Efficient Dimensionality Reduction for Big Data Using Clustering Technique

— Clustering is unsupervised classification of patterns (observations, data items, or feature vectors) into teams (clusters). The drawbacks of clustering has been addressed in several contexts by researchers in several disciplines and so reflects its broad charm and quality in concert of the steps in exploratory data analysis. Clustering is useful in several exploratory pattern analysis, grouping, machine learning and making decisions as well as situations including data mining, document retrieval, image segmentation and pattern classi fication. We are living in a digital world. Every day, people generate massive amount of data and store it, for further analysis and management. The amount of knowledge in our world has been exploding. Big Data refers to extremely large datasets that may be analyzed computationally to reveal patterns, trends, and associations especially relating to human behavior and interactions. Due to the short growth of such information, solutions need to be studied so as to handle and extract price and information from these data sets. Therefore an analysis of the different classes of available clustering techniques with big datasets may provide significant and useful conclusions. The proposed system is to study and analyze some of the popular existing clustering techniques and impact of dimensionality reduction on Big Data.