Improving neighborhood construction with Apollonius region algorithm based on density for clustering

Abstract

Listen

Translate article

With the rapid rate of information flow today, local identification of similar data points has gained greater significance for information processing in various branches of sciences. Geometric methods are especially useful because of their accuracy in locating similar neighborhood points by means of geometric structures. Geometric methods are not accurate enough for large scale data sets. Because of the persistent serious challenges in data point analysis, we have used a geometric method in which the Apollonius circle is been utilized to achieve high local accuracy. This paper proposes a neighborhood construction algorithm, termed Neighborhood Construction with Apollonius Region Density (NCARD). The neighbors of data points are determined not only by using geometric structures but also by means of density information. For efficient clustering, in comparison with the previous methods, the proposed algorithm can work better for high dimensional data; it is also able to identify local outlier data. Moreover, after locating similar data points with Apollonius circle, we will extract density and relationship among the points leading to a unique and rather accurate neighborhood. The proposed algorithm is more accurate than the state-of-the-art and well-known algorithms up to almost 8–13% in real and artificial data sets.