TY - JOUR ID - 4403 TI - Traffic state prediction with machine learning algorithms for short-term and mid-term prediction time horizons JO - Amirkabir Journal of Civil Engineering JA - CEEJ LA - en SN - 2588-297X AU - Rasaizadi, Arash AU - Seyedabrishami, Seyed Ehsan AD - Transportation Planning, Civil engineering department, Tarbiat Modares University, Tehran, Iran AD - Assistant Professor at the Faculty of Civil and Environmental Engineering, Tarbiat Modares University, Tehran, Iran Y1 - 2022 PY - 2022 VL - 54 IS - 4 SP - 1503 EP - 1520 KW - Traffic state prediction KW - Support Vector Machine KW - Random forest KW - Long short-term memory KW - Intelligent Transportation Systems DO - 10.22060/ceej.2021.19650.7219 N2 - Predicting traffic variables and informing the passengers and the transportation network operators is one way to manage the travel demand. By informing the future state of traffic through intelligent transportation systems, there is more readiness to avoid congestion. In this study, three machine learning algorithms, including support vector machine (SVM), random forest (RF), and long short-term memory (LSTM), were used to predict the hourly traffic state, consist of light, semi-heavy and heavy states, for Karaj to Chaloos rural road in the north of Iran. Predictor variables of mid-term models are calendar information, weather, and road blockage policies. In contrast, in short-term models, in addition to the mentioned variables, the observed traffic states in the past three to eight hours have been used, and these models can only predict the future of one and two hours. The results show that short-term LSTM is the most accurate traffic state predictive model, with an accuracy equal to 90.11%. Among the mid-term models, the LSTM model has predicted traffic state more accurately than SVM and RF, and its accuracy is equal to 82.07%. Also, LSTM has the highest values of f1 measure to predict light, semi-heavy, and heavy, which are equivalent to 0.86, 0.93, and 0.81, respectively. Also, the hour, holiday, and type of holiday variables and traffic state observed in 3 to 8 hours later variables have the greatest effect on increasing the accuracy of mid-term and short-term models, respectively. UR - https://ceej.aut.ac.ir/article_4403.html L1 - https://ceej.aut.ac.ir/article_4403_e043489707730641b325fa4e093d7d76.pdf ER -