Modification of the traffic-mode split model under real-time informatization

Abstract The rapid advancement of intelligent transportation and real-time informatization enables travelers to choose the optimal traffic mode by considering dynamic traffic and path navigation information. In this case, the conventional Logit model is limited in predicting traffic modes. Firstly, the relationships between information and personal characteristics were given by analyzing the impact of real-time information on travelers’ behaviors. Then, the defects of the Logit model were pointed out. The Box-Cox of $${X}_{pin}^{\left({\lambda }_{p}\right)}$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:msubsup> <mml:mi>X</mml:mi> <mml:mrow> <mml:mi>pin</mml:mi> </mml:mrow> <mml:mfenced> <mml:msub> <mml:mi>λ</mml:mi> <mml:mi>p</mml:mi> </mml:msub> </mml:mfenced> </mml:msubsup> </mml:math> was modified to indicate the effect of informatization influence degree $${\lambda }_{\text{p}}$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:msub> <mml:mi>λ</mml:mi> <mml:mtext>p</mml:mtext> </mml:msub> </mml:math> on the utility function. Finally, the modified Logit model was verified based on the practical cases of Chengdu province, China. Based on the modified Logit model, the prediction accuracy of traffic modes significantly surpassed that of the conventional Logit model.