Smart occupancy detection for road traffic parking using deep extreme learning machine.

Predicting the location of parking is a long-lasting problem that has ultimate importance in our daily life. In this paper, artificial neural networks are used to predict the parking location that will be helpful for drivers to settle on a reasonable area for stopping. This approach eventually adds to the familiarity and wellbeing of traffic on the roads which results in a decrease in turbulence. By using the approach of Deep Extreme Learning Machine (DELM), reliability can be achieved with a marginal error rate thus reducing the skeptical inclination. In this article, the Proposed Car Parking Space Prediction (CPSP) to elaborate on the dilemma of parking space for vehicles, we have used deep learning neural networks in contrast with feedforward and backward propagation. When the results were taken into consideration, it was unveiled that extreme deep machine learning neural network bears the highest accuracy rate with 60% of training (21431 samples), 40% of test and validation (14287 examples). It has been observed that the proposed DELM has the highest precision rate of 91.25%. Simulation results validate the prediction effectiveness of the proposed DELM strategy. [ABSTRACT FROM AUTHOR]