De-Noising Scheme for VLC-Based V2V Systems; A Machine Learning Approach
| Autor: | Hasan Farahneh, Fatima Hussian, Xavier Fernando |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Sunlight
Computer science business.industry Ambient noise level Irradiance Visible light communication 020206 networking & telecommunications 02 engineering and technology Filter (signal processing) Solar irradiance Communications system Machine learning computer.software_genre Adaptive filter Noise Signal-to-noise ratio 0202 electrical engineering electronic engineering information engineering General Earth and Planetary Sciences 020201 artificial intelligence & image processing Artificial intelligence business computer General Environmental Science |
| Zdroj: | Procedia Computer Science. 171:2167-2176 |
| ISSN: | 1877-0509 |
| DOI: | 10.1016/j.procs.2020.04.234 |
| Popis: | Ambient light noise is a major cause of performance degradation in visible light communication (VLC) systems. It affects outdoor VLC applications in terms of signal to noise ratio (SNR) and bit error rates (BER). Sunlight plays an important role in increasing the effects of ambient noise on VLC signal. VLC is suggested as a promising communication mode between two vehicles, in vehicle-to-vehicle (V2V) communication systems. In this paper, we discuss and propose an efficient method to overcome the effect of sunlight irradiance in VLC links used for V2V communication. We propose K-Nearest Neighbour (KNN), a machine learning-based adaptive filter to combat the effects of solar irradiance. Our smart filter can adapt itself according to varying noise conditions and help to achieve acceptable BER in support of reliable communications. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|