Industry 5.0 aims at maximizing the collaboration between humans and machines. Machines are capable of automating repetitive jobs, while humans handle creative tasks. As a critical component of Industrial Internet of Things (IIoT) systems for service delivery, network data stream analytics often encounter concept drift issues due to dynamic IIoT environments, causing performance degradation and automation difficulties. In this article, we propose a novel multistage automated network analytics framework for concept drift adaptation in IIoT systems, consisting of dynamic data preprocessing, the proposed drift-based dynamic feature selection method, dynamic model learning and selection, and the proposed window-based weighted probability averaging ensemble model. It is a complete automated data stream analytics framework that enables automatic, effective, and efficient data analytics for IIoT systems in Industry 5.0. Experimental results on two public IoT datasets demonstrate that the proposed framework outperforms state-of-the-art methods for IIoT data stream analytics.

中文翻译：

---

适用于 IIoT 系统的多级自动化在线网络数据流分析框架


工业5.0旨在最大限度地提高人与机器之间的协作。机器能够自动执行重复性工作，而人类则能够处理创造性任务。作为工业物联网 (IIoT) 服务交付系统的关键组件，网络数据流分析经常会因动态 IIoT 环境而遇到概念漂移问题，从而导致性能下降和自动化困难。在本文中，我们提出了一种新颖的多级自动化网络分析框架，用于工业物联网系统中的概念漂移适应，包括动态数据预处理、提出的基于漂移的动态特征选择方法、动态模型学习和选择以及提出的基于窗口的加权概率平均系综模型。它是一个完整的自动化数据流分析框架，可以为工业 5.0 中的 IIoT 系统实现自动、有效且高效的数据分析。两个公共物联网数据集的实验结果表明，所提出的框架优于 IIoT 数据流分析的最先进方法。