Adaptive fuzzy clustering based on Genetic algorithm
Zhu Lianjiang, Shouning Qu, Tao Du · 2010
Traditional Fuzzy c-means (FCM) algorithm is commonly used in unsupervised learning. However, there are some limitations. Cluster number should be determined and the cluster center should be initialized before classification. A new algorithm is proposed in the paper. The best cluster number is obtained by analyzing cluster validity function and the cluster center is initialized by HCM. The data set is classified with Fuzzy c-means algorithm based on Genetic algorithm. The experimental results indicate the effectiveness and adaptability of the new algorithm.