Gaussian Kernels Case Study

2428 Words10 Pages
CHAPTER IV 4. PROPOSED RESEARCH METHOD 4.1 INTRODUCTION This research work proposed significant improvements of the DENCLUE for Gaussian kernels. The DENCLUE method employs a cluster model based on kernel density estimation and a cluster is densed by a local maximum of the estimated density function. Data points are assigned to a cluster by hill climbing, i.e. points going to the same local maximum are put into the same cluster. The traditional density estimation methods consider only the location of the point, not variable_of_interest and hence hill climbing makes unnecessary small steps in the beginning and never converges exactly to the maximum. The hill climbing procedure for Gaussian kernels, which adjust the step size automatically. The proposed DENCLUE method does really converge towards a local maximum. 4.2 PROBLEM STATEMENT…show more content…
In density based clustering, queries are not supported efficiently to reduce the number of clustering. The density based clustering is influenced by the density divergence problem that affects the accuracy of clustering and cannot choose its parameter according to distribution of the data set. Traditional density estimation method is considered the location of the point, not variable of interest and hill climbing may make unnecessary small steps in the beginning and never converges exactly to the maximum. In the proposed DENCLUE method, the clusters are formed based on the location of an object and variable_ of_ interest. The proposed DENCLUE method mainly focuses on finding outlier, an increasing accuracy and an improving cluster quality. To achieve the mentioned efficiency by reducing the number of

More about Gaussian Kernels Case Study

Open Document