Real-Time Prediction System of Train Carriage Load Based on Multi-Stream Fuzzy Learning

When a train leaves a platform, knowing the carriage load (the number of passengers in each carriage) of this train will support train managers to guide passengers at the next platform to choose carriages to avoid congestion. This capacity has become critical since the onset of the pandemic. However, with the dynamicity of passengers and the speed of trains improved (about 3 minutes travel between stations) as well as the station stop period reduced (60–90 second per station), the real-time prediction is more challenging. This paper presents an intelligent system, which is developed in collaboration with Sydney Trains, for real-time predicting carriage load across a city passenger train network. The system comprises three innovations. First, a fuzzy time-matching method significantly improves prediction accuracy in the uncertain situations and allows noisy historical data to be used for training. Second, the LightGBM model is extended with an incremental learning scheme to make forecasting in real-time possible. Third, a new multi-stream learning strategy that merges data streams with similar concept drift patterns is pioneered to increase the amount of suitable training data while reducing generalization errors. A comprehensive suite of practical tests on real-world datasets demonstrates the merit of these solutions.

I. Introduction

City trains transport management is an important part of a smart city. One of intelligent train operation management tasks is carriage load prediction, which needs to be real-time. That is, when a train leaves a platform, real-time knowledge of the number of passengers in each train carriage. Carriage load prediction contributes to guiding passengers at the next platform to choose which carriage to take to avoid congestion. It is especially important given COVID-19 because the need to socially distance makes this a vital function for the continued safe-running of any rail transport network. Consequently, many prediction methods in the public transport area have been proposed and classified into a traditional parametric approach such as time-series analysis or a non-parametric method based on multiple regression analysis [3], [4].