Design and development of a generic spatial decision support system, based on artificial intelligence and multicriteria decision analysis

Irfan, Muhammad ORCID: https://orcid.org/0000-0001-7991-1154, Koj, Aleksandra ORCID: https://orcid.org/0000-0002-5294-2492, Sedighi, Majid and Thomas, Hywel ORCID: https://orcid.org/0000-0002-3951-0409 2017. Design and development of a generic spatial decision support system, based on artificial intelligence and multicriteria decision analysis. GeoResJ 14 , pp. 47-58. 10.1016/j.grj.2017.08.003

Preview

PDF - Accepted Post-Print Version Available under License Creative Commons Attribution Non-commercial No Derivatives. Download (1MB) | Preview

Abstract

A new integrated and generic Spatial Decision Support System (SDSS) is presented based on a combination of Artificial Intelligence and Multicriteria Decision Analysis techniques. The approach proposed is developed to address commonly faced spatial decision problems of site selection, site ranking, impact assessment and spatial knowledge discovery under one system. The site selection module utilises a theme-based Analytical Hierarchy Process. Two novel site ranking techniques are introduced. The first is based on a systematic neighbourhood comparison of sites with respect to key datasets (criterions). The second utilises multivariate ordering capability of one-dimensional Self-Organizing Maps. The site impact assessment module utilises a new spatially enabled Rapid Impact Assessment Matrix. A spatial variant of General Regression Neural Networks is developed for Geographically Weighted Regression (GWR) and prediction analysis. The developed system is proposed as a useful modern tool that facilitates quantitative and evidence based decision making in multicriteria decision environment. The intended users of the system are decision makers in government organisations, in particular those involved in planning and development when taking into account socio-economic, environmental and public health related issues.

Item Type:	Article
Date Type:	Publication
Status:	Published
Schools:	Engineering
Subjects:	G Geography. Anthropology. Recreation > GE Environmental Sciences H Social Sciences > H Social Sciences (General) H Social Sciences > HD Industries. Land use. Labor > HD61 Risk Management
Uncontrolled Keywords:	Site Selection; Site Impact Assessment; Self-Organizing Maps; General Regression Neural Networks; Rapid Impact Assessment Matrix; Analytical Hierarchy Process;
Publisher:	Elsevier
ISSN:	2214-2428
Funders:	WEFO
Date of First Compliant Deposit:	29 August 2017
Date of Acceptance:	23 August 2017
Last Modified:	07 Jan 2024 18:12
URI:	https://orca.cardiff.ac.uk/id/eprint/104061

Citation Data

Cited 6 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item