Cluster analysis is one of the popular data mining techniques and it is defined as the process of grouping similar data. K-Means is one of the clustering algorithms to cluster the numerical data. The features of K-Means clustering algorithm are easy to implement and it is efficient to handle large amounts of data. The major problem with K-Means is the selection of initial centroids. It selects the initial centroids randomly and it leads to a local optimum solution. Recently, nature-inspired optimization algorithms are combined with clustering algorithms to obtain the global optimum solution. Crow Search Algorithm (CSA) is a new populationbased metaheuristic optimization algorithm. This algorithm is based on the intelligent behaviour of the crows. In this paper, CSA is combined with the K-Means clustering algorithm to obtain the global optimum solution. Experiments are conducted on benchmark datasets and the results are compared to those from various clustering algorithms and optimization-based clustering algorithms. Also the results are evaluated with internal, external and statistical experiments to prove the efficiency of the proposed algorithm.

This study uses data mining techniques for computer-aided diagnosis that involves the feature extraction for cancer detection, so as to help doctors towards making optimal decisions quickly and accurately. Features play an important role in detecting the cancer in the digital mammogram and feature extraction stage is the most vital and difficult stage. In this paper, an enhanced feature extraction method named Multiscale Surrounding Region Dependence Method (MSRDM) is proposed to be effective in classifying the mammogram images into normal or benign or malignant. This proposed system is based on a four-step procedure: Regions of Interest specification, two dimensional discrete wavelet transformation, and multiscale surrounding region dependence matrix computation and feature extraction. The performance of the proposed feature set is compared with the conventional texture-analysis methods such as gray level cooccurence matrix features and surrounding region dependence method features. Experiments have been conducted on both real and benchmark data and the results have been proved to be progressive.

No abstract

No abstract

No abstract