ABSTRACT The integration of artificial intelligence (AI) and the Internet of Things (IoT) has given rise to AIoT systems. However, the accelerated proliferation of AIoT ecosystems introduces substantial communication and networking difficulties. Mobile edge computing (MEC) has emerged as a promising solution to address time‐sensitive computational demands. This paper addresses the improvement of information freshness, a critical enabler for real‐time decision‐making in dynamic, resource‐constrained AIoT environments. We formulate the UAV‐assisted MEC system as a Markov decision process with the objective of minimizing the age of information (AoI). To this end, we propose an adaptive federated multi‐agent soft actor‐critic framework for resource scheduling. This framework leverages maximum entropy to enable robust exploration and incorporates an innovative adaptive federated learning mechanism by adopting a trainable network to predict the parameter matrix of federated learning. This enables federated learning to better promote knowledge sharing among multiple agents, thereby accelerating convergence and improving performance. Experimental results validate that our approach significantly outperforms state‐of‐the‐art reinforcement learning based algorithms in AoI minimization, stability enhancement, and task completion volume improvement, thereby advancing the safeguarding of communication and networking in AIoT systems.

With the rapid increase in computing demand for the Internet of Vehicles (IoV), the limited on-board computing resources have gradually become a bottleneck restricting the efficient processing of tasks. Unmanned aerial vehicles (UAVs), with their high mobility and flexible deployment capabilities, have become an ideal platform for assisting IoV task offloading. However, the dynamic environment and the mobility of vehicles pose significant challenges for task offloading and resource allocation in UAV-assist IoV networks. This paper proposes a soft asynchronous actor-critic (SAAC) framework with vehicle trajectory prediction based on deep reinforcement learning (DRL) for UAV-assisted IoV task offloading. Firstly, in order to solve the problem of poor stability of traditional multi-agent deep reinforcement learning algorithms in dynamic environments, this paper combines the asynchronous training of multi-agent systems with the soft update and target network mechanism to improve the anti-interference and stability of the algorithm. Secondly, a module based on a recurrent neural network (RNN) integrated with a sliding window mechanism is proposed to address the uncertainty arising from vehicle mobility. This module enables precise prediction of vehicle trajectories, thereby facilitating forward-looking flight strategy planning for UAVs and reducing task transmission delays. Simulation results show that the proposed algorithm is effective, therefore this paper provides a new framework for the UAV-assisted IoV task offloading.

Statistical heterogeneity poses a formidable challenge to federated learning (FL), resulting in inconsistent training objectives and serious biases in local feature representations among FL clients. Recent research on neural collapse has identified an optimal simplex equiangular tight frame (ETF) for the structure of mean class feature vectors and classifier vectors under a balanced data distribution. However, the amount of data pertaining to each class in every FL client, as well as the distribution of existing classes across all FL clients, are both imbalanced. Therefore, we first confirm the occurrence of minority collapse in imbalanced FL scenarios through experimentation. Then, we propose the FedAMA algorithm to mitigate its adverse impact by enforcing adaptive pushing forces to minority classes in the global training stage and re-adjusting the structure of the mean feature and classifier vectors in the local fine-tuning stage. Finally, we theoretically analyze the global convergence of FedAMA and establish its upper bound. Extensive experiments have also been carried out to demonstrate that FedAMA outperforms existing algorithms in terms of global and personalized model performance, particularly in highly heterogeneous settings.

Most existing methods for visual domain adaptation need to convert high-order tensors into one-order high-dimensional vectors through naive vectorization operations. However, they not only destroy the internal spatial structure within the original high-order tensors, but also result in exponentially increasing model parameters. To address these problems, we propose a novel method for visual domain adaptation by representing tensorial features in tensor-train subspace in this paper. Specifically, we firstly provide a theoretical deduction by constructing a tensor-train subspace and proving its linearity and left-orthogonality. Secondly, to extract common tensorial features between source and target domains, we formulate the visual domain adaptation problem into an optimization problem that models the aforementioned common tensor-train subspace between two domains, as well as their corresponding projections. Thirdly, we design a tensor-train subspace representation algorithm (TTSR) to solve the multiple variables optimization problem by optimizing its sub-problems iteratively, so as to process high-order tensorial features. Finally, we evaluate the performance of our proposed TTSR algorithm by conducting extensive experiments on three popular public datasets. The experimental results demonstrate that the TTSR algorithm can improve the classification accuracy of unlabeled target domain than that of baseline algorithms.

The rapid development of edge computing and the Industrial Internet of Things have facilitated near real-time optimization of compute-intensive industrial tasks. Mobile edge computing (MEC) and device-to-device (D2D) offloading are promising ways to achieve near-real-time optimization. In this article, We propose a D2D-assisted MEC computing offloading framework by using deep reinforcement Learning (DRL) with entropy and attention mechanism (DMOEA). DMOEA considers interactions among related entities, including horizontal device-to-device collaboration and vertical device-to-edge offloading. Then, a DRL-based model with multi-actor single-critic structure is designed to solve the offloading strategy. In addition, to further improve efficiency, an attention mechanism is introduced to adapt dynamic changes in network and enhance the exploration ability. The experimental results show that the proposed framework can obtain a fast convergence rate and small oscillation amplitude and also can effectively reduce latency.

The low-rank matrix completion problem is fundamental in both machine learning and computer vision fields with many important applications, such as recommendation system, motion capture, face recognition, and image inpainting. In order to avoid solving the rank minimization problem which is NP-hard, several surrogate functions of the rank have been proposed in the literature. However, the matrix restored from the optimization problem based on the existing surrogate functions seriously deviates from the original one. In this paper, we first design a new non-convex Schatten capped$p$norm which generalizes several existing non-convex matrix norms and balances between the rank and the nuclear norm of the matrix. Then, a matrix completion method based on the Schatten capped$p$norm is proposed by exploiting the framework of the alternating direction method of multipliers. Meanwhile, the Schatten capped$p$norm regularized least squares subproblem is analyzed in detail and is solved explicitly. Finally, we evaluate the performance of the proposed matrix completion method based on extensive experiments in the field of image inpainting. All the experimental results demonstrate that the proposed method can indeed improve the accuracy of matrix completion compared with the existing methods.

Summary It is well known that virtual network (VN) embedding (VNE) aims to solve how to efficiently allocate physical resources to a VN. However, this issue has been proved to be an NP‐hard problem. Besides, as most of the existing approaches are based on heuristic algorithms, which is easy to fall into local optimal. To address the challenge, we formalize the problem as a mixed integer programming problem and propose a novel VNE method based on reinforcement learning in this article. And to solve the problem, we introduce a pointer network to generate virtual node mapping strategies through an attention mechanism, and design a reward function related to link resource consumption to build the connection between node mapping and link mapping stages of VNE. In addition, we present a policy gradient optimization mechanism to leverage the reward information obtained from the sampled solutions, and design an active search based process to automatically update the parameters of the neural network and to obtain near‐optimal embedding solution. The experimental results show that the proposed method can improve the performance in average physical node utilization and long‐term revenue to cost ratio comparing than that of the existing models.

Internet of Things (IoT) can be used to promote many advanced applications by utilizing the sensed data collected from various settings. To reduce the energy consumption of IoT devices, and to extend the lifetime of network, the sensed data are usually compressed before their transmission through compressed sensing theory. By reconstructing the sensed data at the edge of network with more resourceful devices, such as laptops and servers, the intensive computation and energy consumption of the IoT nodes could be effectively offloaded. However, most of the existing data collection schemes are limited in their scalability, because the unified data reconstruction models of them are not suitable for large-scale surveillance scenarios. In our proposed scheme, the whole network is first partitioned into a number of data correlated clusters based on spatial correlation. Then, a data collection tree is built to collect the compressed data in a hybrid mode. Finally, the data reconstruction problem is modelled as a group sparse problem and solved through using an alternating direction method of multiplier-based algorithm. The performance of data communication and reconstruction of the proposed scheme is evaluated through experiments with real data set. The experimental results show that the proposed scheme can indeed lower the amount of data transmission, prolong the network life, and achieve a higher level of accuracy in data collection compared to existing data collection schemes.

The paper proposes a novel signal reconstruction algorithm through substituting the gradient descent method in the iterative hard thresholding algorithm with a faster sparse randomized Kaczmarz method. By designing a series of gradually attenuated weights for the matrix rows whose indexes lie outside of the support set of the original sparse signal, we can focus the iterations on the effective support rows of the measurement matrix. The experiment results show that the proposed algorithm presents a faster convergence rate and more accurate reconstruction accuracy than the state-of-the-art algorithms. Meanwhile, the successful reconstruction probability of the proposed algorithm is higher than that of other algorithms. Moreover, the characteristics of the proposed signal reconstruction algorithm are also analyzed in detail through numerical experiments.

Summary Efficient and fair resource allocation for multitudinous virtual networks running cloud‐based applications is crucial to archive dynamic resources multi‐tenancy in cloud computing. In order to solve the problem, we propose a novel virtual network embedding (VNE) algorithm to increase revenue and utilization of substrate network as well as to improve acceptance fairness of virtual networks. First, we present a virtual topology pre‐transformation mechanism leveraging reusable technology to reduce topology difference and achieve acceptance fairness. Then, because of the Non‐deterministic polynomial‐time (NP)‐hard characteristics of VNE, we model the problem as an integer linear programming problem and solve the VNE problem with a discrete particle swarm optimization‐based algorithm. The operations and parameters of particles are well redefined according to the VNE context. Finally, an incentive convergence mechanism is proposed to reduce mapping complexity, which can be used to accelerate convergence and to save more bandwidth by exploiting individual candidate nodes' lists. Simulation results prove that our proposed method is superior to the existing similar algorithms in terms of physical resource utilization, acceptance fairness, revenue/cost ratio, and searching efficiency. Copyright © 2016 John Wiley & Sons, Ltd.

The constrained capacity of wireless sensor nodes and harsh, unattended deploy environments make the data collected by sensor nodes usually unreliable. We have proposed a count-min sketch based anomaly detection scheme with the goal of detecting the anomaly data values in WSN. In this paper, we analyze the performance of the proposed scheme thoroughly. We show through experiments with real sensed data that the proposed anomaly detection scheme can provide a higher detection accuracy ratio and a lower false alarm ratio than the existed schemes. Meanwhile, it requires less storage space and consumed energy than the non-sketch based anomaly detection scheme.

A wireless mesh network (WMN) presents a new wireless network technology for building commercial mobile ad hoc networks. However, security in WMN has not received enough attention in the research community. One main challenge in designing WMNs is the vulnerability of such networks to malicious attacks. In this paper, we propose a zone-based distributed key management scheme for WMNs in which we show that the proposed scheme would improve key management in security, expandability, validity, fault tolerance and usability.

A wireless mesh network (WMN) is a new wireless network technology and there is a trend to adopt the technology to build commercial mobile ad hoc networks. Since a WMN is such a network without fixed infrastructure and is operated in an open medium, any user within the range covered by radio wave may access the network. Therefore, a critical requirement for the security in WMN is the authentication of a new user who is trying to join the network. In this paper, we present a new authentication scheme based on a combination of techniques, such as zone-based hierarchical topology structure, virtual certification authority (CA), off-line CA, identity-based cryptosystem and multi-signature. We show that our scheme would improve authentication in security, computational overhead, traffic, authentication latency and storage space.

A mobile ad hoc network is a multi-path autonomous system comprised of many mobile nodes with wireless transmission capability. In this paper, we first review current research in intrusion detection in ad hoc networks. Then, by considering the characteristics of such networks in which free movement of mobile nodes can lead to frequent topological changes, especially network separation and convergence, we propose an intrusion detection scheme based on a combination of techniques, such as hierarchical topology structure, distributed voting, off-line CA and composite key management, and show that the proposed scheme could improve intrusion detection in the areas of security, expandability, validity, fault tolerance and usability.

As a fundamental requirement for providing security functionality in sensor networks, key management plays a central role in authentication and encryption. In this paper, we propose the adaptive key selection (AKS) scheme and the adaptive key selection algorithm for secure multiple deployment in sensor networks that target at providing high connectivity between different deployment sets of sensor nodes. Our simulation shows that the AKS scheme can greatly improve the connectivity of sensor nodes while maintaining the security of an existing multiple deployment scheme at the same time.