Clustering Analysis of Fusion Similarity Calculation and Improved Genetic Algorithm

Aiming at the shortcomings of fuzzy C-means clustering analysis (FCM), which is easy to fall into the local minimum, and the sensitivity to the initial clustering center, this paper firstly used a density-based DBSCAN algorithm (ST-DBSCAN) to determine the number of clusters by calculating the distance and density between data. At the same time, based on the genetic simulated annealing algorithm (SAGA), this paper proposed a clustering analysis based on multi-population genetic simulated annealing algorithm. Firstly, it analyzed and evaluated FCM, and proposed the shortcomings of FCM in determining the number of clusters and clustering process. Then, it determined the number of clusters the ST-DBSCAN algorithm in the FCM. At the same time, it studied the genetic simulated annealing algorithm, and optimized the genetic simulated annealing algorithm by adding multiple groups of parallel genetic ideas. Finally, it combined FCM with a variety of genetic simulated annealing algorithms to optimize the clustering process. The experimental results show that the algorithm has better global search ability and convergence ability, and has certain advantages over traditional clustering algorithms in clustering effect and stability.

fuzzy C-means clustering analysis, ST-DBSCAN, genetic simulated annealing algorithm, multi-population genetic simulated annealing algorithm, number of clusters

Yuan Yao, Jin Feng, Clustering Analysis of Fusion Similarity Calculation and Improved Genetic Algorithm. 2019 5th International Conference on Advanced Computing, Networking and Security (ADCONS 2019). 2019: 32-38.