Artificial Bee Colony Reinforced Extended Kalman Filter Localization Algorithm in Internet of Things with Big Data Blending Technique for Finding the Accurate Position of Reference Nodes.

Abstract

In recent years, the growth of internet of things (IoT) is immense, and the observations of their evolution need to be carried out effectively. The development of the IoT has been broadly adopted in the construction of intelligent environments. There are various challenging IoT issues such as routing messages, addressing, Localizing nodes, data blending, etc. Formerly learning eloquent information from big data systems to construct a data-gathering setup in an IoT environment is challenging. Among many viable data sources, the IoT is a rich big data source: Various IoT nodes produce a massive quantity of data. Localization is one of the crucial problems that make a significant impact inside the IoT system. It needs to be engaged with proper and effective procedures to collect all sorts of data without noise. Numerous localization procedures and schemes have been initiated by deploying the IoT sensor with wireless sensor networks for both interior and outside environments. To accomplish higher localization accuracy, with less cost for the large volume of data, it is considered a hectic task in the IoT sensor environment. By viewing the nature of the IoT, the merging of different technologies such as the internet, WiFi, etc., can aid diverse ways to acquire information about various objects' locations. Location-based service is an exceptional service of the IoT, whereas localization accuracy is a significant issue. The data generated from the sensor are available in both static and dynamic forms. In this article, a sophisticated accuracy localization scheme for big data is proposed with an optimization approach that can effectively produce proper and effective outcomes for IoT environments. The theme of the article is to develop an enriched Swarm Intelligence algorithm based on Artificial Bee Colony by using the EKF (Extended Kalman Filter) data blend technique for improving Localization in IoT for the unsuspecting environment. The performance of the proposed algorithm is evaluated by using communication consumption and Localization accuracy and its comparative advantage.