Clustering of Mixed data: A GKMM approach
Journal Title: International Journal of Advanced Biotechnology and Research. - Year 2016, Vol 7, Issue 2
Abstract
ABSTRACTClustering is important problem in data mining techniques. k-Means algorithm is one of the most capable and easy to employ clustering algorithm but having some difficulties i.e. applicable to numeric data, sensitive to the presence of noise and outliers and have initialisation issues. This paper proposed GKMM algorithm to cluster mixed data where the pre-processed data will be used for the clustering to overcome the limitation of local solution and handle only numeric data issues. This work is based on the concept of utilisation of numeric data based genetics clustering algorithm for mixed data and can be an easier alternative to reduce cost and helpful in optimizing performance. Moreover, decrease obvious sensitivity to the initial guess of the cluster centres.
Authors and Affiliations
Abha Sharma*1 and R. S. Thakur2
Keywords
Related Articles
- EP ID EP159634
- DOI -
- Views 76
- Downloads 0
MENTAL DISORDERS AND FUNDAMENTAL SPACE TIME GEOMETRY AT PLANCK SCALE: A HYPOTHESIS
The effect of nitrogen and phosphorous quantities on the major components of Matricaria recutita L. including chamazulene and apigenin 7- glycoside
ABSTRACT In order to investigate the effect of nitrogen (0, 50, 100 and150) and phosphorous (triple super phosphate (TSP)) (0, 75, 150 and 225 kg/ha) quantities on the quantities of major components in Matricaria recut...
OPTIMIZATION OF PROCESS PARAMETERS FOR THE PRODUCTION OF CYCLODEXTRIN GLYCOSYLTRANSFERASE BY NEWLY ISOLATED BACILLUS SP. TPR71H BY CONVENTIONAL METHOD
Zoning Acoustic of Khalkhal City in winter and Summer
ABSTRACT Since the first automobile emerged, pollution in urban areas has become an issue that is still largely unresolved. Many people complain about traffic noise. Noise is unwanted sound and it is one of the main co...
Efficient Recombinant Strategy for the Production of Enfuvirtide In E.coli