acsFSDPC: A Density-Based Automatic Clustering Algorithm with an Adaptive Cuckoo Search
Clustering has gained increasing attention in the data mining field since it plays an important role in the unsupervised classification of samples. While numerous clustering methods have been proposed, these suffer from various limitations including sensible parameter dependence and difficult identification of the number of clusters. In this paper, an automatic density-based clustering method based on an adaptive cuckoo search (acsFSDPC) was proposed. Data points with higher density and larger distance from other data points are assumed as clustering centers. Firstly, an adaptive cuckoo search algorithm is employed using clustering evaluation index as fitness function to determine the optimal cutoff distance for each cluster number. Then, the cluster number with the minimal fitness function value is chosen as the best number of clusters and the corresponding clustering result is the optimal clustering results. The benefits of acsFSDPC are automatic estimation of cluster number and optimal cutoff distance. Experiments of acsFSDPC and its comparison with other recent methods STClu, ACND, CH-CCFDAC, and LR-CFDP are performed on five simulation data sets and a real data set. Results show that the acsFSDPC is promising in estimating the appropriate number of clusters automatically and effectively.
KeywordsAdaptive cuckoo search Automatic clustering Cutoff distance Fitness function
This work was in part supported by the National Natural Science Foundation of China (61502272, 61572284), the Science and Technology Planning Project of Qufu Normal University (xkj201410), the Scientific Research Foundation of Qufu Normal University (BSQD20130119).
- 3.Guo, P., Wang, X., Wang, Y., Cheng, Y., Zhang, Y.: Research on automatic determining clustering centers algorithm based on linear regression analysis. In: International Conference on Image, Vision and Computing, pp. 1016–1023 (2017)Google Scholar
- 6.Zhou, R., Zhang, S., Chen, C., Ning, L., Zhang, Y., Feng, S., Liu, Y., Luktarhan, N.: A Distance and density-based clustering algorithm using automatic peak detection. In: IEEE International Conference on Smart Cloud, pp. 176–183 (2016)Google Scholar
- 7.Yan, H., Lu, Y., Ma, H.: Density-based clustering using automatic density peak detection. In: International Conference on Pattern Recognition Applications and Methods, pp. 95–102 (2018)Google Scholar
- 8.Yang, X.S., Deb, S.: Cuckoo search via Lévy flights. In: World Congress on Nature & Biologically Inspired Computing, NaBIC 2009, pp. 210–214 (2010)Google Scholar
- 10.Ong, P.: Adaptive cuckoo search algorithm for unconstrained optimization. Sci. World J. (9) (2014). https://doi.org/10.1155/2014/943403
- 11.Naik, M., Nath, M.R., Wunnava, A., Sahany, S., Panda, R.: A new adaptive Cuckoo search algorithm. In: IEEE International Conference on Recent Trends in Information Systems, pp. 1–5 (2015)Google Scholar