A Graph Convolutional Method for Traffic Flow Prediction in Highway Network

As a transportation way in people’s daily life, highway has become indispensable and extremely important. Traffic flow prediction is one of the important issues for highway management. Affected by many factors, including temporal, spatial, and other external ones, traffic flow is difficult to accurately predict. In this paper, we propose a graph convolutional method. And the name of our model proposed is the hybrid graph convolutional network (HGCN), which comprehensively considers time, space, weather conditions and date type to achieve better predicted results of traffic flow at highway stations. Compared with baselines implemented by various machine learning models, all metrics of our model are reduced dramatically.

A mobile mapping system utilizing a spherical camera

The transportation departments belonging to respective provinces currently collect highway management data with the use of several methods and systems which include visual field inspections, survey methods, aerial photogrammetry, as well as mobile data acquisition systems. Spherical cameras offer an attractive alternative to standard mobile data acquisition devices for highway management systems as they provide full coverage with a single camera. Inclusion of such a camera requires methods of determining relative, interior and exterior orientation information, as well as bore-sight and lever arm determination. Specialized methods of mosaicking[sic] the imagery are also required. This paper focuses on exploring these methods for spherical cameras. Several computer programs were developed to solve for relative, interior, and exterior orientation parameters. It was concluded that a spherical camera can be efficiently utilized for highway data collection and provides full data coverage with a single camera system.

A mobile mapping system utilizing a spherical camera

The transportation departments belonging to respective provinces currently collect highway management data with the use of several methods and systems which include visual field inspections, survey methods, aerial photogrammetry, as well as mobile data acquisition systems. Spherical cameras offer an attractive alternative to standard mobile data acquisition devices for highway management systems as they provide full coverage with a single camera. Inclusion of such a camera requires methods of determining relative, interior and exterior orientation information, as well as bore-sight and lever arm determination. Specialized methods of mosaicking[sic] the imagery are also required. This paper focuses on exploring these methods for spherical cameras. Several computer programs were developed to solve for relative, interior, and exterior orientation parameters. It was concluded that a spherical camera can be efficiently utilized for highway data collection and provides full data coverage with a single camera system.

Traffic Status Dynamic Evaluation of an Eight-Lane Highway Based on the Lane Level

Traffic status analysis is the basis for highway management and control. Most of the previous research studies were carried out from the perspective of road segments. The purpose of this paper is to analyze the difference in traffic operation characteristics of an eight-lane highway from the perspective of lanes. Lane saturation, average lane speed, and lane density were selected as traffic state evaluation indicators, and the concept of state space division was introduced to classify the traffic operation status of each lane. Then, a single-system multi-index dynamic comprehensive evaluation method was adopted to reflect the time-varying characteristics and the development trend of the operation status of each lane. The research results can provide the theoretical support for more refined highway management and improve the service level of the eight-lane highway.

TOWARDS APPLICATION OF LANDINFRA STANDARD FOR HIGHWAY MANAGEMENT IN KOREA

This paper presents the modeling of the 44 registration subjects officially recorded in the road register of Korea to an international geospatial open standard. Due to current requirements, needs in road management and maintenance, road register data management must be improved as more data is accumulated and collected. Most importantly the metadata concerning road register assets is increasingly important in terms of data quality. This work discussed how OGC LandInfra international open standard will possibly be applied to the Korean Road Register for Highway Management and Maintenance. As a result, we proposed an OGC LandInfra standard-based road data model showing the standard can possibly be applied to the road register.

Granger Causality Analysis on PLUS Highway Traffic Network

PLUS Malaysia Berhad (PMB) is the largest toll expressway operator in Malaysia and South East Asia. Based on this reputation, PLUS handled thousands of vehicles every day. It covers the in-coming and out-coming traffic burdens from the northern areas to the southern areas. In order to manage these traffic burdens, toll plazas are located along this highway. Previous studies revealed that some of these toll plazas are important in managing the traffic burdens. This study analyze the importance of Skudai (SKD) toll plaza in Johor from 2009 until 2013. The causal relationship between SKD toll plaza with other toll plazas in Johor is studied to determine if there is any potential correlation or relationship of SKD with other toll plazas by using the Granger causality analysis. The findings show that there is a bidirectional Granger causality between SKD and Tangkak (TGK) as well as Machap (MAC) toll plazas. Meanwhile, there is only a unidirectional Granger causality between SKD and Yong Peng Utara (YPU) and Yong Peng Selatan (YPS) toll plazas. These results benefit the PLUS highway management to identify which potential toll plazas that can increase the traffic burden out from SKD toll plaza.