Commercial Vehicle Activity Prediction With Imbalanced Class Distribution Using a Hybrid Sampling and Gradient Boosting Approach

摘要

Recent advancements in information and communication technologies have led to the ubiquitous use of mobile sensing devices, such as smartphones and vehicle trackers, to obtain high-resolution movement data of commercial vehicles during the conduct of freight studies. Using a digital data collection platform known as the Future Mobility Sensing (FMS) platform, an ongoing commercial vehicle survey was conducted to collect the stop activity and movement information of heavy goods vehicles operating within Singapore. However, despite the successful recruitment of 1,662 drivers who verified their stop activities as part of the survey, a majority of the stops recorded are left unverified with the verified stops showing a significant imbalance between the different activity types reported. Therefore, the objective of the paper is to develop an activity prediction model using the temporal, sequential, contextual, and environmental features collected through the FMS platform, as well as point-of-interest information from Open Street Map. The proposed model was developed based on a gradient boosting approach and supplemented with different data resampling techniques to address the issue of class imbalance. By integrating the proposed model into the FMS platform, the activity-related fields of the survey can be pre-populated to reduce respondent burden and improve the completion rates of future surveys. The activity prediction model can also be used to recover the activity information from the unverified stops collected through the FMS platform, leading to an increased understanding of the movement and parking behaviours of commercial vehicles operating within Singapore.