Currently, connected vehicles have gradually stepped into our daily lives, and they generally rely on vehicular networks to generate and exchange traffic-related messages to improve the overall travel safety and efficiency. However, due to the open nature of vehicular networks, these traffic-related messages could be erroneous, which may be caused by various reasons, ranging from an onboard device (OBD) sensor malfunctioning and reporting incorrect reading to the message being tampered by a malicious vehicle. To address these rapidly increasing security challenges, we have proposed an AI-enabled trust management system (AIT) in this article, which is an AI-enabled trust management system for vehicular networks using the blockchain technique. In the AIT system, each vehicle first senses, generates, and exchanges messages with other vehicles. These messages then get validated by the neighboring vehicles. As vehicles receive and validate messages from other nearby vehicles, they will establish and manage the trust of those nearby vehicles, which is enabled by utilizing the deep learning algorithm. Once a vehicle identifies untrustworthy vehicles, it reports them to the nearby roadside unit (RSU), and the RSU will validate the authenticity of the report as well as the identity of the vehicle by using the emerging blockchain technique. The security credentials of untrustworthy vehicles will then be revoked by the RSU. We have conducted an extensive experimental study to evaluate the AIT system. Simulation results clearly indicate that AIT performs better than existing approaches and can manage the trust of vehicles and detect malicious ones in an accurate and efficient manner.

Using the convolutional neural network (CNN) method for image emotion recognition is a research hotspot of deep learning. Previous studies tend to use visual features obtained from a global perspective and ignore the role of local visual features in emotional arousal. Moreover, the CNN shallow feature maps contain image content information; such maps obtained from shallow layers directly to describe low-level visual features may lead to redundancy. In order to enhance image emotion recognition performance, an improved CNN is proposed in this work. Firstly, the saliency detection algorithm is used to locate the emotional region of the image, which is served as the supplementary information to conduct emotion recognition better. Secondly, the Gram matrix transform is performed on the CNN shallow feature maps to decrease the redundancy of image content information. Finally, a new loss function is designed by using hard labels and probability labels of image emotion category to reduce the influence of image emotion subjectivity. Extensive experiments have been conducted on benchmark datasets, including FI (Flickr and Instagram), IAPSsubset, ArtPhoto, and Abstract. The experimental results show that compared with the existing approaches, our method has a good application prospect.

With the increase of the number of electric vehicles (EVs), it is of vital importance to develop the efficient and effective charging scheduling schemes for all the EVs. In this article, we aim to maximize the social welfare of all the EVs, charging stations (CSs) and power plant (PP), by taking into account the changing demand of each EV, the changing price, the capacity and the congestion balance between different CSs. To this end, two efficient scheduling algorithms, i.e., Centralized Charging Strategy (CCS) and Distributed Charging Strategy (DCS) are proposed. CCS has a slightly better performance than the DCS, as it takes all the information and make the decision in the central control unit. On the other hand, DCS dose not require the private information from EVs and can make decentralized decision. Extensive simulation are conducted to verify the effectiveness of the proposed algorithms, in terms of the performance, congestion balance, and computing complexity.

In this paper, we study a general Near-Far Computing Enhanced C-RAN (NFC-RAN), in which users can offload the tasks to the near edge cloud (NEC) or the far edge cloud (FEC). We aim to propose a profit-aware task allocation model by maximizing the profit of the edge cloud operators. We first prove that this problem can be transformed to a Multiple-Choice Multi-Dimensional 0-1 Knapsack Problem (MMKP), which is NP-hard. Then, we solve it by using a low complexity heuristic algorithm. The simulation results show that the proposed algorithm achieves a good tradeoff between the performance and the complexity compared with the benchmark algorithm.

With the fast development of mobile edge computing (MEC), user equipments (UEs) can enjoy much higher experience than before by offloading the tasks to its close edge cloud. In this paper, we assume there are several edge clouds, each of which has limited resource. We aim to maximize the number of offloaded tasks and minimize the energy consumption of all the UEs and edge clouds, by selecting the best edge cloud for each UE to offload. We formulate the problem as a mixed-integer non-convex optimization, which is difficult to solve in general. By transforming this problem into a minimum-cost maximum-flow (MCMF) problem, we can solve it efficiently. The simulation shows that our proposed algorithm has better performance and lower complexity than the conventional solutions.

Background modeling plays an important role for video surveillance, object tracking, and object counting. In this paper, we propose a novel deep background modeling approach utilizing fully convolutional network. In the network block constructing the deep background model, three atrous convolution branches with different dilate are used to extract spatial information from different neighborhoods of pixels, which breaks the limitation that extracting spatial information of the pixel from fixed pixel neighborhood. Furthermore, we sample multiple frames from original sequential images with increasing interval, in order to capture more temporal information and reduce the computation. Compared with classical background modeling approaches, our approach outperforms the state-of-art approaches both in indoor and outdoor scenes.

In this paper, a congestion balanced green charging networks is proposed for the electric vehicles (EVs) in smart grid. Firstly, a problem about the congestion probability balance among the charging stations (CSs) is analyzed and formulated, and then a two-layer optimization model is established based on the profit functions of power plant (PP), CSs and EVs. In the first layer, the optimal generation capacities as well as the charging capacities of CSs are determined, while in the second layer, the sum of each CS's profit and that of the EVs which want to charge at the CS is formulated as a profit maximization problem. The two-layer optimization model solves the congestion probability balance problem in the iterative manner, and finally the congestion balanced smart charging algorithm (CBSCA) is obtained. By comparing with other benchmarks, the results show that CBSCA is converged in an acceptable time, and the congestion probabilities among the CSs are balanced.

In this paper, we consider a smart power model, where some subscribers share several energy providers and there are some malicious users in this power grid. The energy providers are managed by a power market scheduling center (PMSC), which broadcasts electricity price to subscribers and energy providers. The energy providers and subscribers update their capacities and energy consumption requirements, respectively, according to the electricity prices received. In order to identify the malicious users and the unstable energy providers, the mechanism of identification and processing (MIP) for the malicious users and unstable energy providers is proposed. By integrating the MIP, we proposed a heuristic algorithm called the dynamic pricing algorithm with malicious users and unstable energy providers (DPAMU) to get the optimal electricity price as well as the optimal power requirement and the load capacity. Finally, the simulation results show that the proposed DPAMU has good convergence performance and can shave and clip the peak load effectively.