An overview of effects of COVID-19 on mobility and lifestyle: 18 months since the outbreak.

The outbreak of SARS-COV-2 has led to the COVID-19 pandemic in March 2020 and caused over 4.5 million deaths worldwide by September 2021. Besides the public health crisis, COVID-19 affected the global economy and development significantly. It also led to changes in people's mobility and lifestyle during the COVID-19 pandemic. In addition to short-term changes, the drastic transformation of the world may account for the potentially disruptive long-term impacts. Recognizing the adverse effects of the COVID-19 pandemic is crucial in mitigating the negative behavioral changes that directly relate to people's psychological and social well-being. It is important to stress that citizens and governments face an uncertain situation since nobody knows exactly how the viruses and cures will develop. Better understanding uncertainties and evaluating behavioral changes contribute to addressing the future of urban development, public transportation, and behavioral strategies to tackle COVID-19 negative consequences. The major sources of impacts on short-term (route, departure time, mode, teleshopping, and teleworking) and medium and long-term (car ownership, work location, choice of job, and residential location) mobility decisions are mostly reviewed and discussed in this paper.

Identifying the electricity-saving driving behaviors of electric bus based on trip-level electricity consumption: a machine learning approach.

Electric buses (EBs) are gaining popularity worldwide as a more sustainable and eco-friendly alternative to diesel buses (DBs). Electricity-saving driving plays a crucial role in minimizing an EB's energy consumption, subsequently leading to an extended driving range. This study proposes a machine learning-based framework for identifying electricity-saving EB driving behaviors during various driving stages, including running on road segments, entering bus stops/intersections, and exiting bus stops/intersections. The proposed random forest (RF) model effectively evaluates the energy consumption level using EB drivers' historical driving data under different scenarios. Specifically, the electricity consumption factor (ECF), as the evaluation index, is divided into three categories to determine the implicit relationship between driving behavior and energy consumption. The results indicate that the classification accuracy of RF models surpasses 90%, which highlights the effectiveness in accurately identifying energy-efficient EB driving behaviors. In addition, the Shapley additive explanations (SHAP) and partial dependency plots (PDPs) are utilized to visualize and interpret the results of RF models. A speed interval of 30-40 km/h is identified as the most energy-efficient range for EB running on a road segment. Findings from this study can be applied to targeted optimization of electricity-saving driving strategies in different driving scenarios to improve the overall efficiency and sustainability of the transportation system.