Detection of car parking space by using Hybrid Deep DenseNet Optimization algorithm

Abstract

Internet of Things (IoT) and related applications have revolutionized most of our societal activities, enhancing the quality of human life. This study presents an IoT-based model that enables optimized parking space utilization. The paper implements a Hybrid Deep DenseNet Optimization (HDDNO) algorithm for predicting parking spot availability involving Machine Learning (ML) and deep learning techniques. The HDDNO-based ML model uses secondary data from the National Research Council Park (CNRPark) in Pisa, Italy. Different regression algorithms are employed to forecast parking lot availability for a given time as part of the prediction process. The DenseNet technique has generated promising results, whereas the HDDNO model yielded better accuracy. The use of five optimizers, namely, Adaptive Moment Estimation (Adam), Root Mean Squared Propagation (RMSprop), Adaptive Gradient (AdaGrad), AdaDelta, and Stochastic Gradient Descent (SGD), have played significant roles in minimizing the loss of the model. The part of Adam has enabled the HDDNO model to generate predictions with high accuracy 99.19% and low loss 0.0306%. This proposed methodology would significantly improve environmental safety and act as an initiative toward developing smart cities.