Decreasing Noise In Acoustic Underwater Transmissions Using Deep Neural Networks

Scientists from Xiamen University and the University of Witwatersrand have designed a new deep learning model to improve the accuracy of ocean and offshore transmissions. This model facilitates the detection of sparse interference in channels despite the presence of other, more common interference such as ambient noise, which was not possible with traditional denoising models. The research study was published in Intelligent and Converged Networks and is a meaningful effort towards reliable underwater transmission in harsh ocean environments.