Alp, S.Dündar, S.İnşaat Mühendisliği / Civil Engineering2025-01-152025-01-152024979-835037943-310.1109/ASYU62119.2024.107571182-s2.0-85213336647https://doi.org/10.1109/ASYU62119.2024.10757118https://hdl.handle.net/20.500.14517/7599IEEE SMC; IEEE Turkiye SectionIn this study, real-time traffic forecasting was conducted using traffic speed data obtained from Bluetooth sensors located in the city of Vigo, Spain. For this purpose, average speed data recorded at fifteen-minute intervals from five different sensors in the city since 2014 were used. Using past average speed values in a time series format as inputs, various deep learning methods were applied to predict traffic speed data for the next fifteen minutes. The Long Short-Term Memory (LSTM) method achieved the highest performance in traffic forecasting. Incorporating additional factors such as time, weather conditions, and environmental factors into the models, along with time-series traffic volumes, could further enhance the performance of near-future traffic forecasting. © 2024 IEEE.eninfo:eu-repo/semantics/closedAccessDeep LearningLong Short Term MemoryTraffic PredictionConference ObjectN/AN/A0