Vehicular Ad-Hoc Networks (VANETs), as the crucial support of Intelligent Transportation Systems (ITS), have received great attention in recent years. With the rapid development of VANETs, various services have generated a great deal of data that can be used for transportation planning and safe driving. Especially, with the advent of Coronavirus Disease 2019 (COVID-19), the transportation system has been impacted, thus novel modes of transportation planning and intelligent applications are necessary. Digital twins can provide powerful support for artificial intelligence applications in Transportation Big Data (TBD). The features of VANETs are varying, which arises the main challenge of digital twins applying in TBD. Network traffic prediction, as part of digital twins, is useful for network management and security in VANETs, such as network planning and anomaly detection. This paper proposes a network traffic prediction algorithm aiming at time-varying traffic flows with a large number of fluctuations. This algorithm combines Deep Q-Learning (DQN) and Generative Adversarial Networks (GAN) for network traffic feature extraction. DQN is leveraged to carry out network traffic prediction, in which GAN is involved to represent Q-network. Meanwhile, the generative network can increase the number of samples to improve the prediction error. We evaluate the performance of our method by implementing it on three real network traffic data sets. Finally, we compare the two state-of-the-art competing methods with our method.

Networked radar systems are vulnerable to different types of attacks, including electronic countermeasure (ECM) jamming and false data injection (FDI) attack. Substantial research has concentrated on ECM jamming, which interferes with radar echoes between a radar and targets. However, FDI attack in which an attacker somehow replaces or modifies radars' measurements, has rarely been considered. FDI attack is much stealthier than ECM jamming, making detection more difficult. In this paper, we take the first attempt to investigate the FDI attack's effects on a networked radar system. Further, we propose a novel data fusion algorithm to combat this attack. The proposed algorithm can dramatically reduce the attack's adverse effects, since it creatively introduces data's confidence factors into data fusion and adaptively decreases the fusion weights of the injected data. Numerical results verify the effectiveness of the proposed algorithm.

In his blogs of 2012, Dr. Göte Nyman coined Internet of Behaviors (IoB). In his idea, people’s behaviors are very good predictors of their needs, and hence technology companies can network human behaviors and construct behavior-based systems to deliver more timely, responsive, and intelligent services with privacy protection. In 2020, Gartner ranked IoB first among its top nine strategic technology trends and suggested that IoB would touch almost half of the world population. Built on his core idea of IoB, this paper is the first one to comprehensively, systematically, and deeply introduce the IoB concept, essential features, architecture, enabling technologies, applications, and open research issues. In this paper, we first give a formal definition and classification of IoB and reveal its fundamental difference from Internet of Things (IoT). Then, we propose a five-layer IoB architecture (consisting of behavior perception, behavior networking, behavior computing, service provision, and security/privacy) and provide the in-depth analysis of IoB enabling technologies. Particularly, we discuss functional requirements and possible fields of an IoB address (i.e., a human behavior identifier), present the networking and maintenance approaches to behaviors, explore four important implications of behavior computing, i.e., intention inference, behavior derivation, behavior programming, and behavior-chain optimization, as well as give a decentralized privacy-protection solution to Dr. Nyman’s behavior-identity-separation idea. Next, we deeply investigate potential IoB applications in smart home/transportation/healthcare/business, and human-robot interaction. Finally, we provide insightful discussions on open research issues. This paper should help researchers and practitioners understand IoB quickly and promote future IoB development.

Clustering is a fundamental and effective technique for utilizing sensor nodes’ energy and extending the network lifetime for wireless sensor networks. In this paper, we propose a novel clustering protocol, LECP-CP (local energy consumption prediction-based clustering protocol), the core of which includes a novel cluster head election algorithm and an inter-cluster communication routing tree construction algorithm, both based on the predicted local energy consumption ratio of nodes. We also provide a more accurate and realistic cluster radius to minimize the energy consumption of the entire network. The global energy consumption can be optimized by the optimization of the local energy consumption, and the energy consumption among nodes can be balanced well. Simulation results validate our theoretical analysis and show that LECP-CP has high efficiency of energy utilization, good scalability and significant improvement in the network lifetime.