DefinePK

Abstract

Accurate traffic flow forecasting in areas with different types of vehicles and varied driving behaviors is crucial for improving urban transportation systems and reducing congestion. In this paper, we introduce a Long Short-Term Memory (LSTM) approach to predict short-term traffic flow in such diverse conditions. Our model uses time-series data from real-world traffic sensors, capturing the patterns and dependencies that occur over time in mixed traffic environments. We tested the model using a dataset from seven days, with six days for training and one day for testing. The LSTM model achieved an R2 value of 0.96, a Mean Squared Error (MSE) of 2.82, and a Mean Absolute Error (MAE) of 1.13. These results demonstrate the effectiveness of LSTM networks in predicting traffic flow in complex traffic conditions, surpassing traditional machine learning models. This study provides valuable insights into using deep learning techniques for intelligent transportation systems (ITS).