An Efficient Parking Management System for Smart Cities Using GA-RBF Model to Optimize Fuel, Time, and Cost

Making better use of parking spots in big parking lots and showing drivers where there are openings makes parking easier for them, which in turn alleviates traffic congestion. With the help of cutting-edge sensing and monitoring technology, this is the desired outcome of smart parking management. Aiming to make parking more effective and less burdensome on depleting resources, the concept of smart parking construction evolved. To achieve the best possible results during model training, feature selection, and preprocessing, it is essential to adhere strictly to this strategy. The steps of data transformation, encoding, imputation, and normalization make up data preparation. After successfully visualizing high-dimensional data in the actual world, the proposed approach are utilizing dimension reduction in feature selection. The model was trained using a GA-RBF. Traditional methods, such as GA and RBF, are surpassed by the suggested approach. Applying the strategy resulted in a 92.27% improvement in accuracy.