Ming Luo¹, Huili Dou², Ning Zheng^3,*

CMC-Computers, Materials & Continua, Vol.78, No.1, pp. 265-282, 2024, DOI:10.32604/cmc.2023.040067

Abstract Traffic prediction already plays a significant role in applications like traffic planning and urban management, but it is still difficult to capture the highly non-linear and complicated spatiotemporal correlations of traffic data. As well as to fulfil both long-term and short-term prediction objectives, a better representation of the temporal dependency and global spatial correlation of traffic data is needed. In order to do this, the Spatiotemporal Graph Neural Network (S-GNN) is proposed in this research as a method for traffic prediction. The S-GNN simultaneously accepts various traffic data as inputs and investigates the non-linear correlations between the variables. In terms… More >

Hideki Fujii¹, Shinobu Yoshimura¹

CMES-Computer Modeling in Engineering & Sciences, Vol.88, No.1, pp. 49-64, 2012, DOI:10.3970/cmes.2012.088.049

Abstract Recently, global warming issues have been discussed all over the world. Of the total amount of CO₂ emitted in Japan, a transportation sector is responsible for 20%. In the transportation sector, 90% of the emission is due to road traffic. This amount must be reduced drastically to realize a low-carbon society. To do so, various measures have been discussed, and the effects of the measures must be estimated quantitatively. In conventional measurement methods, the amount of vehicle emission is simply calculated by multiplying travel distance or gasoline consumption by a specified emission coefficient. Such an approach neglects the effects of… More >