse data cubes is a tedious task that does not always lead to efficient results. We propose to use a Multiple Correspondence Analysis (MCA) in order to enhance data cube representations and make them more suitable for visualization and thus, easier to analyze. We also provide an original quality criterion to measure the relevance of the obtained data representations. Experimental results we led on real data samples have shown the interest and the efficiency of our approach.