University of East Anglia
This PhD project is concerned with developing machine learning methods to improve the performance of seabed mapping within sonar-based systems. When surveying a region of seabed, sonar systems emit a short burst of sound (known as a ping) and as this encounters seabed surfaces or underwater objects, reflections are produced that can be detected. Measuring the angle and duration of the ping return allows the depth at a given location to be calculated. However, each ping results in tens of thousands of returns, with the majority of them being produced by noise. At present, trained human operators apply filters to remove these noise returns to leave, ideally, only those returns that correspond to a genuine seabed or object.
This can essentially be considered a classification problem (i.e. for each ping return, does it correspond to a genuine object or is it noise in which case it can be removed) and is well-suited to machine learning methods. Specifically, the project will examine supervised learning, unsupervised learning and reinforcement learning methods to classify each ping return as either genuine or noise. The effectiveness of approaches will be evaluated against ground-truth data that has been created by experienced human surveyors.
The project is in collaboration with GeoAcoustics Limited, who is a company that designs and manufactures systems for seabed mapping. GeoAcoustics will provide a broad range of sonar data for development as well as providing technical guidance through an industry-based supervisor. There will also be opportunities for placements within GeoAcoustics and to work within their team of engineers.
Primary supervisor: Ben Milner ([email protected] )
Start date: October 2023
For more information on this project, please visit www.uea.ac.uk
Entry requirements: UG First class degree or Distinction at Master’s in Computing science, electronic engineering, applied mathematics
This PhD project is in a competition for studentships allocated to the School of Computing Sciences as a direct result is increased PGT student fee income for the MSc Courses in Cyber Security, Data Science and Computing Sciences. All successful candidates will be expected to support PGT Lab sessions from October 2023 and related activities as allocated in support of these programmes within the working hours permitted for full-time Postgraduate Researchers.
Funding comprises ‘home’ tuition fees and an annual stipend (2022/23 rate is £17,668, 2023/24 tbc) for a maximum of 3 years.
View or Apply
To help us track our recruitment effort, please indicate in your cover/motivation letter where (globalvacancies.org) you saw this job posting.
