Estimating Construction Work Zones Capacity Using Deep Neural NetworkAuthor/Presenter: Mashhadi, Ali Hassandokht; Markovic, Nikola; Rashidi, Abbas
Construction work zones are a major cause of traffic disruptions and delays on roadways. Thus, accurate estimation of traffic states within work zones would be beneficial to both road users and transportation agencies. To this end, a deep neural network has been calibrated based on the hourly data points collected from 80 projects completed in Utah from 2013 to 2020. Reported results show that the proposed model outperforms its counterparts from the literature while achieving the R score of 0.97, RMSE of 185, and MAE of 108. Comparing the study results with the Highway Capacity Manual 2016 (HCM) shows that the proposed model is a good alternative for work zone capacity estimation. Future studies could leverage the probe vehicle data to improve the model’s performance by decreasing the RMSE and MAE values.
Publication Date: 2022
Source URL: Link to URL
Publication Types: Books, Reports, Papers, and Research Articles
Topics: Highway Capacity; Neural Networks; Work Zone Capacity; Work Zones