29 August 2016 Clustering by exponential density analysis and find of cluster centers based on genetic algorithm
Author Affiliations +
Proceedings Volume 10033, Eighth International Conference on Digital Image Processing (ICDIP 2016); 1003362 (2016) https://doi.org/10.1117/12.2244868
Event: Eighth International Conference on Digital Image Processing (ICDIP 2016), 2016, Chengu, China
Abstract
Finding the optimal solution to the problem of selecting clustering centers and improving the performance of existing density-based clustering algorithms, a novel clustering method is proposed in this paper. Our algorithm discovers data clusters according to cluster centers that are identified by a higher density than their nearby points and by a comparatively large distance from points with higher density, and then it finds optimal cluster centers by iteration based on genetic algorithm. We present an exponential density analysis to reduce the impact of model parameters and introduce a penalty factor in order to overcome the excursion of search region for accelerating convergence. Experiments on both artificial and UCI data sets reveal that our algorithm achieves results on Rand Statistic competitive with a variety of classical algorithms.
© (2016) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Dong Kun, Wang Ze, Zhang Rui, Yin Chao, "Clustering by exponential density analysis and find of cluster centers based on genetic algorithm", Proc. SPIE 10033, Eighth International Conference on Digital Image Processing (ICDIP 2016), 1003362 (29 August 2016); doi: 10.1117/12.2244868; https://doi.org/10.1117/12.2244868
PROCEEDINGS
6 PAGES


SHARE
Back to Top