A virtual mart for knowledge discovery in databases

Abstract

The Web has profoundly reshaped our vision of information management and processing, enlightening the power of a collaborative model of information production and consumption. This new vision influences the Knowledge Discovery in Databases domain as well. In this paper we propose a service-oriented, semantic-supported approach to the development of a platform for sharing and reuse of resources (data processing and mining techniques), enabling the management of different implementations of the same technique and characterized by a communitycentered attitude, with functionalities for both resource production and consumption, facilitating end-users with different skills as well as resource providers with different technical and domain specific capabilities. We first describe the semantic framework underlying the approach, then we demonstrate how this framework is exploited to give different functionalities to users through the presentation of the platform functionalities.

Collaborative management of a repository of KDD processes

“…In order to address problems due to a distributed settings and heterogeneity of tools and users, our approach is aimed at formally describe algorithms into an ontology, named KDDONTO (Diamantini et al (2013)), which includes: the task achieved by the algorithm, the KDD phase in which it is commonly used, the search method it implements for achieving its task, some suggestions about algorithms that can be executed before or after it. Moreover, the I/O interface is described together with the preconditions that such I/O data must satisfy in order to be actually used, and performance indexes.…”

“…Since there are many tools available for the same task and they typically have heterogeneous interfaces, we manage integration and reuse of such tools by describing them with open formats (i.e., XML-based). For KDD tools we adopt KDTML (Diamantini et al (2013)), an XML-based open descriptor, aimed at annotating a tool (written in every language and even legacy software) through a set of metadata, in order to describe its details, including its interface, in a structured fashion. Finally, in our platform each KDD service is described by an extended-SAWSDL (eSAWSDL, Diamantini et al (2013)), that is a fullycompatible SAWSDL (Semantic Annotations for WSDL) descriptor with some additional details.…”

“…In this paper we take such a perspective, by proposing a user-and knowledgecentric approach for the sharing and (re-)use of KDD computational resources and processes in KDDVM (KDD Virtual Mart), a collaborative environment where both resources and users are distributed and heterogeneous. In a previous work (Diamantini et al (2013)) we discussed support functionalities for semi-automatic process design and composition, while here the emphasis is put on how semantic technologies and an open approach are capable to enable the sharing and reuse of resources (from single analysis tools to whole processes). In particular, in the context of the KDDVM platform, we discuss how to build and manage a repository of services and a repository of processes.…”

Business Intelligence and the Web

“…As stated by Diamantini et al (2013) in their article "A Virtual Mart for Knowledge Discovery in Databases," this new collaborative vision influences one of the most powerful processes in BI: knowledge discovery from databases. Specifically, the authors propose a service oriented, semantics-supported approach for knowledge discovery in database in which both production and consumption of data processing and mining techniques are provided.…”

A Process to Implement an Artificial Neural Network and Association Rules Techniques to Improve Asset Performance and Energy Efficiency

“…Indeed, to deal with such an amount of data, the application of appropriate algorithms for data understanding and knowledge extraction is necessary. In this context, an important contribution is provided by Knowledge Discovery in Databases (KDD) techniques: analyzing a massive amount of data, KDD's goal is to extract useful information and derive knowledge [12,13]. Data Mining (DM) techniques belong to the KDD domain and, according to [14], they regard the discovery of hidden information and patterns, as well as relationships in large databases [15].…”