Intelligent Allocation of Urban Parking Spaces Using Computational Learning Models

computer Application

The challenge of urban parking stems from increasing vehicle numbers and static infrastructure. A machine learning-based platform is proposed to generate short-term parking occupancy predictions. Performance will be evaluated through interactive visual tools like bar graphs and accuracy analysis. The system also supports long-term strategic planning, leveraging data on vehicle movement to optimize both present and future parking usage. This research is grounded in real-world data collected over a five-month period within an actual urban environment. (January 2022 to June 2023) in a parking garage at a college is one of its main strengths. Some of the variables incorporated in this report are time, day of week, date, weather and seasonal changes, and the occupancy rates As more cars fill up large cities with insufficient parking spaces, the parking problem in the cities is getting worse. Due to population growth and a transportation system reliant on privately owned automobiles, Cities have far more cars than parking spots. Cities that are known for their traffic, fuel waste, sloth, air pollution, and decreased economic output are seriously threatened by this. The system will provide interactive bar graphs that indicate the precision of each machine as it learns the model during testing and training once the model has finished training.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.