CNN based prediction of modulation techniques in Li-Fi
-
Aryan Singh Pundir
and
Prashast Pathak
Abstract
Visible light communication (VLC) being a key component of light-fidelity (Li-Fi), requires adaptive and efficient modulation techniques to guarantee reliable data transmission under varying channel conditions. This study focuses on the prediction of modulation techniques in VLC systems, namely, on-off keying (OOK), pulse position modulation (PPM): 4-PPM, 8-PPM and 16-PPM, 4 – differential pulse interval modulation (DPIM), orthogonal frequency division multiplexing (OFDM) and generalized space shift keying (GSSK), using machine learning based approach. A convolutional neural network (CNN) is trained on a synthetic dataset which is generated under varying channel conditions and noise levels. The trained model is then used to classify modulation techniques based on signal features extracted from simulated VLC signals. The model is then exported and used to predict modulation techniques in a different dataset. The outcomes demonstrate CNNs’ effectiveness in real time modulation technique prediction. This method presents a viable way to boost Li-Fi communication effectiveness in varying environments.
-
Research ethics: Not applicable.
-
Informed consent: Not applicable.
-
Author contributions: The authors have accepted responsibility for the entire content of this manuscript and approved its submission.
-
Use of Large Language Models, AI and Machine Learning Tools: None declared.
-
Conflict of interest: The authors state no conflict of interest.
-
Research funding: None declared.
-
Data availability: The raw data can be obtained on request from the corresponding author.
References
1. Karoti, NM, Paramita, S, Ahmad, R, Bohara, VA, Srivastava, A. Improving the performance of heterogeneous LiFi-WiFi network using a novel link aggregation framework. In: Proc. IEEE wireless communications and networking conference (WCNC). Austin, TX, USA: IEEE; 2022:2322–7 pp.10.1109/WCNC51071.2022.9771553Search in Google Scholar
2. Aliaberi, A, Sofotasios, PC, Muhaidat, S. Modulation schemes for visible light communications. In: Proc. international conference on advanced communication technologies and networking (CommNet). Rabat, Morocco: IEEE; 2019:1–10 pp.10.1109/COMMNET.2019.8742376Search in Google Scholar
3. Mahdiraji, GA, Zahedi, E. Comparison of selected digital modulation schemes (OOK, PPM and DPIM) for wireless optical communications. In: Proc. 4th student conference on research and development (SCOReD). Shah Alam, Malaysia: IEEE; 2006:5–10 pp.10.1109/SCORED.2006.4339297Search in Google Scholar
4. LeCun, Y, Bengio, Y, Hinton, G. Deep learning. Nature 2015;521:436–44. https://doi.org/10.1038/nature14539.Search in Google Scholar PubMed
5. Krizhevsky, A, Sutskever, I, Hinton, GE. ImageNet classification with deep convolutional neural networks. In: Proc. advances in neural information processing systems (NeurIPS). Lake Tahoe, Nevada, USA: NIPS Foundation Inc.; 2012, 25:1097–105 pp.Search in Google Scholar
6. Simonyan, K, Zisserman, A. Very deep convolutional networks for large-scale image recognition. In: Proc. international conference on learning representations (ICLR); 2015.10.1109/ICCV.2015.314Search in Google Scholar
7. Zeiler, M, Fergus, R. Visualizing and understanding convolutional networks. In: Proc. European conference on computer vision (ECCV). Zurich, Switzerland: Springer; 2014, 8689:818–33 pp.10.1007/978-3-319-10590-1_53Search in Google Scholar
8. Goodfellow, I, Bengio, Y, Courville, A. Deep learning. Cambridge, MA: MIT Press; 2016.Search in Google Scholar
9. Kingma, DP, Ba, LJ.: a method for stochastic optimization. In: Proc. international conference on learning representations (ICLR 2015), San Diego, CA, USA; 2015:1–13 pp.Search in Google Scholar
10. Wu, X, Safari, M, Haas, H. Access point selection for hybrid Li-Fi and Wi-Fi networks. IEEE Trans Commun 2017;65:5375–85. https://doi.org/10.1109/tcomm.2017.2740211.Search in Google Scholar
11. Peng, S, Jiang, H, Wang, H, Alwageed, H, Yao, YD. Modulation classification using convolutional neural network-based deep learning model. In: Proc. 26th wireless and optical communication conference (WOCC). Newark, NJ, USA: IEEE; 2017:1–5 pp.10.1109/WOCC.2017.7929000Search in Google Scholar
© 2025 Walter de Gruyter GmbH, Berlin/Boston
