Enhancing real-time performance in digital wireless communications using embedded machine learning

The overall research hypothesis addressed by this project is that machine learning can provide quantitative insights into the likelihood of successful message transmissions over a wireless communication channel by analysing and learning from messages previously sent over the same and adjacent communication channels. Such quantitative insights could then be used to reduce uncertainty and therefore assist schedulers to achieve timely and reliable delivery of messages in real-time distributed systems and to provide valuable metrics when evaluating and optimizing wireless communication systems in general. The project will focus on producing models and algorithms that can be executed in small devices with limited processing and storage capabilities, as well as limited communication bandwidth, as those are the limitations typically found in Internet-of-Things and amateur radio which are the main case studies to be addressed in the project.

<p>The methodology used in the project will follow distinct training and deployment stages, which is typical for ML-based systems. The first stage will obtain large datasets which can train ML models in a way that they can correlate the observed conditions of the wireless channel (i.e. by decoding and analysing messages) with successful or unsuccessful transmissions under a variety of scenarios. Once a model has been trained sufficiently, it is used in the deployment stage to guide scheduler and resource management algorithms in the wireless transceiver. Given the quantitative estimation provided by the ML subsystem, the algorithms can decide parameters for message transmissions (e.g. schedule, choice of frequency/channel, choice of antenna, power, data rate, maximum number of retransmissions) so that a statistical guarantee can be ensured for each message type. For example, scheduling algorithms could be designed to ensure at least 90% of high-criticality messages and at least 75% of low-criticality messages are successfully delivered by their deadlines, and to perform graceful degradation of those guarantees based on estimates by the ML subsystem.<br /> <br /> The ideal candidate will have a degree in Computer Science, Electronic Engineering, or similar, solid programming and software engineering skills, experience in research and development (including the production of technical reports/articles). Desirable skills and experience include: practical application of machine learning algorithms and libraries to real-world problems; embedded systems; scheduling algorithms and real-time analysis; wireless communications: fundamentals (signals, modulation, channel modelling) and practical experience (setting up antennas, transceivers, measurement equipment); and the required knowledge to obtain an amateur radio license in the UK (more details: <a href="http://rsgb.org">Radio Society of Great Britain</a> and <a href="http://ofcom.org.uk">Ofcom</a>).</p> <p>In case of equivalent qualifications and experience, priority will be given to applicants from developing countries and/or from underrepresented groups.</p> <p>This is a fully-funded position, supported by a grant from <a href="http://ardc.net">ARDC</a> covering the PhD fees and providing a stipend for the whole duration of the studies.<br />  </p>

<p>Formal applications for research degree study should be made online through the <a href="https://www.leeds.ac.uk/research-applying/doc/applying-research-degrees">University's website</a>. Please state clearly in the research information section that the research degree you wish to be considered for is <strong>Enhancing real-time performance in digital wireless communications using embedded machine learning</strong> as well as <a href="https://eps.leeds.ac.uk/computing/staff/14038/">Prof Leandro Soares Indrusiak</a> as your proposed supervisor.</p> <p>If English is not your first language, you must provide evidence that you meet the University's minimum English language requirements (below).</p> <p><em>As an international research-intensive university, we welcome students from all walks of life and from across the world. We foster an inclusive environment where all can flourish and prosper, and we are proud of our strong commitment to student education. Across all Faculties we are dedicated to diversifying our community and we welcome the unique contributions that individuals can bring, and particularly encourage applications from, but not limited to Black, Asian, people who belong to a minority ethnic community, people who identify as LGBT+ and people with disabilities. Applicants will always be selected based on merit and ability.</em></p>

Applicants to research degree programmes should normally have at least a first class or an upper second class British Bachelors Honours degree (or equivalent) in an appropriate discipline. The criteria for entry for some research degrees may be higher, for example, several faculties, also require a Masters degree. Applicants are advised to check with the relevant School prior to making an application. Applicants who are uncertain about the requirements for a particular research degree are advised to contact the School or Graduate School prior to making an application.

The minimum English language entry requirement for research postgraduate research study is an IELTS of 6.0 overall with at least 5.5 in each component (reading, writing, listening and speaking) or equivalent. The test must be dated within two years of the start date of the course in order to be valid. Some schools and faculties have a higher requirement.

<p>Fully-funded PhD, covering university fees and a stipend currently of £19,237 for your living costs, at the levels set by UKRI. The funding is provided by a grant from <a href="https://www.ardc.net/">ARDC</a>.</p> <p><strong>Important: </strong> Any costs associated with your arrival at the University of Leeds to start your PhD including flights, immigration health surcharge/medical insurance and Visa costs are not covered under this studentship.</p> <p>Please refer to the <a href="https://www.ukcisa.org.uk/">UKCISA</a> website for information regarding Fee Status for Non-UK Nationals.</p>

<p>For further information about your application, please contact Doctoral College Admissions by email to <a href="mailto:phd@engineering.leeds.ac.uk">phd@engineering.leeds.ac.uk</a>.</p>