CHORRAXALARDAGI TRAFIK OQIMINI SUN'IY INTELLEKT MODULLARI ASOSIDA BOSHQARISH

Published October 14, 2025 | Version v1

Journal article Open

Zamonavir shahar infratuzilmasida transport oqimlarini samarali boshqarish

muammosi tobora dolzarb ahamiyat kasb etmoqda. Ushbu maqolada chorraxalardagi trafik

oqimini sun'iy intellekt modullari yordamida boshqarishning innovatsion yondashuvlari tadqiq

qilingan. Tadqiqot doirasida chuqur o'rganish va chuqur kuchaytirilgan o'rganish algoritmlariga

asoslangan adaptiv svetofor boshqaruv tizimlari tahlil qilingan. Amaliy qismda SUMO

simulyatsiya muhitida tajribalar o'tkazilgan va an'anaviy svetofor boshqaruv usullari bilan

taqqoslangan. Tadqiqot natijalari ko'rsatadiki, sun'iy intellekt modullari asosidagi tizim kutish

vaqtini 25-40% gacha qisqartirishi va transport oqimi o'tkazuvchanligini 30% gacha oshirishi

mumkin. Maqolada taqdim etilgan yechimlar shahar transport infratuzilmasini modernizatsiya

qilish va "Aqlli shaharlar" konsepsiyasini amalga oshirishda amaliy qo'llanilishi mumkinligi

asoslab berilgan

Files

Name	Size	Download all
306-313.pdf md5:231f99a30c44cee27f35dfa6649d2ca8	1.2 MB	Preview Download

AI on the Edge: The Future of Real-Time, Decentralized Traffic Control https://multicorewareinc.com/ai-on-the-edge-the-future-of-real-time-decentralized-traffic- control/ 2. N.Bayko, Y.Mokryk / Optimizing Traffic at Intersections With Deep Reinforcement Learning / Journal of Engineering . 2024. https://doi.org/10.1155/2024/6509852. 3. Swapno, S.M.M.R., Nobel, S.N., Meena, P. et al. A reinforcement learning approach for reducing traffic congestion using deep Q learning. Sci Rep 14, 30452 (2024). https://doi.org/10.1038/s41598-024-75638-0 4. Li, M., Pan, X., Liu, C. et al. Federated deep reinforcement learning-based urban traffic signal optimal control. Sci Rep 15, 11724 (2025). https://doi.org/10.1038/s41598-025-91966-1 5. Lawe, S., & Wang, R. (2016). Optimization of traffic signals using deep learning neural networks. In Lecture Notes in Computer Science (Vol. 9992, pp. 403–415). Springer. https://doi.org/10.1007/978-3-319-50127-7_35