gyssensQcharlie.luc.ac.be laksQcs.concordia.ca We present a multi-dimensional database model, which we believe can serve as a con-ceptual model for On-Line Analytical Pro-cessing (OLAP)-based applications. Apart from providing the functionalities necessary for OLAP-based applications, the main fea-ture of the model we propose is a clear sepa-ration between structural aspects and the con-tents. This separation of concerns allows us to define data manipulation languages in a rea-sonably simple, transparent way. In particu-lar, we show that the data cube operator can be expressed easily. Concretely, we define an algebra and a calculus and show them to be equivalent. We conclude by comparing our ap-proach to related work. The conceptual multi-dimensional database model developed here is orthogonal to its im-plementation, which is not a subject of the present paper. 1

Multidimensional databases support efficiently on-line analytical processing (OLAP). In this paper, we depict a model dedicated to multidimensional databases. The approach we present designs decisional information through a constellation of facts and dimensions. Each dimension is possibly shared between several facts and it is organised according to multiple hierarchies. In addition, we define a comprehensive query algebra regrouping the more popular multidimensional operations in current commercial systems and research approaches. We introduce new operators dedicated to a constellation. Finally, we describe a prototype that allows managers to query constellations of facts, dimensions and multiple hierarchies. 1

Abstract. This research work is aimed at the development of data analysis strategy in a com-plex, multidimensional, and dynamic domain. Our universe of discourse is concerned with the data mining techniques of data warehouses revealing the importance of multivariate structures of social-economic data which influence criminality. Distinct tasks require different data structures and various data mining exercises in data warehouses. The proposed problem solution strategy allows choosing an appropriate method in recognition processes. The ensembles of diverse and ac-curate classifiers are constructed on the base of multidimensional classification and clusterisation methods. Factor analysis is introduced into data mining process for revealing influencing impacts of factors. The temporal nature and multidimensionality of the target object is revealed in dynamic model using multidimension regression estimates. The paper describes the strategy of integrating the methods of multiple statistical analysis in cases, where a great set of variables is observed in short time period. The demonstration of the data analysis strategy is performed using real social and economic development of data warehouses in different regions of Lithuania. Key words: multidimensional statistical methods, data mining, data warehouse, social-economical indicators, criminality.

Abstract not found

ESPLORIS: exploring multi-source statistical information systems through metadata