Görünür Işık Haberleşme Sistemleri için Makine Öğrenmesi Destekli Alıcı Tasarımı

Abstract

Görünür Işık Haberleşme (GIH) Sistemleri, düşük enerji tüketim verimliliği nedeniyle birçok araştırmacı, çalışma ve projeden büyük ilgi toplamıştır. Bu nedenle; bu makale, alınan sinyal biçimine bakılmaksızın sürdürülebilir bir demodülatör yapısı sağlamak için bir makine öğrenme algoritması kullanılarak tasarlanan VLC tabanlı alıcı şemasına odaklanmaktadır. Veri iletiminin sağlanması için haberleşme sistemi, veri bitlerini algılamak için eşik değeri kullanımını gerektiren SPAM (Üst-üste Konumlandırılmış Darbe Genlik Modülasyonu) şemasını kullanmaktadır. Bu nedenle, alıcı birim, eğitim veri setini kullanarak değişken eşik değerini belirlemek için K-En Yakın Komşular (KNN) algoritması tabanlı bir yöntemden oluşmuştur. Önerilen yöntemin Alanda Programlanabilir Kapı Dizileri (FPGA) kartında uygulanabilmesi için bir mimari geliştirilmiştir. Makine öğrenimi tabanlı sistemi SPAM alıcı modeline entegre etmek için, dijital tasarım tekniklerini elde etmek amacıyla matematiksel bir çerçeve geliştirilmiştir. Bu nedenle, makalede hem teorik bir analiz hem de sayısal tasarım tabanlı bir alıcı sistemi önerilmiştir. Bunlara ek olarak, iletilen ve alınan bitler arasındaki fark ile ilgili makine öğrenmesi tabanlı sistemin performansını gözlemlemek için Doğrusal Geri Beslemeli Kaydırma Kaydı (LFSR) kullanılarak tasarlanan Eklemeli Beyaz Gauss Gürültüsü (AWGN) kanal modeli geliştirilmiştir.

Keywords

• FPGA
• makine öğrenmesi
• alıcı
• VLC.

Project Number

OKÜBAP-2023-PT2-046

Machine Learning-Assisted Receiver Design for Visible Light Communication Systems

Abstract

Visible Light Communication (VLC) Systems have been attracted considerable attention from many researchers, papers, and projects due to their energy consumption efficiency. Hence, this paper focuses on VLC-based receiver scheme that is designed by using a machine learning algorithm to provide a sustainable demodulator structure with regardless to received signal format. To provide data transmission, the communication system uses SPAM (Superposed Pulse Amplitude Modulation) scheme which requires the use of threshold values to detect data bits. Hence, the receiver unit consists of a K-Nearest Neighbors (KNN) algorithm-based method to determine variable threshold value by using a training data set. An architecture has been enhanced to implement in Field Programmable Gate Arrays (FPGA) board. To integrate the machine learning based system into SPAM receiver model, a mathematical framework is improved to obtain the digital design techniques. Therefore, both a theoretical analysis and a digital design-based receiver system have been proposed in the paper. Addition to these, an Additive White Gaussian Noise (AWGN) channel model, which is designed by using Linear Feedback Shift Register (LFSR) is improved to observe performance of the Machine Learning based System related to the difference between transmitted and received bits.

Keywords

• FPGA
• machine learning
• receiver
• VLC

Supporting Institution

Osmaniye Korkut Ata Universitesi

Project Number

OKÜBAP-2023-PT2-046

Thanks

Osmaniye Korkut Ata Universitesi

References

1. Xu B, Hussain B, Wang Y, Cheng HC, Yue CP. Smart home control system using vlc and bluetooth enabled ac light bulb for 3d indoor localization with centimeter-level precision. Sensors 2022, 22(21): 8181.
2. Al Hasnawi R, Marghescu I. A survey of vehicular VLC methodologies. Sensors 2024, 24(2): 598.
3. Vieira M, Vieira MA, Galvão G, Louro P, Fantoni A, Vieira P, Véstias M. Enhancing Airport Traffic Flow: Intelligent System Based on VLC, Rerouting Techniques, and Adaptive Reward Learning. Sensors 2025, 25(9): 2842.
4. Bhutani M, Singh B, Gupta A, Sudha K, Sharma S, Banerjee S, Talwar M, Chaurasiya VK. Visible Light Communication Technologies: A Review of IEEE 802.15. 7 and Its Role in Next‐Generation Networks. Int J Commun Syst. 2025, 38(11): e70149.
5. Ke X, Wei M, Qin H. Research on resource allocation of hybrid indoor VLC networks. Opt. Commun. 2025, 578: 131503.
6. Çürük SM. Comparison of Fourier and Trigonometric Transform based Multicarrier Modulations for Visible Light Communication. Turk J Sci Technol. 2024, 19(2): 397-405.
7. Li S, Pandharipande, A, Willems F M. Unidirectional visible light communication and illumination with LEDs. IEEE Sens J. 2016, 16(23): 8617-8626.
8. Yuan Y, Zhang M, Luo P, Ghassemlooy Z, Lang L, Wang D, Zhang B Han D. SVM-based detection in visible light communications. Optik 2017, 151, 55-64.

9. Şahan MK. Development of receiver structures for visible light communication systems, MSc, Osmaniye Korkut Ata University, Osmaniye, Türkiye, 2024.
10. Li JF, Huang ZT, Zhang RQ, Zeng FX, Jiang M, Ji YF. Superposed pulse amplitude modulation for visible light communication. Opt Express 2013, 21(25): 31006-31011.
11. Aydin B, Duman Ç. Examination of OOK modulation schemes in Li-Fi systems, Optik 2022, 270: 169996.
12. Bera K, Karmakar N. Interference Mitigation in VLC Systems using a Variable Focus Liquid Lens. Photonics 2024, 11(6): 506.
13. Sönmez, M. Artificial neural network-based threshold detection for OOK-VLC Systems. Opt Commun, 2020, 460: 125107.
14. Ma J, He J, Shi J, Zhou Z, Deng R. Nonlinear compensation based on k-means clustering algorithm for Nyquist PAM-4 VLC system. IEEE Photon Technol Lett. 2019, 31(12): 935-938.
15. Berenguer PW, Nölle M, Molle L, Raman T, Napoli A, Schubert C, Fischer JK. Nonlinear digital pre-distortion of transmitter components. J Lightwave Technol. 2015, 34(8): 1739-1745.
16. Zhang J, Si-Ma LH, Wang BQ, Zhang JK, Zhang YY. Low-complexity receivers and energy-efficient constellations for SPAD VLC systems. IEEE Photon Technol Lett 2016, 28(17): 1799-1802.
17. Saxena VN, Dwivedi VK, Gupta J. Machine learning in visible light communication system: A survey. Wirel Commun Mob Comput. 2023, 1: 3950657.
18. Perera A, Botirov K, Sallouha H, Katz M. ML-Aided 2D Indoor Positioning Using Energy Harvesters and Optical Detectors for Self Powered Light-based IoT Sensors. IEEE Sens J. 2025, 25(9): 15958-15967.
19. ElFar SH, Yaseen M, Ikki S. A Novel Machine Learning Algorithm With Mathematical Modeling for Channel Estimation in VLC Systems. IEEE Wirel. Commun Lett. 2025, 14(7): 2084-2088.
20. Singh A, Salameh HB, Ayyash M, Elgala H. Energy Efficient OIRS-aided VLC Systems Employing ML-based User Orientation and Obstacle Awareness. IEEE Sens J. 2024, 24(24): 42118-42126.
21. Ullah K, Salman M, Bolboli J, Chung WY. Image-based VLC Signal Demodulation Using Machine Learning. IEEE Commun Lett. 2025, 29(1): 145-149.
22. Sheikholeslami SM, Rasti-Meymandi A, Seyed-Mohammadi SJ, Abouei J, Plataniotis KN. Communication-efficient federated learning for hybrid VLC/RF indoor systems. IEEE Access, 2022, 10: 126479-126493.
23. Ma G, Parthiban R, Karmakar N. An artificial neural network-based handover scheme for hybrid LiFi networks. IEEE Access 2022, 10: 130350-130358.
24. Nguyen PD, Shiraki Y, Ishikawa K, Muramatsu J, Harada N, Moriya T. Distribution matching for dimming control in visible-light region-of-Interest signaling. IEEE Photon J 2023, 15(1): 1-14.
25. Sönmez M. The Performance Analysis of K-Nearest Neighbors Based Detection Algorithm in Visible Light Communication Systems. Int. J. Sci. Res. Publ. 2021, 11(12): 479-483.
26. Komine T, Nakagawa M. Fundamental analysis for visible-light communication system using LED lights. IEEE Trans. Consum. Electron. 2004, 50(1): 100-107.
27. Wang Z, Zhong WD, Yu C, Chen J, Francois CPS, Chen W. Performance of dimming control scheme in visible light communication system. Opt. Express 2012, 20(17): 18861-18868.
28. Neokosmidis I, Kamalakis T, Walewski JW, Inan B, Sphicopoulo T. Impact of nonlinear LED transfer function on discrete multitone modulation: Analytical approach. J of Lightwave Technol. 2009, 27(22): 4970-4978.