While fuzzy c-means may be a fashionable soft cluster method, its effectiveness is essentially restricted to spherical clusters. By applying kernel tricks, the kernel fuzzy c-means algorithmic program attempts to deal with this downside by mapping knowledge with nonlinear relationships to acceptable feature areas. Kernel combination, or choice, is crucial for effective kernel cluster. Unfortunately, for many applications, it’s harsh to seek out the right combination. We have a tendency to propose a multiple kernel fuzzy c-means (MKFC) algorithmic program that extends the fuzzy c-means algorithmic program with a multiple kernel learning setting. By incorporating multiple kernels and mechanically adjusting the kernel weights, MKFC is more proof against ineffective kernels and impertinent options. This makes the selection of kernels less crucial. Additionally, we show multiple kernel k-means (MKKM) to be a special case of MKFC. Experiments on artificial and real-world knowledge demonstrate the effectiveness of the planned MKFC algorithmic program. he proposed algorithmic program is straightforward to implement and provides soft clustering results that area unit proof against orthogonal, redundant, ineffective, and unreliable options or kernels. Experiments show that the tactic effectively incorporates multiple kernels and yields higher overall performance. These characteristics build it helpful for real-world applications