การคาดการณ์เวลามาถึงของรถบัสไฟฟ้าสำหรับระบบขนส่งมวลชนของมหาวิทยาลัยเชียงใหม่โดยใช้เทคนิคการเรียนรู้ของเครื่อง

Abstract

This thesis proposcs the Arrival Time Estimation of Electric Bus for Chiang Mai University's Public Transportation System Using Machine Learning Techniques. This rescarch aims to create an arrival time cstimation model for the electric bus service of Chiang Mai University. To achieve that, we have consisted of arrival time estimation model for the electric bus that with 3 methods are 1. Support Vector Regression (SVR) 2. Autoregression (AR) 3. Long Short-Term Memory (LSTM) to capture the regullarities in the data The mode! was trained using machine leaming approach well suited for leamning from real-time dala coming directly from the bus's onboard GPS unit. Experimental results based on real data records of four representative bus lines, spanning over 4 months demonstrated the superiority of the proposed support vector regression compared to the autoregression and the long short-term memory as measured by the Mean Absolute Error (MAE)