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.