Kolmogorov-Arnold Network (KAN) arxitekturasi asosida transport oqimining bashorat va tahlil modelini ishlab chiqish

Komoliddin Tashmetov

Komoliddin Tashmetov Toshkent davlat transport universiteti

Ключевые слова: Transport oqimi, transport intensivligi, transport tizimi, bashorat modeli, sun’iy intellekt, KolmogorovArnold tarmog‘i, mashinani o‘qitish, mashinani chuqur o‘qitish, ko‘p qatlamli perseptron

Аннотация

Ushbu tadqiqot ishida yo‘l transport oqimlarini bashorat qilish va tahlil etishga oid arxitekturalar va modellar o‘rganilgan bo‘lib, bunda asosiy urg‘u Kolmogorov-Arnoldning KAN arxitekturasiga qaratilgan. Tadqiqotda ushbu arxitekturaning an’anaviy mashinani o‘qitish arxitekturasidan farqlari keltirilib, ularning samaradorligi taqqoslangan. KAN arxitekturasining asosiy teoremalari va formulalari keltirilib, ularning nazariy asoslari yoritilgan. Tadqiqot davomida KAN modeli asosida olingan natijalar ko‘rib chiqilgan va ushbu natijalarning xulosalari keltirilgan. O‘qitish jarayonida model 87% aniqlikni ko‘rsatgan bo‘lsa, haqiqiy sharoitdagi bashoratlarda uning aniqligi 87–90% oralig‘ida aniqlangan. Natijada, tadqiqotchilar tomonidan KAN modelini yanada takomillashtirish masalasi ilgari surilgan va kelgusidagi rivojlantirish yo‘nalishlari belgilangan.

Литература

[1] Jamoliddin o‘g‘li N.N., Sodiqovich Y.S. RESPUBLIKAMIZDA TRANSPORT OQIMINI TASHKIL ETISHDA INTELLEKTUAL TRANSPORT TIZIMLARINING QO ‘LLANILISHI // ZAMONAVIY ILM-FAN VA TADQIQOTLAR: MUAMMO VA YECHIMLAR. 2024. Vol. 1, № 1. P. 25–30.
[2] Ibrohimjonovna D.M. TRANSPORT TIZIMIDA INTELLEKTUAL BILIMLARNI QO‘LLASH SALOHIYATI // Ta’lim innovatsiyasi va integratsiyasi. 2024. Vol. 12, № 2. P. 160–164.
[3] Chen C. et al. Traffic Flow Prediction Based on Deep Learning in Internet of Vehicles // IEEE Trans. Intell. Transport. Syst. 2021. Vol. 22, № 6. P. 3776–3789.
[4] Boukerche A., Tao Y., Sun P. Artificial intelligence-based vehicular traffic flow prediction methods for supporting intelligent transportation systems // Computer Networks. 2020. Vol. 182. P. 107484.
[5] Belhadi A. et al. A recurrent neural network for urban long-term traffic flow forecasting // Appl Intell. 2020. Vol. 50, № 10. P. 3252–3265.
[6] Oliveira D.D. et al. Forecasting vehicular traffic flow using MLP and LSTM // Neural Comput & Applic. 2021. Vol. 33, № 24. P. 17245–17256.
[7] Hussain B. et al. Intelligent Traffic Flow Prediction Using Optimized GRU Model // IEEE Access. 2021. Vol. 9. P. 100736–100746.
[8] Wang S. et al. Truck Traffic Flow Prediction Based on LSTM and GRU Methods With Sampled GPS Data // IEEE Access. 2020. Vol. 8. P. 208158–208169.
[9] Liu Z. et al. KAN: Kolmogorov-Arnold Networks:arXiv:2404.19756. arXiv, 2024.
[10] Vaca-Rubio C.J. et al. Kolmogorov-Arnold Networks (KANs) for Time Series Analysis: arXiv:2405.08790. arXiv, 2024.
[11] Genet R., Inzirillo H. TKAN: Temporal Kolmogorov-Arnold Networks: arXiv:2405.07344. arXiv, 2024.