Efficient Big Data Clustering Using Adhoc Fuzzy C Means and Auto-Encoder CNN

Abstract

Clustering, a well-known unsupervised machine learning technique is effective in handling massive amount of data for a variety of applications. Clustering is the process of grou** identical data into clusters that belong to a specific category. Big data consists of massive amounts of data generated every second; hence, clustering this data is quite challenging. Deep learning techniques are used to analyze large amounts of data, which necessitates the use of a large number of samples for training, resulting in a time-consuming and inefficient process. The adhoc fuzzy C means method can be used to overcome this limitation. In this research study, a fusion approach known as fusion clustering is built by combining auto-encoder features with adhoc fuzzy C means (AFCM) technique to improve the fusion approach. The auto-encoder, in combination with the CNN approach, is used for feature engineering to improve the performance, resulting in increased computational speed. The efficiency of the proposed model is improved by evaluating each performance metrics in detail by using three different data types: MNIST, Fashion-MNIST dataset, and USPS. The comparison of each dataset demonstrates that the proposed adhoc fuzzy C means (AFCM) model outperforms other state-of-the-art techniques.