MASHINAVIY O‘QITISH ASOSIDA YO‘LLARDAGI TIRBANDLIK HOLATLARINI TAHLIL QILISHNING INTELLEKTUAL ALGORITMLARI

Akmal Axatov; Bunyod Eshtemirov

Авторы

Akmal Axatov Samarqand davlat universiteti
Bunyod Eshtemirov Samarqand davlat universiteti

Ключевые слова:

Algoritimni baholash ko‘rsatkichlari, tirbandlik holati bashorati, XGBoost, Random Forest Classifier, Logistic Regression, LGBMClassifier, YOLO

Аннотация

Hozirgi vaqtda shaharlarning kengayishi va transport vositalari sonining ortishi tirbandlik muammosini dolzarb masalaga aylantirdi. Ushbu muammoni hal qilishda video tasvirlardan transport vositalarini tanib olish uchun YOLO, SSD va Faster R-CNN kabi ilg‘or algoritmlardan foydalanish muhim rol o‘ynaydi. Bu texnologiyalar transport vositalarining turini, joylashuvini va sonini aniqlashda yuqori aniqlik va tezlik bilan ishlaydi. YOLO (You Only Look Once) algoritmi tasvirni bir marta ko‘rib, transport vositalarining aniqligini va joylashuvini belgilaydi, bu esa real vaqt rejimida samarali ishlash imkonini beradi. SSD (Single Shot MultiBox Detector) esa bir nechta konvolyutsion qatlamlardan foydalanib, yuqori aniqlik bilan transport vositalarini aniqlaydi va real vaqt rejimida ishlaydi. Faster R-CNN (Region-based Convolutional Neural Networks) algoritmi esa region prediktsiyasi va konvolyutsion neyron tarmoqlarni birlashtirib, transport vositalarini aniqlashda yuqori aniqlikni ta’minlaydi, lekin tezligi biroz sekinroq. Video tasvirlardan transport vositalarini aniqlash natijasida hosil bo‘lgan ma’lumotlar to‘plami tirbandlik holatlarini bashorat qilishda foydalaniladi. Bu ma’lumotlar to‘plami transport vositalarining soni, turli vaqtlardagi joylashuvi, harakat yo‘nalishi va tezligi kabi ma’lumotlarni o‘z ichiga oladi. Bu ma’lumotlardan foydalangan holda, tirbandlikni bashorat qilish uchun turli sun’iy intellekt algoritmlari qo‘llaniladi. Ushbu tadqiqot ishida XGBoost, Random Forest Classifier, LGBMClassifier (Light Gradient Boosting Machine Classifier) va Logistic Regression kabi tirbandlikni bashorat qilishda eng ko‘p qo‘llaniladigan algoritmlardan foydalanib tirbandlik holatlari bashorat qilindi hamda natijalar baholanib taqqoslandi.

Библиографические ссылки

He K., Zhang X., Ren S., and Sun J. “Deep residual learning for image recognition”. In: Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 770–778.

Huang J., Rathod V., Sun C., Zhu M., Korattikara A., Fathi A., Fischer I., Wojna Z., Song Y., Guadarrama S. “Speed/accuracy trade-offs for modern convolutional object detectors”. In: Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 7310–7311.

Akhatov A., Nazarov F.M. and Eshtemirov B., “Detection and analysis of traffic jams using computer vision technologies,” International conference on Artificial Intelligence and Information Technologies (ICAIIT 2023), Uzbekistan, Samarkand, 2023, 2, pp. 761–766, https://doi.org/10.1201/9781032684994.

Gilmore J. F. and Elibiar K. J., "Traffic Management Applications of Neural Networks," in Proceedings of the IEEE International Conference on Neural Networks (ICNN), 2022.

Nurfita R. D. and Ariyanto G., “Implementasi Deep Learning Berbasis Tensorflow Untuk Pengenalan Sidik Jari” Emitor: Jurnal Teknik Elektro, 18, 22- 27. 2018.

Eshtemirov B., Nazarov F.M., Saydullayev Q.Sh. Microscopic and macroscopic flow models of traffic management. Samarqand davlat universiteti ilmiy axborotnomasi, 2023-yil, 1-son (137/2) Aniq va tabiy fanlar seriyasi.

Akhatov A., Eshtemirov B., "Transport harakatini boshqarish usullari", Sun’iy intellekt va raqamli ta’lim texnologiyalari: amaliyot, tajriba, muammo va istiqbollari mavzusidagi xalqaro ilmiy-amaliy anjuman materiallari to‘plami, 3-4 iyun 2024-yil.

Khan S., Naseer M., Hayat M., Zamir S. W., Khan F. S., and Shah M., " Transformers in vision: A survey", ACM computing surveys (CSUR), 54(10s), 1-41. DOI: 10.1145/3505244.

Eshtemirov B., Nazarov F., Yarmatov Sh.. Technologies for identifying vehicles standing at traffic lights based on video data. Central asian journal of mathematical theory and computer sciences, Volume: 03 Issue: 12 | Dec 2022 ISSN: 2660-5309.

Eshtemirov B., Nazarov F., Khamidov M., Deep learning-based traffic congestion forecasting research. International conference on Artificial intelligence and information technologies (ICAIIT-2023), Uzbekistan, Samarkand, 2023.

Liu, Yunxiang, and Hao Wu. "Prediction of road traffic congestion based on random forest." 2017 10th International Symposium on Computational Intelligence and Design (ISCID). Vol. 2. IEEE, 2017.

Xiong, Y. Research on prediction of the use of electronic coupons based on XGBoost. Computer Science and Application, 9(5), 1029–1035. DOI 10.12677/CSA.2019.95116.

A. Akhatov, B. Eshtemirov, “Sun’iy intellektdan foydalanib yo‘llardagi tirbandlilarni baholash bosqichlari va algoritmlari”, Amaliy matematikaning zamonaviy muammolari va istiqbollari mavzusidagi Respublika ilmiy-amaliy konferensiya Tezislar to‘plami, Qarshi, QarDU, 2024-yil 24-25-may.

Saxena S., Bremond F., Thonnat M., Crowd behavior recognition for video surveillance. In Proceedings of the 10th International Conference on Advanced Concepts for Intelligent Vision Systems, ACIVS ’08, pages 970–981, Berlin, Heidelberg, 2008. Springer-Verlag.

Shi J., and Tomasi C., Good features to track. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), pages 593– 600, jun 1994.

Valera M. and Velastin S., Intelligent distributed surveillance systems: a review. IEEE Proceedings on Vision, Image and Signal Processing, 152(2):192– 204, april 2005..

Long J., Gao Z., Ren H., and Lian A., “Urban tra/c congestion propagation and bottleneck identiBcation,” Science in China - Series F: Information Sciences, vol. 51, no. 7, pp. 948–964, 2008.

Sobral A. L. O., Schnitman L. and De Souza F., Highway traffic congestion classification using holistic properties. In: 10th IASTED International Conference on Signal Processing, Pattern Recognition and Applications, 2013.

Vaswani A., Shazeer N., Parmar N., Uszkoreit J., Jones L., Gomez A.N., Kaiser L., Polosukhin, I., Attention is all you need. Advances in neural information processing systems, 30, (NIPS 2017).

Wang X., Zeng R., Zou F., Liao L. and Huang F., STTF: An efficient transformer model for traffic congestion prediction. International Journal of Computational Intelligence Systems, 16(1), 2, 2023.

Eshtemirov B., Nazarov F., Yarmatov Sh.. Video Data Processing Methodology for Investigation. Vital Annex: International Journal of Novel Research in Advanced Sciences (IJNRAS), Volume: 01 Issue: 06 | 2022, ISSN: 2751-756X.