A guided genetic algorithm-based ensemble voting of polynomial regression and LSTM (GGA-PolReg-LSTM) for congestion prediction using IoT and air quality data in sustainable cities
Résumé
A sustainable city is a smart city with a minimal impact on the environment, by incorporating technologies to reduce pollution. Traffic congestion which is a major concern contributes to global warming and climate change. Traffic forecasting projects future traffic patterns, using historical and current data to enhance traffic flow management. We propose a whole novel approach for predicting traffic congestion rate based on air quality data. We developed a new ensemble voting model based on Long Short Term Memory (LSTM) and Polynomial Regression (PolReg) models that use a new voting thresholded algorithm instead of the existing voting ones. The hyperparameters were optimized with the Genetic Agorithm, to overcome the nonstationarity of time series. A comparative study with the literature confirmed that our framework outperforms existing researches by keeping an absolute effectiveness according to learning curves, with Mean Absolute Error of 0.04, R-Squared of 0.93, and Root Mean Square Error (RMSE) of 0.05.