PREDICTING UNIVERSITY PARKING OCCUPANCY USING MACHINE LEARNING METHODS
Received: 2026-05-15
Published: 2026-06-06
Abstract
This paper presents the development of an intelligent system for monitoring and predicting parking lot occupancy on a university campus. An architecture based on YOLOv8 for real-time detection and a two-layer LSTM network for short-term forecasting is proposed. Detection accuracy reached 96.8%, and the coefficient of determination for the 1-hour forecast horizon is R²=0.961. The software architecture and pilot deployment results are described
List of references
-
Nurullayev S., Cho S.-W. Generalizable Occupancy Detection Using Convolutional Neural Network and Transfer Learning // Sensors. — 2023. — Vol. 23, No. 2. — P. 815. DOI: 10.3390/s23020815
-
Stolfi D.H., Alba E., Yao X. Predicting Car Park Occupancy Rates in Smart Cities // Sensors. — 2020. — Vol. 20, No. 5. — P. 1370. DOI: 10.3390/s20051370
-
Camero A., Toutouh J., Stolfi D.H., Alba E. Evolutionary Deep Learning for Car Park Occupancy Prediction in Smart Cities // Computational Intelligence: International Joint Conference. — 2021. — P. 386–401.
-
Hochreiter S., Schmidhuber J. Long Short-Term Memory // Neural Computation. — 1997. — Vol. 9, No. 8. — P. 1735–1780. (Cited 2024 as foundational reference)
-
Jocher G., Chaurasia A., Qiu J. Ultralytics YOLOv8 [Software]. — 2023. — URL: https://github.com/ultralytics/ultralytics
-
Islam M.A., Ullah M.S., Noor J. Smart Parking System Using IoT and Machine Learning // IEEE Access. — 2022. — Vol. 10. — P. 13041–13053. DOI: 10.1109/ACCESS.2022.3146312
About the Authors
License
This work is licensed under a Creative Commons Attribution 4.0 International License.