CrowdBox: Crowdsourced Network-in-Box Recruitment for Edge Computing-Enabled Industrial Internet of Things

The rapidly increasing number of smart devices deployed in the Industrial Internet of Things (IIoT) environment has been witnessed. To improve communication efficiency, edge computing-enabled Industrial Internet of Things (E-IIoT) has gained attention recently. Nevertheless, E-IIoT still cannot conquer the rapidly increasing communication demands when hundreds of millions of IIoT devices are connected at the same time. Considering the future 6G environment where smart network-in-box (NIB) nodes are everywhere (e.g., deployed in vehicles, buses, backpacks, etc.), we propose a crowdsourcing-based recruitment framework, leveraging the power of the crowd to provide extra communication resources and enhance the communication capabilities. We creatively treat NIB nodes as edge layer devices, and CrowdBox is devised using a Stackelberg game where the E-IIoT system is the leader, and the NIB nodes are the followers. CrowdBox can calculate the optimal reward to reach the unique Stackelberg equilibrium where the utility of E-IIoT can be maximized while none of the NIB nodes can improve its utility by deviating from its strategy. Finally, we evaluate the performance of CrowdBox with extensive simulations with various settings, and it shows that CrowdBox outperforms the compared algorithms in improving system utility and attracting more NIB nodes.

A QoS-aware Fuzzy-based System for Assessment of Edge Computing Resources in SDN-VANETs

Vehicular Ad hoc Networks (VANETs) face resource management challenges due to their dynamic network topology and massive amount of data generated by the ever-rising number of vehicles. In this paper, we implement a Fuzzy-based System for Assessment of Neighboring Vehicles Processing Capability (FS-ANVPC), in which we consider two models (FS-ANVPC1 and FS-ANVPC2) to assess the available edge computing resources in Software Defined-VANETs. The proposed system determines the processing capability of each neighboring vehicle, and based on the final value, it can be decided whether the edge layer can be used by the vehicles in need of additional resources. FS-ANVPC1 takes into consideration the available resources of the neighboring vehicles and the predicted contact duration between them and the vehicle in need, while FS-ANVPC2 includes in addition the quality of service of the communication link among vehicles. We evaluate the proposed system by computer simulations. From the evaluation results, we see that FS-ANVPC2 shows better results than FS-ANVPC1 although its complexity is higher.

Availability of an RFID Object-Identification System in IoT Environments

Through the latest technological and conceptual developments, the centralized cloud-computing approach has moved to structures such as edge, fog, and the Internet of Things (IoT), approaching end users. As mobile network operators (MNOs) implement the new 5G standards, enterprise computing function shifts to the edge. In parallel to interconnection topics, there is the issue of global impact over the environment. The idea is to develop IoT devices to eliminate the greenhouse effect of current applications. Radio-frequency identification (RFID) is the technology that has this potential, and it can be used in applications ranging from identifying a person to granting access in a building. Past studies have focused on how to improve RFID communication or to achieve maximal throughput. However, for many applications, system latency and availability are critical aspects. This paper examines, through stochastic Petri nets (SPNs), the availability, dependability, and latency of an object-identification system that uses RFID tags. Through the performed analysis, the optimal balance between latency and throughput was identified. Analyzing multiple communication scenarios revealed the availability of such a system when deployed at the edge layer.

Security and Privacy for Mobile IoT Applications Using Blockchain

Internet of Things (IoT) applications are becoming more integrated into our society and daily lives, although many of them can expose the user to threats against their privacy. Therefore, we find that it is crucial to address the privacy requirements of most of such applications and develop solutions that implement, as far as possible, privacy by design in order to mitigate relevant threats. While in the literature we may find innovative proposals to enhance the privacy of IoT applications, many of those only focus on the edge layer. On the other hand, privacy by design approaches are required throughout the whole system (e.g., at the cloud layer), in order to guarantee robust solutions to privacy in IoT. With this in mind, we propose an architecture that leverages the properties of blockchain, integrated with other technologies, to address security and privacy in the context of IoT applications. The main focus of our proposal is to enhance the privacy of the users and their data, using the anonymisation properties of blockchain to implement user-controlled privacy. We consider an IoT application with mobility for smart vehicles as our usage case, which allows us to implement and experimentally evaluate the proposed architecture and mechanisms as a proof of concept. In this application, data related to the user’s identity and location needs to be shared with security and privacy. Our proposal was implemented and experimentally validated in light of fundamental privacy and security requirements, as well as its performance. We found it to be a viable approach to security and privacy in IoT environments.

Energy Theft Detection in an Edge Data Center Using Deep Learning

With the development of smart grid information physical systems, some of the data processing functions gradually approach the edge layer of end-users. To better realize the energy theft detection function at the edge, we proposed an energy theft detection method based on the power consumption information acquisition system of power enterprises. The method involves the following steps. In the centralized data center, K-means is used to decompose a large amount of data into small data and then input and train neural network parameters to realize feature extraction. We design a neural network named DWMCNN, which can extract features from the day, week, and month and can extract more accurate features. In the edge data center, the random forest (RF) algorithm is used to classify the extracted features. The experimental results show that the clustering method accords with the idea of edge computing-distributed processing and improves the operation speed and that the feature extractor has good convergence performance. In addition, compared with the methods based on various classifiers, this method has higher accuracy and lower computational complexity, which is suitable for the deployment of edge data centers.

Data Collection and Analysis of Track and Field Athletes’ Behavior Based on Edge Computing and Reinforcement Learning

With the development of multimedia technology, the computer auxiliary system has become an effective means of daily training in track and field. This paper designs a data acquisition and analysis system for track and field athletes. The system uses sensor modules attached to the athlete’s body to collect movement data for analysis. The whole system is implemented by edge computing architecture. In order to reduce average response time, the DDPG algorithm is used to optimize the resource allocation of the edge layer. Experimental results show that the response time of the proposed algorithm can be controlled within 1 s. Meanwhile, the SVM algorithm on the edge server is arranged to classify the data, and the overall recognition accuracy is over 90%.

On-Line Interpretation and Real-Time Diagnosis of Rocket’s Single Equipment

The work state of a launch vehicle is generally interpreted automatically on software. However, the sheer number of target parameters makes it difficult to realize real-time interpretation, and abnormal interpretation result does not necessarily mean that the vehicle is in abnormal state. This paper introduces the edge computing to achieve on-line interpretation and real-time diagnosis of a single launch vehicle. Firstly, the parameters to be interpreted were subjected to thresholding, leaving only those with high interpretation value. Next, the interpretation server layer of the real-time diagnosis model was built based on the attribute and value reduction algorithm of variable precision rough set (VPRS). Moreover, the higher-grade criteria were written in criterion modeling language (CML) and used to interpret the various higher-grade interpretation data pushed by the edge layer in real time. On this basis, the outputs of the edge layer and interpretation server layer were integrated to achieve the real-time diagnosis of single vehicle faults. Finally, the proposed model was proved feasible through the application in a launch vehicle.

Optimization of the Enterprise Human Resource Management Information System Based on the Internet of Things

In this paper, the optimization of the enterprise HR information system is studied based on IoT first-off technology, the system demand phase is analysed, and the edge control system is designed and built. The hardware and software system and edge node management platform are implemented first, and then the communication scenarios between the edge layer of the system and the sensing layer, the edge layer, and the cloud layer are analysed, and the business type-driven link selection algorithm and the northbound multilink switching algorithm are designed and implemented, respectively, to guarantee the communication reliability between different layers of the system. Based on the implementation of the above functions, the edge control system can meet the intelligence, expandability, and security requirements of IoT applications. An in-depth investigation and research are launched mainly on the enterprise demand to determine the functional requirements and performance requirements of the enterprise and to achieve the basic logical structure; in the system design phase, the system architecture and other aspects of the design are realized. According to the conditions of the system function structure, a number of system module functions are designed in detail. The system is composed of the following modules, namely, personnel change management, organization management, and salary and benefits management. The system consists of the following modules, namely, personnel change management, organization management, compensation and benefits management, and personnel information management. The system modules run through the process of human resource management; in the system implementation stage, the system coding and page operation are realized based on the development tools and software development techniques. The system finally achieves the system design objectives and is put on a trial operation to meet its actual business requirements.

A Resilient and Hierarchical IoT-based Solution for Stress Monitoring in Everyday Settings

<div><div><div><p>Long-term stress is a global health concern because it impacts our physical and mental health. The emergence of Internet of Things (IoT) and Artificial Intelligence (AI) makes stress monitoring and treatment more accessible compared to today’s physician-centered healthcare system. However, existing solutions either fail to incorporate IoT technology or are not cost-effective. We propose a resilient, hierarchical IoT-based solution for stress monitoring to tackle the above problems. Multimodal data was collected from wearable sensors and underwent preprocessing, feature extraction, and multiple imputation. We applied three feature-selection methods prior to lightweight SVM classification at the edge layer, and utilized a CNN and a matching network model in the cloud layer. We obtained an accuracy of 86.7347% and an F1 score of 0.8725 at the edge using only 10 features selected based on the Fisher score. An accuracy of 98.9247% and an F1 score of 0.9876 was achieved by a matching network model based on electrocardiogram (ECG) data. The trade-off between the communication cost from the edge to the cloud and the overall accuracy was evaluated. Our hierarchical-IoT solution for stress-level evaluation provides insights into the potentiality of IoT and AI technology-based eHealth solutions.</p></div></div></div>

A Resilient and Hierarchical IoT-based Solution for Stress Monitoring in Everyday Settings

<div><div><div><p>Long-term stress is a global health concern because it impacts our physical and mental health. The emergence of Internet of Things (IoT) and Artificial Intelligence (AI) makes stress monitoring and treatment more accessible compared to today’s physician-centered healthcare system. However, existing solutions either fail to incorporate IoT technology or are not cost-effective. We propose a resilient, hierarchical IoT-based solution for stress monitoring to tackle the above problems. Multimodal data was collected from wearable sensors and underwent preprocessing, feature extraction, and multiple imputation. We applied three feature-selection methods prior to lightweight SVM classification at the edge layer, and utilized a CNN and a matching network model in the cloud layer. We obtained an accuracy of 86.7347% and an F1 score of 0.8725 at the edge using only 10 features selected based on the Fisher score. An accuracy of 98.9247% and an F1 score of 0.9876 was achieved by a matching network model based on electrocardiogram (ECG) data. The trade-off between the communication cost from the edge to the cloud and the overall accuracy was evaluated. Our hierarchical-IoT solution for stress-level evaluation provides insights into the potentiality of IoT and AI technology-based eHealth solutions.</p></div></div></div>