Traffic speed is one of the critical indicators reflecting traffic status of roadway networks. The abnormality and sudden changes of traffic speed indicate the occurrence of traffic congestions, accidents, and events. Traffic control and management systems usually take the spatiotemporal variations of traffic speed as the critical evidence to dynamically adjust the traffic signal timing plan, broadcast traffic accidents, and form a management strategy. Meanwhile, transport is multimodal in most cities, including vehicles, pedestrians, and bicyclists. Traffic states of different traffic modes are usually used simultaneously as the significant input of advanced traffic control systems, e.g., multiobjective traffic signal control system, connected vehicles, and autonomous driving. In previous studies, Wi-Fi and Bluetooth passive sensing technology was demonstrated as an effective method for obtaining traffic speed data. However, there are some challenges that greatly affect the accuracy the estimated traffic speed, e.g., traffic mode uncertainty and the errors caused by sensors’ detection range. Thus, this study develops a real-time method for estimating the multimodal traffic speed of road networks covered by Wi-Fi and Bluetooth passive sensors. To address the two identified challenges, an algorithm is developed to correct the biased estimated traffic speed based on the received signal strength indicator of Wi-Fi and Bluetooth signals, and a novel semisupervised Possibilistic Fuzzy $C$ -Means clustering algorithm is proposed for identifying traffic modes of Wi-Fi and Bluetooth device owners. The performance of the proposed algorithms is evaluated by comparing with the selected baseline algorithms. The experimental results indicate the superiority of the proposed algorithm. The proposed method of this study can provide accurate and real-time multimodal traffic speed information for supporting traffic control and management, and, thus, improving the operational performance of the whole road network.

A large number of charging piles installed on roadside parking spaces and smart poles on the roadside of the Internet have become essential substation infrastructure (roadside) for building a vehicle-road coordinated charging network for electric vehicles. The management system of China National Grid's network-load interaction includes the interaction between these main stations (traffic control stations) and substations (roadsides). The Internet-friendly interactive communication protocol for China's vehicle-road coordination is IEC 60870-5-104 (104 protocol). The control network of the vehicle-road collaborative charging network has many characteristics, such as multiple levels, multiple types, and frequent information exchange for monitoring and control. Various types of operational information and control commands are subject to eavesdropping, tampering, and interruption during collection, transmission, and triggering. This paper proposes a command-level anomaly detection (CAD) method for a vehicle-road collaborative charging network. The CAD method analyzes the protocol for the specification format and business command characteristics of the 104 protocol. This paper uses the dynamic analysis protocol fuzzy test to realize the dynamic information in the program to guide the generation of test cases and pass the Markov state transition diagram. We describe the state transition and abnormality identification of protocol messages. We also design a long-term memory network to implement instruction-level anomaly feature mining. The experiment proved the validity of CAD. If we adopt other new protocols for the vehicle-road coordinated network in different countries or regions, the analysis of the new protocol can be completed in the same way, which has strong application value and prospect.

In the cloud computing era, a paper recommender system is usually deployed on the cloud server and return recommendation results to readers directly. However, considering the paper recommender system, processing tremendous paper citation data on the cloud cannot provide fine-grained personalized and real-time recommendations for each reader because these recommended papers from the cloud are far from readers and probably not correlated strongly with each other for helping each reader research further and deeper in the interested field. Recently, the edge-cloud collaboration-based recommender system has been used for releasing parts of the cloud computing task to the edge and provides the recommendation near the client. Based on the edge computing recommender system, a keywords-driven and weight-aware paper recommendation approach is presented, namely, LP-PR_k+ (link prediction-paper recommendation), to enable intelligent, personalized, and efficient paper recommendation services in the mobile edge computing environment. Specifically, the whole paper recommendation process mainly covers two parts: optimizing the existing paper citation graph via introducing a weighted similarity (i.e., building a weighted paper correlation graph) and then recommending a set of correlated papers according to the weighted paper correlation graph and the users’ query keywords. Experiments on a real-world paper correlation dataset, Hep-Th, show the capability of our proposal for improving the paper recommendation performance and its superiority against other related solutions.