Search

To better understand the research focus and development direction in the field of driving behavior active intervention, thereby laying a scientific foundation for further research, we used the combination of topic words and keywords to retrieve relevant articles from the Core Collection Database of Web of Science (WOS). A total of 578 articles published from 1992 to 2022 were finally obtained. Firstly, the time distribution characteristics, country distribution, institution distribution and main source journal distribution of published articles were explored. Then, by using the CiteSpace and VOSviewer software, cited reference co-citation analysis, keyword co-occurrence analysis and burst detection analysis were carried out respectively to visually explore the knowledge base, research topic, research frontier and development trend of this field. The results indicate that the USA, Australia and China are the three most active countries in the studies of driving behavior active intervention. Accidental Analysis & Prevention, Transportation Research Part F: Traffic Psychology and Behavior, and Journal of Safety Research are widely selected journals for publications related to this field. The research frontiers in the field of driving behavior active intervention focus on: “traffic safety and crashes analysis, as well as enforcement intervention”, “driving risk and education for young drivers”, “information provision and driving behavior”, “workload and situation awareness for automated driving”. It is worth noting that in recent years, “warning system”, “time”, “work load” have become research hotspots in this field. To sum up, by a bibliometric overview of research on driving behavior active intervention over the past thirty years, this paper clarifies the development skeleton of this research field, determines its hot topics and research progress, and provides a reference for the follow-up exploratory scientific research in this field.

The development of an efficient traffic incident detection system is essential for road safety risk warning and active safety control. Despite the fact that a large amount of traffic data can be collected from various detectors installed on expressways, the utilization rate of multisource data is still low, and the spatiotemporal traffic flow data need to be further mined. We propose a multilevel fusion method for the detection of traffic incidents, consisting of both data-level fusion and feature-level fusion. Accordingly, a macro and micro data-level fusion framework was developed, which created virtual detectors by converting video data into virtual loop data, thereby densifying the layout of the original loop detectors without increasing traffic facilities. Both sectional traffic flow data from loop detectors and single vehicle behavior data from video detectors were considered. Based on the fused data, several spatiotemporal variables are constructed to extract the spatiotemporal variation characteristics of traffic flow before and after an incident. The feature-level fusion framework made use of neural networks with a bidirectional encoding strategy to extract multisource features from various detectors and jointly encoded them to generate a comprehensive representation. Specifically, the inner networks extracted features from the multisource data, whereas the outer networks combined features from multiple single-source data to create a comprehensive representation for traffic incident detection. The results demonstrate that the model based on multisource data fusion was superior to single-source models. In addition, the performance of the proposed model was superior to that of the five common methods for detecting traffic incidents. Furthermore, the ablation experiments validated the advantages of key model components. [ABSTRACT FROM AUTHOR]