Introduction to the Special Issue on Smart Systems for Industry 4.0 and IoT

The development of big data applications is driving the dramatic growth of hybrid data, often in the form of complex sets of cross-media content including text, images, videos, audios, and time series. Tremendous volumes of these heterogeneous data are derived from multiple IoT sources and present new challenges for the design, development, and implementation of effective information systems and decision support frameworks to meet heterogeneous computing requirements. Emerging technologies allow for the near real-time extraction and analysis of heterogeneous data to find meaningful information.

Machine-learning algorithms allow computers to learn automatically, analyzing existing data to establish rules to predict outcomes of unknown data. However, traditional machine learning approaches do not meet the needs for Internet of Things (IoT) applications, calling for new technologies. Deep learning is a good example of emerging technologies that tackle the limitations of traditional machine learning through feature engineering, providing superior performance in highly complex applications. However, these technologies also raise new security and privacy concerns. Technology adoption and trust issues are of timely importance as well.

Industrial operations are in the midst of rapid transformations, sometimes referred to as Industry 4.0, Industrial Internet of Things (IIoT), or smart manufacturing. These transformations are bringing fundamental changes to factories and workplaces, making them safer and more efficient, flexible, and environmentally friendly. Machines are evolving to have increased autonomy, and new human-machine interfaces such as smart tools, augmented reality, and touchless interfaces are making interaction more natural. Machines are also becoming increasingly interconnected within individual factories as well as to the outside world through cloud computing, enabling many opportunities for operational efficiency and flexibility in manufacturing and maintenance.

An increasing number of countries have put forth national advanced manufacturing development strategies, such as Germany's Industry 4.0, the United States’ Industrial Internet and manufacturing system based on CPS (Cyber-Physical Systems), and China's Internet Plus Manufacturing and Made in China 2025 initiatives. Smart Manufacturing aims to maximize transparency and access of all manufacturing process information across entire manufacturing supply chains and product lifecycles, with the Internet of Things (IoT) as a centerpiece to increase productivity and output value. This manufacturing revolution depends on technology connectivity and the contextualization of data, thus putting intelligent systems support and data science at the center of these developments.

The first theme of this special issue focuses on “Theories, models, and algorithms for smart system in Industry 4.0 and IoT”. In the article, titled “User-empowered Privacy-preserving Authentication Protocol for Electric Vehicle Charging based on Decentralized Identity and Verifiable Credential”, Paramaswarath et al. developed a user-empowered privacy-preserving authentication protocol to provide the Zero-Knowledge Proof (ZKP)-security for EV charging. The experimental results showed the proposed protocol can provide a secure way for charging service while empowering users and preserving their privacy. The article by Ahmed et al., titled “Heterogeneous Energy-aware Load Balancing for Industry 4.0 and IoT Environments”, presents an energy reduction method for heterogeneous clustering. The aim of this research is to achieve the load balancing by feature selection based on machine learning approaches. The experimental results demonstrate that it can lead to a reduction in both energy consumption as well as execution time.

In the article “Roadside Unit-based Unknown Object Detection in Adverse Weather Conditions for Smart Internet of Vehicles”, Chen et al. implemented a YOLO-based real-time object detection system with edge computing mode in poor lighting conditions. The experimental results illustrated that the proposed system can learn uncategorized objects dynamically and detect instances accurately. The article by Lv et al., titled “Computational Intelligence in Security of Digital Twins Big Graphic Datain Cyber-Physical Systems of Smart Cities”, integrates data mining techniques and data security mechanisms to optimize the privacy protection of frequent subgraph mining on a single multi-graph. Finally, the proposed Differential Privacy-AlexNet (DP-AlexNet) model outperformed Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN) for processing big graphic data.

The article by Lin et al., titled “Smart System: Joint Utility and Frequency for Pattern Classification”, provides two new algorithms, namely UFCgen and UFCfast, for big data analysis. Both algorithms can deal with three types of patterns - High Frequency and High Utility Itemset (HFHUI), High Frequency and Low Utility Itemset (HFLUI), and Low Frequency and High Utility Itemset (LFHUI) for pattern classification in smart systems effectively. In the article “The Core Industry Manufacturing Process of Electronics Assembly based on Smart Manufacturing”, Chen et al. adopted the Bayesian network inference to find the critical factors of the metal residues between electronic circuits. In addition, the authors also applied the Convolutional Neural Network (CNN) into the false defection during automatic optical inspection (AOI). The proposed approaches can enhance the yield rate and reduce the cost during the manufacturing process. The article by Liu et al., titled “Two-stage Competitive Particle Swarm Optimization Based Timing-driven X-routing for IC Design under Smart Manufacturing”, presents a novel Timing-Driven X-routing Steiner Minimum Tree (TD-XSMT) algorithm based on particle swarm optimization (PSO) and re-designed its framework. The experimental results indicate that the proposed algorithm can obtain better wirelength as well as source-to-sink pathlength for IC Design in a smart manufacturing context.

The second theme of this issue focuses on “New Industry 4.0 and IoT framework for smart system and applications”. In the article “Integration of DevOps Practices on a Noise Monitor System with CircleCI and Terraform”, Robero et al. describe some DevOps practices on noise monitor system (NMS) through pipelines (CircleCI), clean coding (SonarCloud), IAC (Terraform), and monitoring (CloudWatch). The experimental results suggest that the proposed system can improve quality and maintainability of the software components. The article by Ren et al., titled “Application Massive Data Processing Platform for Smart Manufacturing based on Optimization of Data Storage”, presents a Lambda-based massive data processing platform to be in line with the real-time feedback needs of the high-precision manufacturing process. The experimental results indicate it can optimize image data storage by the AOI technologies in manufacturing. In the article “Scientific Workflows in IoT Environments: A Data Placement Strategy Based on Heterogeneous Edge-Cloud Computing”, Due et al. implemented a data placement model to share datasets within the individual and among multiple workflows. In advance, authors also applied the reinforcement learning into the data placement strategy in the runtime stage of scientific workflows. In the article “Smart Allocation of Standby Resources for Cloud Survivability in Smart Manufacturing”, Nong et al. describe a smart survivability framework to allocate resources for standby Virtual Machine (VM) efficiently. The proposed framework can predict the resource utilization of VMs and also forecast the latest running status of the failed VM. The article by Liu et al., titled “Performance-driven X-architecture Routing Algorithm for Artificial Intelligence Chip Design in Smart Manufacturing”, presents an effective performance-driven X-architecture routing algorithm for AI chip design in smart manufacturing. The experimental results indicated the proposed algorithm outperformed other state-of-the-art algorithms with better total wirelength.

All selected articles make innovative contributions to the evolution of artificial intelligence (AI), machine learning, and deep learning as a foundation for the success of Industry 4.0 and IoT. We would like to thank all the contributors of this special issue for their participation and valuable scientific contributions. We hope that readers of ACM TMIS and scholars researching in the smart systems for Industry 4.0 and IoT will find this special issue of great interest and benefit.