Estimasi Panjang Antrian Pada Simpang Bersinyal Dengan Menggunakan Artificial Neural Network

Abstract

Signalized intersections are nodes in the transportation network where vehicles in different directions meet and are critical points for congestion. Vehicle queue length is one of the performance parameters of a signalized intersection. Long queues of vehicles are at high risk of accidents involving many vehicles. Feedback signal control (actuated signal control) can be used to improve intersection performance. One of the variables that can be used as a feedback input is the length of the vehicle queue. Traffic in Indonesia is mixed traffic where various types of vehicles use the same road lanes and with low lane discipline. This causes the traffic system to become complex and to be stochastic and non-linear. Queue length modeling using a static linear algorithm is unable to capture the phenomenon of this complex traffic system. Therefore, this study aims to build a queue length model based on machine learning, that is, using an artificial neural network (ANN). This model studies traffic systems with historical data so that through the training process it can model queue lengths with a good degree of accuracy. An estimation model was built and applied to a section of the Muara Rapak signalized intersections, Balikpapan. Data on queue length for 10 days, 2 hours/day, obtained using CCTV and direct field surveys. The results of the model test show that ANN has a good level of accuracy with MAE, RMSE and MAPE of 3.8 m, 4.9 m and 6%, respectively.