Cyber-physical systems (CPS) refer to systems that integrate communication, control, and computational elements into physical processes to facilitate the control of physical systems and effective monitoring. The systems are designed to interact with the physical world, monitor and control the physical processes while in operation, and generate data. Deep Neural Networks (DNN) comprise multiple layers of interconnected neurons that process input data to produce predictions. Spatial-temporal data represents the physical world and its evolution over time and space. The generated spatial-temporal data is used to make decisions and control the behavior of CPS. This paper systematically reviews the applications of DNNs, namely convolutional, recurrent, and graphs, in handling spatial-temporal data in CPS. An extensive literature survey is conducted to determine the areas in which DNNs have successfully captured spatial-temporal data in CPS and the emerging areas that require attention. The research proposes a three-dimensional framework that considers: CPS (transportation, manufacturing, and others), Target (spatial-temporal data processing, anomaly detection, predictive maintenance, resource allocation, real-time decisions, and multi-modal data fusion), and DNN schemes (CNNs, RNNs, and GNNs). Finally, research areas that need further investigation are identified, such as performance and security. Addressing data quality, strict performance assurance, reliability, safety, and security resilience challenges are the areas that are required for further research.

Cyber-Physical Systems (CPS) are new systems designed to support and synthesize sensing, communication, and computing components that interact with physical objects so that the system can sense, monitor, control, and respond to changes occurring in their operating environments. With developing Internet of Things (IoT), edge/cloud computing, and Artificial Intelligence (AI), another new paradigm - Digital Twin (DT), as an enabler for realizing the Metaverse of CPS has emerged recently. The DT provides a virtual replica of the physical world, allowing for real-time monitoring, control, and analysis of safety-critical systems like the CPS. Even though many CPS-related problems can be addressed using DT concepts, it is critical to define DT’s integration clearly to leverage its features to the best possible extent. This paper introduces a new layer called the data layer in the CPS layer architecture to support different DT functionalities. Like the layer and abstract design paradigm of modern operation systems and computer networks, the data layer serves as an abstraction layer, providing immense flexibility and interchangeability of various data sources, supporting applications, and adapting to other components and environments. This also accelerates the growth of smart-world systems and their integration in different application domains (smart grid, smart transportation, smart manufacturing, smart cities, smart healthcare, etc.). To this end, this paper presents a new data layer structure to support CPS applications and the integration of multiple CPS. We propose a hierarchical architecture to synthesize DT techniques as an independent layer in our architecture, deeply integrated into existing CPS. We discuss key issues: leveraging the data layer to support applications in various CPS, incorporating the data layer and physical layer, and building a data layer using distributed computing, naming services, etc. Finally, the paper outlines future research directions based on the presented new data layer architecture for CPS.

The Internet of Things (IoT) constitutes a vast network comprising various components such as physical devices, vehicles, buildings, and other items equipped with sensors, actuators, and software. These components are interconnected, facilitating the collection and exchange of copious data across networked communications. IoT empowers extensive monitoring and control over a myriad of objects, enabling them to gather and disseminate data that bolster applications, thereby enhancing the system’s capacity for informed decision making, environmental surveillance, and autonomous inter-object interaction, all without the need for direct human involvement. These systems have achieved seamless connectivity requirements using the next-generation wireless network infrastructures (5G, 6G, etc.), while their diverse reliability and quality of service (QoS) requirements across various domains require more efficient solutions. Open RAN (O-RAN), i.e., open radio open access network (RAN), promotes flexibility and intelligence in the next-generation RAN. This article reviews the applications of O-RAN in supporting the next-generation smart world IoT systems by conducting a thorough survey. We propose a generic problem space, which consists of (i) IoT Systems: transportation, industry, healthcare, and energy; (ii) targets: reliable communication, real-time analytics, fault tolerance, interoperability, and integration; and (iii) artificial intelligence and machine learning (AI/ML): reinforcement learning (RL), deep neural networks (DNNs), etc. Furthermore, we outline future research directions concerning robust and scalable solutions, interoperability and standardization, privacy, and security. We present a taxonomy to unveil the security threats to emerge from the O-RAN-assisted IoT systems and the feasible directions to move this research forward.

The rapid advancement and widespread adoption of artificial intelligence (AI) across diverse industries, including healthcare, finance, manufacturing, and retail, underscore the transformative potential of AI technologies. This necessitates the development of viable AI model marketplaces that facilitate the development, trading, and sharing of AI models across the pervasive industrial domains to harness and streamline their daily activities. These marketplaces act as centralized hubs, enabling stakeholders such as developers, data owners, brokers, and buyers to collaborate and exchange resources seamlessly. However, existing AI marketplaces often fail to address the demands of modern and next-generation application domains. Limitations in pricing models, standardization, and transparency hinder their efficiency, leading to a lack of scalability and user adoption. This paper aims to target researchers, industry professionals, and policymakers involved in AI development and deployment, providing actionable insights for designing robust, secure, and transparent AI marketplaces. By examining the evolving landscape of AI marketplaces, this paper identifies critical gaps in current practices, such as inadequate pricing schemes, insufficient standardization, and fragmented policy enforcement mechanisms. It further explores the AI model life-cycle, highlighting pricing, trading, tracking, security, and compliance challenges. This detailed analysis is intended for an audience with a foundational understanding of AI systems, marketplaces, and their operational ecosystems. The findings aim to inform stakeholders about the pressing need for innovation and customization in AI marketplaces while emphasizing the importance of balancing efficiency, security, and trust. This paper serves as a blueprint for the development of next-generation AI marketplaces that meet the demands of both current and future application domains, ensuring sustainable growth and widespread adoption.