Original scientific paper
https://doi.org/10.7307/ptt.v36i4.592
Optimised LSTM Neural Network for Traffic Speed Prediction with Multi-Source Data Fusion
Yongpeng ZHAO
; Lanzhou Jiaotong University, School of Traffic and Transportation; Gansu Provincial Highway and Transportation Construction Group Co., Ltd
Yongcang LI
; Gansu Road and Bridge Construction Group Co., Ltd
Changxi MA
; Lanzhou Jiaotong University, School of Traffic and Transportation
Ke WANG
; Lanzhou Jiaotong University, School of Traffic and Transportation
Xuecai XU
; Huazhong University of Science and Technology, School of Civil and Hydraulic Engineering
Abstract
Predicting traffic speed accurately and in real-time is crucial for the development of smart transportation systems. Given the nonlinear and stochastic nature of vehicle data, integrating diverse spatio-temporal data sources with the Improved Particle Swarm Optimisation (IPSO) offers a promising approach to optimise the Long Short-Term Memory Neural Network (LSTM). Firstly, we enhance the optimisation capabilities of PSO by implementing nonlinear inertial weight and adaptive variation. Secondly, addressing the challenge of selecting the LSTM hyperparameters, the PSO algorithm effectively identifies global optimal solutions for hyperparameter optimisation, ensuring appropriate settings through iterative training. Subsequently, we conduct a case study using multi-source spatio-temporal traffic speed data, comparing our proposed IPSO-LSTM model with traditional neural network prediction models and advanced models. Results from the experiment demonstrate that the IPSO-LSTM model presented in this study addresses issues of parameter selection and inaccurate prediction encountered by traditional LSTM models in traffic state prediction. Moreover, it enhances the model’s ability to capture speed time series dynamics. Notably, in processing complex speed data, our model exhibits superior accuracy and stability in prediction.
Keywords
traffic speed prediction; multi-source data fusion; improved particle swarm optimisation; long short-term memory network
Hrčak ID:
320283
URI
Publication date:
27.8.2024.
Visits: 61 *