ABSTRACT
Social Internet of Things (SIoT) supports several applications and networking services for the Internet of Things (IoT) in a much powerful and productive way. SIoT is a larger social networking site, providing link among people and objects. Therefore, several studies have been presented to improve data gathering, cleaning, storage, and real-time analytics. This chapter presents a new big data analytics method in SIoT using butterfly optimization based feature selection with gradient boosting tree (GBT) technique called BOAFS-GBT. The proposed BOAFS-GBT model initially performs feature selection using BOAFS model, which elects a useful set of features from the big data. Then, GBT model is used for the classification of the feature-reduced data into several classes. Besides, big data Hadoop framework has been employed for big data processing. The results of the BOAFS-GBT model has been validated against three dataset and the obtained results notified the effective performance by attaining maximum accuracy of 97.88% on GPS trajectories dataset, 96.87% on movement prediction, and 94.88% on water treatment dataset.
