Predicting irregularities in arrival times for transit buses with recurrent neural networks using GPS coordinates and weather data

摘要

Intelligent transportation systems (ITS) play an important role in the quality of life of citizens in any metropolitan city. Despite various policies and strategies incorporated to increase the reliability and quality of service, public transportation authorities continue to face criticism from commuters largely due to irregularities in bus arrival times, most notably manifested in early or late arrivals. Due to these irregularities, commuters may miss important appointments, wait for too long at the bus stop, or arrive late for work. Therefore, accurate prediction models are needed to build better customer service solutions for transit systems, e.g. building accurate mobile apps for trip planning or sending bus delay/cancel notifications. Prediction models will also help in developing better appointment scheduling systems for doctors, dentists, and other businesses to take into account transit bus delays for their clients. In this paper, we seek to predict the occurrence of arrival time irregularities by mining GPS coordinates of transit buses provided by the Toronto Transit Commission (TTC) along with hourly weather data and using this data in machine learning models that we have developed. In our study, we compared the performance of a Long Short Term Memory Recurrent Neural Network (LSTM) model against four baseline models, an Artificial Neural Network (ANN), Support Vector Regression (SVR), Autoregressive Integrated Moving Average (ARIMA) and historical averages. We found that our LSTM model demonstrates the best prediction accuracy. The improved accuracy achieved by the LSTM model may lend itself to its ability to adjust and update the weights of neurons while accounting for long-term dependencies. In addition, we found that weather conditions play a significant role in improving the accuracy of our models. Therefore, we built a prediction model that combines an LSTM model with a Recurrent Neural Network Model (RNN) that focuses on the weather condition. Our findings also reveal that in nearly 37% of scheduled arrival times, buses either arrive early or late by a margin of more than 5 min, suggesting room for improvement in the current strategies employed by transit authorities.