Time filter

Source Type

Reddy M.V.J.,Madanapalle Institute of Technology and Science Madanapalle | Kavitha B.,P.A. College
2010 IEEE International Conference on Computational Intelligence and Computing Research, ICCIC 2010 | Year: 2010

Most previous clustering algorithms focus on numerical data whose inherent geometric properties can be exploited naturally to define distance functions between data points. However, much of the data existed in the databases is categorical, where attribute values cannot be naturally ordered as numerical values. Due to the differences in the characteristics of these two kinds of data, attempts to develop criteria functions for mixed data have been not very successful. In this research, we propose a novel divide-and-conquer technique to solve this problem. First, the original mixed dataset is divided into two sub-datasets: the pure categorical dataset and the pure numeric dataset. Next, existing well established clustering algorithms designed for different types of datasets are employed to produce corresponding clusters. Last, the clustering results on the categorical and numeric dataset are combined as a categorical dataset, on which the categorical data clustering algorithm is employed to get the final output. Our main contribution in this research is to provide an algorithm framework for the mixed attributes clustering problem, in which existing clustering algorithms can be easily integrated. © 2010 IEEE. Source

Avanthi P.,Madanapalle Institute of Technology and Science Madanapalle | Sreedevi M.,Madanapalle Institute of Technology and Science Madanapalle
International Journal of Applied Engineering Research | Year: 2015

Smart suggest search engine with Location Sensing Recommendation (LSR) is used to generate recommendations based on location-based ratings. The existing recommendation systems follow the traditional way to generate recommendations for user which does not consider the spatial properties. On contrary the proposed implementation location sensing recommendation offers three types of location-based ratings 1) spatial ratings for non-spatial items 2) non-spatial ratings for spatial items and 3) spatial ratings for spatial items. The proposed system follows a technique of user partitioning technique which influences the proposed recommendations along with the rating spatially close to the location of querying users in the way of maximizing the system scalability without sacrificing quality of the recommendations. It also follows a technique of travel penalty which is featured to produce recommendations to users based on closer in travel distance. Location sensing recommendation uses these techniques either together or separately based on the type of location-based ratings offered. The proposed system also uses a technique of k-means clustering for generating recommendations to users. © Research India Publications. Source

Discover hidden collaborations