Automatic intersection identification and extraction are an important foundation for urban road network updates and traffic network analysis and modeling. Existing intersection extraction methods based on steering angles and stopping points suffer from inadequate sampling amounts and threshold settings. To address this problem, we propose a road network intersection automatic extraction method based on vehicle trajectory intersection clustering. First, the continuous trajectory segments are extracted from trajectory data based on the sampling interval. Second, the maximum reconstruction error method is developed to extract straight-line trajectory segments from continuous trajectory segments. The overlapped straight-line trajectory segments belonging to the same direction are merged to reduce the number of segments and enhance road network patterns. To further improve the calculation efficiency of the intersection points of straight-line segments, bounding box filtering and orthogonal filtering are used to filter the straight-line trajectory segments that do not have an intersection relationship. Finally, the obtained straight-line segment intersection points are clustered using a density peak clustering algorithm. The road intersections are automatically extracted using the clustering center. The experimental results on real vehicle trajectories in Lianyungang City show that the proposed method performs well on intersection recognition and calculation efficiency.

Multi-intersection cooperative control for arterial or network scenarios is a crucial issue in urban traffic management. Multi-agent reinforcement learning (MARL) has been recognised as an efficient solution and shows outperformed results. However, most existing MARL-based methods treat intersection equally, ignoring different importance of each intersection, such as high traffic volume, connecting multiple main roads, serving as entry or exit point for highways or commercial areas, etc. Besides, learning efficiency and practicality remain challenges. To address these issues, this paper proposes a novel importance-aware MARL-based method named IALight for traffic optimisation control. First, a normalised traffic pressure is introduced to ensure our state and reward design can accurately reflect the status of intersection traffic flow. Second, a reward adjustment module is designed to modify the reward based on intersection importance. To enhance practicality and safety for real-world applications, we adopt a green duration optimisation strategy under a cyclic fixed phase sequence. Comprehensive experiments on both synthetic and real-world traffic scenarios demonstrate that the proposed IALight outperforms the traditional and deep reinforcement learning baselines by more than 20.41% and 17.88% in average vehicle travel time, respectively.

GPS trajectory data in intersections are series data with different lengths. Dynamic time wrapping (DTW) is good to measure the similarity between series with different lengths, however, traditional DTW could not deal with the inclusive relationship well between series. We propose a unified generalized DTW algorithm (GDTW) by extending the boundary constraint and continuity constraint of DTW and using the weighted local distance to normalize the cumulative distance. Based on the density peak clustering algorithm DPCA using asymmetric GDTW to measure the similarity of two trajectories, we propose an improved DPCA algorithm (ADPC) to adopt this asymmetric similarity measurement. In experiments using the proposed method, the number of clusters is reduced.

Accurate traffic state prediction plays an important role in traffic guidance, travel planning, etc. Due to the existence of complex spatio-temporal relationships, there are some challenges in forecasting. Firstly, in terms of spatial correlation, some models only consider the road network structure information, and ignore the relative location relationships between nodes. Secondly, some models ignore the different impacts of nodes in the global road network on traffic. To solve these problems, we propose a new traffic state-forecasting model, namely, spatio-temporal attention-gated recurrent neural network (ST-AGRNN). In the proposed model, structure-based and location-based localized spatial features are obtained simultaneously by Graph Convolutional Networks (GCNs) and DeepWalk. The localized temporal features are obtained by gated recurrent unit (GRU). The attention-based approach is used to obtain global spatio-temporal features. Experimental validation is performed with two real-world public datasets, and the results show that the ST-AGRNN model outperforms the state-of-the-art methods.

Urban road intersection recognition and feature extraction are crucial for road network modeling and traffic flow analysis. This paper proposes a novel method of intersection recognition and feature extraction based on vehicle trajectory data. First, valid spatial-temporal continuous trajectory segments of each vehicle are obtained by time differences analysis between adjacent trajectory points. Second, based on the basis that the turning behaviors of vehicles mostly occurring at the intersection area, the turning angles are calculated, and the valid turning points are extracted as the samples of clustering algorithm. Finally, the density peak clustering algorithm (DPCA) is used to recognize the intersections from road network which reconstructed from the vehicle trajectory data. The experiment on real-world vehicle navigation trajectories in the city of Lianyungang shows that the proposed method is able to recognize intersection accurately with scalability.

Due to the tiny and delicate structure of the cochlea, the auditory system is the most sensitive to explosion impact damage. After being damaged by the explosion impact wave, it usually causes long-term deafness, tinnitus, and other symptoms. To better understand the influence of impact load on the cochlea and basilar membrane (BM), a three-dimensional (3D) fluid-solid coupling finite element model was developed. This model accurately reflects the actual spatial spiral shape of the human cochlea, as well as the lymph environment and biological materials. Based on verifying the reliability of the model, the curve of impact load-amplitude response was obtained, and damage of impact load on the cochlea and the key macrostructure-BM was analyzed. The results indicate that impact wave at middle frequency has widest influence on the cochlea. Furthermore, impact loading causes tears in the BM and destroys the cochlear frequency selectivity.