Title: Soft prediction model for spatial data analysis

Authors: J. Velmurugan; M. Venkatesan

Addresses: School of Computing Science and Engineering, VIT University, Vellore, India ' School of Computing Science and Engineering, VIT University, Vellore, India

Abstract: A natural disaster causes huge loss in terms of people life and infrastructures. Landslide is one of the prime disasters in the hill regions such as Uttarakhand, Sikkim and Ooty in India. The extent of damages of landslide could be reduced or minimised by proposing novel landslide risk analysis model. Landslide is generated by various factors such as rainfall, soil, slope, land use and land covers, geology, etc. Data science and soft computing plays major role in landslide risk analysis. In this paper, classification data science technique is integrated with rough set model and soft Bayesian prediction model (SBPM) is proposed to analyse the possibilities of various landslide risk level at Coonor Taluk of Niligiri district. The proposed model is validated with real time data and performance is compared with other classification models.

Keywords: geographical information system; GIS; rough set; Bayesian; landslide; disaster.

DOI: 10.1504/IJGENVI.2018.091465

International Journal of Global Environmental Issues, 2018 Vol.17 No.2/3, pp.130 - 143

Received: 15 Oct 2016
Accepted: 11 Apr 2017

Published online: 01 May 2018 *

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