Space-assisted vehicular networks (SAVN) provide seamless coverage and on-demand data processing services for user vehicles (UVs). However, ultra-reliable and low-latency communication (URLLC) demands imposed by emerging vehicular applications are hard to be satisfied in SAVN by existing computation offloading techniques. Traditional deep reinforcement learning algorithms are unsuitable for highly dynamic SAVN due to the underutilization of environment observations. An AsynchronouS federaTed deep Q-learning (DQN)-basEd and URLLC-aware cOmputatIon offloaDing algorithm (ASTEROID) is presented in this paper to achieve throughput maximization considering the long-term URLLC constraints. Specifically, we first establish an extreme value theory-based URLLC constraint model. Second, the task offloading and computation resource allocation are decomposed by employing Lyapunov optimization. Finally, an asynchronous federated DQN-based (AF-DQN) algorithm is presented to address the UV-side task offloading problem. The server-side computation resource allocation is settled by an queue backlog-aware algorithm. Simulation results verify that ASTEROID achieves superior throughput and URLLC performances.

The huge amount of data produced in the 6G networks not only brings new challenges to the reliability and efficiency of mobile devices but also drives rapid development of new storage techniques. With the benefits of fast access speed and high reliability, NAND flash memory has become a promising storage solution for the 6G networks. In this paper, we investigate a protograph-coded bit-interleaved coded modulation with iterative detection and decoding (BICM-ID) utilizing irregular mapping (IM) in the NAND flash-memory systems. First, we propose an enhanced protograph-based extrinsic information transfer (EPEXIT) algorithm to facilitate the analysis of protograph codes in the IM-BICM-ID systems. With the use of EPEXIT algorithm, a simple design method is conceived for the construction of a family of high-rate protograph codes, called irregular-mapped accumulate-repeat-accumulate (IMARA) codes, which possess excellent decoding thresholds and linear-minimum-distance-growth property. Furthermore, motivated by the voltage-region iterative gain characteristics of IM-BICM-ID systems, a novel read-voltage optimization scheme is developed to acquire accurate read-voltage levels, thus minimizing the decoding thresholds (in dB) of protograph codes. Analyses and simulations indicate that the proposed IMARA-aided IM-BICM-ID scheme and read-voltage optimization scheme remarkably improve the convergence and decoding performance of flash-memory systems. Thus, the proposed protograph-coded IM-BICM-ID can be viewed as a reliable and efficient storage solution for the new-generation mobile networks, such as Internet of Vehicles.

The increasing number of Unmanned Aerial Vehicles (UAVs) in the low-altitude airspace and the increasing complexity of the work environment present new challenges for ensuring airspace security, especially the effective conflict detection and resolution (CD&R) of UAVs. In the era of the sixth generation (6G) technology, there is an improvement in communication speed and capacity in comparison with the traditional communication technologies, which contributes to forming a UAV Internet of Things (IoTs) through remote intelligent control platform and improve the effect of CD&R. In this paper, we innovatively develop a cooperative CD&R method in the UAV IoT environment considering UAV relative motion relationships and UAV priorities. Using this method in 6G environment, the real-time and reactive conflict-free paths for UAVs can be generated. The developed method has the advantage of smaller calculation and needs fewer UAVs to take maneuvers than the CD&R methods based on traditional Artificial Potential Field (APF). To verify the effectiveness of CD&R methods, a safety assessment method (evaluate from both conflict feature and network structure perspectives) is also proposed. A Monte Carlo Simulation with ``clone mechanism'' is designed to incorporate the effect of CD&R systems. Three cases of distributed CD&R protocols are simulated and compared. The simulations with different parameter settings are also discussed. Quantitative simulation experiments show that the safety effect of CD&R proposed in this paper is improved a lot due to the improved APF and the UAV priority determination. Meanwhile, the safety assessment method is demonstrated to be feasible for evaluating the safety of CD&R systems.

In recent years, the increasing prevalence of Intelligent Transportation Systems with advanced technologies has led to the emergence of many targeted forms of malware such as ransomware, Trojans, viruses, and malicious mining programs. And malware authors use policies like category disguise or family obfuscation in malware components to evade detection, which poses a great security threat to enterprises, government agencies, and Internet users. In this paper, we propose a malware family classification approach based on multimodal fusion and weight self-learning. Firstly, multiple modalities of malware such as byte, format, statistic, and semantic are fused in various ways to generate effective features. And then, we creatively add a weight self-learning mechanism of malware families into the classification model, which works by continuously calculating log-loss based on the family label and the probabilities predicted by each feature. The approach proves to achieve excellent classification performance on highly imbalanced malware family datasets with high efficiency and small resource overhead, which helps to identify and classify malware families and enhance the efficiency of massive malware analysis in Intelligent Transportation Systems.

The number of affirmed COVID-19 cases showed an enormous increase in the recent past throughout the globe. Keeping in view the catastrophic destruction of this devastating virus, there is a must-need situation to maximize the use of existing healthcare technologies such as the healthcare Internet of Things (H-IoT). In healthcare, patient wearable devices are widely recognized as a dormant technology with enormous capabilities to assess and combat various diseases, e.g., cough, seizure, temperature, heartbeat, and so on. As we know, in the H-IoT, patient-wearable devices are dispersed in an infrastructure-free environment that exposes them to several private and public coercion while accumulating and transmitting high sensitive data over the wireless communication channel. Therefore, security is the main concern of these applications, and thus, the primary focus of this article to outline the limitations and challenges in the present literature from 2019 to 2021, to identify the requirements of H-IoT applications used in the context of COVID-19. Following this, we will move one step ahead to explore the current security techniques adopted in these applications. Consequently, we will identify the network architectural, cryptographic, protocols, and operational security challenges during our study to recommend viable research directions and opportunities, which could be helpful and capable to minimize the network architecture, deployment, and maintenance cost with more productive outcomes.

In this paper, we present a three-byte-based Media Access Control (MAC) protocol to resolve the mutual authentication problem in an Autonomous Internet of Vehicles (AIoV) network. Initially, the network architecture is divided into two chains, i.e. the local and public chain, wherein the local chain the authentication and communication process is controlled by Cluster head (CH), while in the public chain it is controlled by the base station (BS). The proposed paradigm uses the 48-bit MAC address of the vehicle’s embedded sensors for authentication, with the ability to alter the authentication parameters by triggering the last three bytes (24 bits) of the MAC address with a predetermined time interval. Persistent triggering of the last three bytes of an AIoV’s MAC address guarantees its integrity in the network because only legal vehicles are capable of initiating and validating the authentication request with the other vehicles in the network. Initially, the MAC addresses of all AIoVs are registered with the BS in the public chain through the concerned CH. Likewise, the MAC-address triggering of registered AIoVs is carried out in the BS with a defined time period and broadcasted in the public chain, which is further distributed through CHs in the local chain. Most of the computation is supervised by BS and CH in the public and local chains respectively, which minimize the client-side authentication complexity and enhances network efficiency in terms of authentication with 98.3% detection rate, communications, and computing costs, along with 11% improvement in the latency, 15% improvement in packet loss ratio (PLR), and throughput.

Light-field (LF) cameras, also known as plenoptic cameras, permit the recording of the 4D LF distribution of target scenes. However, many times, surface errors of a microlens array (MLA) are responsible for degradation in the images captured by a plenoptic camera. Additionally, the limited pixel count of the sensor can cause missing parallax information. The aforementioned issues are crucial for creating accurate maps for Intelligent Autonomous Transport System (IATS), because they cause loss of LF information, and need to be addressed. To tackle this problem, a learning-based framework by directly simulating the LF distribution is proposed. A high-dimensional convolution layer with densely sampled LFs in 4D space and considering a soft activation function based on ReLU segmentation correction is used to generate a superresolution (SR) LF image, improving the convergence rate in the deep learning network. Experimental results show that our proposed LF image reconstruction framework outperforms the existing state-of-the-art approaches; specifically, it is effective for learning the LF distribution and generating high-quality LF images. Different image quality assessment methods are used to evaluate the performance of the proposed framework, such as PSNR, SSIM, IWSSIM, FSIM, GFM, MDFM, and HDR-VDP. Additionally, the computational efficiency was evaluated in terms of number of parameters and FLOPs, and experimental results demonstrated that our proposed framework reached the highest performance in most of the datasets used.

Online advertising utilizes the Internet technique to deliver marketing messages to promotional consumers. It is growing in recent years to facilitate the increasing demands of electronic commerce. Advertisers bid and pay for the advertisement whenever potential customers click it. The way of Pay-Per-Click (PPC) is vulnerable to malicious clicks that mimic real user behaviour to trick the platform into counting their clicks as legitimate. It causes massive financial losses on advertisers and also significantly reduces the credibility of online advertising platforms. The common strategies to detect fraud clicks are dynamically tailoring and interpreting data based on the machine learning model. These algorithms treat multi-dimensional data as an individual feature vector or matrix, making it different to explore intrinsic relations among a sequence of data. Million daily fraud clicks on various types further disperse the focus of models and result in relatively low efficiency for the current fraud prediction system. To tackle the fraud click problem, we introduce a tensor-based mechanism to predict fraud clicks. This paper considered reconstructing data into a high-rank tensor, implement tensor decomposition and transformation to explore hidden information under each data and explore the joined effect among a sequence of data. The proposed tensor transformation algorithm with locality-sensitive hashing (LSH) is tested by extensive experiments using real-world data. Compared with the state-of-art machine learning algorithms, our model can achieve significant performance in terms of accuracy and prediction-recall rate.

Joint angle error of robotic arm has great impacts on the accuracy of the end-effector, which is critical in industrial applications. Therefore, in this article, an online cognitive joint angle error compensation method based on incremental learning is proposed to reduce joint angle error. The proposed method consists of a joint angle error solver and a compensation module, which ensure that the robot can obtain effective joint angle compensation in various situations. The joint angle error solver is used to solve joint angle error online. It uses the redundant constraint method for multilink position measurement so as to calculate the position error of the robot accurately later. The compensation module uses the self-feedback incremental fuzzy neural network (SFIFN) to predict and update the compensation in real time. SFIFN is a variant of the fuzzy neural network (FNN), which uses long short-term memory to introduce a feedback mechanism based on FNN. The incremental learning capability of SFIFN reduces the time for solving error and makes the module runs in real time. Specifically, two inertial measurement units mounted at the ends of links are used to measure pose changes of the ends of corresponding links. Both the simulated and the real experiments show that the proposed method yields good compensations to joint angle error and its potentials for smart manipulation.

Existing task offloading mechanisms are developed on some single and rigid quality of service (QoS) performance metrics, which is widely apart from satisfying the true intent of a user vehicle (UV), thereby resulting in low quality of experience (QoE), large queuing latency, and poor reliability. There is an unprecedented demand for an intent-aware task offloading strategy that provides improved QoE and guarantees reliability. In this paper, we develop a novel task offloading framework for air-ground integrated vehicular edge computing (AGI-VEC), which is called the learning-based Intent-aware Upper Confidence Bound (IUCB) algorithm. IUCB enables a UV to learn the long-term optimal task offloading strategy while satisfying the long-term ultra-reliable low-latency communication (URLLC) constraints in a best effort way under information uncertainty. IUCB can achieve three-dimension intent awareness including QoE awareness, URLLC awareness, and trajectory similarity awareness. Simulation results demonstrate that IUCB significantly outperforms existing EMM, sleeping-UCB, and UCB mechanisms in terms of QoE, end-to-end delay, queuing delay, throughput, and times of task offloading failure.

The analysis for social networks, such as the socially connected Internet of Things, has shown a deep influence of intelligent information processing technology on industrial systems for Smart Cities. The goal of social media representation learning is to learn dense, low-dimensional, and continuous representations for multimodal data within social networks, facilitating many real-world applications. Since social media images are usually accompanied by rich metadata (e.g., textual descriptions, tags, groups, and submitted users), simply modeling the image is not effective to learn the comprehensive information from social media images. In this work, we treat the image and its textual description as multimodal content, and transform other metainformation into the links between contents (such as two images marked by the same tag or submitted by the same user). Based on the multimodal content and social links, we propose a Deep Attentive Multimodal Graph Embedding model named DAMGE for more effective social image representation learning. We introduce both small- and large-scale datasets to conduct extensive experiments, of which the results confirm the superiority of the proposal on the tasks of social image classification and link prediction.

In this article, we propose a downlink non-orthogonal multiple access (NOMA) based coordinated direct and relay system with one cell-center user and multiple cell-edge users, where a decode-and-forward (DF) relay bridges the connection between the base station and the cell-edge users. Both full-duplex (FD) and half-duplex (HD) protocols are considered for the relay. We assume that the performance of the cell-edge users is subjected to the relay, and the cancellation of the mutual interference between the relay and cell-center user is imperfect. Both the exact analytical expression of outage probability and an approximate expression of the ergodic sum rate at high signal-to-noise ratio (SNR) are derived. Numerical results demonstrate that: 1) the FD relaying NOMA system outperforms the HD relaying NOMA system at low SNR, but the situation is exactly the opposite at high SNR; 2) the mutual interference can cause a larger performance gap than the self-interference at the relay; 3) the power allocation coefficients for the cell-center user and relay can affect the performance more significantly than those for cell-edge users.11This article was presented in part at the IEEE International Workshop on Signal Processing Advances in Wireless Communications 2019 [1].

Currently, blockchain technology has been widely used due to its support of transaction trust and security in next generation society. Using Internet of Things (IoT) to mine makes blockchain more ubiquitous and decentralized, which has become a main development trend of blockchain. However, the limited resources of existing IoT cannot satisfy the high requirements of on-demand energy consumption in the mining process through a decentralized way. To address this, we propose a decentralized on-demand energy supply approach based on microgrids to provide decentralized on-demand energy for mining in IoT devices. First, energy supply architecture is proposed to satisfy different energy demands of miners in response to different consensus protocols. Then, we formulate the energy allocation as a Stackelberg game and adapt backward induction to achieve an optimal profit strategy for both microgrids and miners in IoT. The simulation results show the fairness and incentive of the proposed approach.