Search

Abstract Energy efficiency and physical-layer security are crucial considerations in the advancement of mobile edge computing systems. This paper addresses the trade-off between secure-reliability and energy consumption in finite blocklength (FBL) communications. Specifically, we examine a three-node scenario involving a user, a legitimate edge computing server, and an eavesdropper, where the user offloads sensitive data to the edge server while facing potential eavesdropping threats. We propose an optimization framework aimed at minimizing energy consumption while ensuring secure-reliability by decomposing the problem into manageable subproblems. By demonstrating the convexity of the objective function concerning the variables, we establish the existence of an optimal parameter selection for the problem. This implies that practical optimization of parameters can significantly enhance system performance. Our numerical results demonstrate that the application of FBL regime and retransmission mechanism can effectively reduce the energy consumption of the system while ensuring secure-reliability. For the quantitative analyses, the retransmission mechanism is 33.1% better than no retransmission, and the FBL regime is 13.1% better than infinite blocklength (IBL) coding.

In Internet of Vehicles (IoV), the security-threat information of various traffic elements can be exploited by hackers to attack vehicles, resulting in accidents, privacy leakage. Consequently, it is necessary to establish security-threat assessment architectures to evaluate risks of traffic elements by managing and sharing security-threat information. Unfortunately, most assessment architectures process data in a centralized manner, causing delays in query services. To address this issue, in this paper, a Hierarchical Blockchain-enabled Security threat Assessment Architecture (HBSAA) is proposed, utilizing edge chains and global chains to share data. In addition, data virtualization technology is introduced to manage multi-source heterogeneous data, and a metadata association model based on attribute graph is designed to deal with complex data relationships. In order to provide high-speed query service, the ant colony optimization of key nodes is designed, and the HBSAA prototype is also developed and the performance is tested. Experimental results on the large-scale vulnerabilities data gathered from NVD demonstrate that the HBSAA not only shields data heterogeneity, but also reduces service response time.

Abstract This paper aims to increase the Unmanned Aerial Vehicle's (UAV) capacity for target tracking. First, a control model based on fuzzy logic is created, which modifies the UAV's flight attitude in response to the target's motion status and changes in the surrounding environment. Then, an edge computing-based target tracking framework is created. By deploying edge devices around the UAV, the calculation of target recognition and position prediction is transferred from the central processing unit to the edge nodes. Finally, the latest Vision Transformer model is adopted for target recognition, the image is divided into uniform blocks, and then the attention mechanism is used to capture the relationship between different blocks to realize real-time image analysis. To anticipate the position, the particle filter algorithm is used with historical data and sensor inputs to produce a high-precision estimate of the target position. The experimental results in different scenes show that the average target capture time of the algorithm based on fuzzy logic control is shortened by 20% compared with the traditional proportional-integral-derivative (PID) method, from 5.2 s of the traditional PID to 4.2 s. The average tracking error is reduced by 15%, from 0.8 m of traditional PID to 0.68 m. Meanwhile, in the case of environmental change and target motion change, this algorithm shows better robustness, and the fluctuation range of tracking error is only half of that of traditional PID. This shows that the fuzzy logic control theory is successfully applied to the UAV target tracking field, which proves the effectiveness of this method in improving the target tracking performance.

Industrial Internet of Things (IIoT) is a pivotal driving force behind the intelligent transformation of the global industrial system, bringing about a gradual shift in production methods. However, due to users completing remote access and data transmission through open channels, ensuring user legitimacy and data security has become an important factor in IIoT. In addition, resource limited users or devices need to collect and publish corresponding messages while also timely processing instant messages obtained from the network. Leveraging edge computing technology effectively mitigates the transmission time of messages, addressing the challenges of high computing pressure and prolonged response time associated with cloud server computing. Therefore, investigating authentication key agreement based on edge computing in the IIoT environment holds substantial theoretical significance and practical importance. This article introduces an IIoT authentication that ensures both security and efficiency by integrating elliptic curve cryptography and three-factor authentication. Within this scheme, the user and the edge server accomplish security authentication. Through security analysis, the proposed scheme is proven to meet the essential security requirements. Performance analysis shows that it achieves higher security, supports more functions, and achieves lower computational and communication costs compared to related schemes.

ObjectiveReal-time monitoring of cow ruminant behavior is of paramount importance for promptly obtaining relevant information about cow health and predicting cow diseases. Currently, various strategies have been proposed for monitoring cow ruminant behavior, including video surveillance, sound recognition, and sensor monitoring methods. However, the application of edge device gives rise to the issue of inadequate real-time performance. To reduce the volume of data transmission and cloud computing workload while achieving real-time monitoring of dairy cow rumination behavior, a real-time monitoring method was proposed for cow ruminant behavior based on edge computing.MethodsAutonomously designed edge devices were utilized to collect and process six-axis acceleration signals from cows in real-time. Based on these six-axis data, two distinct strategies, federated edge intelligence and split edge intelligence, were investigated for the real-time recognition of cow ruminant behavior. Focused on the real-time recognition method for cow ruminant behavior leveraging federated edge intelligence, the CA-MobileNet v3 network was proposed by enhancing the MobileNet v3 network with a collaborative attention mechanism. Additionally, a federated edge intelligence model was designed utilizing the CA-MobileNet v3 network and the FedAvg federated aggregation algorithm. In the study on split edge intelligence, a split edge intelligence model named MobileNet-LSTM was designed by integrating the MobileNet v3 network with a fusion collaborative attention mechanism and the Bi-LSTM network.Results and DiscussionsThrough comparative experiments with MobileNet v3 and MobileNet-LSTM, the federated edge intelligence model based on CA-MobileNet v3 achieved an average Precision rate, Recall rate, F1-Score, Specificity, and Accuracy of 97.1%, 97.9%, 97.5%, 98.3%, and 98.2%, respectively, yielding the best recognition performance.ConclusionsIt is provided a real-time and effective method for monitoring cow ruminant behavior, and the proposed federated edge intelligence model can be applied in practical settings.

Abstract Resource optimization, timely data capture, and efficient unmanned aerial vehicle (UAV) operations are of utmost importance for mission success. Latency, bandwidth constraints, and scalability problems are the problems that conventional centralized processing architectures encounter. In addition, optimizing for robust communication between ground stations and UAVs while protecting data privacy and security is a daunting task in and of itself. Employing edge computing infrastructure, artificial intelligence-driven decision-making, and dynamic task offloading mechanisms, this research proposes the dynamic task offloading edge-aware optimization framework (DTOE-AOF) for UAV operations optimization. Edge computing and artificial intelligence (AI) algorithms integrate to decrease latency, increase mission efficiency, and conserve onboard resources. This system dynamically assigns computing duties to edge nodes and UAVs according to proximity, available resources, and the urgency of the tasks. Reduced latency, increased mission efficiency, and onboard resource conservation result from dynamic task offloading edge-aware implementation framework (DTOE-AIF)'s integration of AI algorithms with edge computing. DTOE-AOF is useful in many fields, such as precision agriculture, emergency management, infrastructure inspection, and monitoring. UAVs powered by AI and outfitted with DTOE-AOF can swiftly survey the damage, find survivors, and launch rescue missions. By comparing DTOE-AOF to conventional centralized methods, thorough simulation research confirms that it improves mission efficiency, response time, and resource utilization.

Scheduling scientific workflows is essential for edge data centers operations. Fault tolerance is a crucial focus in workflow scheduling (WS) research. This study proposed fault-tolerant WS in edge data centers using Task Prioritization Adaptive Particle Swarm Optimization (TPAPSO). The aim is to minimize the Makespan, execution costs, and overcoming failures at all workflow processing stages, including when virtual machines are insufficient or tasks fail. The approach proposes three components: initial heuristic list, scheduling tasks with TPAPSO, and implementing performance monitoring with fault tolerance (PMWFT). TPAPSO-PMWFT is simulated using CloudSim 4.0. The experiments indicate that the suggested approach shows superior results compared to existing methods.

Mobile Augmented Reality (MAR) applications enhance user experiences by providing realistic information about the current location through mobile devices. However, MAR applications are computationally intensive, leading to high energy consumption and latency issues. To address these challenges, this research presents a Hybrid Monte Carlo Tree Search (HMCTS) based task offloading scheme, combining a genetic algorithm with Monte Carlo tree search for efficient task management. The proposed method uses YoloV7 for object recognition and aims to reduce energy consumption, response time, and migration time. Experimental results demonstrate that the HMCTS approach significantly reduces energy consumption to 1290 kJ, response time to 24 ms, and migration time to 0.52 ms, outperforming existing techniques. These improvements highlight the potential of the HMCTS method for enhancing the performance of MAR applications. Proposed hybrid approach aims to improve the efficiency and effectiveness of task offloading in MAR applications. The HMCTS model dynamically offloads tasks to edge servers, optimizing scheduling time, response time, and energy consumption.

With the rapid development of mobile communication technologies and Internet of Things (IoT) devices, Multi-Access Edge Computing (MEC) has become one of the most potential technologies for wireless communication. In MEC systems, faster and more reliable data processing can be provided to IoT devices through computation offloading, but edge servers have limited computing and storage resources. The prerequisite for whether an IoT device can offload a computation task to an edge server for processing is whether the edge server has enough remaining available resources and whether the edge server caches the services related to the task, followed by finding the best way to offload the task. Therefore, to process tasks efficiently, offloading decisions, resource allocation, and edge caching need to be jointly considered during offloading tasks to edge servers. Reinforcement Learning (RL) has recently emerged as a key technique for solving the computation offloading problem in MEC, and a large number of optimization methods have emerged. In this context, we provide a comprehensive survey of RL-based computation offloading fundamental principles and theories in MEC, including mechanisms for finding optimal offloading decisions, methods for joint resource allocation, and means for joint edge caching. In addition, we also discuss the challenges and future work of RL-based computation offloading methods.

To enable machines to understand human-centric images and videos, they need the capability to detect human–object interactions. This capability has been studied using various approaches, but previous research has mainly focused only on recognition accuracy using widely used open datasets. Given the need for advanced machine-learning systems that provide spatial analysis and services, the recognition model should be robust to various changes, have high extensibility, and provide sufficient recognition speed even with minimal computational overhead. Therefore, we propose a novel method that combines the skeletal method with object detection to accurately predict a set of $ \langle $ human, verb, object $ \rangle $ triplets in a video frame considering the robustness, extensibility, and lightweight of the model. Training a model with similar perceptual elements to those of humans produces sufficient accuracy for advanced social systems, even with only a small training dataset. The proposed model is trained using only the coordinates of the object and human landmarks, making it robust to various situations and lightweight compared with deep-learning methods. In the experiment, a scenario in which a human is working on a desk is simulated and an algorithm is trained on object-specific interactions. The accuracy of the proposed model was evaluated using various types of datasets.

The integration of Mixed Reality (MR) technology into Autonomous Vehicles (AVs) has ushered in a new era for the automotive industry, offering heightened safety, convenience, and passenger comfort. However, the substantial and varied data generated by MR-Connected AVs (MR-CAVs), encompassing both highly dynamic and static information, presents formidable challenges for efficient data management and retrieval. In this paper, we formulate our indexing problem as a constrained optimization problem, with the aim of maximizing the utility function that represents the overall performance of our indexing system. This optimization problem encompasses multiple decision variables and constraints, rendering it mathematically infeasible to solve directly. Therefore, we propose a heuristic algorithm to address the combinatorial complexity of the problem. Our heuristic indexing algorithm efficiently divides data into highly dynamic and static categories, distributing the index across Roadside Units (RSUs) and optimizing query processing. Our approach takes advantage of the computational capabilities of edge servers or RSUs to perform indexing operations, thereby shifting the burden away from the vehicles themselves. Our algorithm strategically places data in the cache, optimizing cache hit rate and space utilization while reducing latency. The quantitative evaluation demonstrates the superiority of our proposed scheme, with significant reductions in latency (averaging 27%−49.25%), a 30.75% improvement in throughput, a 22.50% enhancement in cache hit rate, and a 32%−50.75% improvement in space utilization compared to baseline schemes.

The growing development of the Internet of Things (IoT) is accelerating the emergence and growth of new IoT services and applications, which will result in massive amounts of data being generated, transmitted and processed in wireless communication networks. Mobile Edge Computing (MEC) is a desired paradigm to timely process the data from IoT for value maximization. In MEC, a number of computing-capable devices are deployed at the network edge near data sources to support edge computing, such that the long network transmission delay in cloud computing paradigm could be avoided. Since an edge device might not always have sufficient resources to process the massive amount of data, computation offloading is significantly important considering the cooperation among edge devices. However, the dynamic traffic characteristics and heterogeneous computing capabilities of edge devices challenge the offloading. In addition, different scheduling schemes might provide different computation delays to the offloaded tasks. Thus, offloading in mobile nodes and scheduling in the MEC server are coupled to determine service delay. This paper seeks to guarantee low delay for computation intensive applications by jointly optimizing the offloading and scheduling in such an MEC system. We propose a Delay-Greedy Computation Offloading (DGCO) algorithm to make offloading decisions for new tasks in distributed computing-enabled mobile devices. A Reinforcement Learning-based Parallel Scheduling (RLPS) algorithm is further designed to schedule offloaded tasks in the multi-core MEC server. With an offloading delay broadcast mechanism, the DGCO and RLPS cooperate to achieve the goal of delay-guarantee-ratio maximization. Finally, the simulation results show that our proposal can bound the end-to-end delay of various tasks. Even under slightly heavy task load, the delay-guarantee-ratio given by DGCO-RLPS can still approximate 95%, while that given by benchmarked algorithms is reduced to intolerable value. The simulation results are demonstrated the effectiveness of DGCO-RLPS for delay guarantee in MEC.

Federated learning has been explored as a promising solution for training machine learning models at the network edge, without sharing private user data. With limited resources at the edge, new solutions must be developed to leverage the software and hardware resources as the existing solutions did not focus on resource management for network edge, specially for federated learning. In this paper, we describe the recent work on resource management at the edge and explore the challenges and future directions to allow the execution of federated learning at the edge. Problems such as the discovery of resources, deployment, load balancing, migration, and energy efficiency are discussed in the paper.

Edge technology aims to bring cloud resources (specifically, the computation, storage, and network) to the closed proximity of the edge devices, i.e., smart devices where the data are produced and consumed. Embedding computing and application in edge devices lead to emerging of two new concepts in edge technology: edge computing and edge analytics. Edge analytics uses some techniques or algorithms to analyse the data generated by the edge devices. With the emerging of edge analytics, the edge devices have become a complete set. Currently, edge analytics is unable to provide full support to the analytic techniques. The edge devices cannot execute advanced and sophisticated analytic algorithms following various constraints such as limited power supply, small memory size, limited resources, etc. This article aims to provide a detailed discussion on edge analytics. The key contributions of the paper are as follows-a clear explanation to distinguish between the three concepts of edge technology: edge devices, edge computing, and edge analytics, along with their issues. In addition, the article discusses the implementation of edge analytics to solve many problems and applications in various areas such as retail, agriculture, industry, and healthcare. Moreover, the research papers of the state-of-the-art edge analytics are rigorously reviewed in this article to explore the existing issues, emerging challenges, research opportunities and their directions, and applications.

The ever-growing deluge of astronomical data challenges traditional server-based processing, hindering real-time analysis and scientific discovery. This paper proposes a novel approach: edge computing directly on an sCMOS camera using a System-on-Chip (SoC) architecture currently developed at Creotech Instruments. We present a custom-designed camera equipped with an FPGA-based SoC, enabling on-board preprocessing and feature extraction of astronomical images. This significantly reduces data transmission, minimizes latency, and empowers real-time decision-making for critical observations. We showcase the camera's capabilities through real-world scenarios, demonstrating its usability in astronomy.

Abstract Smartphone sensors have gained considerable traction in Human Activity Recognition (HAR), drawing attention for their diverse applications. Accelerometer data monitoring holds promise in understanding students’ physical activities, fostering healthier lifestyles. This technology tracks exercise routines, sedentary behavior, and overall fitness levels, potentially encouraging better habits, preempting health issues, and bolstering students’ well-being. Traditionally, HAR involved analyzing signals linked to physical activities using handcrafted features. However, recent years have witnessed the integration of deep learning into HAR tasks, leveraging digital physiological signals from smartwatches and learning features automatically from raw sensory data. The Long Short-Term Memory (LSTM) network stands out as a potent algorithm for analyzing physiological signals, promising improved accuracy and scalability in automated signal analysis. In this article, we propose a feature analysis framework for recognizing student activity and monitoring health based on smartphone accelerometer data through an edge computing platform. Our objective is to boost HAR performance by accounting for the dynamic nature of human behavior. Nonetheless, the current LSTM network’s presetting of hidden units and initial learning rate relies on prior knowledge, potentially leading to suboptimal states. To counter this, we employ Bidirectional LSTM (BiLSTM), enhancing sequence processing models. Furthermore, Bayesian optimization aids in fine-tuning the BiLSTM model architecture. Through fivefold cross-validation on training and testing datasets, our model showcases a classification accuracy of 97.5% on the tested dataset. Moreover, edge computing offers real-time processing, reduced latency, enhanced privacy, bandwidth efficiency, offline capabilities, energy efficiency, personalization, and scalability. Extensive experimental results validate that our proposed approach surpasses state-of-the-art methodologies in recognizing human activities and monitoring health based on smartphone accelerometer data.

Internet of Things (IoT) technologies are increasingly implemented in buildings as the cost-effective smart sensing infrastructure of building automation systems (BASs). They are also dispersed computing resources for novel distributed optimal control approaches. However, wireless communication networks are critical to fulfill these tasks with the performance influenced by inherent uncertainties in networks, e.g., unpredictable occurrence of link failures. Centralized and hierarchical distributed approaches are vulnerable against link failure, while the robustness of fully distributed approaches depends on the algorithms adopted. This study therefore proposes a fully distributed robust optimal control approach for air-conditioning systems considering uncertainties of communication link in IoT-enabled BASs. The distributed algorithm is adopted that agents know their out-neighbors only. Agents directly coordinate with the connected neighbors for global optimization. Tests are conducted to test and validate the proposed approach by comparing with existing approaches, i.e., the centralized, the hierarchical distributed and the fully distributed approaches. Results show that different approaches are vulnerable against to uncertainties of communication link to different extents. The proposed approach always guarantees the optimal control performance under normal conditions and conditions with link failures, verifying its high robustness. It also has low computation complexity and high optimization efficiency, thus applicable on IoT-enabled BASs.

This article designs a foreign object recognition system based on machine vision and applies it to the protection of the main transportation belt conveyor. The study uses YOLOv5s as the deep learning model to deploy the trained model to the edge computing module. Real time video is captured by an industrial intrinsic safety camera and transmitted to the edge computing module to identify the foreign matters in the coal flow. Finally, only the recognition results are transmitted externally. When a high level of foreign object danger is detected, an alarm signal will be sent to the collaborative controller, which will issue a shutdown command to the specific single controller. Simultaneously upload the processed real-time video and alarm information to the control platform for display. This design improves the intelligence, stability, and reliability of the protection of the current main conveyor belt conveyor.

Abstract Internet of Things (IoT) technology has revolutionized modern industrial sectors. Moreover, IoT technology has been incorporated within several vital domains of applicability. However, security is overlooked due to the limited resources of IoT devices. Intrusion detection methods are crucial for detecting attacks and responding adequately to every IoT attack. Conspicuously, the current study outlines a two-stage procedure for the determination and identification of intrusions. In the first stage, a binary classifier termed an Extra Tree (E-Tree) is used to analyze the flow of IoT data traffic within the network. In the second stage, an Ensemble Technique (ET) comprising of E-Tree, Deep Neural Network (DNN), and Random Forest (RF) examines the invasive events that have been identified. The proposed approach is validated for performance analysis. Specifically, Bot-IoT, CICIDS2018, NSL-KDD, and IoTID20 dataset were used for an in-depth performance assessment. Experimental results showed that the suggested strategy was more effective than existing machine learning methods. Specifically, the proposed technique registered enhanced statistical measures of accuracy, normalized accuracy, recall measure, and stability.

Abstract With the rapid advancement of sports analytics and fan engagement technologies, the volume and diversity of physique data generated by smart devices across various distributed sports platforms have grown significantly. Extracting insights and enhancing fan experiences from such data offer considerable benefits. Yet, this process unveils two primary challenges. Firstly, efficiently utilizing the vast datasets in sports analytics is daunting due to the complex nature of the sports industry. Secondly, the data collected from diverse sources and stored in distributed platforms contain sensitive information like fan preferences and athlete performance metrics, posing risks of privacy breaches. To address these challenges, we leverage an advanced Locality-Sensitive Hashing technique, known as PSDFP $$_{\text {ALSH}}$$ ALSH , tailored for the sports domain. This paper presents a new privacy-preserving method for sports data fusion and prediction in distributed environments, utilizing enhanced Locality-Sensitive Hashing to protect sensitive information while maintaining high data utility. Through extensive experimentation, our approach demonstrates superior performance over existing methods in terms of Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and computational efficiency.

Abstract The effective functioning and regulation of power systems crucially rely on the coordination of distance and directional overcurrent relays. Accurate fault detection and successful clearing sequences require support for each relay and the maintenance of the coordination time interval (CTI) between major distance relays, directional overcurrent relay support, and other relay zones. Efficiently initiating relays while adhering to complex coordination limitations poses a challenging task that demands innovative solutions. This study addresses the intricate problem of relay coordination by employing heuristic methods, specifically genetic algorithms (GA) and biogeography-based optimization (BBO), in both a 9-bus and 39-bus system. The primary objective is to determine the most efficient time setting factor (TSM) that minimizes the duration of relay operation. Additionally, the intelligent features of the overcurrent relay are carefully chosen to enhance the research's results. The integration of edge computing capabilities plays a significant role in advancing this coordination method. By incorporating advanced algorithms and communication technologies at the edge, the prompt activation of relays becomes possible, thereby meeting coordination demands. This study explores the combination of edge-based servers with genetic algorithms (GA) and biogeography-based optimization (BBO) techniques to enhance relay coordination. The findings indicate a notable enhancement compared to conventional approaches. However, comparative research suggests that BBO's performance is similar to GA, without a distinct advantage in achieving higher outcomes.

With the continuous advancement of agricultural Internet of Things (IoT) technologies, real-time monitoring of agricultural environments has become increasingly significant. This monitoring provides valuable information on pest and disease occurrences and corresponding ecological conditions. However, as the agricultural environments have extensive coverage, the number of monitoring IoT devices and the volume of information will rapidly increase. This leads to a surge in network traffic and computing demands. To address this issue, this article proposes an agricultural environmental monitoring IoT system that utilizes edge computing and deep learning technologies. It combines the Long-Range Wide Area Network (LoRaWAN) for long-range transmission with pest recognition and counting modules. By offloading workloads traditionally processed in the cloud to edge nodes, the proposed system effectively reduces transmission and cloud computing pressures for the agricultural monitoring IoT. Simulation experiments demonstrate stable LoRaWAN protocol-based data transmission at the edge, with an overall packet loss rate of less than 5%, meeting the transmission quality requirements. Moreover, this article investigates a pest recognition and counting method based on deep learning technology. Pest images, captured by monitoring nodes, are recognized and counted online using the TensorFlow framework. Experimental results indicate an accuracy of 89% in pest recognition. By digitally transmitting pest image recognition results to the cloud, the proposed system significantly alleviates transmission and cloud computing pressures for the monitoring IoT.

The focus of this article lies on the notion of the edge version of doubly resolving sets (EVDRSs) in circulant networks. EVDRSs refer to unique edge subsets that are necessary for identifying individual edges in a network and distinguishing them based on their edge distances to the elements of the EVDRS. The main objectives were to define the minimal size of EVDRSs for circulant networks $ C_n(1, 2) $ and to investigate their basic properties. The systematic research helped to achieve a new understanding of the existence, construction, and characterization of EVDRSs in circulant networks $ C_n(1, 2) $. It is established that the EVDRSs in the circulant network $ C_n(1, 2) $ are finite and are bounded by the order of the network. Among the numerous implications of these findings are those that refer to the design and optimization of distributed sensor networks, improving communication and network protocols, as well as tracking the spread of infectious diseases and epidemics over social networks. The application of the identified methodology helps improve the process of network optimization which contributes to the development of more effective and robust circulant-based structures.

Abstract Physical reservoir computing is a promising solution for accelerating artificial intelligence (AI) computations. Various physical systems that exhibit nonlinear and fading-memory properties have been proposed as physical reservoirs. Highly-integrable physical reservoirs, particularly for edge AI computing, has a strong demand. However, realizing a practical physical reservoir with high performance and integrability remains challenging. Herein, we present an analogue circuit reservoir with a simple cycle architecture suitable for complementary metal-oxide-semiconductor (CMOS) chip integration. In several benchmarks and demonstrations using synthetic and real-world data, our developed hardware prototype and its simulator exhibit a high prediction performance and sufficient memory capacity for practical applications, showing promise for future applications in highly integrated AI accelerators.

Abstract Data privacy is playing a vital role while facing the digital life aspects. Today, the world is being extensively inter-connected through the internet of things (IoT) technologies. This huge interconnectivity is bringing very wonderful capabilities for improving the quality of life (QoL) with itself, for instance, in distributed healthcare. On the other hand, there are new challenges in the interconnectivity per use. One of the most challenging issues of IoT use in social systems and digital life is secure, trustable, and reliable interactions over IoT networks such that safety, security, and privacy in both aspects of cyber and physical worlds for humankind should be planned and controlled. Due to the less physical activity of most people in the current world, fitness and aerobic sports are now an important need at any age to help them keep healthy in their cyber-physical life, specifically, for the younger student that are still in the growth ages. However, these sport activities need to be monitored seriously and closely to not put their life in danger. Herewith, healthcare services through IoT is becoming more applicable. Therefore, health information privacy for athletes is now a hot topic of investigation as we present the topic here. We propose an IoT-based physique healthcare system considering private information sharing for athletes based on data hiding at the edge of a collaborative system. The proposed system pays attention to the key factors of healthcare IoT infrastructure but it is bringing its new suggestions for more safety. Moreover, many evaluations based on different kinds of healthcare data are provided.

Federated learning (FL) is rapidly shaping into a key enabler for large-scale Artificial Intelligence (AI) where models are trained in a distributed fashion by several clients without sharing local and possibly sensitive data. For edge computing, sharing the computational load across multiple clients is ideal, especially when the underlying IoT and edge nodes encompass limited resource capacity. Despite its wide applicability, monitoring FL deployments comes with significant challenges. AI practitioners are required to invest a vast amount of time (and labor) in manually configuring state-of-the-art monitoring tools. This entails addressing the unique characteristics of the FL training process, including the extraction of FL-specific and system-level metrics, aligning metrics to training rounds, pinpointing performance inefficiencies, and comparing current to previous deployments. This work introduces FedMon, a toolkit designed to ease the burden of monitoring FL deployments by seamlessly integrating the probing interface with the FL deployment, automating the metric extraction, providing a rich set of system, dataset, model, and experiment-level metrics, and providing the analytic means to assess trade-offs and compare different model and training configurations.

The Autonomous Underwater Glider (AUG) is a kind of prevailing underwater intelligent internet vehicle and occupies a dominant position in industrial applications, in which path planning is an essential problem. Due to the complexity and variability of the ocean, accurate environment modeling and flexible path planning algorithms are pivotal challenges. The traditional models mainly utilize mathematical functions, which are not complete and reliable. Most existing path planning algorithms depend on the environment and lack flexibility. To overcome these challenges, we propose a path planning system for underwater intelligent internet vehicles. It applies digital twins and sensor data to map the real ocean environment to a virtual digital space, which provides a comprehensive and reliable environment for path simulation. We design a value-based reinforcement learning path planning algorithm and explore the optimal network structure parameters. The path simulation is controlled by a closed-loop model integrated into the terminal vehicle through edge computing. The integration of state input enriches the learning of neural networks and helps to improve generalization and flexibility. The task-related reward function promotes the rapid convergence of the training. The experimental results prove that our reinforcement learning based path planning algorithm has great flexibility and can effectively adapt to a variety of different ocean conditions.

Monitoring the water usage of different appliances and informing consumers about it has been shown to have an impact on their behavior toward drinking water conservation. The most practical and cost-effective way to accomplish this is through a non-intrusive approach, that locally analyzes data received from a flow sensor at the main water supply pipe of a household. In this work, we present two different methods addressing the challenges of disaggregating end-use consumption and classifying consumption events. The first method is model-based (MB) and uses a combination of dynamic time wrapping and statistical bounds to analyze four water end-use characteristics. The second, learning-based (LB) method is data-driven and formulates the problem as a time-series classification problem without relying on a priori identification of events. We perform an extensive computational study that includes a comparison between an MB and an LB method, as well as an experimental study to demonstrate the application of the LB method on an edge computing device. Both methods achieve similar F1 scores (LB: 71.73%, MB: 71.04%) with the LB being more precise. The embedded LB method achieves a slightly higher score (72.01%) while enhancing on-site real-time processing, improving security and privacy and enabling cost savings. HIGHLIGHTS Application and comparison of model-based and data-driven approaches to make predictions based on aggregated water consumption information.; Classification accuracy per water end-use category depends on the classification approach.; Real-time implementation of a neural network-based approach on an edge computing device.;

In deterministic mobile edge computing (MEC) networks, accurately predicting latency is critical for optimizing resource allocation and enhancing quality of service (QoS). This paper introduces a novel approach leveraging attention mechanism enhanced long short-term memory (LSTM) networks to predict latency in MEC networks. The proposed model integrates attention mechanisms into LSTM networks to capture temporal dependency and emphasize relevant features in the input data, thereby improving the prediction accuracy. T extensive experiments are conducted by using practical MEC network data, demonstrating that the proposed approach significantly outperforms traditional LSTM and other baseline models in terms of prediction accuracy and computational efficiency. Additionally, we analyze the impact of various configurations in the attention mechanism and LSTM on the model performance, providing insights into the optimal settings. The findings of this study contribute to the advancement of latency prediction techniques in deterministic MEC networks, facilitating more efficient and reliable network management.

With the massive access to sensing, measuring, and user-side intelligent terminal devices, the functionalities and applications at the edge-side of digital distribution networks have become significantly enriched. However, the limited computation resources of edge computing devices must be utilized efficiently to achieve various functions, presenting challenges to resource scheduling within digital distribution networks. To tackle these challenges, this paper proposes an optimal resource scheduling method for multi-functional edge computing devices. The collaborative processing relationships of multi-functional applications for edge computing devices in digital distribution networks are analyzed to achieve various functions. These applications are further abstracted into computational task models with different characteristics. On this basis, constraints for resource scheduling are established, including the logical relationships between tasks, the multi-core configuration, and the resource limitation of devices. With the proposed scheduling method, computation resources of the edge computing device can be optimally allocated to different tasks, achieving multiple objectives such as reducing the process latency, avoiding task abandonment, and maximizing resource backup. The results of the case study indicate that using the proposed method, the overall task completion time is reduced by 20%, the task processing success rate increases to 95%, and the adequate resource reservation ratio improves to 40%.

The combination of Machine Learning (ML), smart energy meters, and availability of household appliance energy profile data has opened new opportunities for Non-Intrusive Load Monitoring (NILM). However, the number of options makes it challenging in selecting optimal combinations for different energy applications, which requires studies to examine their trade-offs.This paper contributes one such study that investigated four established ML approaches – K Nearest Neighbour (KNN), Support Vector Machine (SVM), eXtreme Gradient Boosting (XGBoost) and Convolutional Neural Network (CNN) – and their performance in classifying appliance events from Alternating Current (AC) and Root Mean Square (RMS) energy data where the sampling frequency and training dataset set size was varied (10 Hz–1 kHz and 50–2000 examples per class, respectively). The computational expense during training, testing and storage was also assessed and evaluated with reference to real-world applications.The CNN classifier trained on AC data at 500 Hz and 11,000 examples gave the best F1-score 0.989 followed by the KNN classifier 0.940. The storage size required by the CNN models was 3̃MB, which is very close to fitting on cost-effective embedded system microcontrollers. This would prevent high-rate data needing to be sent to the cloud as analysis could be performed on edge computing Internet-of-Things (IoT) devices.

To meet the grand challenges of agricultural production including climate change impacts on crop production, a tight integration of social science, technology and agriculture experts including farmers are needed. Rapid advances in information and communication technology, precision agriculture and data analytics, are creating a perfect opportunity for the creation of smart connected farms (SCFs) and networked farmers. A network and coordinated farmer network provides unique advantages to farmers to enhance farm production and profitability, while tackling adverse climate events. The aim of this article is to provide a comprehensive overview of the state of the art in SCF including the advances in engineering, computer sciences, data sciences, social sciences and economics including data privacy, sharing and technology adoption. More specifically, we provide a comprehensive review of key components of SCFs and crucial elements necessary for its success. It includes, high-speed connections, sensors for data collection, and edge, fog and cloud computing along with innovative wireless technologies to enable cyber agricultural system. We also cover the topic of adoption of these technologies that involves important considerations around data analysis, privacy, and the sharing of data on platforms. From a social science and economics perspective, we examine the net-benefits and potential barriers to data-sharing within agricultural communities, and the behavioral factors influencing the adoption of SCF technologies. The focus of this review is to cover the state-of-the-art in smart connected farms with sufficient technological infrastructure; however, the information included herein can be utilized in geographies and farming systems that are witnessing digital technologies and want to develop SCF. Overall, taking a holistic view that spans technical, social and economic dimensions is key to understanding the impacts and future trajectory of Smart and Connected Farms.

Keamanan merupakan salah satu aspek penting di kehidupan manusia. Umumnya, keamanan dapat berarti perlindungan dari bahaya fisik dan non fisik seperti kecelakaan, kebakaran, ataupun pencurian. Kemajuan teknologi yang ada dapat dimanfaatkan untuk meningkatkan keamanan, khususnya untuk kasus pencurian. Sistem kamera pengawas seperti CCTV telah terbukti dalam meningkatkan keamanan. Tetapi, CCTV mengharuskan pengawas untuk memantau layar CCTV secara manual 24/7 untuk melihat adanya pergerakan manusia. Pada penelitian ini, dibangun sistem deteksi menggunakan sensor passive infrared (PIR) yang dikontrol oleh ESP32-CAM. Algoritma single shot detector (SSD) digunakan untuk memproses data citra dan edge computing digunakan untuk mendukung waktu proses deteksi sehingga dapat memberikan informasi secara real-time. Proses transmisi data citra pada edge computing menggunakan protokol MQTT. Setiap ESP32-CAM akan menjadi publisher dan edge akan menjadi subscriber. Dataset yang digunakan untuk melatih algoritma SSD berjumlah 1050 data. Seluruh data dibagi menjadi 3 bagian yaitu 735 data latih (70%), 210 data evaluasi (20%), dan 105 (10%) data uji. Data uji pada penelitian ini terdiri dari 3 jenis data, diantaranya 35 data uji siang hari, 35 data uji sore hari, dan 35 data uji malam hari. Algoritma SSD pada penelitian ini menghasilkan ketepatan deteksi 87.51% mAP pada data uji siang hari, 81.39% mAP pada data uji sore hari, dan 76.82% mAP pada data uji malam hari. Proses dari saat sensor HC-SR501 mendeteksi gerakan hingga informasi sampai ke user membutuhkan rata-rata waktu 2,843 detik.

Recent years, the tremendous number of distributed energy resources, electric vehicles are integrated into the Low-Voltage Distribution Network (LVDN), large amount of data are generated by edge devices in LVDN. The cloud data centers are unable to process these data timely and accurately, making it impossible to meet the demand for fine-grained control of LVDN. To solve the above problems, this paper proposes a flexible orchestration of lightweight artificial intelligence (AI) for edge computing in LVDN. Firstly, the application requirements of LVDN are analysed through feature extraction of its historical data, and a lightweight AI library is constructed to meet its requirements. Secondly, based on the multi-factor priority, a flexible orchestration model is established, to allow the lightweight AI embedded in the edge devices of the LVDN. Finally, the particle swarm optimization algorithm is used to provide the best solution. The simulation results show that the method proposed in this paper can support the deployment of AI at the edge. It can significantly improve the utilization of edge computing resources, and reduce the pressure of cloud computing and the time of application processes.

ObjectiveIt is of great significance to improve the efficiency and accuracy of crop pest detection in complex natural environments, and to change the current reliance on expert manual identification in the agricultural production process. Targeting the problems of small target size, mimicry with crops, low detection accuracy, and slow algorithm reasoning speed in crop pest detection, a complex scene crop pest target detection algorithm named YOLOv8-Entend was proposed in this research.MethodsFirstly, the GSConv was introduecd to enhance the model's receptive field, allowing for global feature aggregation. This mechanism enables feature aggregation at both node and global levels simultaneously, obtaining local features from neighboring nodes through neighbor sampling and aggregation operations, enhancing the model's receptive field and semantic understanding ability. Additionally, some Convs were replaced with lightweight Ghost Convolutions and HorBlock was utilized to capture longer-term feature dependencies. The recursive gate convolution employed gating mechanisms to remember and transmit previous information, capturing long-term correlations. Furthermore, Concat was replaced with BiFPN for richer feature fusion. The bidirectional fusion of depth features from top to bottom and from bottom to top enhances the transmission of feature information acrossed different network layers. Utilizing the VoVGSCSP module, feature maps of different scales were connected to create longer feature map vectors, increasing model diversity and enhancing small object detection. The convolutional block attention module (CBAM) attention mechanism was introduced to strengthen features of field pests and reduce background weights caused by complexity. Next, the Wise IoU dynamic non-monotonic focusing mechanism was implemented to evaluate the quality of anchor boxes using "outlier" instead of IoU. This mechanism also included a gradient gain allocation strategy, which reduced the competitiveness of high-quality anchor frames and minimizes harmful gradients from low-quality examples. This approach allowed WIoU to concentrate on anchor boxes of average quality, improving the network model's generalization ability and overall performance. Subsequently, the improved YOLOv8-Extend model was compared with the original YOLOv8 model, YOLOv5, YOLOv8-GSCONV, YOLOv8-BiFPN, and YOLOv8-CBAM to validate the accuracy and precision of model detection. Finally, the model was deployed on edge devices for inference verification to confirm its effectiveness in practical application scenarios.Results and DiscussionsThe results indicated that the improved YOLOv8-Extend model achieved notable improvements in accuracy, recall, mAP@0.5, and mAP@0.5:0.95 evaluation indices. Specifically, there were increases of 2.6%, 3.6%, 2.4% and 7.2%, respectively, showcasing superior detection performance. YOLOv8-Extend and YOLOv8 run respectively on the edge computing device JETSON ORIN NX 16 GB and were accelerated by TensorRT, mAP@0.5 improved by 4.6%, FPS reached 57.6, meeting real-time detection requirements. The YOLOv8-Extend model demonstrated better adaptability in complex agricultural scenarios and exhibited clear advantages in detecting small pests and pests sharing similar growth environments in practical data collection. The accuracy in detecting challenging data saw a notable increased of 11.9%. Through algorithm refinement, the model showcased improved capability in extracting and focusing on features in crop pest target detection, addressing issues such as small targets, similar background textures, and challenging feature extraction.ConclusionsThe YOLOv8-Extend model introduced in this study significantly boosts detection accuracy and recognition rates while upholding high operational efficiency. It is suitable for deployment on edge terminal computing devices to facilitate real-time detection of crop pests, offering technological advancements and methodologies for the advancement of cost-effective terminal-based automatic pest recognition systems. This research can serve as a valuable resource and aid in the intelligent detection of other small targets, as well as in optimizing model structures.

Abstract Sensors, wearables, mobile devices, and other Internet of Things (IoT) devices are becoming increasingly integrated into all aspects of our lives. They are capable of gathering enormous amounts of data, such as image data, which can then be sent to the cloud for processing. However, this results in an increase in network traffic and latency. To overcome these difficulties, edge computing has been proposed as a paradigm for computing that brings processing closer to the location where data is produced. This paper explores the merging of cloud and edge computing for IoT and investigates approaches using machine learning for dimensionality reduction of images on the edge, employing the autoencoder deep learning-based approach and principal component analysis (PCA). The encoded data is then sent to the cloud server, where it is used directly for any machine learning task without significantly impacting the accuracy of the data processed in the cloud. The proposed approach has been evaluated on an object detection task using a set of 4000 images randomly chosen from three datasets: COCO, human detection, and HDA datasets. Results show that a 77% reduction in data did not have a significant impact on the object detection task’s accuracy.

Abstract The increasing popularity of various intelligent sensor and mobile communication technologies has enabled quick health physique sensing, monitoring, collection and analyses of students, which significantly promoted the development of sport education. Through collecting the students’ physiological signals and transmitted them to edge servers, we can precisely analyze and judge whether a student is in poor health (e.g., an outlier). However, with time elapsing, the accumulated physiological signals of students become massive, which places a heavy burden on the quick storage and in-time processing of physiological data of students. In this situation, it is becoming a necessity to develop a time-aware outlier detection technique for health physique evaluation of students in a time-efficient way. Considering this challenge, we propose a novel time-aware outlier detection method named TOD based on Locality-Sensitive Hashing. TOD condenses extensive physiological student data into a concise set of health indices. Leveraging these indices, we can efficiently identify potential student outliers from a large pool of candidates with precision and speed. Finally, we have designed a group of simulated experiments based on WS-DREAM dataset. Experiment results prove the feasibility and superiority of the TOD method compared with other existing methods.

Edge data analytics refers to processing near data sources at the edge of the network to reduce delays in data transmission and, consequently, enable real-time interactions. However, data analytics at the edge introduces numerous security risks that can impact the data being processed. Thus, safeguarding sensitive data from being exposed to illegitimate users is crucial to avoiding uncertainties and maintaining the overall quality of the service offered. Most existing edge security models have considered attacks during data analysis as an afterthought. In this paper, an overview of edge data analytics in healthcare, traffic management, and smart city use cases is provided, including the possible attacks and their impacts on edge data analytics. Further, existing models are investigated to understand how these attacks are handled and research gaps are identified. Finally, research directions to enhance data analytics at the edge are presented.

The latest effort in delivering computing resources as a service to managers and consumers represents a shift away from computing as a product that is purchased, to computing as a service that is delivered to users over the internet from large-scale data centers. However, with the advent of the cloud-based IoT and artificial intelligence (AI), which are advancing customer experience automations in many application areas, such as recommender systems (RS), a need has arisen for various modifications to support the IoT devices that are at the center of the automation world, including recent language models like ChatGPT and Bard and technologies like nanotechnology. This paper introduces the marketing community to a recent computing development: IoT-driven fog computing (FC). Although numerous research studies have been published on FC “smart” applications, none hitherto have been conducted on fog-based smart marketing domains such as recommender systems. FC is considered a novel computational system, which can mitigate latency and improve bandwidth utilization for autonomous consumer behavior applications requiring real-time data-driven decision making. This paper provides a conceptual framework for studying the effects of fog computing on consumer behavior, with the goal of stimulating future research by using, as an example, the intersection of FC and RS. Indeed, our conceptualization of the “fog-based recommender systems” opens many novel and challenging avenues for academic research, some of which are highlighted in the later part of this paper.

Abstract Powered by data-driven technologies, precision agriculture offers immense productivity and sustainability benefits. However, fragmentation across farmlands necessitates distributed transparent automation. We developed an edge computing framework complemented by auction mechanisms and fuzzy optimizers that connect various supply chain stages. Specifically, edge computing offers powerful capabilities that enable real-time monitoring and data-driven decision-making in smart agriculture. We propose an edge computing framework tailored to agricultural needs to ensure sustainability through a renewable solar energy supply. Although the edge computing framework manages real-time crop monitoring and data collection, market-based mechanisms, such as auctions and fuzzy optimization models, support decision-making for smooth agricultural supply chain operations. We formulated invisible auction mechanisms that hide actual bid values and regulate information flows, combined with machine learning techniques for robust predictive analytics. While rule-based fuzzy systems encode domain expertise in agricultural decision-making, adaptable training algorithms help optimize model parameters from the data. A two-phase hybrid learning approach is formulated. Fuzzy optimization models were formulated using domain expertise for three key supply chain decision problems. Auction markets discover optimal crop demand–supply balancing and pricing signals. Fuzzy systems incorporate domain knowledge into interpretable crop-advisory models. An integrated evaluation of 50 farms over five crop cycles demonstrated the high performance of the proposed edge computing-oriented auction-based fuzzy neural network model compared with benchmarks.

Abstracts: The Internet of Things (IoT) has been growing quickly since the 5 G era arrived, which has boosted the quantity of data stream and computational demands. Ultra-dense Edge Computing (UDEC) is a result of the growing popularity of Mobile Edge Computing (MEC) and Ultra-dense Network (UDN), two vital technologies with bright futures. Task offloading is viewed in the UDEC network as a successful strategy to offer mobile users low-latency and flexible computing capabilities. However, the edge cloud's constrained computing capacity and mobile users' dynamically shifting computing requirements present difficulties for the reasonable scheduling of computing requests to the edge cloud. The Power Allocation (PA) problem for mobile users to address this issue. This problem attempts to use quasiconvex technique to minimize energy consumption. Next, the Joint Request Offloading and Resource Scheduling (JRORS) problem is treated as a mixed-integer nonlinear programming problem to minimize request delay and improve welfare. The request offloading problem and the computational resource scheduling challenge are two subproblems of the JRORS problem that can be further broken down, the JRORS issue is therefore viewed as a dual decision-making problem. A Ratio of Power Consumption to Welfare (RCW) problem through mathematical modeling. An improved snake optimizer (SO) is therefore proposed, which was added with oscillation factor to optimize the location of the weight parameter in the location update and the variation of food production. It can enhance the global search capability and local search ability. By conducting simulation experiments, divide the mobile users into nine groups for testing, select energy consumption, welfare, and RCW as the objective functions, respectively, and compare them with other swarm optimization algorithms, such as Differential Evolution (DE), Particle Swarm Optimization (PSO), Ant-Lion Optimizer (ALO), Butterfly Optimization Algorithm (BOA), and Gray Wolf Optimizer (GWO). The improved algorithm achieved minimal energy consumption and optimal welfare in nearly every test case, contributing to the enhanced effectiveness and cost-efficiency of edge systems, thereby achieving the optimization of task offloading and scheduling.

Litchi, a succulent and perishable fruit, presents a narrow annual harvest window of under two weeks. The advent of smart agriculture has driven the adoption of visually-guided, automated litchi harvesting techniques. However, conventional approaches typically rely on laboratory-based, high-performance computing equipment, which presents challenges in terms of size, energy consumption, and practical application within litchi orchards. To address these limitations, we propose a real-time litchi detection methodology for complex environments, utilizing portable, low-energy edge computing devices. Initially, the litchi orchard imagery is collected to enhance data generalization. Subsequently, a convolutional neural network (CNN)-based single-stage detector, YOLOx, is constructed to accurately pinpoint litchi fruit locations within the images. To facilitate deployment on portable, low-energy edge devices, we employed channel pruning and layer pruning algorithms to compress the trained model, reducing its size and parameters. Additionally, the knowledge distillation technique is harnessed to fine-tune the network. Experimental findings demonstrated that our proposed method achieved a 97.1% compression rate, yielding a compact litchi detection model of a mere 6.9 MB, while maintaining 94.9% average precision and 97.2% average recall. Processing 99 frames per second (FPS), the method exhibited a 1.8-fold increase in speed compared to the unprocessed model. Consequently, our approach can be readily integrated into portable, low-computational automatic harvesting equipment, ensuring real-time, precise litchi detection within orchard settings.

The real-time transmission of online monitoring data for high-voltage transmission equipment in remote areas is a difficult problem in practical applications due to the lack of network. For this purpose, the article designs an online monitoring system for high-voltage transmission equipment based on ubiquitous IoT and LoRa technology. It constructs a low-power, long-distance LoRa wireless communication self-organizing network, transmits the transmission equipment status information and other data collected by front-end sensors to the LoRaWAN gateway, and then uploads the data to the back-end server through a 5G wireless network to achieve the overall communication link of the online monitoring system. The simulation experiment results show that compared with the existing technical solutions ZigBee, LoRa, and NB-IoT, using the scheme designed in the article, the system transmission speed (20-100 kbit/s) is the fastest, and the packet loss rate, transmission delay, and average time consumption (1.6%, 0.27s, and 60s, respectively) are the lowest. This indicates that the system not only has a fast transmission speed but also takes into account the characteristics of low power consumption and long distance, achieving stable data transmission, and is suitable for online monitoring of high-voltage transmission equipment in remote areas.

ObjectiveIn order to tackle the challenges of low reliability, weak risk resistance and limited real-time performance in existing centralized control architectures for active vibration isolation systems, and considering the current state of research on vibration systems and edge computing, this study proposes a distributed control architecture for large-scale shipborne active vibration isolation systems based on edge computing.MethodsFirst, the traits of the centralized and distributed control approaches are analyzed. Second, the entire architecture of the control system is studied, leading to the design of its hierarchical structure and overall layout, which is partitioned into three levels: cloud, edge and end. The architectural design and interconnections of each level are expounded upon in detail. Finally, an experimental platform is created, and the system's reliability and real-time performance are evaluated through testing.ResultsThe experimental results indicate that the designed system architecture continues to operate normally under sudden circumstances, demonstrating stability and reliability. Moreover, the clock synchronization deviation is reduced to 1 microsecond, enhancing the system's real-time performance.ConclusionThe system architecture is rationally and efficiently designed, effectively enhancing the reliability, risk resistance and real-time performance of the vibration isolation system

The development of communication technology will promote the application of Internet of Things, and Beyond 5G will become a new technology promoter. At the same time, Beyond 5G will become one of the important supports for the development of edge computing technology. This paper proposes a communication task allocation algorithm based on deep reinforcement learning for vehicle-to-pedestrian communication scenarios in edge computing. Through trial and error learning of agent, the optimal spectrum and power can be determined for transmission without global information, so as to balance the communication between vehicle-to-pedestrian and vehicle-to-infrastructure. The results show that the agent can effectively improve vehicle-to-infrastructure communication rate as well as meeting the delay constraints on the vehicle-to-pedestrian link.

Abstract The Smart Grid (SG) heavily depends on the Advanced Metering Infrastructure (AMI) technology, which has shown its vulnerability to intrusions. To effectively monitor and raise alarms in response to anomalous activities, the Intrusion Detection System (IDS) plays a crucial role. However, existing intrusion detection models are typically trained on cloud servers, which exposes user data to significant privacy risks and extends the time required for intrusion detection. Training a high-quality IDS using Artificial Intelligence (AI) technologies on a single entity becomes particularly challenging when dealing with vast amounts of distributed data across the network. To address these concerns, this paper presents a novel approach: a fog-edge-enabled Support Vector Machine (SVM)-based federated learning (FL) IDS for SGs. FL is an AI technique for training Edge devices. In this system, only learning parameters are shared with the global model, ensuring the utmost data privacy while enabling collaborative learning to develop a high-quality IDS model. The test and validation results obtained from this proposed model demonstrate its superiority over existing methods, achieving an impressive percentage improvement of 4.17% accuracy, 13.19% recall, 9.63% precision, 13.19% F1 score when evaluated using the NSL-KDD dataset. Furthermore, the model performed exceptionally well on the CICIDS2017 dataset, with improved accuracy, precision, recall, and F1 scores reaching 6.03%, 6.03%, 7.57%, and 7.08%, respectively. This novel approach enhances intrusion detection accuracy and safeguards user data and privacy in SG systems, making it a significant advancement in the field.

Abstract With the exponential growth of various data interactions on network systems, network intrusions are also increasing. The emergence of edge computing technology brings a new solution to network security. However, due to the difficulty of processing massive and unbalanced data at the edge, higher accuracy requirements are necessary for deployed detection models. This paper proposes a multi-classification model for network intrusion detection based on reconstruction and feature matching. This model can be deployed on small-scale edge nodes, effectively identifying various attack behaviors through the utilization of reconstruction errors and adaptive scaling. Furthermore, we proposed a model transfer method based on feature matching to enhance the training and detection efficiency of multi-classification models under different data distribution conditions. The proposed model has been evaluated on the CICIDS2017 dataset in terms of accuracy, recall, precision and F1 score. The model demonstrates high accuracy for normal flows in the network, majority class attacks, and minority class attacks, achieving an overall multi-class accuracy of 99.81%, outperforming similar models. Furthermore, this model demonstrates faster convergence and training speed after feature matching, exhibiting better robustness and outstanding performance at the edge.

Abstract Automatic target tracking in emerging remote sensing video-generating tools based on microwave imaging technology and radars has been investigated in this paper. A moving target tracking system is proposed to be low complexity and fast for implementation through edge nodes in a mini-satellite or drone network enabling machine intelligence into large-scale vision systems, in particular, for marine transportation systems. The system uses a group of image processing tools for video pre-processing, and Kalman filtering to do the main task. For testing the system performance, two measures of accuracy and false alarms probability are computed for real vision data. Two types of scenes are analyzed including the scene with single target, and the scene with multiple targets that is more complicated for automatic target detection and tracking systems. The proposed system has achieved a high performance in our tests.

Abstract Physical, social, and routine environments can be challenging for learners with autism spectrum disorder (ASD). ASD is a developmental disorder caused by neurological problems. In schools and educational environments, this disorder may not only hinder a child’s learning, but also lead to more crises and mental convulsions. In order to teach students with ASD, it is essential to understand the impact of their learning environment on their interaction and behavior. Different methods have been used to diagnose ASD in the past, each with their own strengths and weaknesses. Research into ASD diagnostics has largely focused on machine learning algorithms and strategies rather than diagnostic methods. This article discusses many diagnostic techniques used in the ASD literature, such as neuroimaging, speech recordings, facial features, and EEG signals. This has led us to conclude that in schools and educational settings, autism can be diagnosed cheaply, quickly, and accurately through face analysis. To facilitate and speed up the processing of facial information among children in educational settings, we applied the AlexNet architecture designed for edge computing. A fast method for detecting autism spectrum disorders from the face can be applied to educational settings using this structure. While we have investigated a variety of methods, the face can provide us with appropriate information about the disorder. In addition, it can produce more interpretive features. In order to help students in schools who are suffering from this disease, key factors must be considered: potential clinical and therapeutic situations, efficiency, predictability, privacy protection, accuracy, cost-effectiveness, and lack of methodological intervention. The diseases are troublesome, so they should be identified and treated.

Abstract The integration of edge intelligence (EI) in animation design, particularly when dealing with large models, represents a significant advancement in the field of computer graphics and animation. This survey aims to provide a comprehensive overview of the current state and future prospects of EI-assisted animation design, focusing on the challenges and opportunities presented by large model implementations. Edge intelligence, characterized by its decentralized processing and real-time data analysis capabilities, offers a transformative approach to handling the computational and data-intensive demands of modern animation. This paper explores various aspects of EI in animation and then delves into the specifics of large models in animation, examining their evolution, current trends, and the inherent challenges in their implementation. Finally, the paper addresses the challenges and solutions in integrating EI with large models in animation, proposing future research directions. This survey serves as a valuable resource for researchers, animators, and technologists, offering insights into the potential of EI in revolutionizing animation design and opening new avenues for creative and efficient animation production.