Machine learning for signal demodulation in underwater wireless optical communications

Abstract

The underwater wireless optical communication (UWOC) system has gradually become essential to underwater wireless communication technology. Unlike other existing works on UWOC systems, this paper evaluates the proposed machine learning-based signal demodulation methods through the selfbuilt experimental platform. Based on such a platform, we first construct a real signal dataset with ten modulation methods. Then, we propose a deep belief network (DBN)-based demodulator for feature extraction and multi-class feature classification. We also design an adaptive boosting (AdaBoost) demodulator as an alternative scheme without feature filtering for multiple modulated signals. Finally, it is demonstrated by extensive experimental results that the AdaBoost demodulator significantly outperforms the other algorithms. It also reveals that the demodulator accuracy decreases as the modulation order increases for a fixed received optical power. A higher-order modulation may achieve a higher effective transmission rate when the signal-to-noise ratio (SNR) is higher.