Machine learning is an approach that is useful when a practical optimisation problem is difficult to describe precisely. This approach has found multiple applications. Recently, the machine learning has been used in communication systems at the physical layer for designing the communication modems. The machine learning can improve the detection performance and, at the same time, reduce the modem complexity. The underwater acoustic communication deals with complex propagation channels. However, there are efficient numerical models for signal propagation in such channels. Therefore, a good training of machine learning techniques is possible, thus eliminating one of the main problems of application of machine learning in practice. This project will deal with development of innovative techniques based on machine learning for joint channel estimation and data demodulation in underwater acoustic channels. This activity will be based on using underwater channel models developed in the Underwater Information Systems Group at York, and recent results on development and experimental investigation of underwater acoustic modems. The project will involve modern methods of the optimization theory, linear algebra, mathematical statistics, as well as using numerical simulation in Matlab and/or other software platforms. The modem designs will be tested in the university water tank, lake, and sea experiments.
It is also possible to do this research in an MSc by Research project.
Candidates should have (or expect to obtain) a minimum of a UK upper second class honours degree (2.1) or equivalent in Electronic and Electrical Engineering, Physics, Computer Science, Mathematics or a closely related subject.
How to apply:
Applicants should apply via the University’s online application system at https://www.york.ac.uk/study/postgraduate-research/apply/. Please read the application guidance first so that you understand the various steps in the application process.