Car rental system with automated detection of "green" areas for parking
Students Name: Kropyvnytskyi Taras Serhiiovych
Qualification Level: magister
Speciality: Software Engineering
Institute: Institute of Computer Science and Information Technologies
Mode of Study: full
Academic Year: 2022-2023 н.р.
Language of Defence: ukrainian
Abstract: The goal of the qualification work is to create an algorithm for the automated selection of parking spaces for a rented car and a graphical user interface where he can use the services of the service and view the results of the algorithm. The work consists of four sections and two appendices: overview of the subject area and analysis of existing solutions for the problem of selecting optimal parking zones, analysis of solutions and approaches for implementing the algorithm for finding optimal, “green” parking zones, implementation of the algorithm for searching parking zones and UI development parts of the project, practical research results of the search algorithm for automated selection of car parking spaces and their analysis. In the first and second chapters, during the analysis of approaches to solving the given problem, several libraries for working with neural networks were considered, and the most optimal one was chosen. Various approaches for implementing the prediction algorithm are also considered. A proprietary algorithm based on artificial intelligence was created to solve the given problem. The third chapter describes the process of developing a web application for determining the optimal zones for car parking: database design, algorithm development in the TypeScript programming language (AngularJs + NestJs). The project is implemented in the form of SPA (single page application). In the fourth chapter, the practical application of the created neural network was investigated for the task of predicting the availability of parking zones. The work of the neural network was tested experimentally. The volume of work without appendices is 57 pages. Keywords: parking zone prediction, Dijkstra’s shortest path algorithm, Angular, NestJs, BrainJs.