Neural-Network-Based Models for Short-Term Traffic Flow Forecasting Using a Hybrid Exponential Smoothing and Levenberg–Marquardt Algorithm

TLDR

The study introduces a neural‑network training scheme that combines hybrid exponential smoothing with a Levenberg–Marquardt algorithm to enhance generalization for short‑term traffic flow forecasting. The method first applies exponential smoothing to traffic flow data to reduce lumpiness, then trains the neural network weights using a variant of the LM algorithm, and is evaluated on the Mitchell freeway in Western Australia. Neural networks trained with this approach achieve smoother inputs and outperform models trained with other short‑term forecasting or generalization algorithms in terms of generalization performance.

Abstract

This paper proposes a novel neural network (NN) training method that employs the hybrid exponential smoothing method and the Levenberg-Marquardt (LM) algorithm, which aims to improve the generalization capabilities of previously used methods for training NNs for short-term traffic flow forecasting. The approach uses exponential smoothing to preprocess traffic flow data by removing the lumpiness from collected traffic flow data, before employing a variant of the LM algorithm to train the NN weights of an NN model. This approach aids NN training, as the preprocessed traffic flow data are more smooth and continuous than the original unprocessed traffic flow data. The proposed method was evaluated by forecasting short-term traffic flow conditions on the Mitchell freeway in Western Australia. With regard to the generalization capabilities for short-term traffic flow forecasting, the NN models developed using the proposed approach outperform those that are developed based on the alternative tested algorithms, which are particularly designed either for short-term traffic flow forecasting or for enhancing generalization capabilities of NNs.