Combination predicting model of traffic congestion index in weekdays based on LightGBM-GRU

Abstract

Tree-based and deep learning methods can automatically generate useful features. Not only can it enhance the original feature representation, but it can also learn to generate new features. This paper develops a strategy based on Light Gradient Boosting Machine (LightGBM or LGB) and Gated Recurrent Unit (GRU) to generate features to improve the expression ability of limited features. Moreover, a SARIMA-GRU prediction model considering the weekly periodicity is introduced. First, LightGBM is used to learn features and enhance the original features representation; secondly, GRU neural network is used to generate features; finally, the result ensemble is used as the input for prediction. Moreover, the SARIMA-GRU model is constructed for predicting. The GRU prediction consequences are revised by the SARIMA model that a better prediction can be obtained. The experiment was carried out with the data collected by Ride-hailing in Chengdu, and four predicted indicators and two performance indexes are utilized to evaluate the model. The results validate that the model proposed has significant improvements in the accuracy and performance of each component.

Traffic Prediction in Smart Cities Based on Hybrid Feature Space

“…[53] stack LSTM and transfer-learning not consider Heterogeneous data sources [54] hybrid CNN-LSTM other exogenous data sources [55] Vehicular Ad hoc Networks not discuss probabilistic traffic prediction techniques and hybrid classifiers [56] bagging, boosting, stacking, and random forest ensemble models not pay attention to deep learning and missing data imputation methods. [61] Deep Belief Network (DBN) works only ETA not work on heterogeneous data sources [62] LightGBM-GRU for enhancing features list heterogeneous data sources are ignored [63] CNN not work on hybrid deep learning models and exogenous data sources [64] Support Vector Machine (SVM) and Multinomial Naïve Bayes (MNB) not work on hybrid deep learning models and exogenous data sources [65] LSTM + CNN + ATTENTION not works on heterogeneous data sources [66] is that the authors did not take into consideration the impact of heterogeneous data sources on predicting traffic congestion on road network. The authors in [37] introduced the path based deep learning framework for capturing spatialtemporal features as well as effective speed prediction.…”

A Hybrid Ensemble Learning Approach Utilizing Light Gradient Boosting Machine and Category Boosting Model for Lifestyle-Based Prediction of Type-II Diabetes Mellitus

“…These strategies, along with others, contribute to LightGBM's superior computational efficiency and accuracy compared to other algorithms. Cheng W et al [30] introduced the use of LightGBM in combination with a closed recurrent unit to predict weekday traffic congestion. The objective of their study was to built a model that could effectively capture and express features limited by traditional approaches.…”

A boosting ensemble learning based hybrid light gradient boosting machine and extreme gradient boosting model for predicting house prices

“…Reference 27 proposed LGBM and gated recurrent unit in predicting weekdays traffic congestion. The study's objective was to create a model that can improve the ability of expression of features which are limited by generating them using the proposed model.…”