No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
A Federated Learning-Based Blockchain-Assisted Anomaly Detection Scheme to Prevent Road Accidents in Internet of Vehicles
Abstract
In the modern era, the internet of vehicles (IoV) is being utilized in commercial applications and extensively explored in research. However, internal fault in IoV can cause accidents on the road. Moreover, privacy concerns can hamper the internal data sharing to build a model to detect the anomaly. Federated learning (FL) and blockchain are emerging technologies that can assist in mitigating these challenges. FL-based anomaly detection is introduced to prevent road accidents with the help of blockchain. An environment is built to conduct experiments to prove the feasibility of the proposed scheme. The performance analysis demonstrates that our presented scheme outperforms the traditional scheme while having privacy concerns.
ResearchGate has not been able to resolve any citations for this publication.
In this article, we present a comprehensive study with an experimental analysis of federated deep learning approaches for cyber security in the Internet of Things (IoT) applications. Specifically, we first provide a review of the federated learning-based security and privacy systems for several types of IoT applications, including, Industrial IoT, Edge Computing, Internet of Drones, Internet of Healthcare Things, Internet of Vehicles, etc. Second, the use of federated learning with blockchain and malware/intrusion detection systems for IoT applications is discussed. Then, we review the vulnerabilities in federated learning-based security and privacy systems. Finally, we provide an experimental analysis of federated deep learning with three deep learning approaches, namely, Recurrent Neural Network (RNN), Convolutional Neural Network (CNN), and Deep Neural Network (DNN). For each deep learning model, we study the performance of centralized and federated learning under three new real IoT traffic datasets, namely, the Bot-IoT dataset, the MQTTset dataset, and the TON_IoT dataset. The goal of this article is to provide important information on federated deep learning approaches with emerging technologies for cyber security. In addition, it demonstrates that federated deep learning approaches outperform the classic/centralized versions of machine learning (non-federated learning) in assuring the privacy of IoT device data and provide the higher accuracy in detecting attacks.
The gradual increase in the density of highway vehicles and traffic flow makes the abnormal driving state of vehicles an indispensable tool for assisting traffic dispatch. Intelligent transportation systems can detect and track vehicles in real time, acquire characteristics such as vehicle traffic, vehicle speed, vehicle flow density, and vehicle trajectory, and further perform advanced tasks such as vehicle trajectory. The detection of abnormal vehicle trajectory is an important content of vehicle trajectory understanding. And the development of the Internet of Things (IoT) and 5G technology has led to a continuous increase in the rate of data information circulation. The “Internet of Vehicles” generated based on the practice of 5G communication technology constitutes a vehicle abnormal trajectory detection system, which has very high feasibility and safety and stability. Therefore, this research is aimed at the needs of preventing major accidents and forensic analysis during highway vehicles. Based on the integration of the Internet of Things 5G communication technology, a trajectorial anomaly detection of highway vehicle trajectory based on the integration of the Internet of Things 5G is proposed. By accurately sensing unsafe events at the perception layer, network layer, and application layer, the vehicle driving trajectory state is divided into several simple semantic representations. The semantic representation is analyzed, and then the moving target detection and moving target tracking algorithms needed to extract the vehicle trajectory are introduced. Through video detection and tracking of moving vehicle targets, the driving trajectory of the vehicle is obtained, and the movement characteristics of the vehicle in each frame of image are extracted. According to the relationship between the trajectory of the vehicle and the lane line, the vehicle trajectory analysis is realized, and then it is judged whether the vehicle has abnormal trajectory. Compared with the traditional method of manually detecting the driving condition of the vehicle, the abnormal trajectory detection of the vehicle based on the integration of the Internet of Things and 5G can quickly detect the abnormal trajectory of the vehicle in the traffic monitoring video.
1. Introduction
With the increase of road vehicles, traffic has become more and more congested, and the rate of traffic accidents has become higher and higher, especially on highways. Once the phenomenon of abnormal driving such as illegal stop and retrograde occurs, it is often accompanied by major traffic accidents, causing serious consequences. The traditional judgment of abnormal vehicle driving requires manual viewing of surveillance videos to monitor and manage traffic conditions [1]. However, the efficiency of this method is very low, the work intensity of the staff is also very high, and there are problems that are missed and cannot be found in time, which cannot meet the needs of current operation management. At the same time, current vehicle abnormal trajectory detection still faces problems such as lack of data, inaccuracy of abnormal definition, occlusion, and poor real-time performance in practical applications.
The development of the Internet of Things (IoT) and the Internet has led to a continuous increase in the rate of data information circulation. As the fifth-generation cellular mobile communication technology, 5G has large-capacity wireless network technology and high-speed wireless transmission technology that surpass 4G. This can be integrated with the large-scale Internet of Things that blows out network requests and network traffic to realize the real interconnection of everything. 5G communication technology can take advantage of its own advantages such as low cost, large capacity, and low energy consumption to flexibly deploy and operate logistics networks, improve the utilization of network space in the process of highway vehicle management, control vehicle driving, and solve the problems faced by vehicles during driving [2, 3]. Therefore, an automatic detection system for abnormal events of highway vehicles based on the integration of the Internet of Things and 5G technology came into being. Through real-time processing and analysis of traffic monitoring video data, it can automatically detect and identify abnormal trajectory of vehicles on the road, such as speeding, sudden braking, illegal steering, unauthorized lane changes, running red lights, and vehicles’ going backwards. The abnormal driving of the vehicle is likely to cause traffic accidents. In the early stage of abnormal vehicle driving, rapid detection and timely warning and trajectory restraint can significantly reduce the incidence of traffic accidents [4]. However, the monitoring of the remote abnormal driving trajectory of existing vehicles mainly returns data through the Internet of Things card, which is limited by the transmission speed and can only transmit small-scale data. Under the existing network transmission conditions, it is difficult to support a large number of vehicles to send back large-scale data (such as high-definition video) concurrently in real time [4]. How to achieve automatic detection of traffic incidents efficiently, accurately, and quickly is still a major problem facing the current highway traffic field.
Therefore, this research was based on 5G communication technology and the Internet of Things fusion system technology, taking the driving video of highway vehicles as the research object. Starting research from several key technologies such as moving target detection, tracking, and abnormal trajectory description, an automatic detection algorithm was designed for abnormal driving on expressways. Through the Internet of Things converged 5G communication technology, problems such as the serious lack of transportation safety and emergency response mechanisms in the information age were solved. The application of the system uses networked and informational means to carry out automated and intelligent safety monitoring and strategy formulation, which is expected to fundamentally reduce the safety risks of the Internet of Vehicles information system, reduce the occurrence of traffic safety accidents, and reduce casualties and economic losses.
2. The Application of IoT and 5G Technology in the Driving Trajectory of Highway Vehicles
Detecting the driving of highway vehicles has been relatively mature for the application of the Internet of Things technology. However, with the abnormal expansion of the trajectory of highway vehicles, the existing communication technology has limitations in terms of safety, real-time performance, and transmission rate. As the latest level of current communication technology capabilities, 5G’s interconnection of everything has greatly promoted the development of the Internet of Things [5].
2.1. The Role of IoT and 5G Technology on Highway Traffic
In the context of the Internet of Things, the practical advantages of 5G communication technology are mainly reflected in the fact that this technology can increase data traffic, expand equipment, and make communication more reliable. 5G technology allows users to directly handle some network services on the network platform, saving users time and ensuring the reliability of communication services. Therefore, in the context of the Internet of Things, 5G communication technology can realize “things and things” communication services. And according to the scenarios required by the Internet of Things, the communication protocol is customized to enable the Internet of Things to have the function of the “Internet of Things.” The integration of the Internet of Things and 5G communication technology realizes the communication interconnection between vehicles and vehicles, vehicles and people, vehicles and road infrastructure, and vehicles and network service platforms (as shown in Figure 1) [6]. “Vehicle to vehicle” can monitor the information between vehicles in the system in real time and realize the functions of vehicle-assisted driving, emergency collision warning, vehicle lane change and steering assist. “Vehicle and person” establishes the interconnection of information between vehicles and pedestrians, which can avoid collisions between vehicles and pedestrians and ensure the safety of pedestrians. “Vehicle and network” realizes the network interconnection between the vehicle and the network platform in the vehicle network system, and the network platform can provide navigation information and road traffic information for the vehicle. “Vehicles and road” provide basic road information for vehicles, such as road traffic conditions and speed limit information, so that violations caused by speeding vehicles can be effectively avoided.
Contagious disease pandemics present a significant threat worldwide in terms of both human health and economic damage. New diseases emerge annually and place enormous burdens on many countries. Additionally, using humans to handle pandemic situations increases the chances of disease spreading. Therefore, various technologies that do not directly involve humans should be employed to handle pandemic situations. The Internet of Drones (IoDT), artificial intelligence (AI), and blockchain are emerging technologies that have revolutionized the modern world. This paper presents a blockchain-based AIempowered pandemic situation supervision scheme in which a swarm of drones embedded with AI is engaged to autonomously monitor pandemic outbreaks, thereby keeping human involvement as low as possible. A use case based on a recent pandemic (i.e., COVID-19) is discussed. Two types of drone swarms are used to handle multiple tasks (e.g., checking face masks and imposing lockdowns). A lightweight blockchain is considered to handle situations in remote areas with poor network connectivity. Additionally, a two-phase lightweight security mechanism is adopted to validate the entities in the proposed scheme. A proof of concept is established using an experimental environment setup and dataset training. An analysis of the experimental results demonstrates the feasibility of the proposed scheme.
The communication and networking field is hungry for machine learning decision-making solutions to replace the traditional model-driven approaches that proved to be not rich enough for seizing the ever-growing complexity and heterogeneity of the modern systems in the field. Traditional machine learning solutions assume the existence of (cloud-based) central entities that are in charge of processing the data. Nonetheless, the difficulty of accessing private data, together with the high cost of transmitting raw data to the central entity gave rise to a decentralized machine learning approach called
Federated Learning
. The main idea of federated learning is to perform an on-device collaborative training of a single machine learning model without having to share the raw training data with any third-party entity. Although few survey articles on federated learning already exist in the literature, the motivation of this survey stems from three essential observations. The first one is the lack of a fine-grained multi-level classification of the federated learning literature, where the existing surveys base their classification on only one criterion or aspect. The second observation is that the existing surveys focus only on some common challenges, but disregard other essential aspects such as reliable client selection, resource management and training service pricing. The third observation is the lack of explicit and straightforward directives for researchers to help them design future federated learning solutions that overcome the state-of-the-art research gaps. To address these points, we first provide a comprehensive tutorial on federated learning and its associated concepts, technologies and learning approaches. We then survey and highlight the applications and future directions of federated learning in the domain of communication and networking. Thereafter, we design a three-level classification scheme that first categorizes the federated learning literature based on the high-level challenge that they tackle. Then, we classify each high-level challenge into a set of specific low-level challenges to foster a better understanding of the topic. Finally, we provide, within each low-level challenge, a fine-grained classification based on the technique used to address this particular challenge. For each category of high-level challenges, we provide a set of desirable criteria and future research directions that are aimed to help the research community design innovative and efficient future solutions. To the best of our knowledge, our survey is the most comprehensive in terms of challenges and techniques it covers and the most fine-grained in terms of the multi-level classification scheme it presents.
With the widely used Internet of Things, 5G, and smart city technologies, we are able to acquire a variety of vehicle trajectory data. These trajectory data are of great significance which can be used to extract relevant information in order to, for instance, calculate the optimal path from one position to another, detect abnormal behavior, monitor the traffic flow in a city, and predict the next position of an object. One of the key technology is to cluster vehicle trajectory. However, existing methods mainly rely on manually designed metrics which may lead to biased results. Meanwhile, the large scale of vehicle trajectory data has become a challenge because calculating these manually designed metrics will cost more time and space. To address these challenges, we propose to employ network representation learning to achieve accurate vehicle trajectory clustering. Specifically, we first construct the k-nearest neighbor-based internet of vehicles in a dynamic manner. Then we learn the low-dimensional representations of vehicles by performing dynamic network representation learning on the constructed network. Finally, using the learned vehicle vectors, vehicle trajectories are clustered with machine learning methods. Experimental results on the real-word dataset show that our method achieves the best performance compared against baseline methods.
Geographic routing is a research hotspot of the internet of vehicle (IoV) and intelligent traffic system (ITS). In practice, the vehicle movement is not only affected by its characteristics and the relationship between vehicle and position, but also affected by some implicit factors. Pointing to this problem, we combine the vehicle moving position probability matrix, the vehicle position association matrix, and the implicit factors to study the influence of vehicle position potential features, vehicle association potential features, and propose a routing algorithm based on vehicle position analysis (RAVP), which can obtain the more accurate vehicle prediction trajectory. Then, vehicle distance is obtained based on vehicle prediction trajectory. By the normalization of vehicle distance and cache, the vehicle data forwarding capability is obtained and the transmission decision is made. Simulation results show that the proposed algorithm outperforms the other three routing algorithms in terms of packet delivery ratio, average end to end delay and routing overhead ratio.
In this paper we propose a novel observer-based method to improve the safety and security of connected and automated vehicle (CAV) transportation. The proposed method combines model-based signal filtering and anomaly detection methods. Specifically, we use adaptive extended Kalman filter (AEKF) to smooth sensor readings of a CAV based on a nonlinear car-following model. Using the car-following model the subject vehicle (i.e., the following vehicle) utilizes the leading vehicle's information to detect sensor anomalies by employing previously-trained One Class Support Vector Machine (OCSVM) models. This approach allows the AEKF to estimate the state of a vehicle not only based on the vehicle's location and speed, but also by taking into account the state of the surrounding traffic. A communication time delay factor is considered in the car-following model to make it more suitable for real-world applications. Our experiments show that compared with the AEKF with a traditional χ²-detector, our proposed method achieves a better anomaly detection performance. We also demonstrate that a larger time delay factor has a negative impact on the overall detection performance.
This paper presents a blockchain enabled secure data acquisition scheme utilizing an Unmanned Aerial Vehicle (UAV) swarm where data are collected from internet of things (IoT) devices and subsequently, forwarded to the nearest server through the UAV swarm. Before initiating data acquisition, the UAV swarm shares a shared key with IoT devices in order to maintain communications. However, prior to transmitting data, IoT devices encrypt the data and forward it to the UAV swarm. Upon receiving the data, the UAV swarm implements a two-phase validation utilizing the π-hash bloom filter and the digital signature algorithm to validate the sender; in addition, prior to forwarding data to the nearest server, it performs encryption. However, before adding data in blockchain, consent from all validators is required. Finally, the data are stored in blockchain with the approval of validators. A security analysis is performed to demonstrate the feasibility of the proposed scheme. Finally, the effectiveness of the proposed scheme is manifested through implementation and simulation. The security analysis and the performance results show that UAV assist IoT devices both in terms of connectivity and energy consumption, and provides security against the threats mentioned in the paper.
Anomaly detection is an important part of an Intelligent Transportation System. In this study, image processing and machine learning techniques are used to detect anomalies in vehicle movements. These anomalies include standing and traveling in reverse direction. Images are captured using CCTV cameras from front and rear side of the vehicle. This capability makes the results robust to the variations in operational and environmental conditions. Multiple consecutive frames are acquired for motion detection. Features such as edges and license plate corner locations are extracted for tracking purposes. Direction of the traffic flow is obtained from the trained classifier. K-nearest neighbor is chosen as the classifier model. The proposed method is evaluated on a public highway and promising detection results are achieved.
Federated averaging (FedAvg) is a communication-efficient algorithm for distributed training with an enormous number of clients. In FedAvg, clients keep their data locally for privacy protection; a central parameter server is used to communicate between clients. This central server distributes the parameters to each client and collects the updated parameters from clients. FedAvg is mostly studied in centralized fashions, requiring massive communications between the central server and clients, which leads to possible channel blocking. Moreover, attacking the central server can break the whole system's privacy. Indeed, decentralization can significantly reduce the communication of the busiest node (the central one) because all nodes only communicate with their neighbors. To this end, in this paper, we study the decentralized FedAvg with momentum (DFedAvgM), implemented on clients that are connected by an undirected graph. In DFedAvgM, all clients perform stochastic gradient descent with momentum and communicate with their neighbors only. To further reduce the communication cost, we also consider the quantized DFedAvgM. The proposed algorithm involves the mixing matrix, momentum, client training with multiple local iterations, and quantization, introducing extra items in the Lyapunov analysis. Thus, the analysis of this paper is much more challenging than previous decentralized (momentum) SGD or FedAvg. We prove convergence of the (quantized) DFedAvgM under trivial assumptions; the convergence rate can be improved to sublinear when the loss function satisfies the PŁ property. Numerically, we find that the proposed algorithm outperforms FedAvg in both convergence speed and communication cost.
This letter presents a federated learning-based data-accumulation scheme that combines drones and blockchain for remote regions where Internet of Things devices face network scarcity and potential cyber threats. The scheme contains a two-phase authentication mechanism in which requests are first validated using a cuckoo filter, followed by a timestamp nonce. Secure accumulation is achieved by validating models using a Hampel filter and loss checks. To increase the privacy of the model, differential privacy is employed before sharing. Finally, the model is stored in the blockchain after consent is obtained from mining nodes. Experiments are performed in a proper environment, and the results confirm the feasibility of the proposed scheme.
The modern era is filled with smart entities (e.g., smart vehicles) that have both sense and actuate capabilities. These entities can collect lots of data during their functional period and these data can be utilized for the wellbeing of citizens. However, these data are very sensitive raising issues like privacy. Moreover, network scarcity, bandwidth consumption, etc. can worsen the circumstance. Federated learning (FL), internet of drones (IoD), and dew computing (DC) are revolutionary technologies that can be engaged to mitigate the aforementioned challenges. An FL-based computing paradigm is initiated over the dew computing to process road-related data to bring efficiency in the applications (e.g., finding parking locations) utilizing IoD. An experimental environment is established containing a traffic dataset as a proof of concept. The experimental results exhibit the feasibility of the proposed scheme.
Federated Learning (FL) is an emerging approach for collaboratively training Deep Neural Networks (DNNs) on mobile devices, without private user data leaving the devices. Previous works have shown that non-Independent and Identically Distributed (non-IID) user data harms the convergence speed of the FL algorithms. Furthermore, most existing work on FL measures global-model accuracy, but in many cases, such as user content-recommendation, improving individual User model Accuracy (UA) is the real objective. To address these issues, we propose a Multi-Task FL (MTFL) algorithm that introduces non-federated Batch-Normalization (BN) layers into the federated DNN. MTFL benefits UA and convergence speed by allowing users to train models personalised to their own data. MTFL is compatible with popular iterative FL optimisation algorithms such as Federated Averaging (FedAvg), and we show empirically that a distributed form of Adam optimisation (FedAvg-Adam) benefits convergence speed even further when used as the optimisation strategy within MTFL. Experiments using MNIST and CIFAR10 demonstrate that MTFL is able to significantly reduce the number of rounds required to reach a target UA, by up to
$5\times$
when using existing FL optimisation strategies, and with a further
$3\times$
improvement when using FedAvg-Adam. We compare MTFL to competing personalised FL algorithms, showing that it is able to achieve the best UA for MNIST and CIFAR10 in all considered scenarios. Finally, we evaluate MTFL with FedAvg-Adam on an edge-computing testbed, showing that its convergence and UA benefits outweigh its overhead.
Internet of Things (IoT) established the foundation of the smart world via its diverse functionalities (e.g., remote data acquisition, automated task execution). This trend continues to military applications too by introducing internet of military things (IoMT). Due to being at infancy level, new technologies require to move forward and assist IoMT to gain maturity. Mixed reality (MR) can be a potential technology which fuses the virtual and actual world. MR can improve the quality of service (QoS) in terms of inventory management, remote mission handling, battlefield assistance, etc. However, data among these applications is surrounded by cyber threats (e.g., illegal data modification, unauthorised data access). Blockchain is another promising technology which brings security in the distributed world. A content sharing scheme for MR application is proposed on the top of blockchain to bring security in the multi-user environment in IoMT. A smart contract is employed to manage security in accessing data by different users. Moreover, an experimental environment is set to observe the performance of the proposed scheme. The analysis manifests that proposed scheme maintains security without affecting the regular performance.
To stay up to date with world issues and cutting-edge technologies, the newspaper plays a crucial role. However, collecting news is not a very easy task. Currently, news publishers are collecting news from their correspondents through social networks, email, phone call, fax, etc. and sometimes they buy news from the agencies. However, the existing news sharing networks may not provide security for data integrity and any third party may obstruct the regular flow of news sharing. Moreover, the existing news schemes are very vulnerable in case of disclosing the identity. Therefore, a universal platform is needed in the era of globalization where anyone can share and trade news from anywhere in the world securely, without the interference of third-party, and without disclosing the identity of an individual. Recently, blockchain has gained popularity because of its security mechanism over data, identity, etc. Blockchain enables a distributed way of managing transactions where each participant of the network holds the same copy of the transactions. Therefore, with the help of pseudonymity, fault-tolerance, immutability, and the distributed structure of blockchain, a scheme (termed as NEWSTRADCOIN) is presented in this paper in which not only news can be shared securely but also anyone can earn money by selling news. The proposed NEWSTRADCOIN can provide a universal platform where publishers can directly collect news from news-gatherers in a secure way by maintaining data integrity, without experiencing the interference of a third-party, and without disclosing the identity of the news gatherer and publishers.
This paper introduces a blockchain-based secure healthcare scheme in which health data (HD) are collected from users via an unmanned aerial vehicle (UAV) and stored on the nearest server. In the proposed scheme, a UAV first establishes a relation with body sensor hives (BSHs) via a token and then shares a shared key with BSHs to enable low-power secure communication. After retrieving the HD, the UAV decrypts the encrypted HD (encrypted by a BSH) using the shared key and exercises a two-phase authentication mechanism. Upon successful validation, the UAV transmits the HD to the nearest server to store it securely in blockchain. A security analysis is discussed to show the feasibility of the proposed secure healthcare scheme. Finally, the performance of the proposed scheme is investigated through simulation and implementation. The security and the performance analysis demonstrate that the proposed scheme supports better assistance to BSHs while maintaining security.
Trespassing in the marine area is a very critical issue. As a result, countries are losing revenue as well as it's a threat against the sovereignty of the country. As sea area is large, it's not always possible to monitor every part in real-time. Unmanned aerial vehicle (UAV) is a promising technology that can assist to alleviate this issue. However, communication between the control center and a UAV encircles with cyber threats as well as data in the surveillance may experience unauthorised modification. This paper represents a blockchain-empowered smart surveillance architecture in which UAV performs surveillance and uses a two-phase authentication process to verify the marine vehicles. The experimental result manifests that the proposed scheme is faster and consumes less energy than the existing authentication algorithms.
Internet of things (IoT), mobile edge computing (MEC), and unmanned aerial vehicle (UAV) have attracted significant attention in both industry and academic research. By consolidating these technologies, IoT can be facilitated with improved connectivity, better data transmission, energy saving, and other advantages. However, the communication between these entities is subject to potential cyber threats. In addition, the integrity of the data must be maintained after storing into local storage. Blockchain is a data structure that supports features like pseudonymity, data integrity etc. This paper represents a blockchain based data acquisition process in which information is gathered from IoTs using UAV as a relay and is securely kept in blockchain at MEC server. In the proposed scheme, data are encrypted prior to transfer to MEC server with the assistance of a UAV. Upon receiving the data, MEC server validates the data and the identity of the sender. Successful validation is followed by stocking of the data into blockchain, subsequent to obtaining consent from the validators. Security analysis is conducted in order to show the feasibility of the proposed secure scheme. Finally, the performance of the proposed scheme is analyzed via simulation and implementation.
Mobile Edge Computing (MEC) can facilitate various important image retrieval applications for mobile users by offloading partial computation tasks from resource-limited mobile devices to edge servers. However, existing related works suffer from two major limitations. (i) High network bandwidth cost: they need to extract numerous features from the image and upload these feature data to the cloud server. (ii) Low retrieval accuracy: they separate the feature extraction processes from the image data set in the cloud server, thus unable to provide effective features for accurate image retrieval. In this paper, we propose a cloud-guided feature extraction approach for mobile image retrieval. In the proposed approach, the cloud server first leverages the relationships among labeled images in the data set to learn a projection matrix P. Then, it uses the matrix P to extract discriminative features from the image data set and form a low-dimensional feature data set. Follow that, the cloud server sends the matrix P to the edge server and uses it to multiply the image x. The result PTx, i.e., image features, is uploaded to the cloud server to find the label of the image with the most similar multiplying result. The label is regarded as the retrieval result and returned to the mobile user. In the cloud-guided feature extraction approach, the matrix P can extract a small number of effective image features, which not only reduces network traffic but also improves retrieval accuracy. We have implemented a prototype system to validate the proposed approach and evaluate its performance by conducting extensive experiments using a real MEC environment and data set. The experimental results show that the proposed approach reduces the network traffic by nearly 93% and improves the retrieval accuracy by nearly 6.9% compared with the state-of-the-art image retrieval approaches in MEC.
Unmanned aerial vehicle (UAV) is an emerging technology that becomes popular not only in military operation but also in civil applications. Internet of things (IoT) is another popular technology which brings automation in our daily life. Like other areas, IoT also exposes its potential in healthcare. Using IoT sensors, it becomes easy to monitor the health of a user remotely. UAV consolidated with mobile edge computing (MEC) can provide real-time services in outdoor health monitoring. However, communication among them surrounds with cyber threats and data integrity issue. Blockchain is a data structure in which data are shared among peers. In this paper, a blockchain based secure outdoor health monitoring scheme using UAV is proposed for a smart city. In the proposed scheme, health data (HD) are accumulated from users wearable sensors and these HD are transmitted to the nearest MEC server via UAV. Prior to transmitting to MEC, HD experience encryption in order to provide protection against cyber threats. Moreover, after arriving at MEC, HD are diagnosed and if any abnormalities are found in the user’s health, MEC server notifies the user and the nearest hospitals. When the processing is completed, HD are stored in blockchain with the consent of validators. Finally, simulation results and experimental set up are discussed in order to manifest the feasibility of the proposed scheme.
Rapid progress in Intelligent Transportation Systems (ITS) during the last few decades has resulted in the emergence of the Internet of Vehicles (IoV), in which smart vehicles communicate with each other for information sharing. The exponential increase in the number of vehicles, together with an increasing data demands from in-vehicle users, has led to a tremendous growth of upstream data in the IoV infrastructure. However, the highly dynamic topology and distributed nature of vehicular networks exposes the vehicular traffic to higher security risks. To address these challenges, in this paper, "Sec-IoV", a multi-stage model for anomaly detection is specifically proposed for securing vehicle-to-vehicle (V2V) communications in IoV setups. The proposed anomaly detection model comprises of multiple stages: (a) relevant feature set selection, (b) optimization of Support Vector Machine (SVM) parameters, and (c) classification of vehicular traffic into benign and anomalous. The first two stages are expressed using the multi-objective optimization problems, which are iteratively computed using the hybridization of a meta-heuristic approach "Artificial Bee Colony (ABC) Optimization" with a Cauchy based mutation operator. This coupling is referred to as "C-ABC". It improves the local search capability of the optimizer with faster convergence. The last stage of data classification is then performed by employing SVM with a refined set of parameters. For the extensive evaluation of the proposed model, different state-of-the-art models have been executed on OMNET++ and SUMO. The obtained results in terms of the detection rate, accuracy, and false positive rate reflect the effectiveness of the proposed Sec-IoV model against the existing state-of-the-art schemes.
In order to stay up to date with world issues and cutting-edge technologies, the newspaper plays a crucial role. However, collecting news is not a very easy task. Currently, news publishers are collecting news from their correspondents through social networks, email, phone call, fax etc. and sometimes they buy news from the agencies. However, the existing news sharing networks may not provide security for data integrity and any third party may obstruct the regular flow of news sharing. Moreover, the existing news schemes are very vulnerable in case of disclosing the identity. Therefore, a universal platform is needed in the era of globalization where anyone can share and trade news from anywhere in the world securely, without the interference of third-party, and without disclosing the identity of an individual. Recently, blockchain has gained popularity because of its security mechanism over data, identity, etc. Blockchain enables a distributed way of managing transactions where each participant of the network holds the same copy of the transactions. Therefore, with the help of pseudonymity, fault-tolerance, immutability and the distributed structure of blockchain, a scheme (termed as NEWSTRADCOIN) is presented in this paper in which not only news can be shared securely but also anyone can earn money by selling news. The proposed NEWSTRADCOIN can provide a universal platform where publishers can directly obtain news from news-gatherers in a secure way by maintaining data integrity, without experiencing the interference of a third-party, and without disclosing the identity of the news gatherer and publishers.
- Tao Sun
- Dongsheng Li
- Bao Wang
Tao Sun, Dongsheng Li, and Bao Wang. 2021. Decentralized federated averaging. CoRR, abs/2104.11375. arXiv: 2104.
11375. https://arxiv.org/abs/2104.11375.
APS Failure at Scania Trucks Data Set
- Tony Lindgren
- Jonas Biteus
Tony Lindgren and Jonas Biteus. 2016. Aps failure at scania
trucks data set. (2016). https : / / archive. ics. uci. edu / ml /
datasets/APS+Failure+at+Scania+Trucks.