Tai-Yu Ma

Mode choice with latent preference heterogeneity: a case study for employees of the EU institutions in Luxembourg

In this study, we apply a latent class choice modelling approach to the employees of the European Investment Bank and the Court of Justice of the European Union in Luxembourg to investigate commuting mode choice behaviour by incorporating individual preference heterogeneity. We found a two-segment preference differentiation of mode choice behaviour determined by their household locations, attitudes towards transport modes as well as their socio-demographic characteristics. Validity and overall goodness-of-fit are compared with a conditional multinomial Logit model. The empirical study confirmed that travel time and the availability of free parking are the two major determinants for Luxembourg residents with respect to their commuting trips by car. The sensitivity analysis indicates that reducing travel time in public transport could be an efficient way to shift car users towards public transport. The results provide useful insights to evaluate the effect of determinants on individual commuting mode choice behaviour for different preference groups.

A Hybrid Algorithm for Fast Learning Individual Daily Activity Plans for Multiagent Transportation Simulation

This paper propose a hybrid learning algorithm based on the competing risk duration model and the cross entropy method for generating complete all-day activity plan in multiagent transportation simulation. We formulate agents activity scheduling problem as a sequential Markov decision process. By initially generating individuals activity type and duration sequence from empirical data based on the competing risk duration model, the obtained plans can be efficiently improved by reinforcement learning technique towards near-optimal activity plan. We apply the cross entropy method to efficiently learn near-optimal activity plan. The numerical result shows that the proposed method generates consistent daily activity plans for multiagent transportation simulation.