Pavement condition monitoring is an important task in road asset management and efficient abnormal pavement condition detection is critical for timely conservation management decisions. The present work introduces a mobile pavement condition monitoring approach utilizing low-cost sensor technology and machine-learning-based methodologies. Specifically, an on-board unit (OBU) embedded with an inertial measurement unit (IMU) and global positioning system (GPS) is applied to collect vehicle posture data in real time. Through a comprehensive analysis of both time domain and frequency domain data features for both normal and abnormal pavement conditions, feature engineering is conducted to identify how the most important features affect abnormal pavement condition recognition. Six machine learning models are then developed to identify different types of pavement conditions. The performance of different algorithms and the significance of different features are then analyzed. Moreover, the influence of vehicle speed on pavement condition assessment is further examined and classification models for different speed intervals are developed. The results indicate that the random forest (RF) model that considers vehicle speed achieves the best performance in pavement condition monitoring. The outcomes of the present work would contribute to cost-effective pavement condition monitoring and provide an important reference for pavement maintenance sectors.

With the rapid development of vehicle electrification, taxis in many cities have been shifted to electric vehicles (EVs). To better support the service of electric taxi (ET) systems, it is important to conduct rational charging infrastructure planning based on its real operational characteristics and charging demand. However, due to lack of large-scale operational data, previous studies less addressed the charging station planning problem with real-world ET operation information. The present work discussed a data-driven method for pre-location of ET charging stations. Firstly, based on the trajectory data of a large-scale ETs, the spatio-temporal operation characteristics of ETs are analyzed. Then the K-means clustering algorithm is applied to analyze the spatial distribution of ET service drop-off points for finding the potential location with high charging demand. At last, considering the service radius of charging station facilities and the spatial analysis results, a feasible charging station pre-location plan is determined. When considering a service radius of 2.5km, 88 pre-located charging stations in Shenzhen are obtained. The present work could provide important reference for better planning of charging facilities.