Application of Machine Learning to Child Mode Choice with a Novel Technique to Optimize Hyperparameters.

Travel mode choice (TMC) prediction is crucial for transportation planning. Most previous studies have focused on TMC in adults, whereas predicting TMC in children has received less attention. On the other hand, previous children's TMC prediction studies have generally focused on home-to-school TMC. Hence, LIGHT GRADIENT BOOSTING MACHINE (LGBM), as a robust machine learning method, is applied to predict children's TMC and detect its determinants since it can present the relative influence of variables on children's TMC. Nonetheless, the use of machine learning introduces its own challenges. First, these methods and their performance are highly dependent on the choice of "hyperparameters". To solve this issue, a novel technique, called multi-objective hyperparameter tuning (MOHPT), is proposed to select hyperparameters using a multi-objective metaheuristic optimization framework. The performance of the proposed technique is compared with conventional hyperparameters tuning methods, including random search, grid search, and "Hyperopt". Second, machine learning methods are black-box tools and hard to interpret. To overcome this deficiency, the most influential parameters on children's TMC are determined by LGBM, and logistic regression is employed to investigate how these parameters influence children's TMC. The results suggest that MOHPT outperforms conventional methods in tuning hyperparameters on the basis of prediction accuracy and computational cost. Trip distance, "walkability" and "bikeability" of the origin location, age, and household income are principal determinants of child mode choice. Furthermore, older children, those who live in walkable and bikeable areas, those belonging low-income groups, and short-distance travelers are more likely to travel by sustainable transportation modes.

Insight into the nonlinear effect of COVID-19 on well-being in China: Commuting, a vital ingredient.

Background: COVID-19 had a devastating impact on people's work, travel, and well-being worldwide. As one of the first countries to be affected by the virus and develop relatively well-executed pandemic control, China has witnessed a significant shift in people's well-being and habits, related to both commuting and social interaction. In this context, what factors and the extent to which they contribute to well-being are worth exploring. Methods: Through a questionnaire survey within mainland China, 688 valid sheets were collected, capturing various aspects of individuals' life, including travel, and social status. Focusing on commuting and other factors, a Gradient Boosting Decision Tree (GBDT) model was developed based on 300 sheets reporting working trips, to analyze the effects on well-being. Two indicators, i.e., the Relative Importance (RI) and Partial Dependency Plot (PDP), were used to quantify and visualize the effects of the explanatory factors and the synergy among them. Results: Commuting characteristics are the most critical ingredients, followed by social interactions to explain subjective well-being. Commuting stress poses the most substantial effect. Less stressful commuting trips can solidly improve overall well-being. Better life satisfaction is linked with shorter confinement periods and increased restriction levels. Meanwhile, the switch from in-person to online social interactions had less impact on young people's life satisfaction. Older people were unsatisfied with this change, which had a significant negative impact on their life satisfaction. Conclusions: From the synergy of commuting stress and commuting time on well-being, the effect of commuting time on well-being is mediated by commuting stress in the case of China. Even if one is satisfied with online communication, the extent of enhancement on well-being is minimal, for it still cannot replace face-to-face interaction. The findings can be beneficial in improving the overall well-being of society during the pandemic and after the virus has been eradicated.

The Impact of COVID-19 on Travel Mode Choice Behavior in Terms of Shared Mobility: A Case Study in Beijing, China.

Shared mobility is growing rapidly and changing the mobility landscape. The COVID-19 pandemic has complicated travel mode choice behavior in terms of shared mobility, but the evidence on this impact is limited. To fill this gap, this paper first designs a stated preference survey to collect mode choice data before and during the pandemic. Different shared mobility services are considered, including ride hailing, ride sharing, car sharing, and bike sharing. Then, latent class analysis is used to divide the population in terms of their attitudes toward shared mobility. Nested logit models are applied to compare travel mode choice behavior during the two periods. The results suggest that shared mobility has the potential to avoid the high transmission risk of public transport and alleviate the intensity of private car use in the COVID-19 context, but this is limited by anxiety about shared spaces. As the perceived severity of the pandemic increases, preference for ride hailing and ride sharing decreases, and a price discount for ride hailing is more effective than that for ride sharing at maintaining the ridership despite the impact of COVID-19. These findings contribute to understanding the change in travel demand and developing appropriate strategies for shared mobility services to adapt to the pandemic.