Wajid Rafique

Rapid development of the Industrial Internet of Things (IIoT) is turning the management of machinery and decision-making into a multitude of operational data. A key issue in such an environment would be the ability to predict the failure of assets well to reduce downtimes and maximize on performance. The role of predictive maintenance (PdM) is significant here, although the current literature usually focuses on the development of the algorithms and ignores the consideration of technological, organizational, and industrial aspects. This article will provide an extensive overview of artificial intelligence (AI)-driven PdM in the framework of Industry 4.0 and suggest a hybrid taxonomy that will combine AI paradigms, stages of maintenance lifecycle, and industrial deployment scenarios. The taxonomy offers a multidimensional viewpoint connecting data analytics, machine learning (ML), and operational readiness as a conceptual framework to tie together scholarly research and industrial practice. This article critically examines the existing issues, such as data heterogeneity, model interpretability, and scalability and presents research gaps that impede the adoption of PdM, in particular by small- and medium-sized enterprises (SMEs). This work provides a systematic basis to the development of explainable, adaptive, and interoperable PdM systems by providing engineering and computer science viewpoints. The results highlight the necessity of multidisciplinary solutions that can make the AI innovation stay relevant to the real-world maintenance plans and create resilient and smart industrial ecosystems.

The exponential growth of Internet of Things (IoT)-generated content has given rise to efficient, secure, and scalable caching mechanisms to manage real-time data exchanges, driving the evolution of information-centric IoT architecture. However, centralized content distribution models introduce single points of failure, trust vulnerabilities, and scalability limitations, compromising the reliability and security of IoT services. Blockchain technology, with its decentralized, immutable, and tamper-resistant properties, offers a trustworthy caching framework, ensuring data authenticity, provenance, and secure access control, thereby ensuring trust in information-centric IoT. This paper presents a comprehensive survey of the literature on Blockchain-based information-centric IoT services, systematically analyzing trust frameworks, security models, and identity management solutions. We examine Blockchain and information-centric networking synergies in establishing trust, preserving privacy, enhancing attack resilience, and ensuring fairness in content delivery in IoT services. Additionally, we provide a detailed taxonomy of the literature on trustworthy information-centric IoT, considering key parameters such as data provenance, lightweight consensus mechanisms, identity management, decentralized trust models, and smart contract-based access control. The survey also investigates real-world implementations of trustworthy information-centric IoT solutions, highlighting deployment-level performance metrics and design considerations to evaluate their practical feasibility. Finally, we outline future research directions, emphasizing the need for scalable lightweight consensus protocols, adaptive caching strategies, and privacy-aware access control mechanisms to advance trustworthy IoT caching architectures.

The growing adoption of the Internet of Things (IoT) in healthcare has led to a surge in real-time data from wearable devices, medical sensors, and patient monitoring systems. This latency-sensitive environment poses significant challenges to traditional cloud-centric infrastructures, which often struggle with unpredictable service demands, network congestion, and end-to-end delay constraints. Consistently meeting the stringent QoS requirements of smart healthcare, particularly for life-critical applications, requires new adaptive architectures. We propose ML-RASPF, a machine learning-based framework for efficient service delivery in smart healthcare systems. Unlike existing methods, ML-RASPF jointly optimizes latency and service delivery rate through predictive analytics and adaptive control across a modular mist–edge–cloud architecture. The framework formulates task provisioning as a joint optimization problem that aims to minimize service latency and maximize delivery throughput. We evaluate ML-RASPF using a realistic smart hospital scenario involving IoT-enabled kiosks and wearable devices that generate both latency-sensitive and latency-tolerant service requests. Experimental results demonstrate that ML-RASPF achieves up to 20% lower latency, 18% higher service delivery rate, and 19% reduced energy consumption compared to leading baselines.

The growing adoption of the Internet of Things (IoT) in healthcare has led to an extensive growth in real-time data from wearable devices, medical sensors, and patient monitoring systems. This data and latency-sensitive environment poses a significant challenge to conventional cloud-centric infrastructures, which struggle with unpredictable service demands, link congestion, and end-to-end delay across distributed environments. Specifically, traditional cloud infrastructures struggle to deliver consistent service quality in smart healthcare, where both low end-to-end latency and adaptive service delivery rates are critical for life-saving applications. We propose ML-RASPF, a machine learning-based service delivery framework for efficient and scalable IoT service delivery in smart healthcare systems to address these issues. ML-RASPF formulates the provisioning task as a joint optimization problem that aims to minimize service latency and maximize delivery rate stability. The framework comprises three key components: (i) a network parameter initialization module, (ii) a supervised learning model for traffic demand prediction, and (iii) a reinforcement learning-based service adaptation engine for real-time resource allocation. These modules intelligently distribute workloads across a hybrid cloud environment. We evaluate ML-RASPF using a realistic smart hospital scenario involving IoT-enabled kiosks and wearable devices delivering both latency-sensitive and latency-tolerant services. Experimental results demonstrate that ML-RASPF significantly outperforms state-of-the-art edge–cloud systems in terms of latency reduction, energy efficiency, bandwidth utilization, and service delivery rate.

Beyond fifth generation (B5G) is expected to tremendously improve network capabilities by using a higher frequency band compared to 5G, capable of delivering higher network capacity with much lower latency. It is expected that there will be around 30 billion connected objects by 2030, approximately 3.5 times the population then which underscores the pressing need for advanced network capabilities to support diverse applications ranging from smart transportation and energy management to healthcare and public safety. Network slicing enables sharing of network resources by transforming the physical network into logically independent networks, each specifically tailored to meet the requirements of heterogeneous services (e.g., Internet of things applications, gaming services, holographic communication). Each slice is an end-to-end logical network comprising network, compute, and storage resources. Softwarization and virtualization are the main drivers for innovation in B5G, enabling network developers and operators to develop network-aware applications to match customer demands. Smart cities vertical offers unique service characteristics, performance requirements, and technical challenges in B5G network slicing. Therefore, this paper provides a comprehensive survey on B5G network slicing use cases, synergies, practical implementations and applications based on their quality of service parameters for smart cities applications. The paper gives a detailed taxonomy of the B5G network slicing framework requirements, design, dynamic intra-slice and inter-slice resource allocation techniques, management and orchestration, artificial intelligence/machine learning-empowered network slicing designs, implementation testbeds, 3GPP specifications and projects/standards for B5G network slicing. Furthermore, the paper provides a thorough discussion on the technical challenges that can arise when implementing B5G network slicing for smart cities applications and offers potential solutions. Finally, the paper discusses B5G network slicing current and future research directions for smart cities applications.

The Internet of Medical Things (IoMT) connects a huge amount of smart sensors with the Internet for healthcare service provisioning. IoMT’s privacy-preserving becomes a challenge considering the life-saving data collected and transferred through IoMT. Traditional privacy protection techniques use centralized management strategies, which lead to a single point of failure, lack of trust, state modification, information disclosure, and identity theft. Edge computing enables local computation of IoMT data, which reduces traffic to the cloud and also helps in accomplishing latency-sensitive healthcare applications and services. This paper proposes a novel framework (i.e., SecureMed) that uses blockchain-based distributed authentication implemented at the edge cloudlets to enforce privacy protection. In SecureMed, IoMT devices interact with edge cloudlets using smart contracts. It uses trusted edge nodes to implement an authentication algorithm that uses public/private key matching to authenticate IoMT. Experimental evaluation performed using the Pythereum blockchain shows that SecureMed outperforms the traditional blockchain scheme based on latency, bandwidth consumption, deployment time, scalability, and accuracy. Therefore, it can be used to protect the edge-enabled IoMT from privacy attacks and to ensure end-to-end healthcare service provisioning.