SUN’IY INTELLEKTGA ASOSLANGAN RADIOTEXNIKA TIZIMLARINING AXBOROTNI QAYTA ISHLASH OPERATORI UCHUN AVTOMATLASHTIRILGAN ISH STANSIYASINI ISHLAB CHIQISH
Article Sidebar
Main Article Content
Abstract:
Maqolada radio-efir monitoringi jarayonini avtomatlashtirish uchun konvolyutsion neyron tarmog‘i (CNN) va SDR (Software Defined Radio) texnologiyalarini qo‘llash masalalari ko‘rib chiqiladi. Tadqiqotda kirish ma’lumotlari sifatida o‘lchamli spektrogrammalar ishlatiladi. 33 milliondan ortiq parametrga ega bo‘lgan CNN modelini real vaqt rejimida ishga tushirish uchun NVIDIA RTX 4090 grafik protsessori imkoniyatlari tahlil qilinadi.
Article Details
How to Cite:
References:
O'Shea, T. J., & West, N. (2016). Radio Machine Learning Dataset Generation with GNU Radio. Proceedings of the GNU Radio Conference.
Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press.
NVIDIA. (2022). NVIDIA Ada Lovelace Architecture: Whitepaper.
Chollet, F. (2017). Deep Learning with Python. Manning Publications.
Wang, J., et al. (2019). Deep Learning for Wireless Communications: An Emerging Paradigm. IEEE Wireless Communications.
Zhu, Z., et al. (2021). Deep Learning-Based Automatic Modulation Recognition: Models, Datasets, and Challenges. IEEE Access.
Ettus Research. (2023). USRP B210 Hardware Specifications and Manual.
Zhang, M., et al. (2018). Automatic Modulation Classification Using Deep Learning in the Presence of Signal Impairments. IEEE Transactions on Cognitive Communications and Networking.
Liu, X., et al. (2017). Deep Learning-based Automatic Modulation Recognition for Cognitive Radio. Proceedings of the International Conference on Communications.
Ramjee, S., et al. (2019). Fast Deep Learning for Automatic Modulation Classification. IEEE Access.