An Improved STL-LSTM Model for Daily Bus Passenger Flow Prediction during the COVID-19 Pandemic.

Feng Jiao,Haifeng Huang,Rongjia Song,Lei Huang

doi:10.3390/s21175950

Feng Jiao, Haifeng Huang + Show 2 more

Open Access

https://doi.org/10.3390/s21175950

Copy DOI

Abstract

The COVID-19 pandemic is a significant public health problem globally, which causes difficulty and trouble for both people’s travel and public transport companies’ management. Improving the accuracy of bus passenger flow prediction during COVID-19 can help these companies make better decisions on operation scheduling and is of great significance to epidemic prevention and early warnings. This research proposes an improved STL-LSTM model (ISTL-LSTM), which combines seasonal-trend decomposition procedure based on locally weighted regression (STL), multiple features, and three long short-term memory (LSTM) neural networks. Specifically, the proposed ISTL-LSTM method consists of four procedures. Firstly, the original time series is decomposed into trend series, seasonality series, and residual series through implementing STL. Then, each sub-series is concatenated with new features. In addition, each fused sub-series is predicted by different LSTM models separately. Lastly, predicting values generated from LSTM models are combined in a final prediction value. In the case study, the prediction of daily bus passenger flow in Beijing during the pandemic is selected as the research object. The results show that the ISTL-LSTM model could perform well and predict at least 15% more accurately compared with single models and a hybrid model. This research fills the gap of bus passenger flow prediction under the influence of the COVID-19 pandemic and provides helpful references for studies on passenger flow prediction.

Highlights

The results indicate that when the hyperparameter ‘epochs’ was equal to 65, 100, 65, or 50, respectively, the where yi is the value, whichmodel is the label data; yi is the predicted value; n is performance of actual the corresponding couldofbethe most optimal
The results indicate that the test set were close to the actual values, which means that the prediction when the hyperparameter ‘epochs’ was equal to 65, 100, 65, or 50, respectively, the perresult errors were could few
We used the data during the COVID-19 pandemic in Beijing to test the performance of the proposed model

Summary

Introduction

Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. Since COVID-19 appeared in Wuhan, China, in December 2019, it has spread rapidly around the world. On 11 March 2020, WHO stated that the current COVID-19 outbreak should be called a global pandemic. Until 1 September 2020, there had been

Objectives

Methods

Results

Conclusion