The University of Liverpool and STFC’s Hartree centre have developed this studentship in partnership with Gencoa, a medium-sized company based in Liverpool.
The studentship aims to marry Gencoa’s optical plasma sensing capabilities with novel signal processing algorithms to enable smarter self-learning diagnostic tools that can be applied on, for example, the production lines for mobile phone components. Once these algorithms are embedded within the Gencoa’s OPTIX gas sensing product, the production line will have increased productivity and a differentiated market position longer-term.
In the context of a production line, both run-time speed and accuracy are important: while impurities may be orders of magnitude less abundant than other gasses present, the impact of not detecting them can be significant. Mature algorithms exist for processing spectra. However, these algorithms are either fast and inaccurate or accurate and (very) slow.
The aim of this project is to develop algorithms that are both fast and accurate. The proposed approach is to speed up mature numerical Bayesian algorithms that are already accurate. These algorithms are accurate because they search over the space of all combinations of peaks that could be present in each spectrum. The algorithms explicitly compare the measured spectrum with those associated with each combination and also explicitly consider the extent to which the combination is consistent with prior knowledge (Gencoa are developing libraries to make it possible to predict which set of peaks would be likely to co-occur; a single impurity will typically give rise to multiple peaks). This approach makes it possible for the algorithms to make accurate inferences about whether a bump in the noise-floor or on the side of a large peak is caused by chance or by the presence of a low-amplitude peak.
We have identified three ways of increasing speed. First, we will use a fast search algorithm (Hierarchical Importance with Nested Training Samples, HINTS). Second, we will embed that search algorithm in a statistical framework (Sequential Monte Carlo (SMC) samplers) that makes parallel processing (eg on GPUs and large compute clusters) possible. Third, we will enhance a pre-existing parallel implementation of SMC samplers to be suited to the problem class that this algorithmic challenge exemplifies (where existing approaches to load-balancing are ineffective). We do not believe any of these techniques have been applied to spectral analysis in the past. Combining them is likely to result in significant benefits to Gencoa, but also to the many other organisations that rely on spectral analysis to support their activities.
This project is part of the EPSRC Funded CDT in Distributed Algorithms: The What, How and where of Next-Generation Data Science. https://www.liverpool.ac.uk/research/research-at-liverpool/research-themes/digital/cdt-distributed-algorithms/
The University of Liverpool is working in partnership with the STFC Hartree Centre and other industrial 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 data science, be it in academia or industry.
Each student is based at the University of Liverpool and every project within the centre is offered in collaboration with an Industrial partner who as well as providing co-supervision and placements will also offer the unique opportunity for students to access state of the art computing platforms, work on real world problems, benchmarking and data. Our graduates will gain unparalleled experiences working across academic disciplines in highly sought-after topic areas, answering industry need.
As well as learning from academic and industrial world leaders, the centre has a dedicated programme of interdisciplinary research training including the opportunity to undertake modules at the global pinnacle of Data science teaching. A large number of events and training sessions are undertaken as a cohort of PhD students, allowing you to build personal and professional relationships that we hope will lead to research collaboration either now or in your future.
The learning nurtured at this centre will be based upon anticipation of the hardware recourses arriving on desks of students after they graduate, rather than the hardware available today.
For information technical queries please contact Marco Broccardo [email protected]
or Luke Mason [email protected]
For general application process queries contact [email protected]