Highway Regional Classification Method Based on Traffic Flow Characteristics for Highway Safety Assessment

Accurate regional classification of highways is a critical prerequisite to implement a tailored safety assessment. However, there has been inadequate research on objective classification considering traffic flow characteristics for highway safety assessment purposes. We propose an objective and easily applicable classification method that considers the administrative divisions of South Korea. We evaluated the feasibility of this method through various theoretical analysis techniques using the data collected from 536 permanent traffic volume counting stations for the national highways in South Korea in 2019. The ratio of the annual average hourly traffic volume to the annual average daily traffic was used as the explanatory variable. The corresponding results of factor and cluster analyses with this ratio showed a 61% concordance with the urban, suburban, and rural areas classified by the administrative divisions. The results of two-sample goodness-of-fit tests also confirmed that the difference in the three distributions of hourly volume ratios was statistically significant. The results of this study can help enhance highway safety and facilitate the development and application of more appropriate highway safety assessment tools, such as Road Assessment Programs or crash prediction models, for specific regions using the proposed method.

Novel Classification of IoT Devices Based on Traffic Flow Features

The concept of IoT (Internet of Things) assumes a continuous increase in the number of devices, which raises the problem of classifying them for different purposes. Based on their semantic characteristics, meaning, functionality or domain of usage, the system classes have been identified so far. This research purpose is to identify devices classes based on traffic flow characteristics such as the coefficient of variation of the received and sent data ratio. Such specified classes can combine devices based on behavior predictability and can serve as the basis for the creation of network management or network anomaly detection classification models. Four generic classes of IoT devices where defined by using the classification of the coefficient of variation method.

Novel Classification of IoT Devices Based on Traffic Flow Features

The concept of IoT (Internet of Things) assumes a continuous increase in the number of devices, which raises the problem of classifying them for different purposes. Based on their semantic characteristics, meaning, functionality or domain of usage, the system classes have been identified so far. This research purpose is to identify devices classes based on traffic flow characteristics such as the coefficient of variation of the received and sent data ratio. Such specified classes can combine devices based on behavior predictability and can serve as the basis for the creation of network management or network anomaly detection classification models. Four generic classes of IoT devices where defined by using the classification of the coefficient of variation method.

Impacts of Autonomous Vehicles on Traffic Flow Characteristics under Mixed Traffic Environment: Future Perspectives

Vehicle automation and communication technologies are considered promising approaches to improve operational driving behavior. The expected gradual implementation of autonomous vehicles (AVs) shortly will cause unique impacts on the traffic flow characteristics. This paper focuses on reviewing the expected impacts under a mixed traffic environment of AVs and regular vehicles (RVs) considering different AV characteristics. The paper includes a policy implication discussion for possible actual future practice and research interests. The AV implementation has positive impacts on the traffic flow, such as improved traffic capacity and stability. However, the impact depends on the factors including penetration rate of the AVs, characteristics, and operational settings of the AVs, traffic volume level, and human driving behavior. The critical penetration rate, which has a high potential to improve traffic characteristics, was higher than 40%. AV’s intelligent control of operational driving is a function of its operational settings, mainly car-following modeling. Different adjustments of these settings may improve some traffic flow parameters and may deteriorate others. The position and distribution of AVs and the type of their leading or following vehicles may play a role in maximizing their impacts.

Bifurcation analysis of modified density gradient continuum traffic model

This paper proposes a new density gradient continuous traffic flow model, and analyzes the linear stability of the model, as well as the bifurcation type of the model. Numerical simulation of the new model verifies the usability of the model. From the perspective of system stability, the bifurcation analysis method is used to analyze the nonlinear traffic phenomena on the expressway. The equilibrium solution of the model is discussed. On this basis, Hopf bifurcation, saddle bifurcation and Bogdanov–Takens bifurcation are obtained, and the existence conditions and fractional types of Hopf bifurcation and saddle bifurcation are obtained. The traffic flow characteristics of Hopf bifurcation and saddle node bifurcation are analyzed.

Recognition Method of Vehicle Cluster Situation Based on Set Pair Logic considering Driver’s Cognition

The recognition of vehicle cluster situations is one of the critical technologies of advanced driving, such as intelligent driving and automated driving. The accurate recognition of vehicle cluster situations is helpful for behavior decision-making safe and efficient. In order to accurately and objectively identify the vehicle cluster situation, a vehicle cluster situation model is proposed based on the interval number of set pair logic. The proposed model can express the traffic environment’s knowledge considering each vehicle’s characteristics, grouping relationships, and traffic flow characteristics in the target vehicle’s interest region. A recognition method of vehicle cluster situation is designed to infer the traffic environment and driving conditions based on the connection number of set pair logic. In the proposed model, the uncertainty of the driver’s cognition is fully considered. In the recognition method, the relative uncertainty and relative certainty of driver’s cognition, traffic information, and vehicle cluster situation are fully considered. The verification results show that the proposed recognition method of vehicle cluster situations can realize accurate and objective recognition. The proposed anthropomorphic recognition method could provide a basis for vehicle autonomous behavior decision-making.

Traffic Flow Parameters Collection under Variable Illumination Based on Data Fusion

Accurate traffic flow parameters are the supporting data for analyzing traffic flow characteristics. Vehicle detection using traffic surveillance pictures is a typical method for gathering traffic flow characteristics in urban traffic scenes. In complicated lighting conditions at night, however, neither classical nor deep-learning-based image processing algorithms can provide adequate detection results. This study proposes a fusion technique combining millimeter-wave radar data with image data to compensate for the lack of image-based vehicle detection under complicated lighting to complete all-day parameters collection. The proposed method is based on an object detector named CenterNet. Taking this network as the cornerstone, we fused millimeter-wave radar data into it to improve the robustness of vehicle detection and reduce the time-consuming postcalculation of traffic flow parameters collection. We collected a new dataset to train the proposed method, which consists of 1000 natural daytime images and 1000 simulated nighttime images with a total of 23094 vehicles counted, where the simulated nighttime images are generated by a style translator named CycleGAN to reduce labeling workload. Another four datasets of 2400 images containing 20161 vehicles were collected to test the proposed method. The experimental results show that the method proposed has good adaptability and robustness at natural daytime and nighttime scenes.