A Multi-Stage Automated Online Network Data Stream Analytics Framework for IIoT Systems

Abstract--Industry 5.0 aims at maximizing the collaboration Industry 4.0 and Industry 5.0 both rely heavily on IoT The IIoT's basic premise is that intelligent machines are often more I. HE fourth industrial revolution (Industry 4.0) enables smart manufacturing via the application of various technologies, On the other hand, IIoT data samples are usually nonstationary such as the Internet of Things (IoT), Artificial Intelligence data streams generated in ever-changing IIoT environments (AI), big data analytics, cloud computing, and edge due to their dynamic nature [6]. Industry 4.0 also applications, IIoT data analytics often suffers from concept achieves technological advancements that increase the level of drift issues when IIoT data distributions change over time. Recently, The occurrence of concept drift poses considerable challenges as the fifth industrial revolution, Industry 5.0 has been in developing ML models, since their learning performance proposed as a human-centered design solution for the next evolutionary may progressively degrade owing to data distribution changes state. Thus, advanced online adaptive learning models should and machines work collaboratively with human resources to be developed to detect and react to concept drift that occurs enable customizable autonomous production through business in IIoT data streams. The drift adaptation procedure is also social networks [1]. In Industry 5.0, humans can devote their referred to as automated model updates in the network data creativity to responsible activities, while computers take over analytics automation process, as its main purpose is to improve repetitive and monotonous duties, hence improving production model performance by updating the learning model.