A Novel Context-Aware Computing Framework with the Internet of Things and Prediction of Sensor Rank Using Random Neural XG-Boost Algorithm

The amount of sensors being used worldwide is gradually increasing as the Internet of Things (IoT) draws closer. According to market data, sensor deployments have grown significantly over the last decade, and the pace of expansion is expected to accelerate. Massive amounts of information are being produced by these sensors continually. However, before we can add value to raw sensor data, we must first comprehend it. This challenge involves gathering, modeling, interpreting, and communicating sensor data context. In sensor data analysis, context-aware computation has been proven successful. Relevance is defined by the user's job when a system uses context to provide necessary details and resources to a user. In this paper, we propose a novel IoT context-aware system for predicting the rank of sensors based on context data. Fuzzy Logic-based Contextual Defensible Reasoning (FL-CDR) is presentedusing Random Neural XG-Boost Algorithm to Predict Sensor Rank in a Novel Context-Aware Computing Framework with the Internet of Things.The proposed is proved effective in ranking the sensors based on the context data. Using the XGBoost algorithm achieves the maximum accuracy by 97.03% and the lowest latency by 15%.