Accurate anomaly recognition in video surveillance is critical to ensuring public safety, infrastructure protection, and intelligent security operations. However, existing methods often fail to generalize across diverse and dynamic environments due to their limited capacity to model complex spatio-temporal patterns. In this paper, we propose a novel Graph-Based Temporal Attention Memory Network (G-TAMNet) that significantly advances video anomaly detection by capturing intricate temporal dependencies and spatial relationships. By integrating temporal self-attention into a graph convolutional network (GCN) framework, our model enhances the learning of salient and contextually relevant features that traditional approaches tend to overlook. Furthermore, to enable deployment in resource-constrained settings, such as IoTbased surveillance systems, we incorporate model quantization strategies that reduce computational overhead without compromising detection accuracy. Extensive evaluations of three widely used benchmarks, UCFCrime, LAD-2000, and RWF-2000 the effectiveness of the proposed G-TAMNet model, achieving accuracy, precision, recall, and F1-scores of 54.3% / 61.1% / 59.01% / 61.1%,79.3% / 69.1% / 70.0% / 69.1%,and 94.0% / 94.0% / 94.2% / 94.1%, respectively. These results reflect consistent performance gains of 3.3%, 9.9%, and 0.74% in accuracy over existing state-ofthe-art methods on the corresponding datasets. Such improvements underscore the robustness, scalability, and practical viability of GTAMNet for real-time anomaly detection in resource-constrained IoT surveillance systems. In addition, its reliable generalization across diverse environments highlights the potential of the model to advance intelligent security analytics and transform real-world applications in the domain of information forensics.

A metaverse can bring many benefits (i.e., self-sustaining and proactive analytics (e.g., analysis before user requests)) to wireless applications; however, its deployment is very challenging due to simultaneous quality of service (QoS) and quality of physical experience (QoE) constraints. Furthermore, the computing and communication resources of end-nodes are limited. For instance, immersive experience devices (e.g., augmented reality (AR) headsets) in a metaverse have limited computing power and therefore, might not be able to perform rendering tasks. Consequently, this paper proposes a novel task offloading framework for metaverse-empowered wireless systems. Our formulated problem aims at minimizing the cost of task offloading in the metaverse while considering both QoS and QoE constraints by optimizing the task offloading, resource allocation, and transmit power allocation variables. For QoS, we consider latency and reliability, whereas for QoE, we consider both immersive experience and packet error rate. To optimize the formulated problem, we use a decomposition-based scheme that further uses modified block-successive upper-bound minimization (BSUM), convex optimization, and multi-agent reinforcement learning (MARL) for transmit power allocation, resource allocation, and task offloading, respectively. Our solution of using convex optimization-assisted MARL for joint resource allocation and task offloading significantly improves the performance of learning in terms of reward and attaining fast QoS as well as QoE. Furthermore, BSUM significantly improves transmit power allocation when used in conjunction with a convex optimizer and MARL. Other than that, we also use a dueling (i.e., it is a reinforcement learning architecture combining the dueling network structure with the double deep Q-learning network method for more stable and efficient Q-value learning) concept to further improve the performance of MARL. Our analyses show that convex optimization, BSUM, and dueling help in significantly improving the performance of MARL. Compared to traditional MARL, our proposal results in significant improvement in terms of reward and cost, as illustrated by the results.

To address the limitations of existing wireless networks for demanding applications like brain-computer interfaces and intelligent transportation systems, we propose an advanced framework for joint resource allocation and task offloading across integrated terrestrial and non-terrestrial networks (TN-NTN). This framework utilizes multiple layers, including ground users, UAVs, HAPs, and satellites, to improve service quality and immersive experiences, particularly in scenarios like Metaverse applications. Ground users request resources, while UAVs and HAPs serve as resource providers, and satellites ensure reliable communication during emergencies. A double auction-based incentive scheme is employed in which operators control UAV and HAP resources to maximize utility, and users aim to minimize computation costs and protect data privacy. To handle the complexity of the operator-user interaction, which results in an NP-hard optimization problem, we applied a hierarchical multi-agent federated deep reinforcement learning (FeDRL) approach. Our simulation results demonstrate that the FeDRL algorithm significantly improves social welfare by 6.38%, 17.43%, and 28.73% over modified MADDPG, FRL, and DDPG algorithms, respectively.

The development of wireless systems based on metaverse to effectively enable novel applications (e.g., surveillance and remote healthcare) gained significant interest from the research community. A metaverse combines many technologies with a virtual representation of the real world system for enabling applications. Although a metaverse enables many applications, there are challenges associated with its deployment. Therefore, in this paper, we consider sensing in metaverse-empowered unmanned aerial vehicle (UAV) networks. A massive number of sensors are considered to effectively sense the physical world states and share them with the metaverse. A problem is formulated to minimize the cost of sensing in terms of energy and latency. Our problem is based on optimizing the resource allocation and association for sensing units. We present a solution based on double deep Q-network (DDQN) for joint association and resource allocation in sensing for metaverse over UAVs network because the defined problem is non-convex and combinatorial. In the end, we validate our idea with comprehensive simulation results.

Dangerous surroundings and difficult-to-reach landscapes introduce significant complications for adequate disaster management and recuperation. These problems can be solved by engaging unmanned aerial vehicles (UAVs) provided with embedded platforms and optical sensors. In this work, we focus on enabling onboard aerial image processing to ensure proper and real-time disaster detection. Such a setting usually causes challenges due to the limited hardware resources of UAVs. However, privacy, connectivity, and latency issues can be avoided. We suggest a UAV-assisted edge framework for disaster detection, leveraging our proposed model optimized for onboard real-time aerial image classification. The optimization of the model is achieved using post-training quantization techniques. To address the limited number of disaster cases in existing benchmark datasets and therefore ensure real-world adoption of our model, we construct a novel dataset, DisasterEye, featuring disaster scenes captured by UAVs and individuals on-site. Experimental results reveal the efficacy of our model, reaching high accuracy with lowered inference latency and memory use on both traditional machines and resource-limited devices. This shows that the scalability and adaptability of our method make it a powerful solution for real-time disaster management on resource-constrained UAV platforms.The code and DisasterEye dataset are available at: https://github.com/Branislava98/TensorRT.

The rapid advancement of metaverse applications in wireless environments necessitates efficient resource management to enhance Quality of Experience (QoE). This paper presents a novel framework for optimizing wireless resource allocation within the metaverse to optimize QoE using convex optimization and matching theory. We formulate a QoE optimization problem considering packet error rate (PER) and immersive experience. Our problem also enables us to trade off between immersive experience and PER while computing QoE. The formulated problem is a mixed-integer non-linear programming (MINLP) problem, which is addressed through decomposition, convex optimization, matching theory, and block successive upper-bound minimization (BSUM). Specifically, for a solution, our proposed model integrates matching theory, BSUM, and convex optimization to optimize the association, transmit power allocation, and resource allocation. Finally, numerical results are provided.

Federated learning (FL) offers many benefits, such as better privacy preservation and less communication overhead for scenarios with frequent data generation. In FL, local models are trained on end-devices and then migrated to the network edge or cloud for global aggregation. This aggregated model is shared back with end-devices to further improve their local models. This iterative process continues until convergence is achieved. Although FL has many merits, it has many challenges. The prominent one is computing resource constraints. End-devices typically have fewer computing resources and are unable to learn well the local models. Therefore, split FL (SFL) was introduced to address this problem. However, enabling SFL is also challenging due to wireless resource constraints and uncertainties. We formulate a joint end-devices computing resources optimization, task-offloading, and resource allocation problem for SFL at the network edge. Our problem formulation has a mixed-integer non-linear programming problem nature and hard to solve due to the presence of both binary and continuous variables. We propose a double deep Q-network (DDDQN) and optimization-based solution. Finally, we validate the proposed method using extensive simulation results.

Energy consumption forecasting in microgrids is critical to ensure efficiency, reliability, and sustainability. It can be beneficial for optimizing grids, reducing costs, demand-supply balancing, and enhancing sustainability. The forecast scope can range from hours or days to months and years, based on the goal of the entity doing the prediction. In the case of microgrids, the focus tends to be in the short to medium range, hours to days to achieve efficient energy distribution, cost minimization, and renewable energy utilization. In this dynamic and localized setup, the energy consumption forecast is an integral part of the process. Therefore, in this paper, we explore different ways we can generate reliable forecasts of energy consumption by a group of residential houses from the Pecan Street dataset. Leveraging on the advancement of LLMs and transformers, we propose an LLM-based model and we benchmark our findings against other models. Our results highlight the advantage and performance that can be achieved with our transformer based which demonstrates a superior predictive accuracy over other architectures.

Fire poses significant ecological danger and can lead to human losses if not mitigated early. Fire detection systems on remote sensing devices have become critical to disaster prevention and management. In this paper, we propose a lightweight and effective fire detection model based on MobileViT-XS, compressed through the distillation of knowledge from a stronger teacher model. Our model combines the local feature extraction capabilities of convolutional networks with the global context capabilities of vision transforms. This allows our proposed model to achieve high detection accuracy and real-time inference, making it suitable for deployment on UAVs and other resource-constrained devices. Through rigorous experiments on the ADSF dataset, the proposed method achieves an accuracy, F1-score, and recall of 95.50%, along with a precision of 95.52%, thereby outperforming contemporary methods. Extensive evaluations on ADSF confirm that our method not only surpasses existing state-of-the-art techniques in accuracy but also provides significantly faster processing speeds.

Federated Learning (FL) allows collaborative training while ensuring data privacy across distributed edge devices, making it a popular solution for privacy-sensitive applications. However, FL faces significant challenges due to statistical heterogeneity, particularly domain heterogeneity, which impedes the global mode’s convergence. In this study, we introduce a new framework to address this challenge by improving the generalization ability of the FL global model under domain heterogeneity, using prototype augmentation. Specifically, we introduce FedAPC (Federated Augmented Prototype Contrastive Learning), a prototype-based FL framework designed to enhance feature diversity and model robustness. FedAPC leverages prototypes derived from the mean features of augmented data to capture richer representations. By aligning local features with global prototypes, we enable the model to learn meaningful semantic features while reducing overfitting to any specific domain. Experimental results on the Office-10 and Digits datasets illustrate that our framework outperforms SOTA baselines, demonstrating superior performance.

Recently, the research community has recently shown overwhelming interest in metaverse-enabled wireless devices, due to their compelling proactive learning and self-sustainability attributes. Proactive learning enables machine learning models to be trained before user requests, while self-sustainability allows a system to function with the least amount of assistance from network administrators/users. Because of these features, one can use metaverse to enable various applications (e.g., entertainment and collision avoidance) in intelligent transportation systems. However, the limitations of computing processing power (e.g., in autonomous cars) and communication resources make implementing metaverse-empowered vehicular networks challenging. Motivated by these facts, we present a new framework for cooperative sensing, communication, learning, and task offloading for vehicular networks enabled by the metaverse. Subsequently, we formulate a cost-function minimization problem that accounts for transmission energy and transmission latency. The cost is minimized by optimizing task offloading, wireless resource distribution, transmit power allocation, and sensing interval. We employ a decomposition-based strategy for simultaneous resource allocation, task offloading, sensing interval optimization, and transmit power allocation. Due to the combinatorial nature of the resource allocation and task offloading problems, matching-based solutions are used. For sensing interval optimization, convex optimization is used. On the other hand, due to the non-convex and continuous nature of the transmit power allocation problem, a proximal term is introduced into the objective function to approximate it as convex objective function, which is then solved using a convex optimizer. To gain further insights, the proposed scheme is supported by extensive numerical results.

Vision Large Language Models (VLMs) combine visual understanding with natural language processing, enabling tasks like image captioning, visual question answering, and video analysis. While VLMs show impressive capabilities across domains such as autonomous vehicles, smart surveillance, and healthcare, their deployment on resource-constrained edge devices remains challenging due to processing power, memory, and energy limitations. This survey explores recent advancements in optimizing VLMs for edge environments, focusing on model compression techniques, including pruning, quantization, knowledge distillation, and specialized hardware solutions that enhance efficiency. We provide a detailed discussion of efficient training and fine-tuning methods, edge deployment challenges, and privacy considerations. Additionally, we discuss the diverse applications of lightweight VLMs across healthcare, environmental monitoring, and autonomous systems, illustrating their growing impact. By highlighting key design strategies, current challenges, and offering recommendations for future directions, this survey aims to inspire further research into the practical deployment of VLMs, ultimately making advanced AI accessible in resource-limited settings.

In recent years, there has been a rising trend towards emerging applications (e.g., brain-computer interaction and haptics-based autonomous cars) with diverse requirements. To effectively enable these applications via autonomous operation and intelligent analytics, one can use a metaverseFor more details on how a metaverse can enable emerging applications and architecture, please refer to khan2024ametaverse. In a metaverse, we have two spaces: (a) a meta space based on a virtual model that performs analysis and resource management and (b) a physical space comprised of real world entities. A metaverse effectively enables emerging applications by performing three main tasks: (a) distributed learning of metaverse models; (b) instantly serving the end-users; and (c) sensing of the physical environment and sharing it with the meta space for synchronized operation. To perform these tasks, efficient wireless resource management is needed. Therefore, a novel resource scheduling framework for the wireless metaverse to enable various applications is proposed. Our aim is to minimize the cost of learning and sensing in metaverse. Subsequently, we formulate a problem. Meanwhile, the reliability as well as latency constraints of the service-requesting devices/users will be fulfilled. We assign multiple resource blocks to learning and sensing devices/units, whereas we use a concept of puncturing for service-requesting devices/users upon arrival. We use a scheme that is based on block successive upper-bound minimization and convex optimization for solving our formulated problem. At the end, we use empirical cumulative distribution function vs. cost and cost vs. metaverse entities for numerical evaluations.

Metaverse has gained rapid interest from the research community due to its various promising features. These features include proactive learning and self-sustainability. These features enable wireless systems with analysis prior to deployment, efficient resource management with strict latency, and operation with the least possible intervention from the operators. Therefore, deploying the metaverse for wireless systems will offer many benefits. However, metaverse signaling itself requires novel design. Therefore, in this work, a new framework using network virtualization for the metaverse is proposed. Such virtualization will provide more flexibility in terms of management by using the shared physical network resources to support different services. The proposed framework takes into account three key stakeholders, namely, the network operators, a metaverse operator, and the end-users. Resources will be purchased by a metaverse operator from network operators and allocated to users in the proposed framework. To carry out this interaction, a cost function is defined that considers both communication resources and computing resources. By optimizing communication resource management, computing resource management, association, communication resources cost, and computing resource management costs, the cost function is minimized. To achieve this, we propose a strategy based on matching theory and convex optimization. In order to demonstrate the effectiveness of the proposed scheme, numerical results are provided in the final section.

Recently, metaverse-empowered wireless systems have gained significant interest in the research community because of the appealing features of self-sustainability and proactive learning. Self-sustainability allows a system to run with the least amount of assistance from network administrators, whereas proactive learning allows for the development of machine learning models prior to user requests. As a result, the idea of the metaverse in vehicular networks can be used to enable a variety of applications (e.g., infotainment and collision avoidance) for a massive number of autonomous vehicles. However, metaverse-empowered vehicular networks are challenging to implement due to computing (i.e., at autonomous cars and network edges) and communication resource constraints. We present a novel framework for joint sensing, communication, and task offloading for vehicular networks empowered by the metaverse in order to address these issues. We formulate a problem to minimize a cost function that takes into account transmission latency, sensing, and transmission energy. Sensing interval, resource distribution, and task offloading are all optimized for minimizing the cost. We use convex optimization for the sensing problem while a decomposition-relaxation-based approach is used for joint resource allocation and task offloading. Finally, numerical results are provided to support the proposed scheme.

In contrast to methods relying on a centralized training, emerging Internet of Things (IoT) applications can employ federated learning (FL) to train a variety of models for performance improvement and improved privacy preservation. FL calls for the distributed training of local models at end-devices, which uses a lot of processing power (i.e., CPU cycles/sec). Most end-devices have computing power limitations, such as IoT temperature sensors. One solution for this problem is split FL. However, split FL has its problems, including a single point of failure, issues with fairness, and a poor convergence rate. We provide a novel framework, called hierarchical split FL (HSFL), to overcome these issues. On grouping, our HSFL framework is built. Partial models are constructed within each group at the devices, with the remaining work done at the edge servers. Each group then performs local aggregation at the edge following the computation of local models. End devices are given access to such an edge aggregated model so they can update their models. For each group, a unique edge aggregated HSFL model is produced by this procedure after a set number of rounds. Shared among edge servers, these edge aggregated HSFL models are then aggregated to produce a global model. Additionally, we propose an optimization problem that takes into account the relative local accuracy (RLA) of devices, transmission latency, transmission energy, and edge servers’ compute latency in order to reduce the cost of HSFL. The formulated problem is a mixed-integer nonlinear programming (MINLP) problem and cannot be solved easily. To tackle this challenge, we perform decomposition of the formulated problem to yield subproblems. These subproblems are edge computing resource allocation problem and joint RLA minimization, wireless resource allocation, task offloading, and transmit power allocation subproblem. Due to the convex nature of edge computing, resource allocation is done so utilizing a convex optimizer, as opposed to a block successive upper-bound minimization (BSUM)-based approach for joint RLA minimization, resource allocation, job offloading, and transmit power allocation. Finally, we present the performance evaluation findings for the proposed HSFL scheme.

Metaverse-empowered wireless system design is considered one of the promising candidates for the design of foreseeable future wireless systems. Therefore, in this paper, we consider energy-efficient (i.e., green) deployment of the metaverse at the network edge. We propose a framework for the deployment of the metaverse at the network edge using the concept of clustering over social networking. Then, we define a cost function that accounts for the energy consumption. We formulate an optimization problem to minimize energy consumption by optimizing clustering and resource allocation. The main problem is decomposed into two sub-problems: (a) clustering and (b) resource allocation. For both clustering and resource allocation, heuristic algorithms are proposed. Finally, we present numerical results.

Multi-access edge computing (MEC) is witnessed to be an integral part of emerging augmented reality (AR) / virtual reality (VR) applications. These applications require contents from the cloud, thus suffer from high latency that is not desirable. To address this issue, one can store the frequently requested content at the MEC server. However, MEC servers have limited computing capabilities. Additionally, there are significant variations in a number of requests from the MEC server. Therefore, we propose collaborative edge caching. Our collaborative edge caching will serve the end-users in collaboration to fully exploit the available caching resources at the network edge. We derive optimization scheme based on the alternating direction method of multipliers(ADMM). Finally, we perform numerical evaluations to demonstrate the effectiveness of our proposed scheme.

Recently, we have witnessed an increasing demand in augmented reality (AR)-based fifth-generation (5G) and beyond applications, such as smart gaming, smart navigation, smart military wearable, and smart industries. These AR-based applications require on-demand computational and caching resources with low latency that can be provided via multiaccess edge computing (MEC) server. However, due to the massive growth of AR-enabled devices, the MEC server resources might be insufficient. To overcome this challenge, we can utilize the computational and caching resources of user equipment (UE) to serve the other UEs in its close vicinity. Successfully enabling such interaction among devices requires an attractive incentive mechanism. Therefore, we propose a contract theory-based incentive mechanism for enabling on-device caching for AR-based applications. In our approach, the MEC offers a reward to the UE for providing its resources (i.e., storage capacity, power, etc.). Furthermore, under the information asymmetry problem, we derive an optimal mechanism via the contract theory for enabling on-device caching subject to the individual rationality and incentive-compatible constraints. Finally, we perform numerical evaluations to validate the effectiveness of our proposed scheme.

Edge Intelligence based on federated learning (FL) can be considered to be a promising paradigm for many emerging, strict latency Internet of Things (IoT) applications. Furthermore, a rapid upsurge in the number of IoT devices is expected in the foreseeable future. Although FL enables privacy-preserving, on-device machine learning, it still exhibits a privacy leakage issue. A malicious aggregation server can infer the sensitive information of other end-devices using their local learning model updates. Furthermore, centralized FL aggregation server might stop working due to security attack or a physical damage. To address the aforementioned issues, we propose a novel concept of socially-aware-clustering-enabled dispersed FL. First, we present a novel framework for socially-aware-clustering-enabled dispersed FL. Second, we formulate a problem for minimizing the loss function of the proposed FL scheme. Third, we decompose the formulated problem into three sub-problems, such as local devices relative accuracy minimization (i.e., end-devices local accuracy maximization) sub-problem, clustering sub-problem, and resource allocation sub-problem, due to the NP-hard nature of the formulated problem. The clustering and resource allocation sub-problems are solved using low complexity schemes based on a matching theory. The end devices' relative accuracy minimization problem is solved by using a convex optimizer. Finally, numerical results are provided for validation of the proposed FL scheme. Furthermore, we show the convergence of the proposed FL scheme for image classification tasks using the MNIST dataset.

Recent years have shown a remarkable interest in federated learning from researchers to make several Internet of Things applications smart. Although, federated learning offers users' privacy preservation, it has communication resources optimization challenge. In this paper, we consider federated learning for cellular networks. We formulate an optimization problem to jointly minimizes latency and effect of loss in federated learning model accuracy due to channel uncertainties. We decompose the main optimization problem into two sub-problems: resource allocation and device association sub-problems, due to the NP-hard nature of the main optimization problem. To solve these sub-problems, we propose an iterative approach which further uses efficient heuristic algorithms for resource blocks allocation and device association. Finally, we provide numerical results for the validation of our proposed scheme.

Traffic classification (TC) has a principal function in autonomous network management. Recently, deep learning and machine learning-based TC have become popular than the traditional port-based and protocol-based TC due to practices such as port disguise and payload encryption. The flow-based TC is reliable as it relies on time-related statistical features. Federated learning is a distributed machine learning technique to train improvised deep/machine learning models with less privacy distress. The organizations or enterprises having similar business models may take participation in building a federated model for their network traffic characterization. In this study, we build a cross-silo horizontal federated model for TC using flow-based time-related features. The federated model shows comparable performance to the centralized model.

Recent years have disclosed a remarkable proliferation of compute-intensive applications in smart cities. Such applications continuously generate enormous amounts of data which demand strict latency-aware computational processing capabilities. Although edge computing is an appealing technology to compensate for stringent latency-related issues, its deployment engenders new challenges. In this article, we highlight the role of edge computing in realizing the vision of smart cities. First, we analyze the evolution of edge computing paradigms. Subsequently, we critically review the state-of-the-art literature focusing on edge computing applications in smart cities. Later, we categorize and classify the literature by devising a comprehensive and meticulous taxonomy. Furthermore, we identify and discuss key requirements, and enumerate recently reported synergies of edge computing-enabled smart cities. Finally, several indispensable open challenges along with their causes and guidelines are discussed, serving as future research directions.