Urban region road network running state characteristic information extraction method

Abstract

The invention discloses an urban region road network running state characteristic information extraction method. The method comprises steps that, step 1, the road network data is acquired; step 2, a road network data input matrix is constructed; step 3, adaptive neighborhood selection is carried out; step 4, characteristic information extraction is carried out; and step 5, visual representation of the road network running state characteristic information is carried out. The method is suitable for urban region road network characteristic information extraction and road network running state representation, on the basis of road network flow, speed and density data, an adaptive neighborhood selection manifold learning method is utilized to extract the road network running characteristic information, the road network running characteristic information has macroscopic property, accuracy, sensitivity and practicality, a macroscopic road network running state can be timely represented, and analysis and decision bases are provided for traffic managers.

Description

technical field [0001] The invention relates to the field of intelligent transportation, in particular to a method for extracting characteristic information of regional road network operation status by adaptive neighborhood selection. Background technique [0002] The objective analysis of the regional road network operation status is the basis for its scientific management and control. However, due to the obvious confusion, complexity, ambiguity and concealment of the road network operation data, it is difficult to reasonably quantify the traffic status of the road network. Therefore, whether the operating state of the road network can be accurately and objectively represented, and the essential factors in the evolution process can be extracted has become an urgent problem to be solved. [0003] At the same time, with the continuous enrichment of traffic information collection methods, the types of data acquired are becoming more and more complex, the time interval of data ...

AI Technical Summary

Problems solved by technology

The application number is: 200910081852.7, the evaluation method of traffic service level based on parameters such as speed, flow, and occupancy proposed in the patent "Regional Traffic Service Level Micro-Indices and Evaluation Method", which focuses on expressing the micro-service level of traffic, and has no macroscopic road network A comprehensive analysis of the road network status cannot fully express the road network operation status; the application number is: 201210084221.2, and the patent "A Regional Traffic Status Evaluation Method" proposes a regional traffic status evaluation method based on the average travel time of the road section. This method only Using the average travel time as a parameter has certain limitations when expressing the state of the road network; the application number is: 201210325652.3, and a scope of application is proposed in the patent "Manifold Learning Adaptive Neighborhood Selection Algorithm Based on Curvature Prediction" The relatively broad curvature-based adaptive neighborhood selection method can effectively reduce the complexity of the manifold learning algorithm and find the optimal neighborhood size, but it does not point out the superiority of this method for traffic data feature extraction; the application number is : 201410057898.6, the patent "A traffic state division method based on semi-supervised machine learning" proposes a traffic state division method based on semi-supervised learning, which mainly uses information such as speed, flow rate, and the maximum speed limit of the road Calculate the maximum bandwidth of traffic and the maximum bandwidth of speed, and jointly compare and classify the state. The maximum speed limit of the road and the traffic and speed do not come from the same data source, and the data acquisition is complicated. The traffic data is data with category labels, and a supervised method is used. more suitable than semi-supervised methods

Images