Title: A new process for mining spatial databases: combining spatial data mining and visual data mining

Authors: Mohammed Midoun; Hafida Belbachir

Addresses: Department Informatique, Université des Sciences et de la Technologie Oran Mohamed Boudiaf, El Mnaouar, BP 1505 Oran, Algeria ' Department Informatique, Université des Sciences et de la Technologie Oran Mohamed Boudiaf, El Mnaouar, BP 1505 Oran, Algeria; Lab LSSD, Université des Sciences et de la Technologie Oran Mohamed Boudiaf, El Mnaouar, BP 1505 Oran, Algeria

Abstract: Spatial data mining (SDM) is a complex process of automatic exploration of spatial data. Unlike the SDM process, the visual data mining (VDM) process uses visualisation for exploratory purposes at all levels of the knowledge discovery process. In this article, we propose a new process for mining large spatial databases. This consists of combining the process of SDM and VDM in one and the same global approach. On the other hand, we propose, a methodological study, trying to combine the methods of SDM with several techniques of visualisation. For each applied SDM method, we use several visualisation techniques and compare the performance of these techniques. To validate our approach, two case studies are proposed. The first is to apply the proposed data mining process to the analysis of electoral results in Algeria. The second case study will involve applying the process to urban planning in the Mostaganem department in Algeria.

Keywords: spatial data mining; SDM; visual data mining; VDM; geographic information system; GIS; visual analytics.

DOI: 10.1504/IJBIS.2022.120366

International Journal of Business Information Systems, 2022 Vol.39 No.1, pp.17 - 51

Received: 07 Dec 2018
Accepted: 08 Jun 2019
Published online: 18 Jan 2022 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article