Long-Term Indian Traffic Flow Prediction Using Hybrid Deep Learning W-(CNN-LSTM) Approach

Abstract

Accurate long-term traffic flow prediction is crucial for effective traffic management strategies. However, the nonlinear and chaotic nature of traffic flow poses significant challenges for decision-makers. In this paper, we propose a novel hybrid deep learning model, named W-CNN-LSTM, for predicting next-day traffic flow. The model combines wavelet decomposition with Convolution Neural Network-Long Short-Term Memory (CNN-LSTM) architecture to capture both high-frequency and low-frequency components of traffic data, enabling better predictive accuracy. Experimental results on an Indian traffic flow dataset demonstrate the superior forecasting performance of the proposed approach compared to five benchmark methods.