Edge computing - enabled road condition monitoring : system development and evaluation

Abstract

Real-time pavement condition monitoring provides highway agencies with timely and accurate information that could form the basis of pavement maintenance and rehabilitation policies. Existing technologies for pavement condition monitoring rely heavily on manual data processing, are expensive and therefore, difficult to scale for frequent, network level pavement condition monitoring. Additionally, these systems require sending large packets of data to the cloud which requires large storage space, are computationally expensive to process, and results in high latency. The current study proposes a solution that capitalizes on the widespread availability of affordable Micro Electro-Mechanical System (MEMS) sensors, edge computing and internet connection capabilities of microcontrollers, and deployable machine learning models (Tiny ML) to (a) design an Internet of Things (IoT)-enabled device that can be mounted on axles of vehicles to stream live pavement condition data (b) reduce latency through on-device processing and analytics of pavement condition sensor data before sending to the cloud servers (c) facilitate participatory crowd-sensing of pavement condition data at the societal level. In this study, three machine learning models including Random Forest, LightGBM and XGBoost were trained to predict International Roughness Index (IRI) at every 0.1-mile segment. XGBoost has the highest accuracy with an RMSE and MAPE of 16.89in/mi and 20.3 percent, respectively. In terms of the ability to classify the IRI of pavement segments based on ride quality according to MAP-21 criteria, our proposed device achieved an average accuracy of 96.76 percent on I-70EB and 63.15 percent on South Providence (MO-163). Overall, our proposed device demonstrates significant potential in providing real-time International Roughness Index (IRI) data to State Highway Agencies (SHA) and state Department of Transportation (DOTs) with a satisfactory level of accuracy.