Abstract: Recent improvements in the Internet of Things (IoT) have allowed healthcare to evolve rapidly. This article summarizes previous studies on IoT applications in healthcare. A comprehensive review and a bibliometric analysis were performed to objectively summarize the growth of IoT research in healthcare. To begin, 2,990 journal articles were carefully selected for further investigation. These publications were analyzed based on various bibliometric metrics, including publication year, journals, authors, institutions, and countries. Keyword co-occurrence and co-citation networks were generated to unravel significant research hotspots. The findings show that IoT research has received considerable interest from the healthcare community. Based on the results of the keyword co-occurrence network, IoT healthcare applications, blockchain applications, Artificial Intelligence (AI) techniques, 5G telecommunications, as well as data analytics and computing technologies emerged as important topics. The co-citation network analysis reveals other important themes, including authentication schemes, fog computing, cloud-IoT integration, and cognitive smart healthcare. Overall, the review offers scholars an improved understanding of the current status of IoT research in healthcare and identifies knowledge gaps for future research. This review also informs healthcare professionals about the latest developments and applications of IoT in the healthcare sector.

Abstract: The adoption of artificial intelligence (AI) in healthcare is growing rapidly. Remote patient monitoring (RPM) is one of the common healthcare applications that assist doctors to monitor patients with chronic or acute illness at remote locations, elderly people in‐home care, and even hospitalized patients. The reliability of manual patient monitoring systems depends on staff time management which is dependent on their workload. Conventional patient monitoring involves invasive approaches which require skin contact to monitor health status. This study aims to do a comprehensive review of RPM systems including adopted advanced technologies, AI impact on RPM, challenges and trends in AI‐enabled RPM. This review explores the benefits and challenges of patient‐centric RPM architectures enabled with Internet of Things wearable devices and sensors using the cloud, fog, edge, and blockchain technologies. The role of AI in RPM ranges from physical activity classification to chronic disease monitoring and vital signs monitoring in emergency settings. This review results show that AI‐enabled RPM architectures have transformed healthcare monitoring applications because of their ability to detect early deterioration in patients' health, personalize individual patient health parameter monitoring using federated learning, and learn human behavior patterns using techniques such as reinforcement learning. This review discusses the challenges and trends to adopt AI to RPM systems and implementation issues. The future directions of AI in RPM applications are analyzed based on the challenges and trends.

Abstract: Artificial Intelligence (AI) at the edge is the utilization of AI in real-world devices. Edge AI refers to the practice of doing AI computations near the users at the network's edge, instead of centralised location like a cloud service provider's data centre. With the latest innovations in AI efficiency, the proliferation of Internet of Things (IoT) devices, and the rise of edge computing, the potential of edge AI has now been unlocked. This study provides a thorough analysis of AI approaches and capabilities as they pertain to edge computing, or Edge AI. Further, a detailed survey of edge computing and its paradigms including transition to Edge AI is presented to explore the background of each variant proposed for implementing Edge Computing. Furthermore, we discussed the Edge AI approach to deploying AI algorithms and models on edge devices, which are typically resource-constrained devices located at the edge of the network. We also presented the technology used in various modern IoT applications, including autonomous vehicles, smart homes, industrial automation, healthcare, and surveillance. Moreover, the discussion of leveraging machine learning algorithms optimized for resource-constrained environments is presented. Finally, important open challenges and potential research directions in the field of edge computing and edge AI have been identified and investigated. We hope that this article will serve as a common goal for a future blueprint that will unite important stakeholders and facilitates to accelerate development in the field of Edge AI.

Abstract: In general, the company sometimes uses unregistered functions in database, which significantly improves performance, but does not leave the possibility of recovery except for backup. That is, actions must be performed immediately after passing the session. A queue problem is likely to cause data loss and downtime of about a week. In modern conditions, this can lead to the bankruptcy of the company. It can be seen that backup systems have been installed and configured, but despite this, they have not succeeded in restoring within the time frame specified in the SLA. In this study, a secured database monitoring method was proposed to improve data backup and recovery operations in cloud computing. In this proposed method, the backup speed is directly proportional to the amount of data, while having at least 30% annual data growth. In 3–4 years, the data at least doubled, but for some companies, this number is even higher, while the backup speed does not change. Those terms and those SLAs that were relevant 3–4 years ago now need to be at least doubled. At the same time, business requirements for data recovery (recovery point objective/recovery time objective) continue to grow

Abstract: OmicStudio focuses on speed, quality together with flexibility. Generally, OmicStudio can not only meet the users' demand of ordinary bioinformatics data analysis, statistics, and visualization, but also provides them freedom of data mining beyond developer's framework. Additionally, unlimited to developer's aesthetics, users can get more elegant graphs through customizing. Available online https://www.omicstudio.cn. In the past decade, an increasing number of cloud-based bioinformatics platforms were spring up, such as Qiita [1], EasyMAP [2], ImageGP [3], MG-RAST [4], gcMeta [5], ETCM [6], Sangerbox [7], antiSMASH [8], EVenn [9], and Majorbio Cloud [10]. These platforms greatly facilitated the biological, medicine and metagenomics research, and provided new vision into big data. Some software deploy various independent tools [11–16], while the others provide complete pipeline [17–21]. The main highlight of these cloud platforms is to convert complicated coding works into easy-used web-based tools [22]. With the assumption that all users already have enough knowledge about bioinformatics before operation, these tools mainly focus on simplifying operation procedure. But the unnoticed truth is that users are also learning while operating, who at the same time expect to get graphs for publication through simple operation. Here, we display the overall framework as well as each independent module of OmicStudio Cloud Platform (https://www.omicstudio.cn). OmicStudio is a one-stop online analysis platform providing high-throughput omics data analysis, as well as an exploratory platform for bioinformatics research. OmicStudio can obtain results rapidly, generate high-quality graphs for publication, and connect with downstream analysis module automatically. It focuses on speed, quality together with flexibility. Generally, OmicStudio can not only meet the users' demand of ordinary bioinformatics data analysis, statistics, and visualization but also provides them freedom of data mining beyond developer's framework. Additionally, unlimited to developer's aesthetics, users can get more elegant graphs through customizing. In terms of website framework, OmicStudio has common configuration that all bioinformatics cloud platform may have, such as Cloud Tools, Cloud Analysis, Omics Courses and Study Materials Center, providing entire bioinformatics service for users. Since its establishment in early 2019, OmicStudio already attracted over 30,000 users, helped whom publish more than 600 research papers (search “OmicStudio” in Google scholar on January 1, 2023), involving various “-omics” fields. An easy-to-use platform which can generate high-quality results is obviously able to make great contribution to scientific research. OmicStudio consists of six modules, named Cloud Tools, Cloud Analysis, Cloud Classroom, Study Materials Center, User's Paper Collection, and User Center. Cloud Tools and Cloud Analysis are the main part of the function for bioinformatics analysis. Cloud Classroom and Study Materials Center help users understand and learn bioinformatics. User's Paper Collection collects the papers published in cooperation with LCBIO and users can take them as reference. User Center is an integrated management module for user's project information. The core functions of the cloud platform are cloud tools and cloud analytics. The main difference is that cloud tools focus on short, quick analysis, while cloud analytics can support time-consuming analysis and have a project management back office. The two modules are distinguished by the nature of the analysis: the analysis with large amount of data and complex calculation needs to be able to run in the background so that users can leave the web page and do their own thing; simple analytics require instant results and can be personalized immediately. Based on this consideration, the module design can allow users to obtain the most comfortable experience in different application scenarios. Other modules serve these two core modules. Cloud Classroom and Study Materials Center provide the basic knowledge of run bioinformatics analysis in the form of video and text respectively. User Center manages the analysis results, and User's Paper Collection provide new users with reference for writing articles. The innovativeness and character of OmicStudio major function will be clarified later. In terms of type of omics and application scenarios, Cloud Tools are classified as: General Omics, Single Cell, Enrichment Analysis, Common Analysis, Databases, and so on (Figure 1). The summary of the useful tool in OmicStudio s are showed in Figure 1. “Set the parameter and start to analyze,” ordinary online bioinformatics tools usually follow this principle. First, users are required to finish the parameter adjustment with unpredictable result, which is with great difficulty. The process of learning that most of us are used to be the “adjust—view the results—adjust again—view the results again” loop. After parameter adjustment and analysis, users need to view the results in backstage. If readjustment is needed, users need to click back to the previous web page, readjust the settings, and view the results again. This is a tedious process with a lot of repetition. Second, for those unfamiliar with bioinformatics, the corresponding relationship between parameter and result is unclear. Consequently, they cannot acquire the desired result through adjusting parameters. Either they are required to spend much time learning the meaning of parameter, which has nothing to do with their goal, or they must do repetitive work repeatedly. Thirdly, there is no uniform standard for development of bioinformatics website. As a result, users must spend time learning how to use these various online tools. Usually, the function of a bioinformatics tool may be simplified to improve user experience, thus users could get desired results without paying too much time cost. But this simplification will not only limit users' cognition (they don't know how much key information is hidden from their simple operation) but also restrict these online tools to becoming multifunctional platforms, which can provide more personalized bioinformatics tools to meet the demand of more advanced scientific research. OmicStudio Cloud Platform focuses on real-time feedback. The results of parameter adjustment can be visualized immediately just on the current web page, which greatly reduces users' time cost of debugging. Furthermore, OmicStudio helps users understand the corresponding relationship between parameters and results in an interesting way, turning tedious data analysis into a game. In this game, users can fully understand bioinformatics and how the tools on this platform work. Real-time feedback makes the influence of parameter more comprehensible without knowing its connotation, and then helps data users understand the meaning of parameter through its influence. OmicStudio overcomes the difficulty for users in understanding the esoteric principles of bioinformatics and tools operation, which is a great breakthrough in development of bioinformatics platform. As mentioned above, the more parameters result in the higher cost of learning. To solve this problem, OmicStudio provides default parameters. In the most convenient way, users only need to upload the documents, wait for the refreshment of the image on the web page (it usually takes just a few seconds), and then download. Despite great number of parameters, each of them has a default value, with which OmicStudio can immediately generate a graph for publication. If users just want to have a glance at their data quality (e.g., using principal component analysis to examine the sample repetition, or using correlation heatmap to check the relevance of data), they can directly download and use, which can be done within 1 min. Default parameters are parameters most frequently used, which are reliable in most cases, and will not be the barrier to choose. Ordinary bioinformatics platforms focus only on the analysis procedure. As a result, for publication purposes, the generated graph is usually needed to be redrawn and readjusted. OmicStudio also provides the adjustment module for drawing graphs. The default style of graphs is well designed and adjustable. Users can adjust the themes, color schemes, fonts, titles, and so on. If OmicStudio cannot meet all the needs, it also provides a further solution: downloadable figures in PowerPoint format. The figure generated from OmicStudio can be split into elements in PowerPoint, each of which can be adjusted independently. The function provided by PowerPoint can all be applied to the adjustment of graphs. It has the same function with Adobe Illustrator, while with lower cost of learning. For scientific research, besides the free adjustable parameters, the further demand is to freely choose what to do in the downstream analysis. Although ordinary bioinformatics cloud platforms can provide easy-to-use analysis procedure, they may limit users to freely choosing what to analyze. The analysis modules of OmicStudio are independent while correlated. As shown below, on the page of one kind of cloud tool, there is a series of related cloud tools displayed on the right sidebar, and users can click it to jump to the page of analysis (analysis can be continued based on current results, and there is no necessary to upload any document). The advantage of it is that users can freely choose what to analyze next, as well as decide when to stop. Figure 2 displays the correlation among cloud tools for Tumor WES. Similar series of modules includes Correlation Analysis, Enrichment Analysis, and so on. Graphs generated by OmicStudio are famous for its beautiful design. Typical examples are shown in Figure 3, which were all downloaded directly from OmicStudio without any extra adjustment. Graphs from OmicStudio are so well designed that they can still meet the standard of aesthetic even after some customized adjustment. In addition, OmicStudio Cloud Platform supports graphic parameter adjustment, such as fonts, color schemes, themes, and axis adjustment. It's convenient for users to customize the graph according to their demand. Ordinary bioinformatics cloud tools save the analysis parameter in background, which is invisible to users. When writing a research paper, it is difficult for users to get the value of parameter from the bioinformatics software. OmicStudio, on the contrary, provides users parameters along with analysis results. Whether how much time goes by, whether how many versions have been updated, users can always find the parameters in their analysis. Downloadable records of analysis include: reference, analysis method, version of software, analysis parameter, basic information of analysis (when and which tools are used in the platform), citation. This series of information establish a foundation for users' writing. Cloud Classroom module includes 9 themes and nearly 100 courses. It's convenient to focus on any course based on demand. The themes include bioinformatics, omics science knowledge and literature interpretation, aiming to meet all the users' demand from understanding of biology to the learning of operation. User's Paper Collection module collects hundreds of research articles published by OmicStudio users, providing name of journal, year of publication, impact factor, source of sample, method used and other information. Users can search, preview, and download pdf version of paper. It's convenient for users to acquire knowledge in interested field, and reproduce the analysis result by OmicStudio. OmicStudio focuses on making scientific research more easily. Since October 2019, the services content of the platform has been upgraded and iterated over 1000 times. There are already more than 30,000 scientific research users. In the past 3 years, 669 research articles cited OmicStudio (Google Scholar, by January 1, 2022). Fengye Lyu designed the platform and idea. Fengye Lyu and Feiran Han wrote the manuscript. Feiran Han was responsible for editing and revising the manuscript. All authors contributed to the development of OmicStudio Platform. The authors acknowledge Wenjing Wang for their advice on this manuscript. Qiulei Lang is the Shareholders of LC-Bio Technology Co. The other authors are employees of LC-Bio. There is no data available.

Abstract: Industry 5.0 is projected to be an exemplary improvement in digital transformation allowing for mass customization and production efficiencies using emerging technologies such as universal machines, autonomous and self-driving robots, self-healing networks, cloud data analytics, etc., to supersede the limitations of Industry 4.0. To successfully pave the way for acceptance of these technologies, we must be bound and adhere to ethical and regulatory standards. Presently, with ethical standards still under development, and each region following a different set of standards and policies, the complexity of being compliant increases. Having vague and inconsistent ethical guidelines leaves potential gray areas leading to privacy, ethical, and data breaches that must be resolved. This paper examines the ethical dimensions and dilemmas associated with emerging technologies and provides potential methods to mitigate their legal/regulatory issues.

Abstract: These days, the usage of machine-learning-enabled dynamic Internet of Medical Things (IoMT) systems with multiple technologies for digital healthcare applications has been growing progressively in practice. Machine learning plays a vital role in the IoMT system to balance the load between delay and energy. However, the traditional learning models fraud on the data in the distributed IoMT system for healthcare applications are still a critical research problem in practice. The study devises a federated learning-based blockchain-enabled task scheduling (FL-BETS) framework with different dynamic heuristics. The study considers the different healthcare applications that have both hard constraint (e.g., deadline) and resource energy consumption (e.g., soft constraint) during execution on the distributed fog and cloud nodes. The goal of FL-BETS is to identify and ensure the privacy preservation and fraud of data at various levels, such as local fog nodes and remote clouds, with minimum energy consumption and delay, and to satisfy the deadlines of healthcare workloads. The study introduces the mathematical model. In the performance evaluation, FL-BETS outperforms all existing machine learning and blockchain mechanisms in fraud analysis, data validation, energy and delay constraints for healthcare applications.

Abstract: Vehicular edge computing (VEC) provides an effective task offloading paradigm by pushing cloud resources to the vehicular network edges, e.g., road side units (RSUs). However, overloaded RSUs are likely to occur especially in urban aggregation areas, possibly leading to greatly compromised offloading performance. Inspired by this, this paper explores this situation by introducing an unmanned aerial vehicle (UAV) to address the VEC overload problem. Specifically, we formulate a novel online UAV-assisted vehicular task offloading problem to minimize vehicular task delay under the long-term UAV energy constraint. To solve the formulated problem, we first decouple the long-term energy constraint based on the Lyapunov optimization technique. In this way, the problem can be solved in a real-time manner without requiring future information. Then, we construct a Markov chain based on Markov approximation optimization to find out the close-to-optimal UAV-assisted offloading strategies. Furthermore, we derive a mathematical analysis to rigorously demonstrate the offloading performance of the proposed algorithm. Additionally, the simulation results show that the proposed method outperforms the baselines by significantly reducing the vehicular task delay constrained by the long-term UAV energy budget under various system parameters, such as the energy budget and computation workloads.

Abstract: Edge computing is an emerging paradigm that offloads the computations and analytics workloads onto the internet of things (IoT) edge devices to accelerate the computation efficiency, reduce the channel occupation of signal transmission, and reduce the storage and computation workloads on the cloud servers. These distinct merits make it a promising tool for IoT-based machine signal processing and fault diagnosis. This article reviews the edge computing methods in signal processing-based machine fault diagnosis from the aspects of concepts, state-of-the-art methods, case studies, and research prospects. In particular, the light-weight designed algorithms and application-specific hardware platforms of edge computing in the typical fault diagnosis procedures including signal acquisition, signal preprocessing, feature extraction, and pattern recognition are reviewed and discussed in detail. The review provides an insight into the edge computing framework, methods, and applications, so as to meet the requirements of IoT-based machine real-time signal processing, low-latency fault diagnosis, and high-efficient predictive maintenances.

Abstract: In the past several years, the world has witnessed an acute surge in the production and usage of smart devices which are referred to as the Internet of Things (IoT). These devices interact with each other as well as with their surrounding environments to sense, gather and process data of various kinds. Such devices are now part of our everyday’s life and are being actively used in several verticals, such as transportation, healthcare, and smart homes. IoT devices, which usually are resource-constrained, often need to communicate with other devices, such as fog nodes and/or cloud computing servers to accomplish certain tasks that demand large resource requirements. These communications entail unprecedented security vulnerabilities, where malicious parties find in this heterogeneous and multiparty architecture a compelling platform to launch their attacks. In this work, we conduct an in-depth survey on the existing intrusion detection solutions proposed for the IoT ecosystem which includes the IoT devices as well as the communications between the IoT, fog computing, and cloud computing layers. Although some survey articles already exist, the originality of this work stems from the three following points: 1) discuss the security issues of the IoT ecosystem not only from the perspective of IoT devices but also taking into account the communications between the IoT, fog, and cloud computing layers; 2) propose a novel two-level classification scheme that first categorizes the literature based on the approach used to detect attacks and then classify each approach into a set of subtechniques; and 3) propose a comprehensive cybersecurity framework that combines the concepts of explainable artificial intelligence (XAI), federated learning, game theory, and social psychology to offer future IoT systems a strong protection against cyberattacks.

Abstract: Nowadays, the concept of Internet of Everything (IoE) is becoming a hotly discussed topic, which is playing an increasingly indispensable role in modern intelligent applications. These applications are known for their real-time requirements under limited network and computing resources, thus it becomes a highly demanding task to transform and compute tremendous amount of raw data in a cloud center. The edge–cloud computing infrastructure allows a large amount of data to be processed on nearby edge nodes and then only the extracted and encrypted key features are transmitted to the data center. This offers the potential to achieve an end–edge–cloud-based big data intelligence for IoE in a typical two-stage data processing scheme, while satisfying a data security constraint. In this study, a deep-reinforcement-learning-enhanced two-stage scheduling (DRL-TSS) model is proposed to address the NP-hard problem in terms of operation complexity in end–edge–cloud Internet of Things systems, which is able to allocate computing resources within an edge-enabled infrastructure to ensure computing task to be completed with minimum cost. A presorting scheme based on Johnson’s rule is developed and applied to preprocess the two-stage tasks on multiple executors, and a DRL mechanism is developed to minimize the overall makespan based on a newly designed instant reward that takes into account the maximal utilization of each executor in edge-enabled two-stage scheduling. The performance of our method is evaluated and compared with three existing scheduling techniques, and experimental results demonstrate the ability of our proposed algorithm in achieving better learning efficiency and scheduling performance with a 1.1-approximation to the targeted optimal IoE applications.

Abstract: Serverless computing is growing in popularity by virtue of its lightweight and simplicity of management. It achieves these merits by reducing the granularity of the computing unit to the function level. Specifically, serverless allows users to focus squarely on the function itself while leaving other cumbersome management and scheduling issues to the platform provider, who is responsible for striking a balance between high-performance scheduling and low resource cost. In this article, we conduct a comprehensive survey of serverless computing with a particular focus on its infrastructure characteristics. Whereby some existing challenges are identified, and the associated cutting-edge solutions are analyzed. With these results, we further investigate some typical open-source frameworks and study how they address the identified challenges. Given the great advantages of serverless computing, it is expected that its deployment would dominate future cloud platforms. As such, we also envision some promising research opportunities that need to be further explored in the future. We hope that our work in this article can inspire those researchers and practitioners who are engaged in related fields to appreciate serverless computing, thereby setting foot in this promising area and making great contributions to its development.

Abstract: Fog computing is a paradigm that utilizes the advantages of both the cloud and the edge devices providing quality services, reducing latency, providing mobility support, multi-tenancy, and many other functions that support modern computing systems. It is sometimes referred to as fog networking or fogging. This paper reviews and discusses cloud computing, briefly highlighting the implemented paradigms before fog computing. These paradigms include cloud, mobile cloud computing, and mobile edge computing. All the paradigms targeted improving the quality of service between the end devices and the cloud itself. A fog computing Taxonomy is presented based on contemporary fog computing research about security challenges, services issues, operational issues, and data management. The standard for elucidating the taxonomy is built on the functional and vital issues in fog computing. Challenges and potential applications are identified. The review shows that security, privacy, application, and communication challenges are prominent among scholars contributions. Potential applications in fog computing are also identified, including healthcare applications, innovative city applications, and farm applications.

Abstract: Successful integration of deep neural networks (DNNs) or deep learning (DL) has resulted in breakthroughs in many areas. However, deploying these highly accurate models for data-driven, learned, automatic, and practical machine learning (ML) solutions to end-user applications remains challenging. DL algorithms are often computationally expensive, power-hungry, and require large memory to process complex and iterative operations of millions of parameters. Hence, training and inference of DL models are typically performed on high-performance computing (HPC) clusters in the cloud. Data transmission to the cloud results in high latency, round-trip delay, security and privacy concerns, and the inability of real-time decisions. Thus, processing on edge devices can significantly reduce cloud transmission cost. Edge devices are end devices closest to the user, such as mobile phones, cyber–physical systems (CPSs), wearables, the Internet of Things (IoT), embedded and autonomous systems, and intelligent sensors. These devices have limited memory, computing resources, and power-handling capability. Therefore, optimization techniques at both the hardware and software levels have been developed to handle the DL deployment efficiently on the edge. Understanding the existing research, challenges, and opportunities is fundamental to leveraging the next generation of edge devices with artificial intelligence (AI) capability. Mainly, four research directions have been pursued for efficient DL inference on edge devices: 1) novel DL architecture and algorithm design; 2) optimization of existing DL methods; 3) development of algorithm–hardware codesign; and 4) efficient accelerator design for DL deployment. This article focuses on surveying each of the four research directions, providing a comprehensive review of the state-of-the-art tools and techniques for efficient edge inference.

Abstract: In the past few years, social media has changed the ways that health seekers seek health information. However, despite the tremendous growth of social media applications in the health-care industry, trust is still among the biggest challenges for social media health services in gaining greater acceptance. Drawn from previous literature on self-determination theory, social support, and trust, this study investigates people’s intentions to seek health-information on social media. The authors carefully selected a sample from Italy with subjects who already had experience in seeking health information on social media. The empirical results show that informational support, emotional support, and the satisfaction of people’s autonomy and relatedness needs play an important role through trust in influencing people’s health-information-seeking intentions on social media. This study is among the first to adopt the theories of self-determination, social support, and trust to investigate people’s intentions to seek health information on social media. KEywORDS Emotional Support, Health-Information-Seeking, Informational Support, Online Health Information, Social Media, Trust

Abstract: Industrial cloud computing and Internet of Things have transformed the healthcare industry with the rapid growth of distributed healthcare data. Security and privacy of healthcare data are crucial challenges in the healthcare industry. This article proposes a novel technique using deep learning and blockchain techniques for electronic health record privacy-preservation. The processed dataset classified normal and abnormal users using the convolutional neural network approach. Then, by using blockchain integrated with a cryptography-based federated learning module, the abnormal users have been processed and removed from the database along with the accessibility for the health records. The simulation has been done in the Python tool and experimental results show that the model’s classification results and performance are better than other existing techniques.

Abstract: Given its advantages in low latency, fast response, context-aware services, mobility, and privacy preservation, edge computing has emerged as the key support for intelligent applications and 5G/6G Internet of things (IoT) networks. This technology extends the cloud by providing intermediate services at the edge of the network and improving the quality of service for latency-sensitive applications. Many AI-based solutions with machine learning, deep learning, and swarm intelligence have exhibited the high potential to perform intelligent cognitive sensing, intelligent network management, big data analytics, and security enhancement for edge-based smart applications. Despite its many benefits, there are still concerns about the required capabilities of intelligent edge computing to deal with the computational complexity of machine learning techniques for big IoT data analytics. Resource constraints of edge computing, distributed computing, efficient orchestration, and synchronization of resources are all factors that require attention for quality of service improvement and cost-effective development of edge-based smart applications. In this context, this paper aims to explore the confluence of AI and edge in many application domains in order to leverage the potential of the existing research around these factors and identify new perspectives. The confluence of edge computing and AI improves the quality of user experience in emergency situations, such as in the Internet of vehicles, where critical inaccuracies or delays can lead to damage and accidents. These are the same factors that most studies have used to evaluate the success of an edge-based application. In this review, we first provide an in-depth analysis of the state of the art of AI in edge-based applications with a focus on eight application areas: smart agriculture, smart environment, smart grid, smart healthcare, smart industry, smart education, smart transportation, and security and privacy. Then, we present a qualitative comparison that emphasizes the main objective of the confluence, the roles and the use of artificial intelligence at the network edge, and the key enabling technologies for edge analytics. Then, open challenges, future research directions, and perspectives are identified and discussed. Finally, some conclusions are drawn.

Abstract: A disassembly line is an industrialized and automated production line which should be scheduled with high production efficiency. Although many disassembly line balancing optimization studies are contributed recently, they increase or reduce the number of workstations to balance the disassembly line. From real-world managerial settings, an increase or decrease workstations, is too expensive and not realistic. The bucket brigades’ disassembly line is self-balancing and self-organizing, which is not constrained by the workstation beat time and only needs to distribute workers on the line according to certain rules to achieve line balancing after a period of time. In this article, a bucket brigades disassembly line balancing optimization method considering uncertainty is proposed, in which a cloud model is used to represent the uncertain disassembly time. The proposed model handles multiple objectives including smoothness, disassembly cost and disassembly energy consumption to be minimized. To solve this complex problem, this article innovates a new heuristic method based on the social engineering optimizer as an enhanced local search metaheuristic. Finally, a ball collector is used to verify the effectiveness of the proposed method and extensive analysis is done to compare the performance of proposed model with other recent algorithms.

Abstract: With the continuous expansion of the power Internet of Things and the number of Smart Devices (SDs), the data generated by SDs has exponentially increased. The traditional cloud-based smart grid cannot meet the low latency and high reliability requirements of emerging applications. By moving computing, data, and services from the centralized cloud to Edge Servers (ESs), edge computing exhibits excellent performance in communication delay and traffic reduction. Simultaneously, service caching also shows attractive advantages in handling the surge in data traffic. This paper considers the joint optimization of computing offloading and service caching in edge computing-based smart grid, and formulates the problem as a Mixed-Integer Non-Linear Program, aiming to minimize the task cost of the system. The original problem is decomposed into an equivalent master problem and sub-problem, and a Collaborative Computing Offloading and Resource Allocation Method (CCORAM) is proposed to solve the problem, which includes two low-complexity algorithms. Specifically, a gradient descent allocation algorithm is first proposed to determine the computing resource allocation strategy, and then a game theory-based algorithm is proposed to determine the computing strategy. Simulation results show that CCORAM with low-complexity is very close to the optimal method, and performs much better than other benchmark methods.

Abstract: To meet the stringent service requirements of 6G applications such as immersive cloud eXtended Reality (XR), holographic communication, and digital twin, there is no doubt that an increasing number of servers will be deployed on the network edge. Then, the techniques, edge computing, edge caching, and edge intelligence will be more widely utilized for intelligent local data storage and processing generated by 6G applications, while innovative access network architecture based on the cloud-edge servers, such as the Open-Radio Access Network (O-RAN) will be adopted to improve the flexibility and openness for new service deployment and frequent network changes. On the other hand, new attack surfaces and vectors targeting local infrastructure and users will emerge along with the deployment of novel network architecture and techniques. Massive researchers have studied the potential security and privacy threats on the 6G network edge as well as the countermeasures. The three techniques, edge computing, edge caching, and edge intelligence have become a double-edged sword that can not only be synchronously utilized to develop defense countermeasures, but also become the targets of many new security and privacy threats. In this article, we provide a comprehensive survey of articles on the three techniques-related security threats and countermeasures on the 6G network edge. We explain how security and privacy can be destroyed by attacking one of the three technologies and how the three services support each other to realize efficient and achievable security protection. Moreover, the researches on the benefits and limitations of Federated Learning (FL) and blockchain for decentralized edge network systems in terms of security and privacy are also investigated. Additionally, we also analyze the existing challenges and future directions towards 6G.

Abstract: Abstract The Industrial Internet of Things (IIoT) promises to deliver innovative business models across multiple domains by providing ubiquitous connectivity, intelligent data, predictive analytics, and decision-making systems for improved market performance. However, traditional IIoT architectures are highly susceptible to many security vulnerabilities and network intrusions, which bring challenges such as lack of privacy, integrity, trust, and centralization. This research aims to implement an Artificial Intelligence-based Lightweight Blockchain Security Model (AILBSM) to ensure privacy and security of IIoT systems. This novel model is meant to address issues that can occur with security and privacy when dealing with Cloud-based IIoT systems that handle data in the Cloud or on the Edge of Networks (on-device). The novel contribution of this paper is that it combines the advantages of both lightweight blockchain and Convivial Optimized Sprinter Neural Network (COSNN) based AI mechanisms with simplified and improved security operations. Here, the significant impact of attacks is reduced by transforming features into encoded data using an Authentic Intrinsic Analysis (AIA) model. Extensive experiments are conducted to validate this system using various attack datasets. In addition, the results of privacy protection and AI mechanisms are evaluated separately and compared using various indicators. By using the proposed AILBSM framework, the execution time is minimized to 0.6 seconds, the overall classification accuracy is improved to 99.8%, and detection performance is increased to 99.7%. Due to the inclusion of auto-encoder based transformation and blockchain authentication, the anomaly detection performance of the proposed model is highly improved, when compared to other techniques.

Abstract: With today’s technological boom, the demand for cloud computing services is increasing day by day. Individuals, companies, and multinational businesses are shifting from self-owned web services to cloud services. Among cloud services providers, the most prominent are Amazon Web Services (AWS), Google Cloud Platform GCP, IBM, and Oracle Cloud.

Abstract: In this chapter, the various water monitoring systems—internet of-things, wireless network systems, cloud computing, optimization systems, and reporting systems—are illustrated. The development of artificial intelligence in water management has the potential to change and manage water resources. The use of AI and cutting-edge technologies such as data analytics, regression models, and algorithms simplifies the water management process. AI-based systems will be sustainable, cost-effective, and capable of predicting potential damage in order to optimize water management solutions with minimal waste. Machine learning algorithms support the water management process and improve the accuracy of sensor-based systems in agriculture.

Abstract: Edge intelligent computing is widely used in the fields, such as the Internet of Medical Things (IoMT), which has advantages, including high data processing efficiency, strong real-time performance and low network delay. However, there are many problems including privacy disclosure, limited calculation force, as well as scheduling and coordination issues. Federated learning can greatly improves training efficiency. However, due to the sensitive nature of the healthcare data, the aforementioned approach of transferring the patient's data to the servers may create serious security and privacy issues. Therefore, this article proposes a Privacy Protection Scheme for Federated Learning under Edge Computing (PPFLEC). First of all, we propose a lightweight privacy protection protocol based on a shared secret and weight mask, which is based on a random mask scheme of secret sharing. It is more accurate and efficient than,homomorphic encryption. It can not only protect gradient privacy without losing model accuracy, but also resist equipment dropping and collusion attacks between devices. Second, we design an algorithm based on a digital signature and hash function, which achieves the integrity and consistency of the message, as well as resisting replay attacks. Finally, we propose a periodic average training strategy, compared with differential privacy to prove that our scheme is 40 % faster in efficiency than in deferential privacy. Meanwhile, compared with federated learning, we can achieve the same efficiency under the condition of ensuring safety. Therefore, our scheme can work well in unstable edge computing environments such as smart healthcare.

Abstract: In the computer world, data science is the force behind the recent dramatic changes in cybersecurity's operations and technologies. The secret to making a security system automated and intelligent is to extract patterns or insights related to security incidents from cybersecurity data and construct appropriate data-driven models. Data science, also known as diverse scientific approaches, machine learning techniques, processes, and systems, is the study of actual occurrences via the use of data. Due to its distinctive qualities, such as flexibility, scalability, and the capability to quickly adapt to new and unknowable obstacles, machine learning techniques have been used in many scientific fields. Due to notable advancements in social networks, cloud and web technologies, online banking, mobile environments, smart grids, etc., cyber security is a rapidly expanding sector that requires a lot of attention. Such a broad range of computer security issues have been effectively addressed by various machine learning techniques. This article covers several machine-learning applications in cyber security. Phishing detection, network intrusion detection, keystroke dynamics authentication, cryptography, human interaction proofs, spam detection in social networks, smart meter energy consumption profiling, and security concerns with machine learning techniques themselves are all covered in this study. The methodology involves collecting a large dataset of phishing and legitimate instances, extracting relevant features such as email headers, content, and URLs, and training a machine-learning model using supervised learning algorithms. Machine learning models can effectively identify phishing emails and websites with high accuracy and low false positive rates. To enhance phishing detection, it is recommended to continuously update the training dataset to include new phishing techniques and to employ ensemble methods that combine multiple machine learning models for better performance.