Raqamli Transformatsiya va Sun’iy Intellekt
TELEKOMMUNIKATSIYA TIZIMLARIDA MA’LUMOTLARNI UZATISH SAMARADORLIGINI NEYRON TARMOQLAR YORDAMIDA OSHIRISHNING QIYOSIY TAHLILI VA SIMULYATSIYASI
1 “Toshkent irrigatsiya va qishloq xo‘jaligini mexanizatsiyalash muhandislari instituti” Milliy tadqiqot universiteti
Zenodo DOI: 10.5281/zenodo.22107752
Keywords
Abstract
Maqola ikki qismni ichiga olgan bo‘lib, birinchi qismda, telekommunikatsiyada ma’lumotlarni uzatishning turli bosqichlarida neyron tarmoqlarni qo‘llash bo‘yicha ishlar tahliliy sharh ko‘rinishda umumiylashtirilgan. Ikkinchi qismda Python muhitida Hamming (7,4) kodi, BPSK modulyatsiyasi va AWGN kanali uchun BER-SNR simulyatsiyasi o‘tkazilib, chuqur neyron tarmoqqa (DNN) asoslangan dekoder an’anaviy qattiq qarorli dekoder bilan taqqoslangan. Natijalar DNN dekoder bit xatoligi koeffitsienti (BER)=10-3 darajada an’anaviy usulda 1,2 dB ustun bo‘lib, optimal soft ML dekoderlashga deyarli teng natija berishini ko‘rsatdi.
References
- Saxena D., Singh A.K. A Proactive Autoscaling and Energy-Efficient VM Allocation Framework Using Online Multi-Resource Neural Network for Cloud Data Center // Neurocomputing (Elsevier). — 2021. — Vol. 426. — P. 248–264.
- Meenalakshmi M., Chaturvedi S., Dwivedi V.K. Deep Learning-Enabled Polar Code Decoders for 5G Networks and Beyond // AEU – International Journal of Electronics and Communications. — 2024. — Vol. 177. — Art. 155220.
- LeCun Y., Bengio Y., Hinton G. Deep Learning // Nature. — 2015. — Vol. 521. — P. 436–444.
- Mao Q., Hu F., Hao Q. Deep Learning in Physical Layer Communications: Evolution and Prospects in 5G and 6G Networks // IET Communications. — 2023. — Vol. 17, No. 16. — P. 1863–1876.
- A Novel Traffic Prediction Method Using Machine Learning for Energy Efficiency in Service Provider Networks // Sensors (MDPI). — 2023. — Vol. 23, No. 11. — Art. 4997.
- A DNN-Based 5G MIMO System Adopting a Mix of Tactics // Discover Electronics (Springer). — 2025. — Vol. 2.
- Zhang G. et al. Energy-Efficient Subchannel and Power Allocation for HetNets Based on Convolutional Neural Network // arXiv preprint. — 2019. — arXiv:1903.00165.
- Gruber T., Cammerer S., Hoydis J., ten Brink S. On Deep Learning-Based Channel Decoding // 51st Annual Conference on Information Sciences and Systems (CISS). — 2017. — P. 1–6.
- O‘Shea T., Hoydis J. An Introduction to Deep Learning for the Physical Layer // IEEE Transactions on Cognitive Communications and Networking. — 2017. — Vol. 3, No. 4. — P. 563–575.
- Advanced Mathematical Modelling for Energy-Efficient Data Transmission and Fusion in Wireless Sensor Networks // arXiv preprint. — 2024. — arXiv:2407.12806.
- Tera S.P., Chinthaginjala R., Natha P. et al. Deep Learning Assisted LDPC Decoding for 5G IoT Networks in Fading Environments // Scientific Reports. — 2025. — Vol. 15.
- Nachmani E., Be'ery Y., Burshtein D. Learning to Decode Linear Codes Using Deep Learning // 54th Annual Allerton Conference on Communication, Control, and Computing. — 2016. — P. 341–346.
- Chaudhary A. et al. Augmenting TCP Communication Efficiency in Cognitive Radio Networks Using Iterative Dimensional Neural Optimization // International Journal of Communication Systems (Wiley). — 2025.