FDM: Fuzzy-Optimized Data Management Technique for Improving Big Data Analytics

Abstract

Big data analytics and processing require complex architectures and sophisticated techniques for extracting useful information from the accumulated information. Visualizing the extracted data for real-time solutions is demanding in accordance with the semantics and the classification employed by the processing models. This article introduces fuzzy-optimized data management (FDM) technique for classifying and improving coalition of accumulated information based semantics and constraints. The dependency of the information is classified on the basis of the relationships modeled between the data based on the attributes. This technique segregates the considered attributes based on similarity index boundaries to process complex data in a controlled time. The performance of the proposed FDM is analyzed using a real-time weather forecast dataset consisting of sensor data (observed) and image data (captured). With this dataset, the functions of FDM such as input semantics analytics and classification based on similarity are performed. The metrics classification and processing time and similarity index are analyzed for the varying data sizes, classification instances, and dataset records. The proposed FDM is found to achieve 36.28% less processing time for varying classification instances, and 12.57% high similarity index.