K-Means Clustering Algorithms: Implementation and Comparison

Abstract

The relationship among the large amount of biological data has become a hot research topic. It is desirable to have clustering methods to group similar data together so that, when a lot of data is needed, all data are easily found in close proximity to some search result. Here we study a popular method, k-means clustering, for data clustering. We implement two different k-means clustering algorithms and compare the results. The two algorithms are Lloyd's k-means clustering and the progressive greedy k-means clustering. Our experimentation compares the running times and distance efficiency.