Transmission Parameter-based Demodulation in Visible Light Communications using Deep Learning
محورهای موضوعی : Optical Communication
Sarah Ayashm
1
,
Seyed Sadra Kashef
2
,
Morteza Valizadeh
3
,
Hasti Akhavan
4
1 - Department of Electrical and Computer Engineering, Urmia University, Iran
2 - Department of Electrical and Computer Engineering, Urmia University, Iran
3 - Department of Electrical and Computer Engineering, Urmia University, Iran
4 - Department of Electrical and Computer Engineering, Urmia University, Iran
کلید واژه: Demodulation, VLC, Distances, Convolutional Neural Network, ISI,
چکیده مقاله :
This paper proposes an innovative approach by employing a one-dimensional Convolutional Neural Network (CNN) for demodulation in VLC systems. The used Data-set is real and available online, providing a robust foundation for analysis. It encompasses modulated signals in seven different modulation types, with 29 transmission distances ranging from 0 to 140 centimeters. By accounting for the varying distances between the transmitter and receiver, the model can more accurately interpret the received signals. Additionally, the study suggests that utilizing memory to learn previous symbols, which is essential for mitigating the effects of inter-symbol interference (ISI), can significantly improve demodulation accuracy. Our results of memory-based demodulation show a better performance in contrast to the previous one (AdaBoost).
This paper proposes an innovative approach by employing a one-dimensional Convolutional Neural Network (CNN) for demodulation in VLC systems. The used Data-set is real and available online, providing a robust foundation for analysis. It encompasses modulated signals in seven different modulation types, with 29 transmission distances ranging from 0 to 140 centimeters. By accounting for the varying distances between the transmitter and receiver, the model can more accurately interpret the received signals. Additionally, the study suggests that utilizing memory to learn previous symbols, which is essential for mitigating the effects of inter-symbol interference (ISI), can significantly improve demodulation accuracy. Our results of memory-based demodulation show a better performance in contrast to the previous one (AdaBoost).