Author(s): Sneha Asopa and Sreekala

Abstract: Regarding intelligent transportation systems in smart cities, precise traffic forecasting is essential for maximizing urban mobility and improving traffic safety. Using a hybrid optimization model that incorporates the Whale Optimization Algorithm (WOA) with the Artificial Bee Colony (ABC) algorithm, this work offers a fresh way to traffic forecasting. The first step of our process involves gathering extensive data from traffic monitoring devices, which includes important characteristics like the number of vehicles, their speeds, and the weather. The dataset, obtained via Kaggle, has several parameters such as temperature, humidity, wind speed, traffic volume, and rainfall. We divide the data into training and testing sets, handle missing values, and normalize features as part of the preprocessing step. The creation and use of the hybrid ABC+WOA model forms the basis of our methodology. Through the optimization of hyperparameters and feature selection, this model aims to improve prediction accuracy by using the global search capabilities of the ABC algorithm and the local search powers of the WOA. Important metrics that together measure the model's accuracy, error size, and predictive potential include Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and R-squared (R²). Compared to conventional techniques, our empirical research shows that the merging of ABC and WOA greatly enhances traffic forecast accuracy. In addition to improving the prediction process, this hybrid method advances the more general objective of creating intelligent transportation systems that can adjust to changing urban settings.

DOI: 10.33545/27075923.2024.v5.i2a.76

Pages: 25-34 | Views: 191 | Downloads: 70

Download Full Article: Click Here