Liangyu Tay, Joanne Mun-Yee Lim, Shiuan-Ni Liang, Chua Kah Keong, Yong Haur Tay

    Traffic volume is a crucial information for many different fields, such as city planner, logistic planning and more. However, installing sensors on each road to collect traffic volume data for the whole traffic network is impractical due to high cost and human labour. Most recent studies implement machine learning, mathematical and statistical methods to learn the behaviour of traffic volume. However, the randomness of traffic volume can hardly be defined by equations or statistical models which leads to the proposed machine learning model. This paper proposed a novel spatial prediction to fill up the traffic volume of a whole network with an estimated 10% of ground truth data. To make up for the lack of data, a spatial-temporal weightage is assigned to each road before fitting the training sample into a tree ensemble model to perform a prediction of the connecting roads. The weightage is first computed using the 10% ground truth data and then the weightage is spread to connecting roads via an innovative repetitive breadth-first search (BFS) method that capture the spatial correlation of a traffic network. Various experiments were conducted to assess the significance of spatial weighting and it was observed that incorporating the weighting resulted in a 1.69% improvement in the Mean Absolute Percentage Error (MAPE). The temporal relationship can be learnt from the trend of hourly traffic data for every day of the week. The proposed model achieved an average percentage error of 2.63% with reduced average percentage error by 95% compared to existing methods.

DOI:https://doi.org/10.1016/j.engappai.2023.107064

Date:2023-11