A robust fuzzy approach for gene expression data clustering

In the big data era, clustering is one of most popular mining method. Most algorithms have complications like automatic cluster number determination, poor precision, inconsistent various datasets and parameter-dependent, etc. A new fuzzy autonomous solution for named Meskat-Mahmudul (MM) algorithm was proposed to overcome complexity parameter-free determination accuracy. The finds out exact clusters based on average silhouette method in multivariate mixed attribute dataset, including real-time gene expression dataset missing values, noise, outliers. Extended K-Means (MMK) enhances algorithm, which serves purpose discovery runtime placement. Several validation methods are used evaluate certify optimum partitioning perfection. Some assess performance other terms time efficiency. Finally, were found superior over conventional algorithms.