Recommendation of Optimal Locations for Government Funded Educational Institutes in Urban India Using a Hybrid Data Mining Technique

Abstract

The Government of India has introduced schemes to build educational facilities in areas where literacy rate is less than the national average. It was found that literacy rate is a sufficient criterion with respect to rural areas but a different approach must be taken for urban planning because of space constraints, heterogeneous communities and the varied background of children living in urban areas. A hybrid data mining method to discover optimum locations for educational facilities in urban areas is proposed. The method is a combination of rule-based classification and spatial clustering. Rule-based classification is used to identify relevant data points from the spatial data set. New parameters like dropout rate and ratio of children out of school to children in school are introduced to measure relevance since literacy rate alone was found to be an insufficient criterion. Spatial clustering is used to group the points according to their location. The center of each cluster signifies the optimum location for an educational facility. A modified COD-CLARANS method is proposed. The algorithm is modified in two aspects. It is proposed that the absolute error, E, is calculated using the shortest path of commute on city roads rather than the obstructed distance calculated in the pre-processing step of the original COD-CLARANS algorithm. Secondly, only areas with space available for the establishment of a facility are considered to represent clusters. The modified method seeks improve efficiency and to make the spatial clustering technique more relevant to the urban setting. A comparison between different clustering algorithms and the modified COD-CLARANS algorithm is presented. � 2015 IEEE.