Through conducting equivalent model training within the paradigm of edge intelligence, the Digital Twin Edge Networks (DITEN) have been widely employed in the Industrial Internet-of-Things (IIoT) to facilitate the cost-effective execution without the operational disruption. However, due to the insufficient consideration of heterogeneity in computing and communication capabilities of distinct industrial terminals in the Digital Twin (DT) model training, the existing approaches of DT construction/update have unbalanced model training cost and loss in the whole life cycle of DT model, hindering the abilities of quick responding to complex and dynamic productions and ensuring the data consistency of virtual-real space. To address this issue, we define a global loss minimization problem with constraint, and propose an original approach of semi-asynchronous federated learning, named EDT-SaFL, as a promising solution. Considering the collaborative utilization of heterogeneous resources, and the contribution of local data quantity and quality to the global model update, the EDT-SaFL consists of three important operations,Terminal Selection for Model Training,Self-Adaptation of Local Training Iterations, andSemi-asynchronous Global Aggregation. With the analysis of convergence, complexity and communication overhead, the experiments have evidently demonstrated the superiority of EDT-SaFL on the datasets of CIFAR-10 and Industrial-Equipment.

With the rapid advancement of 6G, the task offloading has emerged as a critical issue for enhancing computational efficiency in the Industrial Internet of Things (IIoT). However, industrial devices are often constrained by computing power, energy and mobility, challenging the delay-sensitive and compute-intensive tasks consisting of subtasks with complex dependencies, e.g., industrial image recognition. Given the increasing task complexity, developing efficient offloading strategies in dynamic multislot industrial scenarios with mobile devices remains a challenge. To address this issue, a task offloading scheme for industrial image recognition in digital twin edge networks (DITENs) is proposed. By leveraging the digital twin (DT) to accurately model the states of mobile industrial tasks and edge servers, the task offloading is formulated to optimize the weighted sum of task processing delay and energy consumption, that is proven to be NP-hard. Since the task of image recognition can be represented as a directed acyclic graph (DAG), the dependencies between subtasks are extracted using graph convolutional network (GCN) to generate optimal execution priorities for task offloading. Through proving the optimization problem as a Markov decision process (MDP), an improved multiagent deep deterministic policy gradient algorithm, named$\epsilon $-ATN-MADDPG, incorporating the$\epsilon $-greedy strategy and the self-attention mechanism to enable efficient decision-making in dynamic environments, is designed to offer a promising solution. Experimental results on the KolektorSDD dataset demonstrate that this solution outperforms compared methods.

A critical challenge for predicting urban traffic flows is to simultaneously process time series and spatial features from heterogeneous traffic data collected by diverse Internet of Things (IoT) devices. Despite the advent of Transformer-based models with an advanced network structure and excellent prediction performance, standard Transformer models are still struggling to combine both spatial information and temporal relations of traffic flows. To address these challenges, we design a novel Transformer network, namely temporal-spatial traffic-flow Transformer (TST-Trans), for traffic flow prediction with high accuracy. In particular, we use learnable position encoders to replace traditional fixed position encoders. Meanwhile, we introduce a spatiotemporal embedding method that integrates temporal relationships and spatial information with external inputs, thereby capturing the spatiotemporal dependencies of traffic flows. Experiments with the real-world datasets demonstrate that our proposed TST-Trans achieves better prediction accuracy than state-of-the-art methods while requiring fewer parameters. The research results increased by more than 10% compared with Transformer. Compared to spatiotemporal deep hybrid neural network, there is a 2% to 10% improvement in performance on different datasets.

In 6G-enabled vehicle-to-edge networks, through deploying computing power resources closer to mobile vehicles for providing low latency and highly reliable services, Mobile Edge Computing (MEC) as an emerging paradigm has promoting mobile vehicles with limited capacities to come with diversified artificial intelligence (AI) applications. Nevertheless, the computing power of MEC server is still finite, seeking the optimal resource pricing and allocation strategies for MEC servers, and determining the optimal computation offloading for intelligent vehicle applications, still remain challenging issues that are necessary to be reasonably solved to improve the service experience. To address this issue, a scenario that multiple intelligent vehicle applications cooperatively initiate computation offloading requests in 6G-enabled multi-server multi-access vehicle-to-edge computing systems is considered in this paper, and with the defined reasonable utilities for MEC servers and intelligent vehicle applications, a solution of bidding-enabled dynamic resource pricing for computation offloading is proposed. Concretely, through considering the relationship of resource supply and demand, and the bidding among MEC servers, a dynamic resource pricing scheme is designed for MEC servers, meanwhile, with the complete consideration of dynamic resource pricing and time-varying wireless channel interference in multi-cell networks, a Q-learning based offloading decision algorithm is proposed for intelligent vehicle applications. Simulation experiments finally are conducted to demonstrate the efficiency in achieving the win-win situation with guaranteed utilities for both MEC servers and intelligent vehicle applications.

With 52.8 billion RFID tags used worldwide in 2024, a common basic functionality needed by RFID-enabled applications is cardinality estimation — to quickly estimate the number of distinct tags in an RFID system. Although many advanced solutions have been proposed over the past decade, they suffer from one major limitation in practical use: they need to either modify the existing RFID standard or obtain MAC-layer information, both of which however cannot be supported by commercial off-the-shelf (COTS) devices. In this paper, we revisit the counting problem and propose a novel counting scheme called average time duration based counter (ATD) that quickly estimates the number of distinct tags in a standards-compliant manner. Compared with existing work, the competitive advantage of ATD is that it can be directly deployed on a COTS RFID system, with no need for any hardware modifications. In ATD, we found a new and measurable indicator — the time duration between two adjacent singleton slots, which depends on the number of tags. Following this observation, we derive the theoretical relationship between the time indicator and the number of tags and then give the proof of the estimation as well as its parameter settings. Additionally, we propose a flag-flipping solution to address the overlapping problem in the multi-reader case. We implement ATD in a COTS RFID system with 1000 tags. Experimental results show that ATD is$4.2\times $faster than the baseline of tag inventory; the performance gain will be further increased in a larger RFID system.

Emotion recognition as a technology to correctly understand individual emotions could provide guidance for psychological adjustment. Therefore, it is necessary to develop accurate and effective emotion recognition models and algorithms. With the emerging technologies of artificial intelligence and the popularity of video surveillance, the use of neural networks for facial emotion recognition has been proven to be more efficient than traditional methods. However, it still has room for improvement in the delay and robustness of simple neural networks. To address this issue, an optimized convolutional neural network (CNN) enabled facial emotion recognition within collaborative edge computing is investigated in this paper. Within the paradigm of collaborative edge computing, the Raspberry Pi 3B+ acting as the edge computing node is employed to deal with the related issues of multi-view facial emotion recognition. The optimized CNN models deployed on the edge nodes are adopted to collaboratively extract facial features from images and conduct the classification to achieve facial emotion recognition. In terms of the recognition results, the corresponding appropriate psychological adjustment strategies would be pushed to the target. Through using the OpenCV library to implement a prototype on Raspberry Pi 3B+, the experimental results ultimately have been shown to demonstrate the efficiency of the investigations.

As a typical deterministic network, the Industrial Internet of Things (IIoT) has strict requirements on the task processing delay. IIoT leverages edge computing to deliver low-latency services efficiently. However, this requires mobile Internet of Things (IoT) devices to execute reasonable task offloading decisions. To minimize disruption in IIoT operations and facilitate cost-effective execution, our approach capitalizes on the synergy of Digital Twin (DT) for enhanced virtual-real coordination in decision-making. We introduce an innovative solution for mobile inspection tasks within a DITEN-enhanced IIoT framework. This solution, grounded in A-MADDPG based partial offloading, not only addresses the challenges posed by IIoT but also transforms the problem into an optimization problem with constraints. By conceptualizing it as a Markov Decision Process (MDP), we integrate a carefully designed attention mechanism into the MADDPG algorithm, named as Attention enhanced Multi-Agent Deep Deterministic Policy Gradient(A-MADDPG), forging a robust and effective solution. Experimental results underscore the superiority of our proposed method, demonstrating remarkable convergence and outperforming existing baselines in reducing task processing latency.

In vehicular ad-hoc networks, vehicle-to-vehicle fog computing (VFC) can not only alleviate the computing delay of inference tasks from vehicles, but also reduce the computational overheads of RSUs. Existing studies on cooperative vehicle task computation offloading assume that RSUs can obtain global computing capability information of vehicles and the service-providing vehicles are always willing to offer services, while overlooking the privacy and selfishness of vehicles. Motivated by contract theory, we propose a joint service caching and task offloading NP-hard problem for vehicular fog computing, aiming to maximize the minimum service completion rate and to offer incentives for both service vehicles and RSUs. By designing contract-based joint service caching and task offloading algorithms, vehicles are encouraged to provide fog computing resources while protecting privacy. Extensive simulation results show that the proposed greedy algorithm CGA can improve the minimum service completion rate by over 10.8% and 14.7%, given fixed number of edge servers, when compared to a benchmark algorithm without contract, and a designed contract-based algorithm that maximizes the total throughput. Moreover, the designed contract-based approximation algorithm CRA can achieve the performance that are close to the benchmark algorithm without contract.

Digital twin (DT) is a virtual representation of physical entities or processes that enables real-time monitoring, analysis, and optimization in the field of intelligent manufacturing. By simulating and optimizing production processes, DT technology could predict and prevent equipment failures, and enhance the efficiency and quality of industrial parts production. However, effectively deploying DTs into Digital Twin Empowered Edge Network (DITEN) in complex Industrial Internet of Things (IIoT) environments remains a significant challenge. Particularly in scenarios with numerous physical entities within IIoT, optimizing the deployment of DTs on edge nodes to minimize interaction latency with physical entities, as well as reducing workload and energy consumption on edge nodes, becomes crucial. To address this challenge, this paper first designs a Bi-Layer DT architecture for IIoT. Furthermore, an Intrinsic Curiosity Module-based Multi-Agent Proximal Policy Optimization algorithm (ICM-MAPPO) is proposed to solve the optimal deployment problem for DTs in DITEN-Empowered IIoT. Numerical experiments validate the effectiveness of the ICM-MAPPO algorithm in minimizing deployment latency and interaction latency while achieving load balance and reducing energy consumption.

Efficient image segmentation algorithms are critical in computer vision, as they maintain high processing speeds while handling large amounts of data and providing practical solutions in resource-limited environments. While existing classical segmentation methods achieve good results, their real-time performance can be further improved. To address this issue, we propose an efficient segmentation network (ESNet) to capture extensive contextual information and improve segmentation fineness, which are two main issues in semantic segmentation, while ensuring real-time capability. Then, we first introduce an efficient context module (ECM) that effectively enlarges the effective receptive field (ERF) of the model and improves its performance in integrating contextual information. Subsequently, a skip connection with a simple feature fusion module (SFFM) is designed to provide rich detail information, thereby improving segmentation fineness. The efficacy of ESNet was evaluated on the PASCAL VOC2012 semantic segmentation dataset against several state-of-the-art methods. ESNet achieves 71.4 FPS at a resolution of 1024×2048 on a single NVIDIA GeForce RTX 3090 GPU and achieves 62.42% mIoU at a resolution of 320×480 with an extremely simple training recipe, striking a fine balance between segmentation accuracy and inference speed.

The objective of smoke segmentation is to distinguish the smoke area from the background in smoky images, thereby providing essential information for the subsequent smoke removal process. However, current smoke segmentation algorithms consistently underperform in terms of accuracy. To address this challenge, we first developed a new smoke segmentation dataset comprising over 2000 images, each with comprehensive smoke annotations. The dataset can enhance the precision of smoke segmentation and serve as a foundation for training and testing. Then, we designed a smoke prior module to improve the efficacy of smoke removal. This module generates soft attention maps, which can strategically assign the weight of smoke details within the image. Finally, to validate the effect of smoke removal, we have also seamlessly incorporated the smoke prior module into the image fusion, which is crucial for enhancing the overall image clarity and detail. Extensive experimentation demonstrates that the proposed method outperforms state-of-the-art segmentation models in terms of segmentation accuracy and also achieves superior performance on smoke removal tasks.

The Industrial Internet of Things (IIoT) imposes strict requirements on task processing delays. To ensure low-latency services, the edge Computing Power Network (CPN) integrates various multi-domain resources, including computing, storage and communication, enabling fast processing and responsiveness. However, the performance of the CPN is significantly influenced by the scheduling scheme for these multi-domain resources. To explore an optimal scheduling scheme, this paper proposes a mathematical optimization model for the resource scheduling problem. The problem is then transformed into a Markov Decision Process (MDP) and the Discrete Probabilistic Deep Deterministic Policy Gradient (DP-DDPG) algorithm, which modifies the actor network of the original DDPG to output a discrete probability vector, is introduced to obtain the optimal scheme. Experimental results demonstrate that the proposed approach reduces latency within the constraints of limited multi-domain resources, validating its feasibility and effectiveness in IIoT scenarios.

Unmanned aerial vehicle (UAV) assisted data collection has been extensively employed in various application scenarios, e.g., nonterrestrial networks for disaster management, agricultural crop protection, environmental monitoring. However, data collection and transmission model in different applications are not universal, and the timeliness of large-scale data collection and transmission also has been remained as a challenge. To address this issue, artificial intelligence (AI)-empowered intelligent search algorithms for path planning in UAV-assisted data collection networks are investigated in this article. With the constraints, including energy consumption, transmission distances, and full coverage of sensors, a data collection model using UAV in hovering mode is first established for minimizing the flight distances of UAVs, and an adaptive full coverage algorithm (AFCA) is proposed to optimize the Quality of Service through using the model. Subsequently, for optimizing the path planning of UAVs, an intelligent path planning algorithm (IPPA) is proposed through considering the loop and noncrossing characteristics presented by the optimal paths. In six testing cases with different sensor sizes, the experimental results have been shown to demonstrate that the proposed solution outperforms the traditional algorithms.

The design and performance analysis of underwater acoustic sensor networks (UASNs) have attracted intensive attention. In this study, we present a theoretical framework to evaluate the performances of UASNs. In contrast to existing methods, we applied a new communication protocol model to characterize the channel interference by taking into account the unique characteristics of underwater acoustic channels, namely, the concurrent transmission opportunities owing to the large propagation delays of acoustic signals. Using the communication protocol model, we investigated the collision regions of a communication pair and then derived a closed-form expression for the successful packet transmission probability. Moreover, we considered practical networks where each node is equipped with a limited data buffer to store its generated packets. Using collision analysis and a stationary buffer distribution, we derived the closed-form expression of system performance in terms of the throughput and the packet queue delay. Finally, we validated the accuracy of our analysis via extensive simulation results. The impacts of various network parameters on the system performance are also evaluated.

In the paradigm of ubiquitous edge computing, with those advantages, e.g., high mobility, fast response, flexibility and controllability, and low cost of use, Unmanned Aerial Vehicles (UAVs) could be used not only as relays to assist with data collection, but also as computing power nodes to process uncomplicated computational workloads from ground users. Especially, UAVs could be employed to provide alternative computing power resources in field, lake, post-disaster and other complex regional environments. In this paper, to address the issue of computing power scheduling in UAVs empowered aerial computing systems, a scenario where multiple UAVs from the same departure station cooperatively fly over hovering points and achieve the data collection and computation in a decentralized manner is investigated. Nevertheless, due to limited onboard battery capacities of UAVs and diverse service requests of ground users, it is necessary to optimize energy efficiency and service fairness for improving mission execution capabilities of UAVs and the quality of service (QoS) experienced by ground users, and a joint optimization problem of energy efficiency and service fairness is formulated. Through considering complex coupling associations among the departure station, flight paths and hovering points of UAVs, the problem is investigated from the trajectory planning of UAVs and the location planning for both the departure station and hovering points. Proving investigations to be Markov decision processes (MDP), multi-agent cooperation approaches are proposed as promising solutions, and simulation results have been shown to demonstrate that the performance achieved by the proposal outperforms that achieved by schemes commonly used in literatures.

Along with emerging mobile Internet applications embedded in tremendous growth of computing demand, mobile edge computing (MEC) could effectively address the issue of compute-intensive and latency-sensitive computation imposed on mobile terminals through performing computation offloading strategies. However, how to find optimal decisions of transmission power, computing capacity demand, and offloading demand at the end-user and how to determine the resource pricing and allocation at the MEC server with the limited computing capacity still remain challenging issues in operating the MEC system in an optimal fashion. For multiuser in signal cell network with MEC, a dynamic pricing-based computation offloading solution is investigated in this article. Through the use of Q-learning algorithm comprehensively considering those sensitive factors, e.g., time cost, energy consumption and dynamic pricing, the offloading decision at the end-user is achieved with the consideration of time-varying wireless channel conditions. According to the resources supply and demand relationship, a dynamic pricing algorithm for the MEC server is designed to adjust the pricing strategy to achieve the win–win situation. Simulation results have been shown to demonstrate the efficiency in making offloading decision while the wireless channel is fast fading and the resource pricing is adjusted dynamically, and in enhancing utilities for both end-users and the MEC server.

Nowadays, video surveillance is widespread used to achieve security life in the construction of smart city. As a result, prevalence of video surveillance equipments and technologies enables pedestrian identification and tracking to be research hotspots in the field of computer vision, whose development and application are of great significance to the construction of a good social security environment. However, pedestrian identification and tracking in monitoring scenarios still have problems of low recognition accuracy and high model complexity, and computer vision based adaptive recognition methods still have a large room for improvement and development. To address this issue, real-time pedestrian identification and tracking within adaptive collaboration edge computing environment is investigated in this paper. Within the paradigm of edge computing, the Raspberry Pi 3B+ acting as the edge computing node is adopted to handle the related issues of pedestrian identification and tracking. The combination of HOG (Histogram of Oriented Gradient) and SVM (Support Vector Machine) is investigated to achieve pedestrian identification, where, HOG is employed as the feature descriptor and SVM is employed as the classification algorithm. Furthermore, the pixel-based visual tracking algorithm is investigated to achieve effective and uninterrupted pedestrian tracking. By implementing a prototype on Raspberry Pi 3B+ using OpenCV libraries, the experimental results finally have been shown to demonstrate the efficiency of the investigations.

Intelligent transportation is an important guarantee for the safety and efficiency of urban transportation in smart cities, and regular road pavement inspection is the focus of road and bridge maintenance in intelligent transportation. Cracks in concrete pavement are the most common type of pavement damage and the earliest sign of pavement deterioration. However, existing crack detection algorithms suffer from incomplete crack detection and are easily disturbed by pseudo-cracks such as water spots and leaves. To address the above problems, this paper proposes a convolutional neural network (CNN) method that introduces a gradient module and an attention mechanism. The method adopts a CNN model based on the VGG-16 structure as the main body of the network structure, and optimally adjusts the network structure by incorporating a gradient layer and a self-attention mechanism, accelerating the convergence speed of network training and the global information learning ability. A negative sample dataset with pseudo-cracks, such as leaves, water spots and branches was constructed, and comparative experimental analysis was conducted in terms of both visual judgment and objective indicators. The experimental results show that after the introduction of the gradient layer and the self-attentive mechanism, not only the convergence speed of the network training is faster, but also the cracks in the concrete pavement images can be segmented more completely and accurately.

As an advanced method of multivariate data analysis, structural equation modeling (SEM) is to obtain relationships among latent variables in structural models. One characteristic of SEM models is that the same substructures exist in structural models with the same evaluated values. Thus, structural models can be obtained by searching for relationship subgraphs representing substructures. Based on the finding, a decision-making subgraph mining algorithm (DmSMA) is proposed to search for subgraphs which potentially belong to structural models. Experiments of SEM implemented by DmSMA are conducted to indicate that searching for decision-making subgraphs is helpful to obtain effective structural models. As shown by the experimental results including two performance metrics, DmSMA performs better than the compared algorithms to solve SEM through mining decision-making subgraphs.

With the development and application of Internet of Things (IoT) technology, IoT has been widely used in agriculture, industry, and urban construction. In the process of building Smart cities, setting up small-scale weather stations based on IoT technology can effectively monitor certain special environments where large weather stations cannot accurately assess and predict short-term extreme weather events. As the summer heat approaches, the number of heatstroke cases is continuously rising. The Wet Bulb Globe Temperature (WBGT) index, which is closely related to heatstroke, provides a simple method for evaluating the thermal work environment and thermal load of workers in hot conditions. In this paper, through adjusting the model structure and moving window, and optimizing the predictive model parameters, an improved Long Short Term Memory (LSTM) algorithm is proposed to forecast WBGT values at future time points: five minutes, thirty minutes, and sixty minutes ahead. The paper also conducts a simple analysis of the daily average performance of WBGT in relation to air humidity. Additionally, it compares dual-input models that include air humidity as input. Through a comparison of four prediction performance evaluation metrics, simple-input LSTM models demonstrate lower error.

Recently, social networking software is widespread used to achieve intelligent life in the construction of smart city, and sharing selfies on social platforms has been a trend of interaction. As a result, beauty software as a popular tool has been widely welcomed by social media users. Along with the development of beauty technology, the popular beauty software in the market include Qingyan, Meitu, VSCO and so on, whose functions continue to be expanded as users demand for image beautification. However, those functions tend to be manually adjusted by users, which would easily result in facial asymmetry. To address this issue, the principles and key points of several classical beauty algorithms are thoroughly investigated in this paper, such as skin beauty, beauty makeup, image artistry, portrait deformation and sharpening filter. In the experiments, the 68 face feature points in Dlib library are used to perform face detection and locate feature points, and Gaussian filtering, bilateral filtering, local translation and bilinear interpolation methods are used to realize the functions of these beauty algorithms. The analysis results have been shown to demonstrate the efficiency of the investigations.

In the context of edge and fog computing, urban mobility prediction acting as an important role in urban planning, traffic prediction, and resource reservation has making a great contribution for the construction of smart cities, and has been considered to be a challenging research and industrial topic for many years. Generally, those popular prediction methods abstract trajectories into independent points in the manner of gridding, clustering and others. However, these data processing methods make the position representation vector lose the connection relationship between geographic locations which is very important for the mobility prediction. To address this issue, this paper proposes a discrete position relationship model to represent the connection between geographic locations, on the basis, a Long Short Term Memory (LSTM) prediction model is established to predict the next position of the mobile target. Experiments and numerical analyses show that these investigations can take full advantage of the relationship between relative positions and reduce the prediction relative error.

As an efficient development for industrial and scientific applications, workflow technologies have received substantial attention in recent decades. To address the issue of workflow scheduling in a state-of-the-art cloud environment, based on analysis of a decentralized architecture for workflow scheduling, a dependable scheduling strategy with active replica placement (DS-ARP) is proposed in this paper. In this proposal, by analyzing control/data dependencies in a workflow, a game-theory-based active replica placement model is first developed to achieve reasonable replica placement; then, a dependable scheduling algorithm is proposed to enhance the system reliability and security. With five well-known workflow applications, CloudSim-based simulations are performed, and the analytical results are shown to demonstrate the performance of DS-ARP on an average number of initiated replicas, costs resulting from canceled replicas, makespans, deadline violation rates and resource utilization rates.

With the fast development of mobile Internet, Internet of Things (IoT) has been found in many important applications recently. However, it still faces many challenges in security and privacy. Blockchain (BC) technology, which underpins the cryptocurrency Bitcoin, has played an important role in the development of decentralized and data intensive applications running on millions of devices. In this paper, to establish the relationship between IoT and BC for device credibility verification, we propose a framework with layers, intersect, and self-organization Blockchain Structures (BCS). In this new framework, each BCS is organized by Blockchain technology. We describe the credibility verification method and show how it provide the verification. The efficiency and security analysis are also given in this paper, including its response time, storage efficiency, and verification. The conducted experiments have been shown to demonstrate the validity of the proposed method in satisfying the credible requirement achieved by Blockchain technology and certain advantages in storage space and response time.

Sensing devices acting as interconnected data sources are becoming increasingly ubiquitous in concepts of Internet of Things (IoT)-enabled smart cities, but they typically lack physical protection and are susceptible to being compromised. To address this issue, a great-alternative-region (GAR)-based approach for deploying network monitors to locate compromised data sources is proposed. The GAR concept is introduced according to the network topology and connectivity characteristics, and the GARs with the most complete connectivity are identified as the candidate monitor locations, thereby transforming the problem of monitor deployment into a traditional K-center problem. Based on the demonstrated relationship between the monitor locations and the locating accuracy, the optimization objective for reasonably deploying monitors is designed to minimize the maximum number of hops between the data sources and their nearest monitors, and the optimal deployment pattern is achieved using an improved genetic algorithm. Finally, simulation-based results are presented to illustrate the performance of this approach.