Sun'iy intellekt yordamida signallardagi shovqinlarni tozalashning zamonaviy usullari
Abstract
Ushbu maqolada telekommunikatsiya va raqamli aloqa tizimlarida uzatilayotgan signallarni turli xil shovqinlardan (noise) tozalashning dolzarb muammolari tahlil qilingan. An'anaviy matematik filtrlash usullarining cheklovlari ko'rib chiqilib, ularning o'rniga sun'iy intellekt (SI) hamda chuqur o'rganish (Deep Learning) modellariga (DAE, CNN, GAN) asoslangan zamonaviy yondashuvlar taklif etilgan. Maqolada SI modellarining asimptotik samaradorligi asoslab berilgan va signallarni qayta ishlash tizimlariga ushbu algoritmlarni joriy etish bo'yicha amaliy tavsiyalar keltirilgan.
Kalit so'zlar: Signallarni qayta ishlash, shovqin (noise), sun'iy intellekt, chuqur o'rganish (Deep Learning), denoising, neyron tarmoqlari, telekommunikatsiya tizimlari, raqamli filtrlash.
References
1. Haykin, S. (2013). Digital Communication Systems. John Wiley & Sons.
2. Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press.
3. O'Shea, T. J., & Hoydis, J. (2017). An Introduction to Deep Learning for the Physical Layer. IEEE Transactions on Cognitive Communications and Networking.
4. Zhang, K., Zuo, W., Chen, Y., Meng, D., & Zhang, L. (2017). Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising. IEEE Transactions on Image Processing.
5. Proakis, J. G., & Salehi, M. (2008). Digital Communications. McGraw-Hill Education.
