The increasing heterogeneity of network services in next-generation environments require intelligent and adaptive routing frameworks that can align with diverse and dynamic application level service requirements. Software-Defined Networking (SDN) decouples the control plane from data plane to shift the complexity from core network devices. Moreover, Intent-Based Networking (IBN), when integrated with SDN, provides a centralized and programmable platform to translate high level user intents into actionable network configurations. This paper proposes a hybrid quality of service (QoS)-aware routing framework that combines the Analytic Hierarchy Process (AHP) with adaptive Artificial Intelligence (AI) to support intentdriven decision-making in SDN. The AHP module interprets user-defined service intents into weighted QoS priorities, while the AI component dynamically refines these weights based on the network telemetry. This integration enables context-aware path selection that balances structure, adaptability, and explainability. Experimental results on real-world network topologies demonstrate that the proposed framework consistently outperforms benchmark and state-of-the-art approaches in terms of end-to-end (E2E) delay, packet loss, jitter, throughput, and intent satisfaction. Moreover, the system achieves fast re-routing convergence and maintains a low controller overhead, making it suitable for scalable, transparent, and high-performance deployment in IBN-compliant SDN infrastructures.

The increasing complexity of 6G-IoT networks presents challenges in ensuring real-time trust assessment, computational efficiency, and security against adversarial threats. Existing frameworks struggle to dynamically adapt to evolving threats and high-volume data streams, leading to compromised decision reliability. This study proposes TANF (Trustworthy Adaptive Neural Framework), an advanced deep learning-driven trust evaluation system incorporating hierarchical processing, multi-domain trust layers, and Holo-Recursive Memory (HRM) for adaptive optimization. TANF prioritizes high-trust data streams using sensory stream balancing, dynamically allocates resources through task-specific synergy layers, and enhances memory recall by integrating past, present, and predictive state representations. The simulation, conducted in Edge-IIoTset, IoT-23 and CICIDS2017, evaluated trust assessment, computational latency, scalability, and adversarial detection. TANF achieves a precision of 92. 8%, a latency reduction of 34. 5% and a adversarial detection rate of 95. 6%, outperforming ERAI, ROBUST-6G, and IMCS.

The emergence of large-scale quantum computers threatens the security of classical public-key cryptosystems, making it essential to adopt post-quantum (PQ) security in Intelligent Transportation Systems (ITS). We introduce a framework that blends quantum-resilient cryptographic primitives with a sharded blockchain architecture. Each shard maintains a local ledger for its vehicle group, enabling real-time transactions and efficient certificate management without overloading any single chain. A lightweight global chain periodically anchors all shards, preserving system-wide consistency and blocking malicious revocations. Vehicles register or revoke PQ credentials via a lightweight Proof-of-Stake consensus, while roadside units (RSUs) handle signature verification to offload on-board computation. We further demonstrate practicality through a federated-learning case study in which vehicles exchange signed model updates over the same secure channel. SUMO/TraCI simulations with 2 000 vehicles and 10 shards show that despite PQ overhead the system sustains near real-time delays and high throughput. The framework thus offers a decentralized, quantum-resilient solution for secure Vehicle-to-Everything communications in next-generation ITS.

Embedded resources have been becoming part of the Internet of Things networks, where they are increasingly taking part in various kinds of decision-making using Tiny Machine Learning (TinyML) models. Although offloading the TinyML model for these devices includes removing many layers that have less impact on the overall performance, they often lead to a sacrifice on the overall performance of the model. In this paper, we propose a novel device-aware training strategy to customize the training based on the resources on which the model will be applied. We proposed AlphaEnhancer, a resource-aware game agent for medical image super-resolution. We baseline our approach on the Residual Feature Distillation Model (RFDN) and propose a device efficacy metrics, which is based on the learned actions of the agent. The model with the highest efficacy is deemed appropriate for that particular device. Our preliminary results show that our methods performed significantly well with respect to the baseline and other recent state-of-the-art.

Mission-critical networks (MCNs) increasingly depend on distributed intelligence for intrusion detection but remain susceptible to adversarial threats and poisoned feedback. As cyber-physical systems scale, ensuring secure and adaptive anomaly detection across heterogeneous, edge-centric environments is vital. Centralized approaches suffer from latency and single points of failure, while conventional federated learning lacks trust and poisoning resilience. These gaps expose MCNs to inference inconsistencies, delayed mitigation, and adversarial manipulation under real-time constraints. This paper presents a federated swarm intelligence framework for secure anomaly detection and adversarial resilience in MCNs. The system integrates a hybrid global-local anomaly detection model, composed of an autoencoder and an isolation forest with a reputation-based belief propagation protocol. Each node performs local inference and shares Indicators of Compromise (IOCs) with trusted peers. Trust scores are dynamically updated using a similarity-weighted belief function, allowing the swarm to isolate poisoned nodes and maintain robust consensus. A self-healing loop filters malicious contributions from global model updates, ensuring continuous adaptation to threat evolution. Experimental results across TON_IoT, CICIDS2017, and UNSW-NB15 datasets demonstrate improved detection accuracy, reduced false positives, and resilience against up to 30% adversarial node participation. This work establishes a scalable defense paradigm for edge-intelligent, real-time MCN environments.

ABSTRACT Due to the recent advancements in high‐speed networks, underlying hardware computing resources and resource scheduling algorithms, Cloud computing has emerged as a popular computing paradigm globally providing end‐user services such as infrastructure, hardware platforms and application tools. Subsequently, the researchers across various domains have integrated different services to facilitate the end users. However, the real issue faced by the cloud infrastructure is the network latency due to the physical dispersion between clients and cloud data centers. According to an estimate, billions of internet of things (IoT) devices are sharing approximately two exabytes of data daily. Such a huge amount of data can affect network performance if the underlying physical system does not expand up to the required levels, leading to performance degradation. To overcome these issues, a new computing paradigm called Fog Computing has emerged in recent years. In this paper, we discuss the recent developments in fog computing with the integration of real‐time Healthcare 5.0 technology. Furthermore, we describe the proposed layered architecture and taxonomy of resource management (RM) techniques in fog computing, which consists of energy awareness, scheduling, reliability and scalability. Besides that, our survey covers the three‐tier layered architecture, evaluation metrics, real‐time application aspects of fog computing and tools providing the implementation of RM techniques in fog computing. Furthermore, the proposed layered architecture of the standard fog framework and different state‐of‐the‐art techniques for utilising the computing resources of fog networks have been covered in this study. Moreover, we include various sensors to demonstrate the fog data offloading example in healthcare 5.0 applications. We also present a thorough discussion on various current and future real‐time applications of fog computing. Finally, open challenges and promising future research directions have been identified and discussed in the area of fog‐based real‐time applications.

In the context of rapidly growing city road networks, understanding complex traffic patterns and implementing effective safety monitoring through advanced Transportation Cyber-Physical Systems (T-CPS) has become increasingly challenging. This involves understanding spatial relationships and non-linear temporal associations. Accurately predicting traffic in such scenarios, particularly for long-term sequences, is challenging due to the complexity of the data. Traditional ways of predicting traffic flow use a single fixed graph structure based on location. This structure does not consider possible correlations and cannot fully capture long-term temporal relationships among traffic flow data, thereby limiting the system ability to ensure safety and reliability. To address this challenge, we propose a novel traffic prediction framework called Attention-based Spatio-temporal Multi-scale Graph Convolutional Recurrent Network (ASTMGCNet). This study introduces a novel framework designed to improve prediction accuracy in dynamic urban traffic systems by effectively capturing complex spatio-temporal correlations through multi-scale feature extraction and attention mechanisms. ASTMGCNet records changing features of space and time by combining Gated Recurrent Units (GRU) and Graph Convolutional Networks (GCN). Its design incorporates multi-scale feature extraction and dual attention mechanisms, effectively capturing informative patterns at different levels of detail. This strategic design allows ASTMGCNet to effectively capture complex spatio-temporal correlations within traffic sequences, enhancing prediction accuracy. We have tested this method on two different real-world datasets and found that ASTMGCNet predicts significantly better than other methods, demonstrating its potential to advance traffic flow prediction and improve safety and reliability in T-CPS applications.

Federated Learning has emerged as a promising paradigm for collaborative model training in healthcare. FL allows institutions to share knowledge without compromising patient privacy. However, data annotation remains a bottleneck, especially in medical image studies. This work proposes a Federated Active Learning with a Transfer Learning framework for efficient labeling in lung cancer diagnosis. Using ensemble entropy-based uncertainty assessment, FAL-TL streamlines sample annotation, optimizing training across distributed healthcare institutions while safeguarding patient privacy. Using the IQOTH/NCCD Lung Cancer and Chest CT-Scan images Dataset, our FAL-TL framework achieves an impressive 99.20% accuracy, surpassing traditional machine learning models. By integrating transfer learning, FAL-TL adapts pre-trained models to healthcare datasets, significantly enhancing diagnostic accuracy. This research contributes to advancing FL techniques in healthcare, offering a scalable and privacy-preserving solution with transformative implications for diagnostics and patient care.

In the n-tier framework, data generated by the sensors requires immediate execution. The processing elements need powerful resources to entertain incoming requests. Fog computing, unlike cloud computing, provides low latency for real-time applications. However, data generated by the real-time Internet of Things (IoT) devices significantly impacts the fog devices. The data generated must be processed by the fog devices with quick response time, minimum delay, and energy consumption and send it back to the end-users with high reliability and success rate. However, devices fail due to damage or internal state of a fog device which measures incorrectly or causes destruction which badly affects the overall system performance. The end-to-end transmission requests from the IoT devices require immediate response with minimal delay, execution cost, and energy consumption in spite the occurrence of fog devices failure. In this article, we propose a novel energy efficient task scheduling algorithm based on reactive fault tolerance in an n-tier fog computing framework for IoT applications to enhance the overall fog computing performance. In case of fog device failure, the assigned task is rescheduled to other executable fog nodes without further delay. The proposed framework is based on the modified particle swarm optimization and is designed and evaluated in iFogSim. The main objective of the proposed technique is to reduce energy consumption, latency, network bandwidth utilization, and increase system reliability and success rate. Several experiments have been carried out by taking a maximum of ten iterations based on which it is concluded that the proposed technique reduces energy consumption by 3%, latency by 5%, network bandwidth utilization by 3%, and increases the system reliability by 2% and success rate by 8%.

The 5th industrial revolution is characterized by an extensive interconnection of embedded devices, which offer a range of services, including the monitoring of their environments. Images captured from remote cameras require enhancements for effective analysis. Despite recent progress in single-image super-resolution techniques by yielding impressive results through deep convolutional neural networks, the complexity of these advanced models renders them impractical for use on miniaturized Internet of Things (IoT) devices, primarily due to their limited computational capabilities and memory constraints. Furthermore, the rapid evolution of IoT devices necessitates efficient image super-resolution techniques, while existing advanced methods, based on deep convolutional neural networks, are too resource-intensive for these devices, and this gap highlights the need for a more suitable solution. In this study, we introduce a lightweight, efficient super-resolution model specifically designed for IoT devices. This model incorporates a novel deep residual feature distillation block (DRFDB), which leverages a depthwise-separable convolution block (DCB) for effective feature extraction. The focus is on reducing computational and memory demands without compromising on image quality. The proposed DCB extracts coarse features from given input features as calculation units, using two operations, depthwise and pointwise convolutions. These two operations are able to significantly reduce the number of parameters and floating-point operations while maintaining a PSNR value higher than the 90% threshold. We modify the proposed DCB and introduce a multi-kernel depthwise-separable convolution block (MKDCB) to fine-tune the model. The experiments, conduct on various standard datasets such as DIV2K, Set5, Set14, Urban100, and Manga109 by demonstrating that our model significantly outperforms existing methods in terms of both image quality and computational efficiency. The model shows improved performance metrics like PSNR, while requiring fewer parameters and less memory usage, making it highly suitable for IoT applications. This study presents a breakthrough in super-resolution for IoT devices, balancing high-quality image reconstruction with the limited resources of these devices.

Purpose The banking industry has always been vulnerable to cyberattacks. In recent years, Pakistan’s banking sector experienced the most intense cyberattack in its over 70-year history. Due to these attacks, a large number of debit card accounts of major banks were negotiated. This study aims to examine the impact of cyberattack awareness and customers’ commitment levels after these cyberattacks. Design/methodology/approach The study integrated the commitment–trust theory framework for the relationship of trust and commitment to the usage of online banking services. The partial least square structural equation modeling is being used to explore the relationship between customer’s trust, which is an outcome of continuous usage, and customer perception of affirmative cybersecurity measures the bank. Findings The findings revealed that customer trust in online banking is positively associated with customer commitment, but customers’ cyberattack awareness negatively impacts customer trust and commitment to online banking. Practical implications The study highlights the importance of proactive communication, transparency and robust incident response that helps organizations establish themselves as trustworthy entities while prioritizing customer information and transaction protection. Originality/value The authors report on how cyberattacks on the banking sector influence the trust and commitment of the customers in the sector. The variable of cyberattack awareness used in this study is novel in online banking literature.

Strong efforts have been undertaken to enhance the diagnosis and identification of diseases that cause facial paralysis, such as Bell's palsy and stroke, because of their detrimental social effects. Stroke is one of the most serious and potentially fatal conditions among the major cardiovascular disorders. We are introducing a deep-learning-based method for early diagnosis of facial paralysis diseases such as stroke and Bell's palsy. Recognizing the costs associated with traditional diagnostic techniques like magnetic resonance tomography (MRI) and computed tomography (CT) scan images, our model employs a multi-task network, integrating face parsing, facial asymmetry parsing, and category enhancement. Spatial inconsistencies are addressed via a depth-map estimation module that leverages an instance-specific kernel approach. To clarify the boundaries of facial components, we use category edge detection with a foreground attention module, generating generic geometric structures and detailed semantic cues. Our model is trained on two datasets, comprising individuals with regular smiles and those with one-sided facial weakness. This cost-effective, easily accessible solution can streamline the diagnostic process, minimizing data gaps, and reducing needless rescreening and intervention costs.

Internet of things has been one of the predominant research areas for the past two decades. Many application domains have embraced it to solve challenges that have long been considered hurdles. A recent trend in information communication technologies is integrating miniature sensing devices to elevate the experience in serious games. Serious games are games whose sole aim is not entertainment but rather to serve as a source of information and learning in a playful manner. Serious games are becoming one of the sizzling literature topics and are applied to every part of human lives, such as education, healthcare, and physical training, to name a few. Internet of Things, the biggest provider of modern-day games via personal mobiles, can be utilized to design serious games. However, deploying serious games in the Internet of Things environment engenders new challenges. This paper aims to provide a comprehensive survey on Internet of things-enabled serious games and investigate the challenges towards their realization. First, we highlight serious game domains and spot the evolution and motivation that lead to Internet-of-Things-enabled Serious Games. Later, we classify the state-of-the-art by devising a comprehensive taxonomy. In the end, we present numerous unaddressed open challenges in the current form of the state-of-the-art and identify future directions.