Showing papers in "IEEE Consumer Electronics Magazine in 2022"
TL;DR: Wang et al. as mentioned in this paper proposed a digital forensics tool to protect end users in 5G heterogeneous networks, which is built based on deep learning and can realize the detection of attacks via classification.
Abstract: The upcoming 5G heterogeneous networks (HetNets) have attracted much attention worldwide. Large amounts of high-velocity data can be transported by using the bandwidth spectrum of HetNets, yielding both great benefits and several concerning issues. In particular, great harm to our community could occur if the main visual information channels, such as images and videos, are maliciously attacked and uploaded to the Internet, where they can be spread quickly. Therefore, we propose a novel framework as a digital forensics tool to protect end users. It is built based on deep learning and can realize the detection of attacks via classification. Compared with the conventional methods and justified by our experiments, the data collection efficiency, robustness, and detection performance of the proposed model are all refined. In addition, assisted by 5G HetNets, our proposed framework makes it possible to provide high-quality real-time forensics services on edge consumer devices such as cell phone and laptops, which brings colossal practical value. Some discussions are also carried out to outline potential future threats.
42 citations
TL;DR: In this paper , the authors proposed a lightweight authentication protocol for IoT devices named Light-Edge using a three-layer scheme, including IoT device layer, trust center at the edge layer, and cloud service providers.
Abstract: Due to the ever-growing use of active Internet devices, the Internet has achieved good popularity at present. The smart devices could connect to the Internet and communicate together that shape the Internet of Things (IoT). Such smart devices are generating data and are connecting to each other through edge-cloud infrastructure. Authentication of the IoT devices plays a critical role in the success of the integration of IoT, edge, and cloud computing technologies. The complexity and attack resistance of the authentication protocols are still the main challenges. Motivated by this, this article introduces a lightweight authentication protocol for IoT devices named Light-Edge using a three-layer scheme, including IoT device layer, trust center at the edge layer, and cloud service providers. The results show the superiority of the proposed protocol against other approaches in terms of attack resistance, communication cost, and time cost.
35 citations
TL;DR: In this article , the authors present an overview and recent advances of digital twins for healthcare 4.0, and propose an architecture of digital twin for healthcare and open research challenges with possible solutions.
Abstract: Recent trends have shown a widespread increase in the landscape of digital healthcare (i.e., Healthcare 4.0) services, such as personalized healthcare, intelligent rehabilitation, telemedicine, and smart diet management, among others. These healthcare services are based on a variety of diverse requirements. Fulfilling these requirements require proactive intelligent analytics and self-sustainability of networks. Self-sustainability enables the operation of a network with minimum possible interaction from the end-users/network operators, whereas proactive intelligent analytics enables efficient management of resources in response to users' requests. To enable healthcare 4.0 with proactive online analytics and self-sustainability, one can leverage digital twins. In this article, we present an overview and recent advances of digital twins for healthcare 4.0. An architecture of digital twins for healthcare is also proposed. Furthermore, we present several use cases of digital twins. Finally, we present open research challenges with possible solutions.
29 citations
TL;DR: In this article , the authors proposed a biometric method called BioSec to provide authentication in IoT integrated with edge consumer electronics with fingerprint authentication, which ensured the security of biometric data both in the transmission channel and database with the standard encryption method.
Abstract: To address the privacy and security related challenges in Internet of Things (IoT) environment, we proposed a biometric method called BioSec to provide authentication in IoT integrated with edge consumer electronics with fingerprint authentication. Further, we ensured the security of biometric data both in the transmission channel and database with the standard encryption method. In this way, BioSec ensures secure and private communication among edge devices in IoT and Industry 4.0. Finally, we have compared three encryption methods used to protect biometric templates in terms of processing times and identified that AES-128-bit key encryption method outperforms others.
16 citations
TL;DR: In this article , the role of artificial intelligence in providing security to the integrated UAV-AV has also been discussed, and the outstanding research and development challenges that will provide new research avenues for the research community.
Abstract: Unmanned aerial vehicles (UAVs) and autonomous vehicle (AV) technologies are gaining popularity due to their key benefits that include, but are not limited to, infrastructure independence, scalability, and autonomy. Although UAV and AV technologies are vertical; nevertheless, from the services and applications standpoint, these technologies handsomely complement each other. More precisely, the shortcomings faced by AV technology such as real-time navigation, visibility, mapping, content uploading, and maneuvering could be supported by UAV technology. Moreover, security plays a crucial role in the commercial deployment of AVs. This article focuses on the role of futuristic technologies in securing such a critical environment. Specifically, we focus on the data-related security for which blockchain is leveraged. The role of other enabling technologies, such as artificial intelligence, in providing security to the integrated UAV–AV has also been discussed. Finally, we identify the outstanding research and development challenges that will provide new research avenues for the research community.
15 citations
TL;DR: The International Standard 23090-3 (MPEG-I Part 3) as mentioned in this paper was developed by the Joint Video Experts Team of the ITU-T Video Coding Experts Group and the ISO/IEC Moving Picture Experts Group.
Abstract: The amount of video content and the number of applications based on multimedia information increase each day. The development of new video coding standards is a challenge to increase the compression rate and other important features with a reasonable increase in the computational load. The Joint Video Experts Team of the ITU-T Video Coding Experts Group and the ISO/IEC Moving Picture Experts Group (MPEG) have worked together to develop the versatile video coding standard, finalized in July 2020 as the International Standard 23090-3 (MPEG-I Part 3). This article overviews some interesting consumer electronic use cases, the compression tools described in the standard, the current available real-time implementations, and the first industrial trials done with this standard.
13 citations
TL;DR: In this paper , the applicability of Internet attack detection through federated machine learning (FML) has been investigated, to the best of our knowledge, where the application of federated learning to satisfy customer search queries by detecting malicious spam images, which may lead these AI systems to retrieve irrelevant information.
Abstract: Enormous amount of information is processed at different websites, on a number of different AI tools and in multiple data silos. Sharing data between various sources, this is a significant obstacle, due to administrative, organizational, and security considerations. One possible solution is federated machine learning (FML), a system that simultaneously sends machine learning algorithms to all data sources, trains models at each source, and aggregates the learned models. This technique ensures consumer-influenced solution by processing the data locally. This work is the first to investigate the applicability of Internet attack detection through FML, to the best of our knowledge. Our primary contributions include the application of federated learning to satisfy customer search queries by detecting malicious spam images, which may lead these AI systems to retrieve irrelevant information. We assess and analyze the FML-entangled learning output comprehensively in different ways adjustments including balanced and imbalanced customer data distribution, scalability, and overhead communication. Our measuring results show that FML suits practical scenarios, where the variable image size, including the animation ratio to legitimate samples of images, present among the advertisements that may distract consumer from fetching relevant results. With the evaluated results, the state-of-the-art FedLearnSP proved significant image spam detection.
12 citations
TL;DR: In this paper , the authors describe how the future electric energy system with 100% electricity supply from renewable energy sources requires the "birth of security and resiliency" incorporated with its ecosystem.
Abstract: The concept of smart cities is driven by the need to enhance citizens’ quality of life. It is estimated that 70% of the world population will live in urban areas by 2050. The electric grid is the energy backbone of smart city deployments. An electric energy system immune to adverse events, both cyber and physical risks, and able to support the integration of renewable sources will drive a transformational development approach for future smart cities. This article describes how the future electric energy system with 100% electricity supply from renewable energy sources requires the “birth of security and resiliency” incorporated with its ecosystem.
12 citations
TL;DR: In this paper , the authors present a practical prospect of blockchain empowered federated learning to realize fully secure, privacy preserving, and verifiable FL for the IoV that is capable of providing secure and trustworthy ITS services.
Abstract: Internet of Vehicles (IoV) has been sought as a solution to realize an Intelligent Transportation System (ITS) for efficient traffic management. Data driven ITS requires learning from vehicular data and provide vehicles with timely information to support a wide range of safety and infotainment ITS applications. IoV is vulnerable to multitude of cyber-attacks and privacy concerns. Federated learning (FL) is on the verge of delivering the collaborative learning by exchanging learning model parameters instead of actual data, which is expected to provide privacy in IoV. However, despite featuring an inherently secure and privacy-preserving framework, FL is still vulnerable to poisoning and reverse engineering attacks. Blockchain technology (BC) has already demonstrated a zero-trust, fully secure, distributed, and auditable information recording and sharing paradigm. In this article, we present a practical prospect of blockchain empowered federated learning to realize fully secure, privacy preserving, and verifiable FL for the IoV that is capable of providing secure and trustworthy ITS services.
12 citations
TL;DR: A framework that integrates digital twin (DT) with other advanced technologies such as the sixth generation (6G) communication network, blockchain, and AI, to maintain continuous end-to-end metaverse services is proposed.
Abstract: The advances in Artificial Intelligence (AI) have led to technological advancements in a plethora of domains. Healthcare, education, and smart city services are now enriched with AI capabilities. These technological advancements would not have been realized without the assistance of fast, secure, and fault-tolerant communication media. Traditional processing, communication and storage technologies cannot maintain high levels of scalability and user experience for immersive services. The metaverse is an immersive three-dimensional (3D) virtual world that integrates fantasy and reality into a virtual environment using advanced virtual reality (VR) and augmented reality (AR) devices. Such an environment is still being developed and requires extensive research in order for it to be realized to its highest attainable levels. In this article, we discuss some of the key issues required in order to attain realization of metaverse services. We propose a framework that integrates digital twin (DT) with other advanced technologies such as the sixth generation (6G) communication network, blockchain, and AI, to maintain continuous end-to-end metaverse services. This article also outlines requirements for an integrated, DT-enabled metaverse framework and provides a look ahead into the evolving topic.
12 citations
TL;DR: In this paper , the authors discuss various security attack modes in an edge-centric intelligent IoV framework, consisting of distributed smart vehicles, and remote processing units, to address the security challenges.
Abstract: Propelled by the growth of automotive industry, and the ubiquity of smart sensors, intelligent transport systems such as the Internet of Vehicles (IoV) have seen significant research interest in recent times. The emerging distributed IoV networks support real-time vehicular applications through on-device computing, communication-efficient data processing, edge computing, and cloud aggregation. While enriching the user experience by minimizing the end-to-end latency through efficient energy management, IoV deployments face the fundamental challenge of security attacks. In this article, we discuss various security attack modes in an edge-centric intelligent IoV framework, consisting of distributed smart vehicles, and remote processing units. We highlight various attack detection and mitigation mechanism for the proposed IoV framework, to address the security challenges. Finally, we shed light on several future research directions to ensure security of sensory data in edge-centric IoV systems.
TL;DR: In this paper , a simplified tangible augmented reality system is proposed accompanied with the opportunities and challenges of such an implementation, and a simplified tactile XR system is also proposed for tactile internet.
Abstract: The increasing popularity of virtual reality (VR) and augmented reality (AR) applications has unveiled the need for boosting the efforts of implementing extended reality (XR) to users. An analogous high interest from both academia and industry is being shown for tactile internet (TI). The ever-increasing use of virtualization technologies makes the usage of haptic communication even more important in order to create robust tangible systems, but also to achieve an optimal and faster balance among the interaction modalities, as well as between humans and machines. The current wireless mobile networks cannot provide ultra-low latency, massive computational capability, and high communication bandwidth, requirements which are crucial for applications such as extended reality and tactile internet. A simplified tangible XR system is proposed accompanied with the opportunities and challenges of such an implementation.
TL;DR: In this paper , a proof-of-authentication utilizing a lightweight authenticated encryption (AE) scheme to achieve consensus is proposed, which can speed up the consensus in blockchain, utilizing few resources and making it very suitable for applications in IoT sensor nodes.
Abstract: IoT nodes comprise of sensors and embedded resource-constrained systems. On the other hand, blockchain is regarded as computationally expensive due to the consensus algorithms. Therefore, it is challenging to apply blockchain to an IoT system. This work presents a unique concept that integrates blockchain with lightweight cryptographic solutions targeting resource-constrained IoT sensor nodes. In particular, proof-of-authentication utilizing a lightweight authenticated encryption (AE) scheme to achieve consensus is proposed. At sensor nodes, a tag is generated based on sensor data, which is then broadcast to the network. Upon authentication from the cluster head node (e.g., a gateway), the block is hashed using the lightweight hash function and added to the blockchain. The proposed solution can be implemented in software (e.g., microcontroller) or hardware platform (e.g., FPGA, ASIC). Experimental results show that lightweight authentication can perform 1.34 M authentications per-second with only 6.55 k lookup tables (LUTs) on the Spartan-6 FPGA platform. This high-throughput authentication can speed up the consensus in blockchain, utilizing few resources and making it very suitable for applications in IoT sensor nodes.
TL;DR: In this article , the authors integrate signal processing and cryptographic techniques and describe a tailored solution for CAD model ownership and supply chain management, which generates unique identifiers for 3D designs using frequency-domain transforms and employs non-fungible tokens (NFTs) that persist on public distributed ledgers.
Abstract: Digital manufacturing (DM) is actively adopted to the production lifecycles of a variety of critical industries, and this rapid growth has resulted in exponential increase of 3D computer-aided design (CAD) models. Unfortunately, counterfeiting of intellectual property becomes a prominent threat as many 3D designs are accessible online, combined with the proliferation of cheap consumer 3D printers that enable malicious actors to produce non-authentic parts. State-of-the-art techniques to secure manufacturing processes mostly rely on watermarking, which embeds hidden information inside CAD models to prove ownership and authenticity. Nevertheless, such techniques tamper with the model itself, while existing attacks allow removing such watermarks altogether. To address these shortcomings, we integrate signal processing and cryptographic techniques and describe a tailored solution for CAD model ownership and supply chain management. Our approach generates unique identifiers for 3D designs using frequency-domain transforms and employs non-fungible tokens (NFTs) that persist on public distributed ledgers. Our NFTs are implemented on the Ethereum blockchain using smart contracts and their functionality is twofold: (a) authenticate the owner of a CAD model, and (b) enable ownership transfer. To validate our technique, we deployed our smart contract on Ethereum's proof-of-work Ropsten network and demonstrated the applicability of our methodology.
TL;DR: In this paper , the authors discuss major automotive cyber-attacks over the past decade and present state-of-the-art solutions that leverage artificial intelligence for building secure autonomous vehicles.
Abstract: Autonomous vehicles are on the horizon and will be transforming transportation safety and comfort. These vehicles will be connected to various external systems and utilize advanced embedded systems to perceive their environment and make intelligent decisions. However, this increased connectivity makes these vehicles vulnerable to various cyber-attacks that can have catastrophic effects. Attacks on automotive systems are already on the rise in today's vehicles and are expected to become more commonplace in future autonomous vehicles. Thus, there is a need to strengthen cybersecurity in future autonomous vehicles. In this article, we discuss major automotive cyber-attacks over the past decade and present state-of-the-art solutions that leverage artificial intelligence. We propose a roadmap toward building secure autonomous vehicles and highlight key open challenges that need to be addressed.
TL;DR: A blockchain-based solution for CEI that makes the edge devices’ events history immutable and easily traceable and such a secured CEI mechanism can be applied in establishing a transparent and efficient smart city, supply chain, logistics, and transportation systems.
Abstract: —The devices at the edge of a network are not only responsible for sensing the surrounding environment but are also made intelligent enough to learn and react to the environment. Clustered Edge Intelligence (CEI) emphasizes intelligence-centric clustering instead of device-centric clustering. It allows the de- vices to share their knowledge and events with other devices and the remote fog or cloud servers. However, recent advancements facilitate the traceability of the events’ history by analyzing edge devices’ event logs, which are compute-intensive and easy to alter. This article focuses on a blockchain-based solution for CEI that makes the edge devices’ events history immutable and easily traceable. The article further explains how the edge devices’ activities and the environmental data can be secured from the source device to the cloud servers. Such a secured CEI mechanism can be applied in establishing a transparent and efficient smart city, supply chain, logistics, and transportation systems.
TL;DR: In this article , a deep learning model is proposed to process data generated by the Internet-of-Vehicle-Things (IoVT) for intelligent routing and real-time traffic alerts.
Abstract: Intelligent sensing plays an important part in making our use of vehicles safe and problem-free. On average, a person spends over 35 hours in traffic jams each year. This valuable time could be saved by intelligent routing and real-time traffic alerts. Transport is a necessity of life, both in our everyday lives and at work. Navigation apps are now enabling users to access real-time alerts and alternatives. However, with the increase in the number of Internet-of-Vehicle-Things (IoVT), a large amount of data is produced within a short period of time. The huge data produced by the IoVT could be used to obtain greater perspective and to make dramatically smarter decisions. With this data, there is always a risk to security, trust, and privacy (STP). A standardized protocol is needed to preserve privacy and maintain the security of data. This paper addressed several STP issues in an intelligent transportation system. In addition, a deep learning model is proposed to process data generated by the IoVT.
TL;DR: This article discusses major automotive cyber-attacks over the past decade and presents state-of-the-art solutions that leverage artificial intelligence and proposes a roadmap toward building secure autonomous vehicles.
Abstract: Autonomous vehicles are on the horizon and will be transforming transportation safety and comfort. These vehicles will be connected to various external systems and utilize advanced embedded systems to perceive their environment and make intelligent decisions. However, this increased connectivity makes these vehicles vulnerable to various cyber-attacks that can have catastrophic effects. Attacks on automotive systems are already on the rise in today's vehicles and are expected to become more commonplace in future autonomous vehicles. Thus, there is a need to strengthen cybersecurity in future autonomous vehicles. In this article, we discuss major automotive cyber-attacks over the past decade and present state-of-the-art solutions that leverage artificial intelligence. We propose a roadmap toward building secure autonomous vehicles and highlight key open challenges that need to be addressed.
TL;DR: This article explores the integration of DFC with IoT in improving security and privacy solutions for villagers and Consumer Electronic (CE) devices and design and evaluate the performance of an Intrusion Detection System in DFC-based smart village environment.
Abstract: —The Internet of Things (IoT) technology is seen as the foundation for next-generation smart villages due to its ability to use sustainable information and communication technologies. The smart villages can enable real-time data analytic and can automate decision making for local villagers in terms of agriculture, healthcare, transportation, environment, and energy. However, most of the wireless sensing devices exchange information using public network and therefore may not be able to resist all forms of attacks. Additionally, most of the IoT devices are resource restricted and uses cloud servers to process and store data. However, when IoT devices communicate with cloud computing data centers, the volume of data causes network congestion. To provide secure services close to end devices, a new network architecture called Distributed Fog Computing (DFC) can be created and integrated with IoT-based smart villages deployment. Motivated from the aforementioned discussions, this article explores the integration of DFC with IoT in improving security and privacy solutions for villagers and Consumer Electronic (CE) devices. As a case study, we also design and evaluate the performance of an Intrusion Detection System (IDS) in DFC-based smart village environment. Finally, we discuss several open security issues and challenges regarding Fog-to-Things enabled smart villages.
TL;DR: In this paper , the authors proposed a blockchain-based secure storage architecture for Intelligent Internet of Vehicular Things (IoVT), which provides security and privacy at each city's vehicular networks and decentralized storage at the cloud layer with a distributed hash table.
Abstract: Today, the rapid growth of vehicles connected to the Internet enables provides various services to consumers, including traffic management, traffic safety, and entertainment. Vehicular ad-hoc network is one of the most prominent and emerging technologies on the Internet of Vehicular Things (IoVT). This technology offers to fulfill requirements such as robust information exchange, and infotainment among vehicles for the smart city environment. Still, it has some challenges such as centralization, storage, security, and privacy because all city vehicular networks send vehicles and road-related information data directly to the cloud. This article proposes BIIoVT: Blockchain-based secure storage architecture for Intelligent Internet of Vehicular Things to mitigate the above-mention issues. Blockchain provides security and privacy at each city's vehicular networks and decentralized storage at the cloud layer with a distributed hash table. It also examines how the vehicular network offers a secure platform. The validation results of the proposed architecture show an outstanding balance of secure storage and efficiency for the IoVT compared to existing methods.
TL;DR: In this paper , the authors provide an overview of the secure IoT framework, paradigms, enablers, and security problems of combining blockchain and intelligent edge computing, and broader viewpoints for future research directions are investigated.
Abstract: The Blockchain is one of the most promising and artistic cybersecurity solutions. It has been practiced in a variety of reinforcements, including healthcare, transportation, and Internet of Things (IoT) applications. However, Blockchain has a colossal scalability challenge, limiting its ability to control services with high transaction volumes. Edge computing, on the other hand, was designed to allow cloud services and resources to be deployed at the network's edge, although it now faces issues in terms of decentralized security and management. The unification of edge computing and Blockchain within one solution jar provides a vast scale of storage systems, database servers, and authenticity computation towards the end in a safe fashion. Despite the potential of interconnected edge computing and Blockchain environments, difficulties such as scalability, resource management, function integration, self-organization, and new security concerns must be addressed before broad adoption. This article provides an overview of the secure IoT framework, paradigms, enablers, and security problems of combining Blockchain and intelligent edge computing. Finally, broader viewpoints for future research directions are investigated.
TL;DR: In this paper , the authors categorize the different aspects of 6G into four emerging directions that anticipate significant advancements leveraging blockchain, and discuss the potential role of blockchainized 6G under each key emerging direction, expound on the technical challenges in blockchaining 6G along with possible solutions.
Abstract: The next generation of mobile networks, i.e., sixth generation (6G), is expected by 2030, with already burgeoning research efforts towards this goal. Along with various other candidate technologies, blockchain is envisioned to enable and enhance numerous key functionalities of 6G. Thus, the main objective of this paper is threefold: 1) to categorize the different aspects of 6G into four emerging directions that anticipate significant advancements leveraging blockchain, 2) to discuss the potential role of blockchainized 6G under each key emerging direction, 3) to expound on the technical challenges in blockchaining 6G along with possible solutions.
TL;DR: In this article , the authors focus on the data-related security for which blockchain is leveraged and identify the outstanding research and development challenges that will provide new research avenues for the research community.
Abstract: Unmanned aerial vehicles (UAVs) and autonomous vehicle (AV) technologies are gaining popularity due to their key benefits that include, but are not limited to, infrastructure independence, scalability, and autonomy. Although UAV and AV technologies are vertical; nevertheless, from the services and applications standpoint, these technologies handsomely complement each other. More precisely, the shortcomings faced by AV technology such as real-time navigation, visibility, mapping, content uploading, and maneuvering could be supported by UAV technology. Moreover, security plays a crucial role in the commercial deployment of AVs. This article focuses on the role of futuristic technologies in securing such a critical environment. Specifically, we focus on the data-related security for which blockchain is leveraged. The role of other enabling technologies, such as artificial intelligence, in providing security to the integrated UAV–AV has also been discussed. Finally, we identify the outstanding research and development challenges that will provide new research avenues for the research community.
TL;DR: In this article , the authors present a fresh overview to summarize recent development and challenges for model compression, including network pruning, quantization, knowledge distillation, neural architecture search, and more.
Abstract: With the recent success of the deep neural networks (DNNs) in the field of artificial intelligence, the urge of deploying DNNs has drawn tremendous attention because it can benefit a wide range of applications on edge or embedded devices. Lightweight deep learning (DL) indicates the procedures of compressing DNN models into more compact ones, which are suitable to be executed on edge devices due to their limited resources and computational capabilities while maintaining comparable performance as the original. Currently, the approaches of model compression include but not limited to network pruning, quantization, knowledge distillation, neural architecture search. In this work, we present a fresh overview to summarize recent development and challenges for model compression.
TL;DR: In this article , a blockchain-enabled reliable, privacy-preserving authentication for fog-based IoT devices, named BPAF, is presented to achieve reliable authentication of fog nodes without violating the privacy of authenticated users during the authentication process.
Abstract: The development of IoT and fog computing promotes various kinds of authentication mechanisms for IoT devices. Traditional IoT authentication schemes are based on Public Key Infrastructure (PKI) where a centralized certificate authority is introduced. To mitigate the security, privacy, and reliability issues bring from the centralization, some blockchain-based authentication schemes have been presented to achieve decentralized authentication. Unfortunately, they cannot be directly used under the fog-based IoT environment, which consists of resource-constrained IoT devices. To mitigate these issues, we present a Blockchain-enabled reliable, and Privacy-preserving Authentication for Fog-based IoT devices, named BPAF. BPAF achieves reliable authentication of fog nodes without violating the privacy of authenticated users during the authentication process. Security analysis and experimental evaluations show that BPAF achieves privacy-preserving and reliable authentication with high efficiency for both the fog nodes and full nodes participating in the authentication process.
TL;DR: In this paper , the authors identify and discuss solutions under three main categories; direct integration, payment channel network, and new cryptocurrency design and evaluate the pros and cons of each of these approaches and then point out future research challenges.
Abstract: The successful amalgamation of cryptocurrency and consumer Internet-of-Things (IoT) devices can pave the way for novel applications in machine-to-machine economy. However, the lack of scalability and heavy resource requirements of initial blockchain designs hinder the integration, and it is unclear how consumer devices will be adopting cryptocurrency. Therefore, in this article, we critically review the existing integration approaches and cryptocurrency designs that strive to enable micropayments among consumer devices. We identify and discuss solutions under three main categories; direct integration, payment channel network, and new cryptocurrency design. The first approach utilizes a full node to interact with the payment system. Offline channel payment is suggested as a second-layer solution to solve the scalability issue and enable instant payment with low fee. New designs converge to semicentralized scheme and focus on lightweight consensus protocol that does not require high computation power. We evaluate the pros and cons of each of these approaches and then point out future research challenges. Our goal is to help researchers and practitioners to better focus their efforts to facilitate micropayment adoptions.
TL;DR: In this article , the authors exploit the correlation between 2D and 3D detection spaces, enabling 3-D boxes to leverage feature maps generated in image space, extracted through a proposal generation network that is enhanced and utilized for estimating accurate 3D detector and localization.
Abstract: Monocular 3-D object detection is a low-cost and challenging task for autonomous vehicles and robotics. Utilizing a monocular image for 3-D object detection is served as an auxiliary module for autonomous vehicles and is a growing concern recently. Currently, the expensive lidar and stereo cameras have a predominant performance on accurate 3-D object detection, whereas monocular-based methods are considerably lower in performance. This performance gap is minimized by reforming the monocular-based method as a single internal network. We exploit the correlation between 2-D and 3-D detection spaces, enabling 3-D boxes to leverage feature maps generated in image space. The 2-D and 3-D proposals are extracted through a proposal generation network that is enhanced and utilized for estimating accurate 3-D detection and localization. Experimental results on the KITTI dataset demonstrate that in comparison to other monocular object detection methods the proposed method considerably improved the accuracy of 3-D object detection. The mean average precision of 3-D object detection in front view is improved to 25% and the bird's eye view to 32% for the car class on a moderate difficulty level.
TL;DR: YOLOv3 as mentioned in this paper proposes a knowledge distillation loss for the prediction of previously learned knowledge without utilizing previous training data, and these predictions are updated while learning the current model.
Abstract: Deep learning models have revealed outstanding performance on image classification and object detection tasks. However, there is a crucial drop in performance when they are subject to learn new data incrementally in the absence of previous training data. They suffer from catastrophic forgetting—abrupt drop in performance. This phenomenon affects the implementation of artificial intelligence in practical scenarios. To overcome catastrophic forgetting, the previous method has either saved previous data in memory or generated the previous data. However, these methods are computationally complex and infeasible for real-time applications. In this article, we proposed the YOLOv3 as an object detection framework for incremental learning. A knowledge distillation loss is introduced for the prediction of previously learned knowledge without utilizing previous training data. Consequently, these predictions are updated while learning the current model. Experimental results on the Pascal VOC2007 indicate that the proposed method significantly improved the mean average precision up to 74% for two classes in comparison to the state-of-the-art methods.
TL;DR: In this article , the authors proposed a self-fining vehicle using blockchain infrastructure on top of the vehicular edge computing, which is a vehicle that detects and records driving violations, issues tickets, and pays fines without the need for a centralized management system.
Abstract: In recent years driving violations have increased in big and crowded cities specially in developing countries. This has resulted in the escalation of traffic congestions and number of accidents, making them difficult to handle by a central managing authority. New technologies can be used in order to mitigate this problem. Hence, in this article, we propose a novel concept, called self-fining vehicle, using blockchain infrastructure on top of the vehicular edge computing. Self-fining vehicle is a vehicle that detects and records driving violations, issues tickets, and pays fines without the need for a centralized management system. Violations can be coded into on-board units and detected by vehicular communications. The conceptual architecture of secure self-fining vehicle is proposed and discussed in this article. The proposed architecture improves violation data security, processing speed, and communication delay using encryption, authentication, blockchain, and edge computing (EC), enhancing quality of service and consumers’ quality of experience. The performance analysis of the proposed architecture proves its efficiency in terms of latency in service delivery.
TL;DR: In this article , a binocular camera system is designed to effectively solve the problems of distortion and coverage caused by monocular camera, and an image-stitching algorithm is developed to splice the images captured by the camera.
Abstract: The smart unmanned vending machine using machine vision technology suffers from the sharp decrease of detection accuracy due to the incomplete image collection of items by monocular camera in complex environment, and the lack of obvious features in dense stacking of items. In this article, a binocular camera system is designed to effectively solve the problems of distortion and coverage caused by monocular camera. Besides, an image-stitching algorithm is developed to splice the images captured by the camera, which reliefs the burden of computation for back-end recognition processing brought by the binocular camera. A new neural network structure-the YOLOv3-TinyE is proposed based on YOLOv3-tiny model. Based on the dataset of 21,000 images captured in real scenarios containing 20 different type of beverages, the comparison experimental results show that YOLOv3-TinyE model achieves the mean average precision of 99.15%, and the inference speed is 2.91 times faster than that of YOLOv3 model, and the detection accuracy of YOLOv3-TinyE model based on binocular vision is higher than that based on monocular vision. The results suggest that the designed method achieves the goal in terms of inference speed and average precision, that is, it is able to satisfy the requirements for real-world applications.