The proposed IKMN+ algorithm, a modification of the incrementalKMN uses this best distance measure to obtain a partition-based clustering. Our findings revealed that IKNM+ could overcome the issue of initial centroid selection ofk-means algorithm and provides good performance in clustering several ...
In this paper, three partition-based algorithms, PAM, CLARA and CLARANs are combined with k-medoid distance based outlier detection to improve the outlier detection and removal process. The experimental results prove that CLARANS clustering algorithm when combined with medoid distance based outlier ...
K-means algorithm dependence on partition-based clustering technique is popular and widely used and applied to a variety of domains. K-means clustering results are extremely sensitive to the initial centroid; this is one of the major drawbacks of k-means algorithm. Due to such sensitivity; ...
To solve the problem, this paper presents a spatial distance-based spatial clustering algorithm for sparse image data (SDBSCA-SID). Firstly, the imaging range of the image sensor constitutes a two-dimensional (2D) constraint space. Under the constraint, spatial clustering was carried out based ...
Vijay, Ritu, Prerna Mahajan, and Rekha Kandwal. "Hamming Distance based Clustering Algorithm."International Journal of Information Retrieval Research2, no. 1 (January 2012): 11–20. http://dx.doi.org/10.4018/ijirr.2012010102. Full text ...
space. Finally, the local convergence of the algorithm is proved using the Zangwill theorem and bordered Hessian matrix. The experimental results demonstrate that the proposed algorithm has good segmentation performance and strong noise resistance. Compared with existing segmentation algorithms based on ...
[ 11 ]. this is the most frequent situation when the partitions compared where produced by clustering algorithms. the clustering algorithm needs an inter-entity distance matrix, and this matrix is sufficient to derive the intercluster distances used for rar computation. when the partitions are ...
The appropriate measure should be chosen according to the requirement of the clustering algorithm, the type of data (continuous, ordinal, nominal, binary, count or mixed), and whether the data have outliers (e.g., Manhattan distance is less sensitive to outliers compared with Euclidean distance)...
Constrained clustering is becoming an increasingly popular approach in data mining. It offers a balance between the complexity of producing a formal definition of thematic classes—required by supervised methods—and unsupervised approaches, which ignore expert knowledge and intuition. Nevertheless, the appl...
In order to give a better understanding of the GBLD method, Algorithm 1, containing three algorithms, is provided to show the most prominent steps in the calculation of GBLD score. Three inner algorithms of Algorithm 1 are the components of Eq. 7. The main objective of this Algorithm is ...