An adaboost-modified classifier using particle swarm optimization and stochastic diffusion search in wireless IoT networks

Abstract

The main objective of Internet of Things (IoT) is connecting with different objects via Internet without human intervention. Wireless Sensor Networks (WSNs) which involves ubiquitous computing through which small sensors are connected to the Internet and are used for collecting data. Significant amount of information flowing in the internet is made up of sensory data. To resolve the storage issues of the huge data generated by IoT, the Hadoop Distributed File System are used that streams data to user applications as required. It is difficult to accomplish analysis of vast amount of data (big data) with existing data processing methods. To avoid redundant and irrelevant data, the data needs to be classified. This work presents the use of Support Vector Machine, and Adaboost classifiers, and modifying Adaboost classifier with Genetic Algorithm (GA), Stochastic Diffusion Search (SDS), and Particle Swarm Optimization (PSO). To avoid redundant classifiers, an ensemble algorithm is proposed in this work, PSO with Adaboost classifier and SDS-GA with Adaboost classifier, that can reinitialize attributes, thus avoiding reaching local optimum, and optimizing the coefficients of Adaboost weak classifiers. The proposed algorithms effectively classify the data gathered from WSN and IoT applications. The outcomes of the experiment showed that the proposed SDS-GA algorithm is efficient over other algorithms with respect to accuracy, precision, recall, f measure and false discovery rate.