Search

In the realm of multi-UAV-assisted mobile edge computing (MEC), the joint optimization of UAV deployment and task scheduling has emerged as a potent approach for mitigating energy consumption while ensuring high-quality services for mobile users. Nevertheless, the intricate interdependence between UAV deployment and task scheduling presents formidable challenges when implementing this scheme. In response, we introduce a novel methodology called the Dual-Stage Hybrid Strategy with Genetic-Simulated Annealing and Knowledge Sharing (DSHSGSK). DSHSGSK employs an alternating optimization strategy known as HS-GSK, supplemented by an elimination operator, to simultaneously optimize UAV deployment and task scheduling. In pursuit of heightened efficiency in UAV deployment and a more effective task scheduling strategy, we propose an innovative location encoding scheme for UAVs. To harness the local search capabilities of the Harmony search (HS) algorithm and the global search capabilities of the Gaining Sharing Knowledge based Algorithm (GSK), we introduce a coordination parameter (CP) to modulate the frequency of alternation between these two optimization techniques. Experimental results validate the superiority of our proposed method over other state-of-the-art algorithms for jointly optimizing multi-UAV deployment and task scheduling. Notably, our approach excels in terms of energy consumption, underscoring its exceptional performance. [ABSTRACT FROM AUTHOR]

Sudden medical safety accidents or large-scale outbreaks of epidemics will lead to a surge in traffic near hospitals and other medical infrastructure, and traditional edge base stations cannot cope with sudden traffic demands. In addition, the patient's data of health information is private, it is necessary to protect the patient's health information. Therefore, aiming at the practical problems that edge base stations cannot cope with a large number of communication requests and how to protect patients' private data under sudden medical safety accidents, this paper combines hierarchical federated learning with UAV-assisted mobile edge computing environment to build a UAV-assisted MEC system architecture for federated learning. However, federated learning is closely related to participating nodes. Without satisfactory rewards, users and UAVs will be unwilling to consume computing resources and communication resources to participate in federated learning. Therefore, this paper introduced the Stackelberg game and incentive mechanism into federated learning. The interaction between user devices, UAV, and the base station is modeled as a Stackelberg game to determine the maximum amount of data required for model training and the number of user devices and UAV. The incentive mechanism determines the task allocation and reward allocation of federated learning and determines the maximum benefits of three participants in the game process to improve the quality of user devices and the performance of the federated learning model. Experimental results show that the proposed algorithm can inspire user devices, which have high-quality data, to participate in federated learning training, improve training accuracy and maximize social welfare. [ABSTRACT FROM AUTHOR]

With the advancement of the 5G networks, edge computing (EC) assisted Internet of Things (IoT) based applications demand real-time computation and high-volume data-intensive services. Due to the heterogeneity and limited resources of the edge nodes (ENs), and dynamic resource demand of the IoT applications, it is challenging to place the IoT services into the available ENs by ensuring performance measurements on quality of services (QoS). In this paper, a novel quantum-inspired particle swarm optimization-based service placement (QPSO-SP) algorithm is proposed for EC environment. The QPSO-SP is intended to achieve desired service placement while optimizing throughput, energy consumption, delay, and computation load of the system. Quantum particle (QP) is designed to represent a complete solution for IoT service placement in an EC environment. Decoding of the QP is done by using a novel double-hashing technique. The fitness function uses throughput, delay, energy consumption, and load balancing parameters. Extensive simulation is performed and comparison is done with the standard existing algorithms. The parametric study, Taguchi method is conducted. The statistical analysis, ANOVA, followed by Friedman test is also done. The simulation results indicate that the proposed QPSO-SP outperforms existing works in terms of energy consumption, delay, throughput, and load balancing. • A Quantum-Inspired PSO is proposed to address IoT service placement. • Quantum particle is designed to represent complete IoT service placement solution. • The decoding of quantum particle is done using a novel double-hashing technique. • Fitness function considers throughput, energy consumption, delay and load balancing. • Simulation shows efficacy of the proposed work with statistical analysis. [ABSTRACT FROM AUTHOR]

Asynchronous Federated Learning (AFL) has been introduced to improve the efficiency of FL by reducing the latency of Machine Learning (ML) model aggregation, particularly in the Internet of Things (IoT) environment. Meanwhile, decentralized FL, such as leveraging blockchain and directed acyclic graph (DAG)-based ledgers, also has drawn much attention to the integration of FL owing to the security benefit against single-point-failure and Byzantine fault tolerant consensus. We observe that the inherent network asynchrony of DAG-based ledgers is beneficial for implementing asynchronous FL particularly in edge computing domains, even though there is no existing survey work that provides a fundamental overview of such integration. This paper surveys on the integration of asynchronous FL with DAG, which we call AFL-DAG, as a promising approach to realize the intersection of decentralized FL and asynchronous FL. Motivated by the lack of a concrete taxonomy of asynchronous FL and a global model, especially with decentralized FL, we introduce universally applicable terminologies and the extensive classification method of FL in terms of asynchrony. Based on the proposed taxonomy, we present a generic system model of AFL-DAG for edge computing applications. To provide a horizontal overview and cover fundamental concepts in AFL-DAG, we identify four critical design factors and the state-of-the-art solutions are discussed accordingly. Future directions to achieve a practical AFL-DAG are also highlighted. Finally, we explore the opportunities of AFL-DAG by investigating a popular edge computing application, the on-device crowdsourcing, and provide a high-level evaluation of AFL-DAG compared to blockchained-FL. [ABSTRACT FROM AUTHOR]

Approximately one-third of human food is derived from flowering plants, and 80% of those plants require honeybees for pollination. However, climate change is affecting bees as well as the beekeeping industry. Having continuous information on the condition of honey bee colonies would be helpful in studying new diseases such as colony collapse disorder, as well as in developing novel beekeeping tools to improve the health management of bee colonies. In this study, an audio monitoring system is established based on Internet of Thing (IoT) technology to record the sounds produced by bees. A colony status classification model coupled with a machine learning algorithm is used to analyze the sound data of bee colonies under various treatments to classify the colony conditions, such as queenless, virus-infected, and pesticide-contaminated. With an edge computing framework, the classification is done by the monitoring system, which greatly reduces data transmission delay and cloud computing burden. The field test results show that the accuracy and F 1 -score for the classification model for the beehive under various treatments reach 98.8% and 0.98, respectively. The proposed IoT-based audio monitoring system for beehives can assist beekeepers and users in managing bee colonies more effectively by providing automatic, accurate, and real-time monitoring information regarding the current colony conditions. [ABSTRACT FROM AUTHOR]

In recent years, multi-access edge computing (MEC) has become a hot topic. With its distributed characteristics, MEC provides more possibilities for delay-sensitive tasks. In this paper, we study a task offloading problem to shorten task delay. The problem consists of two aspects, bandwidth allocation and task offloading decision-making. Based on alliance game, we formulate bandwidth allocation to minimize the dissatisfaction of alliances. Game participants are all users. We take into account the dissatisfaction of each alliance and find the least dissatisfaction of the alliance. Then, we formulate the task offloading decision-making to minimize task delay. Task delay consists of communication delay and execution delay. Computing and storage capacity are treated as limiting conditions for decision-making. To solve the offloading problem, we convert the dissatisfaction of alliance into a vector, and obtain the Pareto optimal through multi-objective particle swarm algorithm. Then, we use Branch and Bound method to construct the propagation tree to facilitate decision-making. To evaluate the edge servers in the tree, we build an evaluation matrix and transform the matrix to a set of evaluation index which is used on task offloading decision-making. A large number of experimental results show that our algorithm is better than compared algorithm. • The alliance game is used to program the bandwidth allocation problem. • A delay sensitive task offloading problem is formulated. • Multi-objective particle swarm algorithm is used to optimize bandwidth allocation. • The Branch and Bound method is used to construct the propagation tree. [ABSTRACT FROM AUTHOR]

• A CIDS architecture applied to mobile edge computing is proposed. • A task offloading scheduling algorithm based on DQN is proposed. • The task scheduling process is modeled by Markov decision process. • The loss function and objective function are established based on DQN. • Memory playback is introduced to solve the dimensional disasters in Q-learning. Due to the performance and resource limitations of wireless devices at the edge of the network, the intrusion detection system deployed on the mobile edge network will cause severe packet loss when faced with large traffic. Based on this, a collaborative intrusion detection system (CIDS) architecture applied to mobile edge computing is proposed, which can offload part of the detection tasks to an intrusion detection system with better performance and resources on the edge server. On this basis, a task offloading scheduling algorithm based on Deep Q Network (DQN) is proposed. First, the time delay, energy consumption, and offloading decision models are established. Then, the task scheduling process is described as a Markov decision process and the relevant space and value function are established. Finally, the problem of excessive state and action space in Q-learning is solved by the Deep Q Network. Experiments have shown that our proposed scheme enables the system to have advantages over the comparative algorithms in terms of response time, energy consumption, and packet loss rate, etc.. [ABSTRACT FROM AUTHOR]

With the development of mobile augmented reality (MAR) technology, the demand for MAR applications is increasing. However, MAR is rarely used in mobile devices due to its high computational and energy consumption. In this paper, we study the task offloading and parameters optimization of MAR applied to mobile devices in mobile edge computing. Considering the influence of the MAR client energy consumption, service delay and detection accuracy in the task offloading and parameters optimization process, we design a function to evaluate MAR client energy efficiency. The problem of task offloading and parameters optimization is formulated to minimize energy efficiency function under the limitation of MAR task completion time and wireless bandwidth resources. To solve this problem, we propose a server selection and parameters optimization (SSPO) algorithm to realize client task offloading and parameters optimization. The SSPO algorithm first generates priority queue of tasks. Based on the order of priority queue, tasks are offloaded to appropriate mobile edge server according to the analytic hierarchy process. After that, the parameters are calculated and the tasks are redistributed according to the completion time until the energy efficiency function converges. Simulation results show that the proposed algorithm is better than the comparison algorithm. • A multi-MAR client and multi-server system is considered. • We design a function that balances energy, delay and detection accuracy. • We aim to minimize the designed function adjust MAR client parameters. • We design a server selection and parameter optimization algorithm. [ABSTRACT FROM AUTHOR]

Equipment condition monitoring holds immense significance in modern industrial factories, facilitating sustained operation with heightened efficiency, safety, and cost-effectiveness. This paper presents an interactive networked condition monitoring strategy to enhance plant-wide production equipment condition monitoring, leveraging networked control and edge computing approaches. This strategy offers a rapid and efficient solution that comprises four key components: drag-and-drop monitoring algorithm design, executable program generation, networked algorithm implementation, and interactive monitoring process. Initially, algorithms for equipment condition monitoring are designed using pre-defined components and then seamlessly compiled into executable programs with a single click. Subsequently, these algorithms are implemented within an edge computing-based monitoring system using the networked control approach, where the generated programs are remotely deployed into edge nodes positioned adjacent to the equipment. Moreover, the monitoring process features visual displays of parameters and results using configurable widgets, enabling interactive adjustments. Real-world application cases from an aluminum manufacturing factory showcase the strategy's effectiveness in comprehensive condition monitoring of hundreds of equipment across nine workshops, significantly reducing the equipment inspection time to tens of minutes compared to manual inspection. With extensive implementation in various industrial factories, this strategy emerges as a promising solution for equipment condition monitoring in smart factories. • Proposing an interactive networked condition monitoring strategy. • Swift algorithm design and conversion into executable programs. • Deployment of executable programs on remote edge nodes. • Provision of interactive monitoring processes by intuitive visual widgets. [ABSTRACT FROM AUTHOR]

In this paper, nearly 40 commonly used deep neural network(DNN) models are selected, and their cross-platform and cross-inference frameworks are deeply analysed. The main metrics of accuracy, the total number of model parameters, the computational complexity, the accuracy density, the inference time, the memory consumption and other related parameters are used to measure their performance. The heterogeneous computing experiment is implemented on both the Google Colab cloud computing platform and the Jetson Nano embedded edge computing platform. The obtained performance is compared with that of two previous computing platforms: a workstation equipped with an NVIDIA Titan X Pascal and an embedded system based on an NVIDIA Jetson TX1 board. In addition, on the Jetson Nano embedded edge computing platform, different inference frameworks are investigated to evaluate the inference efficiency of the DNN models. Regression models are established to characterize the variation in the computing performance of different DNN classification algorithms so that the inference results of unknown models can be estimated. ANOVA methods are proposed to quantify the differences between models. The experimental results have important guiding significance for the better selection, deployment and application of DNN models in practice. Codes are available at this https URL https://github.com/Foreverzfy/Model-Test. [ABSTRACT FROM AUTHOR]

F ederated L earning (FL) enabled edge computing has been widely used in training complex deep learning models by coordinating various heterogeneous resources in I ndustrial I nternet of T hings (IIoT). However, the existing FL solutions may cause long training time or huge energy consumption for resource-constrained terminal or edge nodes. To address this issue, we propose an adaptive edge intelligence offloading framework based on F ederated S plit L earning (FSL) and R einforcement L earning (RL), named FSLEdge, for IIoT systems. To begin with, a S plit L earning (SL) approach was added to FL to reduce the training time and energy consumption by allowing local devices to offload some training layers into the edge servers while ensuring the protection of private data. Additionally, FSLEdge adopts RL to find the optimal split point to adaptively identify which is the best layers of the deep learning models should be offloaded into the edge servers with the goal of reducing the training time and energy consumption. Experimental studies are conducted under two different datasets: one public, CIFAR10, and one private, GridDataset, a transmission line fault detection dataset in smart grid domain. And the results show that the training time and energy consumption of the system by our proposed FSLEdge can be reduced by 10% and 21%, respectively, compared to the classical FL, without sacrificing accuracy. [ABSTRACT FROM AUTHOR]

In recent years, edge computing has made up for the shortcomings of cloud computing's centralized data processing. It migrates computation to edge devices close to users, which reduces the user's transmission time, calculation time, propagation time, and other times, so it meets the request of delay-sensitive tasks. In this multi-access edge computing system, edge devices are divided into different cooperation spaces. Edge devices in the same cooperation space collaborate with others through sharing resources. Tasks are divided into multiple computations, each of which can be executed on different edge devices. A task offloading problem is formulated to minimize the average delay of all tasks in multi-access edge computing system. An algorithm based on ant colony optimization is proposed in order to find the best solution for task offloading. To make better decisions in the first iteration, the pheromone matrix is initialized considering two factors of base station load and distance between users and base stations. According to the relationship between fitness function and the global optimal value or local optimal value, the values of pheromones are updated dynamically. A large number of experiments show that our algorithm has better performance. • A multi-server, multi-user edge computing system is considered. • Our goal is to minimize the average delay. • For BS selection, we consider the two factors of base station load and distance. • Task Offloading combine Ant Colony Optimization Algorithm is designed. [ABSTRACT FROM AUTHOR]

The emerging technologies in both wireless communication and automation driving that have enabled vehicles to communicate with infrastructure, and with each other, are collectively known as connected vehicle and automated vehicle (CAV) technology. In existing connected automated vehicle-based and traditional traffic control systems, urban arterials with signalized intersections still face issues, including local demand uncertainty and automation level compatibility. Here, a distributed signal control system that integrates automated vehicle path planning information is adapted to address these issues. The proposed method includes planning-based local demand estimation and demand-aware max pressure control in an edge computing environment. A bivariable automation model is developed to represent the various, i.e., L1-L5, automatic driving levels. A real district with typical scenarios is implemented to verify the proposed method. The simulation results show that the proposed demand-aware edge control provides better control results than benchmarks for almost all different performance indices and network demands. The proposed control reduces the waiting time by up to 30%, and the time loss decreased by up to 20%. Moreover, better performances are always obtained at different automation levels, so there is a good compatibility of the automation driving for the adaptation of the CAV flows, especially at the L3-L5 levels. [ABSTRACT FROM AUTHOR]

• Propose a privacy-preservation signaling game for edge-based IoT networks. • Obtain optimal privacy preservation strategies from theoretical and practical views. • Address the problem of obtaining the convergent game equilibrium in practice. • Have a lower computational complexity available to real-life implementation. Data privacy leakage can be severe when a malicious Internet of Things (IoT) node sends requests to gather private data from an edge-computing-based IoT cloud storage system across the edge nodes. To solve this problem, a privacy-preservation signaling game for edge-computing-based IoT networks is proposed to characterize the interactions between an IoT node and its corresponding edge node when managing an IoT resource-grant system. Optimal privacy preservation strategies for edge nodes are then theoretically derived. A signaling Q-learning algorithm is then designed to address the problem of achieving convergent equilibrium and game parameters from a practical perspective. The theoretical results are validated using simulations that focus on two statistical points (i.e., the optimal probability of an IoT node requesting maliciously and the posterior probability of an IoT node being malicious). By comparing the proposed signaling Q-learning algorithm with the greedy algorithm benchmark, the proposed algorithm is shown to more effectively decrease the optimal probability of an IoT node sending malicious requests. Thus, privacy preservation for edge-computing-based IoT cloud storage systems can be strengthened. [ABSTRACT FROM AUTHOR]

With the development of cloud technology, hierarchical and distributed cross-cloud architecture is gradually replacing traditional centralized architecture, for example, used in edge (or fog) computing. Due to the fluctuation of resource requirements, if a node does not have sufficient resources to process requests, the same or higher-level nodes can share their resources by offloading or redirecting requests to themselves, at the possible cost of reduced service quality. However, it is difficult to effectively optimize the sharing effect based on mean requirements. We formulate the multilevel problem with horizontal and vertical resource sharing using stochastic models, identify the optimal structures with embedded subproblems, and obtain the approximation solution in an efficient dynamic programming manner. In the problem setting with a wide range of different parameters, the proposed algorithm can outperform existing mean and heuristic algorithms in all scenarios to improve the total satisfied requirements by up to 26%, and can be hundreds of times faster than these heuristic algorithms. • The demand fluctuation in edge clouds is a new challenge for resource scheduling. • We formulate the general problem in hierarchical and distributed edge clouds. • The problem has non-linear object with non-linear constraints. • We identify the nested subproblems with their optimal condition. • The algorithm outperforms the existing mean and heuristic based algorithms. [ABSTRACT FROM AUTHOR]

The heat generation is significant in the machining process, leading to thermal errors, and finally the geometric precision of machined parts is reduced. So the precision machine tool is a key factor in determining the geometric precision of complex parts. In recent years, the error control method is applied. But the method fails in reducing thermal errors because it cannot effectively process large-volume data, resulting from its low executing efficiency. To solve above issues, a new intelligent digital-twin prediction and reverse control system is designed for thermally induced errors based on the user-edge-cloud architecture to expedite the executing efficiency. The data-driven error modeling method is augmented by an error mechanism-based modeling to express the thermal error as a function with the temperature, armature current, rotational speed, and ambient temperature as independent variables, and then the long-term memorizing behavior of thermal errors is demonstrated. The error model is established based on an improved wavelet threshold denoising (IWTD) and a (long short-term memory) LSTM network to describe the memorizing behavior, and IWTD-LSTM network error prediction model is embedded into the digital-twin system. The digital-twin system and IWTD-LSTM network model were verified on a precision machine tool. With the implementation of the digital-twin system, the thermal error and the volume of the transferred data are reduced by 88.72% and 56.36%, respectively. [ABSTRACT FROM AUTHOR]

Existing deep learning-based low-altitude small object detectors are typically complex in model architecture and demand substantial computational resources, making deployment for real-time detection tasks on edge computing devices challenging. To address this issue, we proposed EL-YOLO, an efficient and lightweight onboard applications object detector. Initially, in order to maintain a lightweight design and improve model accuracy, we propose a novel approach called Sparsely Connected Asymptotic Feature Pyramid Network(SCAFPN). This approach aims to eliminate inter-layer interference during feature fusion, thereby enhancing the model's performance. Furthermore, to establish long-range contextual relationships for small object scale information, we devise a Cross-Space Learning Multi-Head Self-Attention mechanism (CSL-MHSA). To assess EL-YOLO capability for onboard small object detection, we deploy it on the embedded NVIDIA Jetson Xavier Nx platform and employ NVIDIA TensorRT FP16 quantization acceleration. On the VisDrone2019-DET and AI-TOD datasets, EL-YOLO demonstrates a 12.4% and 1.3% improvement in mAP50 compared to YOLOv5s. In comparison with the state-of-the-art YOLOv8s proposed in 2023, it achieves a respective 2.8% and 10.7% increase in mAP50. Moreover, the inference speed for the Small model reaches 24 frames per second, while the Nano model achieves 35 frames per second. This method holds promise for direct integration onto unmanned aerial vehicles for aerial small object detection tasks in the future. [ABSTRACT FROM AUTHOR]

Smart vehicles have a rising demand for computation resources, and recently vehicular edge computing has been recognized as an effective solution. Edge servers deployed in roadside units are capable of accomplishing tasks beyond the capacity which is embedded inside the vehicles. However, the main challenge is to carefully select the tasks to be offloaded considering the deadlines, and in order to reduce energy consumption, while delivering a good performance. In this paper, we consider a vehicular edge computing network in which multiple cars are moving at non-constant speed and produce tasks at each time slot. Then, we propose a task offloading algorithm, aware of the vehicle's direction, based on Rainbow, a deep Q-learning algorithm combining several independent improvements to the deep Q-network algorithm. This is to overcome the conventional limits and to reach an optimal offloading policy, by effectively incorporating the computation resources of edge servers to jointly minimize average delay and energy consumption. Real-world traffic data is used to evaluate the performance of the proposed approach compared to other algorithms, in particular deep Q-network, double deep Q-network, and deep recurrent Q-network. Results of the experiments show an average reduction of 18% and 15% in energy consumption and delay, respectively, when using the proposed Rainbow deep Q-network based algorithm in comparison to the state-of-the-art. Moreover, the stability and convergence of the learning process have significantly improved by adopting the Rainbow algorithm. • We propose a Rainbow-based task offloading algorithm for vehicular networks. • The proposed algorithm aims to jointly minimize average delay and energy consumption. • The performance of the proposed approach is evaluated using real-world traffic data. • Experiments demonstrate significant improvement achieved by the proposed algorithm. [ABSTRACT FROM AUTHOR]

The openness of the intelligent vehicle network makes it easy for selfish or untrustworthy vehicles to maliciously occupy limited resources in the mobile edge network or spread malicious information. However, most of the existing trust models rely on evaluating vehicles or data at the application level. For selfish or forgery attacks in intelligent vehicle networks, we propose a trusted deep reinforcement learning (DRL) cybersecurity approach for computation offloading to evaluate the safety and reliability performance in IoT edge networks, including our intelligent system model and a Deep Policy Gradient Action Quantization (DPGAQ) scheme. By introducing a reputation record table and designing a highly decisive communication trusted computing mode, we can accurately predict the untrusted selfish attack of vehicle in the task offloading of the Internet of things. Furthermore, in the multi-vehicle scenario, because the trusted offloading decision is a mixed integer programming problem, which leads to the dimension explosion of channel state and space, we propose a joint action-value quantization with attention mechanism to approximate the continuous actions values to a limited number of discrete values. Because it is not only inefficient but also unnecessary to generate high-dimensional decision actions in each time frame, we prune the infeasible action decisions by order preserving pruning to reduce the computational complexity of training and achieve efficient training on the premise of ensuring accuracy. To verify the feasibility and effectiveness of our proposed algorithm, millions of channels of edge vehicle networks are used as the input data. The simulation results show that compared with the benchmark trust model, DPGAQ achieves more than 72% reputation level, and improves 11%, 10% and 11% respectively in precision, recall and F-score. [ABSTRACT FROM AUTHOR]

Industry 5.0 (I5.0) is increasingly governed by Operation Technology and Information Technology. It hosts Deep Learning (DL) solutions as a premier tool for the informatization of Quality Inspection (QI) of Mass Produced Products (MPP) and Mass Customized Products (MCP) at the on-premise edge devices. Besides, these ever-evolving MCPs in I5.0 require newer DL models to informatize customized quality parameters, mandating significant storage and computing resources, that is challenging to achieve at resource-constraint edge platform. This work proposes PackMASNet , a continual learning-based information integration scheme that sustainably incorporates the QI information of multiple MCPs in a single Deep Neural Network (DNN) under the following constraints: (i) resource-limited on-premise edge devices, (ii) no access to prior product data, and (iii) negligible deterioration of quality information of frequently manufactured MPPs. A lightweight Cosine-similarity threshold mechanism is incorporated to leverage the benefits of knowledge transfer (cloning) while avoiding its adverse impact in multi-varied MCPs. The scheme proposes DNN performance, storage, computation, data, and time efficient solutions for industries implementing the edge computing paradigm on I5.0. The efficacy of the proposed scheme is validated for the predictive QI of real-world use case in injection molding. The scheme preserves the frequently used information of MPP by 99.07%, saves computation cost by 132 times, reduces the DNN training time by 20.45%, and improves overall performance by 43.60% over the state-of-the-art schemes. • A customer order-driven informatization framework for mass-customized products. • A hybrid PackMASNet scheme that minimizes mass-produced and customized products' performance degradation. • Lightweight Cosine-similarity threshold-based cloning mechanism for resource constraint edge. • Performance validation in a real-world predictive quality inspection of injection molding. [ABSTRACT FROM AUTHOR]

Federated learning is an attractive distributed learning paradigm, which allows resource-constrained edge computing devices to cooperatively train machine learning models, while keeping data locally. However, the non-IID data distribution across devices is one of the main challenges that affect the performance of federated optimization algorithms. Inspired by knowledge distillation, this paper proposes a federated optimization algorithm, Federated Codistillation (FedCodl), in which a distillation term is added to the local objective function, so that local models can be trained on outputs of the global model. We further extend FedCodl to Federated Two-way Codistillation (Fed2Codl) to personalize local models for each device, meanwhile the global model is retained and iteratively updated in parallel. Then, we theoretically provide convergence guarantees for our approaches when learning strongly convex and smooth models. Finally, extensive experiments on federated benchmark datasets demonstrate that our approaches can achieve superior performance under the challenge of multiple non-IID data distribution settings on traditional and deep learning architectures, in terms of classification accuracy and communication efficiency. The biggest accuracy improvement against the standard Federated Averaging (FedAvg) framework is up to 22.26% over all communication rounds. Our results show the potential of the proposed approaches for further applications in federated learning. • A federated optimization framework based on knowledge codistillation is proposed. • An extension is presented to hold a personalized model for each federated device. • Theoretical convergence guarantees for our algorithms are provided. • Performance of the proposed schemes is evaluated on diverse federated benchmarks. [ABSTRACT FROM AUTHOR]

Nowadays, video surveillance systems are commonly found in most public and private spaces. These systems typically consist of a network of cameras that feed into a central node. However, the processing aspect is evolving towards distributed approaches, leveraging edge-computing. These distributed systems are capable of effectively addressing the detection of people or events at each individual node. Most of these systems, rely on the use of deep-learning and segmentation algorithms which enable them to achieve high performance, but usually with a significant computational cost, hindering real-time execution. This paper presents an approach for people detection and action recognition in the wild, optimized for running on the edge, and that is able to work in real-time, in an embedded platform. Human Action Recognition (HAR) is performed by using a Recurrent Neural Network (RNN), specifically a Long Short-Term Memory (LSTM). The input to the LSTM is an ad-hoc, lightweight feature vector obtained from the bounding box of each detected person in the video surveillance image. The resulting system is highly portable and easily scalable, providing a powerful tool for real-world video surveillance applications (in the wild and real-time action recognition). The proposal has been exhaustively evaluated and compared against other state-of-the-art (SOTA) proposals in five datasets, including four widely used (KTH, WEIZMAN, WVU, IXMAX) and a novel one (GBA) recorded in the wild, that includes several people performing different actions simultaneously. The obtained results validate the proposal, since it achieves SOTA accuracy within a much more complicated video surveillance real scenario, and using a lightweight embedded hardware. • Real-time action recognition based on LSTMs with an ultralight feature vector. • Experimental results on for widely used dataset and a novel dataset in-the-wild. • Comparison to other state-of-the-art methods. • Achieves accuracy close to state-of-the-art while reducing computational cost. • Proposal runs in real time in an embedded platform. [ABSTRACT FROM AUTHOR]

Highlights • Handling large volumes of acquired data is challenging for remote monitoring. • Edge classification and compression is a promising solution for smart health. • Adopting data transmission based on patients state enables efficient monitoring. • Leveraging edge computing increases energy efficiency and decreases latency. Abstract Smart healthcare systems require recording, transmitting and processing large volumes of multimodal medical data generated from different types of sensors and medical devices, which is challenging and may turn some of the remote health monitoring applications impractical. Moving computational intelligence to the network edge is a promising approach for providing efficient and convenient ways for continuous-remote monitoring. Implementing efficient edge-based classification and data reduction techniques are of paramount importance to enable smart healthcare systems with efficient real-time and cost-effective remote monitoring. Thus, we present our vision of leveraging edge computing to monitor, process, and make autonomous decisions for smart health applications. In particular, we present and implement an accurate and lightweight classification mechanism that, leveraging some time-domain features extracted from the vital signs, allows for a reliable seizures detection at the network edge with precise classification accuracy and low computational requirement. We then propose and implement a selective data transfer scheme, which opts for the most convenient way for data transmission depending on the detected patient's conditions. In addition to that, we propose a reliable energy-efficient emergency notification system for epileptic seizure detection, based on conceptual learning and fuzzy classification. Our experimental results assess the performance of the proposed system in terms of data reduction, classification accuracy, battery lifetime, and transmission delay. We show the effectiveness of our system and its ability to outperform conventional remote monitoring systems that ignore data processing at the edge by: (i) achieving 98.3% classification accuracy for seizures detection, (ii) extending battery lifetime by 60%, and (iii) decreasing average transmission delay by 90%. [ABSTRACT FROM AUTHOR]

This paper investigates resource allocation in cognitive radio (CR) based mobile edge computing (MEC) systems under time-varying channels while considering non-orthogonal multiple access (NOMA) technique. In contrast to prior research on NOMA-MEC, we introduce a generalized user grouping scheme, which makes the secondary users (SUs) have the flexibility to participate in multiple NOMA groups simultaneously, enabling the partial offloading of their task data to multiple MEC servers. To tackle the non-convex long-term energy minimization problem, we propose a decomposition based soft actor–critic (DB-SAC) approach combining conventional convex optimization with deep reinforcement learning (DRL) algorithms, which divides the problem into a joint communication and computation resource allocation subproblem and an offloading ratios optimization subproblem. The former one is further divided into a series of local computation resource and offloading energy minimization problems, addressed through theoretical analysis and convex optimization techniques. For the latter subproblem, we adopt the SAC algorithm to dynamically allocate offloading ratios for SUs. Simulation results showcase that when compared to the conventional non-generalized user grouping scheme, the generalized user grouping scheme can achieve remarkable energy savings of up to 87.5%. • Introduces flexibility for SUs to join multiple NOMA groups. • Combines convex optimization with DRL for resource allocation. • Splits the problem into communication-computation and offloading ratio subproblems. • Generalized user grouping leads to up to 87.5% energy savings compared to conventional scheme. [ABSTRACT FROM AUTHOR]

Crowdsourcing offers the prospect of a more open and socialized approach to product development by bringing together crowdsourcing community resources and connecting open innovation participants. Doing this effectively involves finding an optimal combination of crowdsourcing resources. However, the crowdsourcing community typically focuses on realizing a wide variety of different micro-tasks to meet overall customer requirements, giving rise to numerous potential ways of combining service resources. The parties making up different crowdsourcing community platforms also have various kinds of privacy preferences, making it hard for operators to disclose all of the information relevant to the development of a particular product. This paper proposes a privacy-aware strategy for the optimal combination of crowdsourcing product development resources based on edge computing and cloud computing. Product development application scenarios are examined that envisage the deployment of privacy-aware edge computing and collaboration between a central cloud and edge-based crowdsourcing communities. The crowdsourcing community environment and its privacy risk model are analyzed and the construction and presentation of cloud crowdsourcing platforms for complex tasks are studied. A mechanism for uncovering the optimal cross-platform combination of crowdsourcing product development services based on privacy-aware cloud-edge collaboration is then elaborated, together with a technique for implementing the proposed mechanism via a cooperative bacteria foraging optimization (CBFO) algorithm. Random test data was obtained based on a cloud crowdsourcing platform and two sets of validation tests were undertaken that show that the proposed method can preserve the privacy of crowdsourcing communities, while efficiently solving the problem of the cross-platform mobilization of crowdsourced product development resources. The approach is compared with more basic bacteria foraging optimization (BFO) and genetic algorithm (GA)-based techniques and it is found that CBFO offers better computational performance when confronted with convergence and other factors that can influence the resource combination optimization model, such as a change in the number of micro-tasks. [ABSTRACT FROM AUTHOR]

Edge computing is a novel and potential computing model which moves storage and computing capabilities to the network edge, substantially decreasing service latency and network traffic. The existing Internet of Things (IoT) network offloading algorithm faces limitations such as a fixed number of applications, high edge-to-edge delay, and reliance on a single Mobile Edge Computing (MEC) server, posing security and privacy concerns. Moreover, resource-constrained mobile devices need more effective data integration and compression strategies. Addressing these challenges, this study suggests an approach based on deep reinforcement learning (DRL), specifically the SAV (State Action Value) Oriented QL (Q-Learning) based Task Offloading method, to optimise task offloading and resource allocation in edge-cloud computing. The model aims to empower Mobile Devices (MDs) to develop optimal offloading decisions for long-term Quality Perception, utilising a neural network to establish the relationship between MD state and action value. The paper introduces a Recurrent Extended Memory Network (REMN) to capture dynamic workload behaviour at Edge nodes (ENs). It incorporates Quality Mapping, Quality Estimation, and a Quality-Aware DRL Task Offloading Algorithm to improve the accuracy and efficiency of the offloading procedure in MEC systems. This systematic approach improves overall system performance and enables MDs to leverage ENs for neural network training, reducing computational burdens. As a result, it can accomplish a more significant number of tasks, reducing latency from 0.74 ms to 7.168 ms and decreasing energy consumption from 270 J to 1820.39 J for tasks ranging from 10 to 50, respectively. [ABSTRACT FROM AUTHOR]

The openness of Mobile Edge Computing (MEC) networks makes them vulnerable to interference attacks by malicious jammers, which endangers the communication quality of mobile users. To achieve secure computing, the conventional method is that the mobile device reduces the attacker's malicious interference by increasing the transmission power. However, the cost of power defense is unacceptable in MEC with resource shortages. Therefore, this paper considers a novel defense strategy based on time-varying channel and describes the malicious interference countermeasure process as a multi-user intelligent game model. Because the interference model and interference strategy are unknown, this paper proposes a deep reinforcement learning multi-user random Game with Post-Decision State (named GPDS) to intelligently resist intelligent attackers. In the GPDS algorithm, mobile users need to obtain the communication quality, spectrum availability, and jammer's strategy from the state of the blocked channel. The reward of the optimal decision strategy is defined as the expected value of the maximum channel throughput, and the potential optimal channel selection strategy is obtained through Nash equilibrium. After GPDS training, mobile users can learn the optimal channel switching strategy after multi-step training. The experimental results show that the proposed GPDS achieves better anti-jamming performance, compared with SOTA algorithms. • We first model the MEC anti-jammer as a multi-user continuous game. • A post decision state is proposed to deal with dynamic unknown information. • A minimax gradient strategy is proposed to realize learning generalization. • State-of-the-art methods are outperformed in both parameters and performance. [ABSTRACT FROM AUTHOR]

The user demand increment and resource restrictions in IoT can provide efficient services without considering the service cost and service quality. Nowadays various computing technologies like fog, cloud, and edge computing and their confluence of IoT are required. The standard IoT services can be transformed into composite services via the incorporation of cloud computing with IoT. These IoT composite services are not suitable for various QoS scenarios which results in performance degradation and exhibited real-time adaptive sensing issues. Therefore, a novel Deep Q-learning Network-based Hybrid Enhanced Chimp Artificial Hummingbird (DQN-Hybrid ECAH) approach is proposed to overcome the state-of-art approach problems. The DQN-Hybrid ECAH approach represents a significant novelty in the field of IoT, as it utilizes a combination of advanced techniques to overcome the challenges posed by composite services in IoT. In particular, the use of deep Q-learning networks allows for the optimization of composite service quality, while the enhanced chimp artificial hummingbird techniques ensure that the approach is both efficient and effective. From the experimental evaluation, it is evident that the proposed approach is superior to other state-of-the-art methods. Specifically, the packet delivery ratio (PDF) and throughput rate obtained were high, with minimum jitter and average end-to-end delay. This demonstrates the effectiveness of the DQN-Hybrid ECAH approach in enhancing composite service quality in IoT applications. Overall, the proposed DQN-Hybrid ECAH approach represents a significant contribution to the field of IoT, providing a novel solution to the challenges associated with composite services in IoT. The approach has the potential to significantly improve the performance of IoT applications, while also reducing the real-time adaptive sensing issues that are often encountered in this context. [ABSTRACT FROM AUTHOR]

Today, fog computing is an emerging technology to support resource-constrained Internet of Things (IoT) applications. The scalability, geographic distribution, and heterogeneity of edge computing nodes, as well as the diversity of users' expectations, have made optimal module placement, considering the maximum use of fog resources, a challenging optimization problem. This paper proposes a method based on distributed learning automata to reduce the search space by using the maximum capacity of fogs in a heterogeneous fog network. In this method, fog topology is mapped to a distributed learning automata. With the cooperation of the automaton in this DLA, the problem of module placement has been solved to reduce energy consumption and delay of applications. To evaluate the amount of energy consumption and the execution time of IoT applications, two single-objective cost functions for energy and delay and another single-objective function with simultaneous consideration of energy and delay have been used. The results indicate that the average efficiency of the proposed method is 15.99%, 18.21%, and 15.53%, respectively, compared to other methods. [ABSTRACT FROM AUTHOR]

Over the last decade, with the increasing popularity and usage of the internet of things worldwide, Internet of Medical Things (IoMT) has emerged as a key technology of the modern era. IoMT uses Artificial Intelligence, 5G, big data, edge computing, and blockchain to provide users with electronic medical services. However, it may face several security threats and attacks over an insecure public network. Therefore, to protect sensitive medical data in IoMT, it is necessary to design a secure and efficient authentication protocol. In this study, we propose a privacy-preserving authentication management protocol based on blockchain. The protocol uses a blockchain to store identities and related parameters to assist communication entities in authentication. In addition, the protocol adopts a three-factor authentication method and introduces Chebyshev chaotic map to ensure the security of user login and authentication. Formal security proof and analysis using the random oracle model and Burrows-Abadi-Needham logic show that the proposed protocol is secure. Moreover, we use informal security analysis to demonstrate that the protocol can resist various security attacks. The functional comparison shows that the protocol has high security. Through performance analysis and comparison with other protocols, the proposed protocol can increase computation overhead, communication overhead, and storage overhead by up to 39.8%, 93.6%, and 86.7%,respectively. • A privacy-protection authentication protocol is designed in IoMT. • This protocol uses blockchain without relying on trust authority. • Multi-factor and Chebyshev chaotic mapping are adopted to ensure security. • The required security functions and performance have better advantage. [ABSTRACT FROM AUTHOR]

Nowadays, numerous mobile devices (MDs) provide nearly anytime and anywhere services, running on top of various computation-intensive applications. However, bearing limited battery, bandwidth, computing, and storage resources, MDs cannot completely execute all tasks of such applications in real-time. Cloud data centers (CDCs) possess enormous resources and energy, which can help execute tasks offloaded from MDs. Nonetheless, CDCs reside in remote sites, thereby leading to long transmission latency. In recent years, small base stations (SBSs) have emerged to offer close proximity, high bandwidth, and low latency services to their nearby and limited MDs. However, it becomes a new challenge to minimize the total system cost in a complex and heterogeneous architecture. To address it, this work proposes an energy-minimized partial computation offloading technique. First, a limited optimization problem of cost minimization for the system is formulated. Afterward, an improved hybrid meta-heuristic algorithm is developed, which synergistically combines a Metropolis acceptance criterion of simulated annealing and genetic operations. One uniqueness of the proposed algorithm is that it simultaneously determines task allocation among MDs, an SBS, and a CDC, the transmission power of MDs, and bandwidth allocation of wireless channels between MDs and SBS. Experiments with real-life tasks from Google data centers have shown that the proposed G enetic S imulated-annealing-based P article swarm optimization (GSP) significantly achieves lower system cost and faster convergence speed than benchmark peers. • A hybrid system architecture is designed and characterized by triple queueing models. • A constrained total cost minimization problem with multiple constraints is formulated. • The cost minimization problem is solved by a hybrid optimization algorithm named GSP. • It combines simulated annealing and genetic operations into a particle swarm optimizer. • Experiments with realistic traces show GSP achieves lower cost and faster convergence. [ABSTRACT FROM AUTHOR]

With rising data security concerns, privacy preserving machine learning (ML) methods have become a key research topic. Federated learning (FL) is one such approach which has gained a lot of attention recently as it offers greater data security in ML tasks. Substantial research has already been done on different aggregation methods, personalized FL algorithms etc. However, insufficient work has been done to identify the effects different model update strategies (concurrent FL, incremental FL, etc.) have on federated model performance. This paper presents results of extensive FL simulations run on multiple datasets with different conditions in order to determine the efficiency of 4 different FL model update strategies: concurrent, semi-concurrent, incremental, and cyclic-incremental. We have found that incremental updating methods offer more reliable FL models in cases where data is distributed both evenly and unevenly between edge nodes, especially when the number of data samples across all edge nodes is small. • Federated learning model performance is influenced by multiple environmental factors. • Different update strategies react differently to dataset size and participant number. • Update strategies can be categorized into incremental and concurrent. • Strategy selection can help inter-institutional collaboration achieve better results. • Incremental modes are more robust to lack of data. [ABSTRACT FROM AUTHOR]

Facing large-scale, intensive offshore wind farms in wide and deep sea areas, total inspection energy consumption (TIEC) optimization is a key issue to be addressed in unmanned aerial vehicle (UAV) inspection. This paper focuses on the TIEC optimization of UAV automatic inspection of offshore wind farms based on the assistance of mobile edge computing (MEC). To tackle this issue, a system model using a UAV to inspect offshore wind farms automatically and an energy consumption model of UAV assisted by MEC servers and near-earth orbiting satellites for inspecting wind turbines are proposed. Based on this, a combinatorial optimization problem based on the distance-constrained capacitated vehicle routing problem (DCVRP) for minimizing the TIEC of UAV inspection was constructed. To solve the optimization problem, an improved hybrid heuristic algorithm is proposed based on the K-means clustering, smallest enclosing circle (SEC), and Lin-Kernighan-Helsgaun (LKH-3) algorithms. The algorithm solves the optimum location and number of automated UAV airports and minimizes the TIEC for UAV inspection. The simulation experimental results show that in an offshore wind farm with 86 wind turbines, compared with other existing schemes, this scheme requires only four automated UAV airfields and can save at most 51.8% of the TIEC. [ABSTRACT FROM AUTHOR]

In this constantly evolving landscape of urbanization, the relationship between technology and automation, in regards to sustainability, holds immense significance. The intricate strands of human intelligence are seamlessly interwoven with the fabric of technological progress, giving rise to exquisite patterns of synergy and collaborative innovation. Automation is just another step in this process which started with the industrial revolution and now has paved way towards urbanization. Smart homes or home automation is a subset of Internet of Things (IoT) based automation that has added into the comfort, ease, and quality of our living standards and is now being integrated to form the concept of Smart Cities. In the past decade, various techniques and processes of smart home automation have been proposed and implemented. To extend and translate the existing methods into new one, the understanding of the former is imperative to the research procedure. This review stands as a comprehensive exploration, diving into the pivotal role of intelligent systems and expert knowledge in driving the transformation of smart homes into sustainable smart cities. By meticulously analyzing and aggregating an array of contemporary techniques used in smart homes, this paper offers profound contributions to the intersection of urban evolution and technological innovation. The review's holistic approach not only facilitates a deep understanding of smart homes' contributions but also charts a course for innovative strategies in city planning, infrastructure, and technological integration. In bridging the gap between technology and sustainable urban development, this exploration underscores the transformative power of leveraging smart home techniques to lay the foundation for harmonious and forward-thinking smart cities. The technologies cover a wide range of methodologies and intelligent systems used for communication, security and management in an urban infrastructure. The paper focuses on analysis of the technology to provide an outlook into achieving the goal of sustainable smart cities and deal with challenges like scalability and big data computation. Our comprehensive analysis yields a holistic set of technology comparisons and illuminates the promising future prospects within this domain. The information is highly insightful in creating a bigger picture for adopting state of the art technologies like Federated Learning (FL), Digital Twin and Embedded Edge computing in better planning and infrastructure management in smart cities. These findings offer reliable and potent methods to chart not only the course of research but also to enhance these technologies for the betterment of mankind's convenience and advancement. • Technical advancement needed for transformation of home automation to a next level. • Smart cities that build from the foundation of homes automations have been discussed. • Comparison with the existing papers to unlock new research directions in this area. [ABSTRACT FROM AUTHOR]

High impedance faults caused by vegetation are difficult to detect when covered conductors in medium voltage overhead power lines are used. Long-term contact of XLPE insulation with vegetation causes partial discharges (PDs) which damage the insulation. Although a cheap and easy to install, contactless detection method was developed using an antenna, there is a lack of classification algorithms for this method. Only two custom machine learning algorithms have been tested so far, and both rendered unsatisfactory results for the real application. This work investigates the use of neural network algorithms for this problem and the application of heterogeneous stacking ensembles using neural networks. We used real data collected from a number of detection stations in the Czech Republic. Also, we limited ourselves to supporting edge computing using devices such as Edge TPU. We propose the application of a heterogeneous stacking ensemble neural network to classify PDs obtained by the contactless method. The algorithm we propose is based on a stacking ensemble with a novel combination of base learners, and the Wide and Deep neural network is used as a meta-learner. We compared the results of our algorithm with other algorithms designated for time series classification. Also, an ablation study of the ensemble was conducted, and satisfactory results were obtained using the proposed algorithm. The ensemble outperformed all algorithms tested and is usable on the edge using AI HW accelerator as the ensemble is only feedforward and contains only well-used and known layers. This research improves our understanding of the classification of PDs using the contactless PD detection method and also introduces a stacking ensemble of convolutional neural network and autoencoders for a time series classification for the first time. [Display omitted] • Detection of partial discharges using heterogeneous ensemble stacking NN. • Novel combination of 1D-CNN and autoencoders in ensemble stacking NN. • Proposed algorithm usable for edge detection using HW NN accelerator. • Evaluated on dataset previously used for best published algorithm for this dataset. • Evaluated on new unvalidated dataset and outperforms wide range of classifiers. [ABSTRACT FROM AUTHOR]

• MOPSO driven framework to prepare robust and computationally efficient 1D-CNN Model. • Effective and efficient classification technique of transmission line faults. • Substantial reduction in computation cost, resource requirement, and processing time. • Several benefits for multi-channel signal processing aimed to edge computing devices. In spite of the amazing success of deep learning in various complex classification tasks, its real-time applications have been greatly hindered due to the enormous computational burden and extensive processing time. In this context, the present investigation is a path-breaking idea and journey toward designing robust and computationally efficient One-dimensional Convolutional Neural Networks (1D-CNN) for the classification of transmission line faults, which demands accurate decisions within 20 ms. Following the multi-channel signal processing approach, sampled three-phase line currents of each half-cycle duration are concatenated to form a one-dimensional array and fed to the 1D-CNN model for exploring unique patterns of line currents associated with various faults. A Particle Swarm Optimization (PSO) driven multi-objective optimization technique is exclusively used to select an optimum number of kernels and kernel sizes for designing a less computation-intensive but robust CNN architecture, making it suitable for fast fault detection and classification without compromising the performance. The efficacy of this holistic design approach has been demonstrated in the simulated environment of an IEEE 5-bus system with significant penetration of distributed generation. With excellent fault pattern extraction through the convolution process, the optimally designed 1D-CNN has proven its strength for accurate transmission line fault classification by combating bidirectional power flow due to renewable energy penetration. The emulation time of the optimally designed 1D-CNN architecture for low-cost, low-power FPGA demonstrates its fastness and suitability for time-critical real-time transmission line fault classification. In general the proposition in the paper explains the candidate Deep Learning (DL) algorithm for multi-channel signal processing focusing on low-computing edge devices. [ABSTRACT FROM AUTHOR]

• This paper proposes a MOMHTS optimized HRFDL architecture for diagnosing the COVID-19 and pneumonia from chest CT and X-ray images via a collaborative edge framework to offer web services in underprivileged areas. • The hyperparameters of the HRFDL classifier are optimized using the MOMHTS algorithm which minimizes the complexity of the Deep learning model that prevents it from being deployed in the edge devices. COVID-19 is a global pandemic that mostly affects patients' respiratory systems, and the only way to protect oneself against the virus at present moment is to diagnose the illness, isolate the patient, and provide immunization. In the present situation, the testing used to predict COVID-19 is inefficient and results in more false positives. This difficulty can be solved by developing a remote medical decision support system that detects illness using CT scans or X-ray images with less manual interaction and is less prone to errors. The state-of-art techniques mainly used complex deep learning architectures which are not quite effective when deployed in resource-constrained edge devices. To overcome this problem, a Multi-Objective Modified Heat Transfer Search (MOMHTS) optimized Hybrid Random Forest Deep learning (HRFDL) classifier is proposed in this paper. The MOMHTS algorithm mainly optimizes the deep learning model in the HRFDL architecture by optimizing the hyperparameters associated with it to support the resource-constrained edge devices. To evaluate the efficiency of this technique, extensive experimentation is conducted on two real-time datasets namely the COVID19 lung CT scan dataset and the Chest X-ray images (Pneumonia) datasets. The proposed methodology mainly offers increased speed for communication between the IoT devices and COVID-19 detection via the MOMHTS optimized HRFDL classifier is modified to support the resources which can only support minimal computation and handle minimum storage. The proposed methodology offers an accuracy of 99% for both the COVID19 lung CT scan dataset and the Chest X-ray images (Pneumonia) datasets with minimal computational time, cost, and storage. Based on the simulation outcomes, we can conclude that the proposed methodology is an appropriate fit for edge computing detection to identify the COVID19 and pneumonia with higher detection accuracy. [ABSTRACT FROM AUTHOR]

• Computing on edge end improves the efficiency and reliability of data analysis. • A lightweight CNN model is efficient for real-time crowd density estimation on edge. • Better crowd density inference speed with a slight increase in estimation accuracy. • Equip the model in an IoT device to monitor the crowd density in a Subway Station. Crowd stampedes and incidents are critical threats to public security that have caused countless deaths during the past few decades. To avoid crowd stampedes, real-time crowd density estimation can help monitor crowd movements, and thus support a timely evacuation strategy development. In previous studies, scholars and engineers developed multiple video-based crowd density estimation algorithms based on deep neural networks. The excessive computational complexity of deep learning algorithms exacerbated the algorithm's efficiency, causing unacceptable real-time performance. In the Internet of Things era, deploying the crowd density estimation task with edge computing is an advanced strategy to maintain the real-time performance of the entire system. Considering the limited computational resources on the edge devices, deep learning-based crowd density estimation algorithms normally cannot be handled. To fulfill the deployment on the edge device, the algorithms need to be optimized with a smaller model size. Therefore, this paper proposes a lightweight Convolutional Neural Networks (CNN) based crowd density estimation model by combining the modified MobileNetv2 and the dilated convolution. Public crowd image data sets are used to conduct experiments for evaluating the performance of the proposed algorithm in terms of accuracy and inference speed. The results show that our model achieves much better inference speed accompanied by a slight increase in accuracy. The proposed method of this study can enhance the performance of the crowd monitoring system, and therefore help avoid crowd stampedes and incidents. [ABSTRACT FROM AUTHOR]

Privacy-preserving Content-Based Image Retrieval (CBIR) method is a promising technology to achieve data confidentiality and searchability in cloud-assisted multimedia (i.e., image or video) data environment. However, inappropriate feature-preserving mechanisms and inefficient ciphertext descriptors resulted in lower performance than expected. Therefore, how to design encryption techniques with high security and how to extract effective features from ciphertext images still hinder privacy-preserving CBIR. For this goal, we propose a privacy-preserving image retrieval based on deep convolutional network features. First, a novel hybrid encryption technique is designed to encrypt images and an improved DenseNet model is fine-tuned by using the encrypted images to construct a feature extractor. The encrypted images and fine-tuning feature extractor are then uploaded to cloud server. Meanwhile, secure CBIR service is executed in the cloud server. We conduct experiments on two public benchmark datasets for performance evaluation in terms of mAP and accuracy. As demonstrated in the experimental results, the proposed method can achieve superior result compared with the existing methods, improving the performance on the two metrics by relatively 1.9% and 10%, respectively. Furthermore, the computational cost and parameters of depthwise separable convolution adopted by the improved DenseNet model are 8 to 9 times smaller than that of standard convolutions of the original DenseNet at only a small reduction in accuracy. • Preserving color features by replacing RGB channels. • The texture features are preserved by scrambling the pixel bit matrix. • A hybrid privacy-preserving mechanism for color and texture information. • The features of encrypted images are extracted by CNN on cloud server. • Experimental results show that our method is highly competitive. [ABSTRACT FROM AUTHOR]

• A low-latency edge caching method based on multi-base station cooperation is proposed. • A migration method based on balanced overhead of communication and migration is proposed. • The problem of minimizing latency is transformed into a problem of maximizing cache reward. • The reinforcement learning method is used to obtain service migration scheme. • The performances of the proposed algorithms are evaluated through experiments. With the increase of mobile terminal equipment and network mass data, users have higher requirements for delay and service quality. To reduce user access latency and more effectively cache diverse content in the edge network, a low-latency edge caching method is proposed. The cache model based on base station cooperation is established and the delay in different transmission modes is considered. Finally, the problem of minimizing latency is transformed into a problem of maximizing cache reward, and a greedy algorithm based on the original dual interior point is used to obtain the strategy of the original problem. Meanwhile, in order to improve service quality and balance communication overhead and migration overhead, a migration method based on balanced communication overhead and migration overhead is proposed. The model that balances communication overhead and migration overhead is established, and the reinforcement learning method is used to obtain a migration scheme that maximizes accumulated revenue. Comparison results show that our caching method can enhance the cache reward and reduce delay. Meanwhile, the migration algorithm can increase service migration revenue and reduce communication overhead. [ABSTRACT FROM AUTHOR]