Abstract
Traffic congestions due to construction and maintenance works of road infrastructure cause travel delays, unpredictability and less tolerant road users. Bicyclists are more flexible with road closures, shifting to alternative routes, public transport and other active transport depending on the infrastructure, quality and transport services. However, the mixed traffic environment near road closures increases the safety risks for bicyclists. Traditional traffic monitoring systems rely on costly and demanding intrusive sensors. The application of wireless sensors and machine learning algorithms can enhance the analysis and prediction ability of traffic distribution and characteristics in the proximity of road closures. This paper applies artificial neural networks (ANNs) coupled with a Generalised Delta Rule (GDR) algorithm to analyse the sensor traffic data before, during and after the closure of the Mill Road Bridge in Cambridge City in the United Kingdom. The ANN models show that the traffic volume of motorbikes (44%) and buses (34%) and the proximity of Mill Road Bridge (39%) are significant factors affecting bicycle traffic before the closure. During the bridge closure, the proximity of the bridge (99%) and traffic volume of large rigid vehicles (51%) are the most important factors of bicycle distribution in nearby streets leading cyclists to unsafe detours. After the reopening of the Mill Road Bridge, unclear signage caused continued traffic impact, with motorbikes (17%) and large vehicles (24%) playing the most significant role in the spatial distribution of bicycle traffic. This paper emphasises safety concerns from mixed traffic and highlights the importance of cost-effective sensor-based traffic monitoring and analysis of the sensor data using neural networks.