Abstract

Geographic Information Systems along with Remote Sensing have aided almost all the areas ranging from Mining, Geosciences, Hydrology, Fisheries, and Environmental to Economical, Socio-Economical, Health and many additional domains. Interpolations like Splines, Inverse Distance Weighting, and Kriging being very important components of GIS are widely applied in the field of geosciences. The general task of these interpolations is to predict or estimate the variables of interest at unknown locations, which is usually done through Simple Kriging, Ordinary Kriging, Universal Kriging, Point Kriging, Block Kriging, Punctual Kriging, Kriging with External Drifts and other hybrid Kriging methods. Whereas for educational datasets Data Mining algorithms have been widely used to predict student’s behavior, performance, forecast admissions for future academic year etc. No attempts as yet has been made to predict unknown educational parameters at unknown locations using Kriging. Thus this study is first ever effort to test the feasibility of applying Kriging on educational datasets. Therefore the basic aim of this study is to highlight the extent of application of Kriging especially Ordinary Kriging on educational datasets. To accomplish this task the paper first highlights various areas where Kriging have been applied, then describes about the secondary data that were obtained in the form of overall results of GTU (Gujarat Technological University) for July’2010 examination of thirty two MCA institutes of Gujarat. Descriptive statistics of the thirty two institutes was carried out and then Semivariogram was plotted and variograms were fitted using Spherical and Exponential models. Further Ordinary Kriging was applied on a sample of five institutes to predict the results of these sample institutes. The simulated results obtained from Kriging were then compared with actual results and RMSE, MSE were used to check the validity of these models. Predicted results show that results of three institutes show no significant differences whereas for other two there were significant differences. Extensive use of R-3.2.0 is made, which is a free software environment for statistical computing and graphics along with the use of package geoR and gstat in the present work for all the basic statistical and geostatistical calculations. Therefore the study opens up a platform for applying Kriging on educational datasets using FOSS4G. Keywords: Data mining, Educational,FOSS, GIS, Interpolations, Kriging, Remote Sensing,Semivariogram, Variogram

Download full paper here

Application of Ordinary Kriging on Educational Data using FOSS4G

Copyright © 2015. All Rights Reserved.

Tagged on:                                 

Leave a Reply

Your email address will not be published. Required fields are marked *