Baotian Dong

Traffic state classification and relevance calculation at intersections are both difficult problems in traffic control. In this paper, we propose an intersection relevance model based on a temporal graph attention network, which can solve the above two problems at the same time. First, the intersection features and interaction time of the intersections are regarded as input quantities together with the initial labels of the traffic data. Then, they are inputted into the temporal graph attention (TGAT) model to obtain the classification accuracy of the target intersections in four states—free, stable, slow moving, and congested—and the obtained neighbouring intersection weights are used as the correlation between the intersections. Finally, it is validated by VISSIM simulation experiments. In terms of classification accuracy, the TGAT model has a higher classification accuracy than the three traditional classification models and can cope well with the uneven distribution of the number of samples. The information gain algorithm from the information entropy theory was used to derive the average delay as the most influential factor on intersection status. The correlation from the TGAT model positively correlates with traffic flow, making it interpretable. Using this correlation to control the division of subareas improves the road network’s operational efficiency more than the traditional correlation model does. This demonstrates the effectiveness of the TGAT model’s correlation.

Complete traffic sensor data is a significant prerequisite for analyzing the changing rules of traffic flow and formulating traffic control strategies. Nevertheless, the missing traffic data are common in practice. In this study, an improved Fuzzy C-Means algorithm is proposed to repair missing traffic data, and three different repair modes are established according to the correlation of time, space, and attribute value of traffic flow. First, a Twice Grid Optimization (TGO) algorithm is proposed to provide a reliable initial clustering center for the FCM algorithm. Then the Sparrow Search Algorithm (SSA) is used to optimize the fuzzy weighting index m and classification number k of the FCM algorithm. Finally, an experimental test of the traffic sensor data in Shunyi District, Beijing, is employed to verify the effectiveness of the TGO-SSA-FCM. Experimental results showed that the improved algorithm had a better performance than some traditional algorithms, and different data repair modes should be selected under different miss rate conditions.

The correlation degree between nodes of urban traffic network is the basis of sub-area division, and the signal coordination control in sub-area is very effective to improve the traffic efficiency of road network. In this paper, based on the study of unsaturated traffic state, the paper first analyzes the shortcomings of the existing correlation degree model, and constructs a comprehensive correlation degree model to measure the relationship between the two nodes by considering the factors of section spacing, section flow, signal period, traffic flow dispersion and queue length. Through VISSIM simulation experiment, the examples of 15 sections of 10 nodes are compared with the classical Whitson model and the merging index. The sub-region based on the DBSCAN algorithm is more close to reality, which can provide a good basis for the signal coordination strategy.

.In order to implement signal control more effectively and improve the operating efficiency of urban traffic systems, this paper proposes a control sub-area division method based on an improved FN division algorithm. Comprehensively consider the intersection spacing, link flow, traffic dispersion, signal cycle, link traffic state and other factors, respectively calculate the correlation degrees of link flow, the intersection signal cycle,the link traffic state of adjacent intersections.Then its introduce the intersection correlation degree to improve the FN algorithm to divide the regional road network traffic district. Finally, the paper select the regional traffic data of Beijing’s road network to verify the model. The result shows that the sub-area division based on improved FN algorithm is more reasonable and effective.

The existing cloud data models cannot meet the management requirements of structured data very well including a great deal of relational data, therefore a two-layer cloud data model is proposed. The composite object is defined to model the nested data in the representation layer, while a 4-tuple is defined to model the non-nested data in the storage layer. Referring the relational algebra, the concept of SNO (Simple Nested Object) is defined as basic operational unit of the algebraic operations; the formal definitions of the algebraic operations consisting of the set operations and the query operations on the representation layer are proposed. The algorithm of extracting all SNOs from a CAO (Component-Attribute-Object) set of a composite object is proposed firstly as the foundation, and then as the idea; the pseudo code implementation of algorithms of the algebraic operations on the storage layer are proposed. Logic proof and example proof indicate that the definition and the algorithms of the algebraic operations are correct.

The decrease of station service level of urban rail transit (URT) is caused by passenger flow congestion, especially in peak hours. It seriously influences the safety of URT daily operation. The existing evaluation methods mainly depend on pedestrian flow indexes. In this paper, a new evaluation method based on travel time delay using the mining technology of automatic fare collection (AFC) data is proposed to provide passenger-oriented service information by synthetic indexes: congestion delay, generalized stranded times, and the number of stranded passengers. To avoid the transfer influence, we selected the specific data, whose origin station and destination station are in the same line. Finally, Beijing Subway is used as a case study to verify this method. Results suggest that the proposed method can effectively assess the station service level.