This PhD project is part of the CDT in Distributed Algorithms: The What, How and where of Next-Generation Data Science.
The University of Liverpool’s Centre for Doctoral Training in Distributed Algorithms (CDT) is working in partnership with the STFC Hartree Centre and 20+ external partners from the manufacturing, defence and security sectors to provide a 4-year innovative PhD training course that will equip over 60 students with: the essential skills needed to become future leaders in distributed algorithms; the technical and professional networks needed to launch a career in next generation data science and future computing; and the confidence to make a positive difference in society, the economy and beyond.
The successful PhD student will be co-supervised and work alongside our external partner Leonardo, and will seek to establish whether multi-modal airborne sensor data, used early in the signal processing chain, can be used to detect and classify objects earlier in the processing chain leading to improved detection and classification performance.
Machine learning algorithms have been applied successfully for many years to databases of visual imagery for the recognition of objects in a scene. Sensors working at radio frequency mostly produce low-resolution data where the signals detected are more abstract and require algorithmic processing to present the information to the human operator.
Radio Frequency sensors can operate actively (detecting reflected signals from objects illuminated by their own transmission) and passively (intercepting emissions and reflections from objects). The characteristics of a target can depend on both reflections and interceptions of RF emissions, which are likely to be at different frequencies and are often context dependent. Long established classical target tracking and detection methods are used by a variety of defence and security applications and tend to work by removing everything that does not look like the signal of interest, which may throw away valuable information and context in the process. This process is typically performed on each type of data separately and only the processed outputs are combined. Real-time co-processing of multiple sensor data streams is analytically and computationally challenging. Fusion of this data usually does not occur until after the individual classical detection processes. However, machine learning techniques may be able to learn to extract the beneficial features from sensor data of the scene to detect all objects of interest and provide classification of object types earlier in the processing than is usually possible.
We will develop new deep learning techniques in the field of artificial intelligence for the accurate classification and detection tasks. To achieve this goal, the student will investigate new ways for effectively enhancing the low resolution images and fusing the data from different sensors so as to extract most useful information for the detection and classification tasks. Supervised, semi-supervised and unsupervised approaches will be investigated in order to achieve the most reliable and accurate solutions. Domain adaption and data augment techniques will be used to improve the generalisation ability of the developed models. These new developments in deep learning will be deeply rooted in the advances in mathematical image processing such as total variational approaches for the segmentation, registration and enhancement. We are expecting that the student will develop an end-to end machine learning solution applicable for the multi-modal airborne sensor data at the end of the project.
There are many possible and interesting approaches for turning low-resolution data into high resolution data, in the emerging field of super resolution, all making use of feature geometry and calculus of variations coupled with novel design of active and loss functions in machine and deep learning context. Therefore, an ideal candidate must have a good degree (e.g. 2:1 or MSc) either in Mathematics (nonlinear optimization, calculus of variations, partial different equations, and iterative methods for nonlinear systems) or in computer science or data sciences (Python or C++ programming, machine learning and deep learning algorithms). Some previous research experience will be highly desirable but not mandatory. The CDT offers a variety of technical and professional training and support for all studentships.
Students are based at the University of Liverpool and part of the CDT and Signal Processing research community. Every PhD is part of a larger research group which is an incredibly social and creative group working together solving tough research problems. Students have 2 academic supervisors and an industrial partner who provides co-supervision, placements and the opportunity to work on real world challenges. In addition, students attend technical and professional training to gain unparalleled expertise to make a difference now and in the future.
This studentship is due to commence 1 October 2021 (Covid-19 Working Practices available).
For any enquiries please contact the supervisors Dr Zheng: [Email Address Removed] and Professor Chen: [Email Address Removed] in the first instance or visit the CDT website for Director, Student Ambassador and Centre Manager details.
Visit the CDT website for application instructions, FAQs, interview timelines and tips.