IoT-Enhanced Smart Parking Management With IncepDenseMobileNet for Improved Classification

This project focuses on optimizing parking management systems through the use of machine learning techniques. The system classifies various parking attributes, such as the occupancy status of parking spaces, vehicle types, parking violations, and payment statuses, using data collected from parking sensors and environmental conditions. The project integrates an enhanced hybrid model combining IncepDenseMobileNet and TabNet for advanced data processing and feature extraction. Additionally, CatBoost, LightGBM, and Artificial Neural Networks (ANN) are separately trained to classify parking space occupancy, vehicle types, parking violations, and payment statuses accurately. These models are trained on a diverse dataset that includes sensor readings, parking spot details, user information, and violation data. The goal is to optimize parking space utilization, improve efficiency in parking management, and provide efficient monitoring for both users and administrators. The system, developed using Flask, features a web platform that allows users to interact seamlessly with the system, providing insights into parking space classifications, violations, and payment statuses.

Keywords: IoT, Smart Parking, Machine Learning, Hybrid Model, IncepDenseMobileNet, TabNet, CatBoost, LightGBM, ANN, Parking Management, Flask, Violation.