Chapter 20 - A real-time performance monitoring model for processing of IoT and big data using machine learning

Abstract

In this chapter, a real-time monitoring model that uses IoT-based sensors, big data handling, and hybrid model is proposed. In the current scenarios, an IoT-based sensor that gathers temperature, mugginess, accelerometer, and spinner information was created. The qualities of IoT-created sensor information from the assembling procedure are continuous, huge sums, and unstructured sort. The proposed huge information preparing stage uses Apache Kafka as a message line. Besides, for the proposed crossover forecast model, density-based spatial clustering of applications with noise (DBSCAN)-based exception location and random forest characterization were utilized to expel anomaly sensor information and give issue recognition during the assembling procedure, separately. The Proposed model is inspired by a model that was applied and tested at an automotive manufacturing assebly [21]. The outcomes demonstrated that IoT-based sensors and the proposed large information handling framework are adequately effective to screen the assembling procedure. The proposed framework is required to help the board by improving dynamics and help forestall unforeseen misfortunes brought about by flaws during the assembling procedure.