Travel Time Prediction on Long-Distance Road Segments in Thailand

Simple item page
dc.contributor.authorChawuthai, Rathachai
dc.contributor.authorAinthong, Nachaphat
dc.contributor.authorIntarawart, Surasee
dc.contributor.authorBoonyanaet, Niracha
dc.contributor.authorSumalee, Agachai
dc.date.accessioned2026-08-06T10:37:06Z
dc.date.available2026-08-06T10:37:06Z
dc.date.issued2022-06-01
dc.description.abstractThis study proposes a method by which to predict the travel time of vehicles on long-distance road segments in Thailand. We adopted the Self-Attention Long Short-Term Memory (SA-LSTM) model with a Butterworth low-pass filter to predict the travel time on each road segment using historical data from the Global Positioning System (GPS) tracking of trucks in Thailand. As a result, our prediction method gave a Mean Absolute Error (MAE) of 12.15 min per 100 km, whereas the MAE of the baseline was 27.12 min. As we can estimate the travel time of vehicles with a lower error, our method is an effective way to shape a data-driven smart city in terms of predictive mobility.
dc.identifier.citationApplied Sciences Switzerland, 12(11), 2022
dc.identifier.doi10.3390/app12115681
dc.identifier.issn20763417
dc.identifier.other2-s2.0-85131746326
dc.identifier.urihttps://dspace.kmitl.ac.th/handle/123456789/13258
dc.sourceApplied Sciences Switzerland
dc.subjectGPS data analytics
dc.subjectmachine learning
dc.subjectsmart mobility
dc.subjecttravel time prediction
dc.titleTravel Time Prediction on Long-Distance Road Segments in Thailand
dc.typeArticle

Files

Collections

Research