Integrating singular value decomposition with deep learning for enhanced travel time estimation in multimodal freight transportation networks

Abstract

Multimodal freight transport allows switching among various modes of transportation to efficiently utilize transport facilities. A multimodal transport system incorporates geographical scales from global to local. Travel time estimation in a multi‐modal cargo transportation network is essential for enhancing supply chain (SC) and logistics operations. Accurate travel time prediction is of great importance for cargo transportation, as it enables SC participants to increase logistics efficiency and quality. It requires adequate input data, which can be generated. In recent times, the machine learning (ML) algorithm has been well‐suited to resolve complex and nonlinear relationships in the collected tracking data. This study designs a deep learning‐powered travel time estimation in multimodal freight transportation networks (DLTTE‐MFTN) technique. The goal of the DLTTE‐MFTN technique is to estimate the travel time using a hyperparameter‐tuned ensemble learning approach. To achieve this, the DLTTE‐MFTN method initially undergoes data pre‐processing to convert the input raw data into a useful format. In addition, the singular value decomposition (SVD) model can be applied for feature dimensionality reduction in multimodal transport data, considerably improving travel time prediction. Besides, the DLTTE‐MFTN method estimates travel time using an ensemble of three DL approaches including one‐dimensional convolutional neural network (1D‐CNN), stacked autoencoder (SAE) attention, and recurrent neural network (RNN). Finally, the hyperparameter tuning of the DL models takes place using the whale optimization algorithm (WOA). The performance analysis of the DLTTE‐MFTN method takes place using the Kaggle dataset. The experimental results stated that the DLTTE‐MFTN technique attains superior performance over other ML and DL models.