Enhancing Clustering Techniques with Hybrid Optimization

In today's creation, there is a demand to evaluate and withdraw intelligence from data. Clustering is a particular method that analytically affects the circulation of data into a class of exact objects. Each one class formed as a reflex is recognized as a cluster, which dwells of objects that have favor in the cluster and inequality with the objects in alternative troops. The present project intends to dig into and evacuate data clustering design using hybrid combination to provide optimization. One of the most known's algorithms is the k-means clustering algorithm which is zestfully enforced to innumerable disputes. Here the algorithm comes with benefits like high-speed and ease of employment, but it encounters the problem of local optimal. So, a hybrid combination of the Fuzzy c-Means Clustering Algorithm along with Particle Swarm Optimization can be used for optimization and better results. Fuzzy clustering is a common problem that leads to effective exploration in a few realistic practices. Fuzzy c-means (FCM) algorithm comes with merit like most used, productive, frank, and effortless performance. As known FCM is very susceptible to load, also it gets ambushed in native capital. To solve many breakthrough problems Particle swarm optimization (PSO) is the solution. In this paper, we have tried a combination of fuzzy clustering approaches. Fuzzy Particle Swarm Optimization can be combined so that we can try taking benefits from both these methods.