STFC IAA Bristol
Lead Research Organisation:
University of Bristol
Department Name: Chemistry
Abstract
Abstracts are not currently available in GtR for all funded research. This is normally because the abstract was not required at the time of proposal submission, but may be because it included sensitive information such as personal details.
Organisations
- University of Bristol (Lead Research Organisation)
- Hamamatsu Photonics (UK) Ltd (Collaboration)
- NORTH BRISTOL NHS TRUST (Collaboration)
- Hormuud Telecom (Collaboration)
- State Agency of Ukraine for Exclusion Zone Management (Collaboration)
- Telesom (Collaboration)
- SELLAFIELD LTD (Collaboration)
- Amazon.com (Collaboration)
People |
ORCID iD |
| Craig Butts (Principal Investigator) |
| Description | Research Grant, Standard TFS |
| Amount | £438,966 (GBP) |
| Funding ID | ST/Y509954/1 |
| Organisation | Science and Technologies Facilities Council (STFC) |
| Sector | Public |
| Country | United Kingdom |
| Start | 11/2023 |
| End | 10/2026 |
| Description | Applying Fast machine Learning to Medical Imaging |
| Organisation | North Bristol NHS Trust |
| Country | United Kingdom |
| Sector | Academic/University |
| PI Contribution | The vast amount of data the LHC provides necessitates that complex pattern recognition, clustering, and classification has to be done to record exciting physics signatures at a manageable rate. This problem is unique in that these algorithms have to work on the order of 100s of nanoseconds and be extremely reliable. This is the cutting edge of fast data selection, and to accomplish this goal we use state-of-the-art electronics systems coupled with machine learning tools. The PI, and co-I, Brooke, along with the Bristol group are world leading experts in this area with demonstrated ability to develop algorithms using custom electronics technologies. These technologies are now becoming commercially available which opens the door to new applications. We have expertise in the implementation and commissioning of these systems, as well as the evaluation of performance. These are the very skills necessary to transition this system to other areas. Co-I, Kuwertz, is an experienced data scientist, especially in working on interdisciplinary data science projects and bringing together experts across domains. |
| Collaborator Contribution | This project seeks to explore how to improve the diagnostic capability of medical imaging by using real-time machine learning tools. In practice the idea is to understand how we can speed up existing techniques where currently human processing or analysis takes place after the fact and to enhance existing techniques by providing new information in real-time e.g., where immediate feedback on an image can help to direct where to perform further scans. A further objective is to understand the potential benefit for adaptive imaging i.e. where the next scans depend on those taken previously. |
| Impact | We have applied for a full time 1.0FTE researcher to continue the technical development of our project from the UKRI Early Stage R & D call. We engaged with our local hospital and local consultant staff to understand the benefits our technology could bring. The lack of widespread use of ML tools to aid medical staff was a key issue we discovered. This seems to be the case not just in the medical arena but other public sector areas. |
| Start Year | 2022 |
| Description | Development through Data Science for Somaliland - Phase 2 - Hormuud Telecom |
| Organisation | Hormuud Telecom |
| Country | Somalia |
| Sector | Private |
| PI Contribution | We will grow the course next year significantly. Amoud University wants to send 246 students. The University of Hargeisa will double its students on the course to 50, and the University of Burao will also send more students. In addition, we will have staff from industry partners joining as well: Central bank in Somaliland, Hormuud Telecom, Premier Bank and Innovii Digital Service, in addition to staff of our current partners Telesom and Candlelight. |
| Collaborator Contribution | £5,000 |
| Impact | Teach data science to a large body of students to help economic development. We aimed to grow the numbers. last yearwe had ~80 students. This year we had near to 700 coming from more institutes. |
| Start Year | 2022 |
| Description | Development through Data Science for Somaliland Phase 2 - Telesom |
| Organisation | Telesom |
| Country | Somalia |
| Sector | Private |
| PI Contribution | Development through Data Science for Somaliland (DDSS) Phase 2 builds on our very successful DDSS program. We have been teaching Data Science techniques, including Python programming and machine learning, to a diverse audience in Somaliland. We have over 300 students signed up for phase 2 training coming from three universities and six industry partners. In addition, we will start a collaborative research program with Somaliland academic colleagues to embed the new knowledge and build on it. Furthermore, we want to exploit green computing with a Somaliland industry partner. This is a great way to combat climate change while generating sustainable economic development in Somaliland. |
| Collaborator Contribution | Telesom, the foremost telecom company in Somaliland, has recently made a pledge that they want to move to full solar power by 2030. We are discussing with Telesom to move part of our cancer treatment simulations to Telesom's fully solar powered facilities and thus emit zero carbon while doing our calculations. Our work, together with our Somaliland partners, is an ideal beta user test case, after which Telesom can offer this as a product. |
| Impact | We had the following aims and met them all: -) teach data science to a large body of students to help economic development. We aimed to grow the numbers. last year we had ~80 students. This year we had near to 700 coming from more institutes. -) We wanted to expand the number of sessions and the scope of the course. We indeed increased the teaching sessions from 15 to 19. Similarly, we increased the number of industry lectures from 10 to 15. -) We wanted to move some of our cancer research simulation to Somalia and we did. It is running stably. We are now pursuing a commercial launch of this service in the UK in partnership with Hormuud Telecom (and Telesom in a later phase). |
| Start Year | 2022 |
| Description | Distributed Radiation Monitoring Technology into the Chornobyl Exclusion Zone - Hamamatsu |
| Organisation | Hamamatsu Photonics (UK) Ltd |
| Country | United Kingdom |
| Sector | Private |
| PI Contribution | UoB's School of Physics/Interface Analysis Centre (IAC) has already developed and validated the necessary hardware and software that together comprises the radiation detector modules and the cloud-based AI-enabled "Overwatch" analytics and visualisation system. Therefore, the system architecture/design is 'ready-to-go' and just requires the additional units to be assembled ahead of deployment in Ukraine. The costs associated with this project are solely for the manufacture of five units to be sent to Ukraine. The project team have an impressive track record in the production, deployment and subsequent commercialisation of the industrially applicable technologies developed. |
| Collaborator Contribution | Hamamatsu wishes to support this work through valuable in-direct and in-kind means. As part of this project, we will supply the UoB team with our C12137-01 (or variants thereof) radiation detection module at cost price. This equates to an approximate £2,000 saving on each device, which has a typical purchase price of £3,950 (plus shipping) to our non-academic customers. Hamamatsu will of course continue to provide Peter and the team with ongoing technical support and guidance, as needed, during any projects that utilise our hardware. |
| Impact | This project sought to implement UoB 'on-edge' radiation detection capabilities to the ChEZ, replacing the infrastructure that was damaged during the Russian occupation of the Zone from February 2022. The project also sought to transfer knowledge and capabilities to Ukrainian national agencies responsible for in-zone monitoring. |
| Start Year | 2022 |
| Description | Distributed Radiation Monitoring Technology into the Chornobyl Exclusion Zone - SAUEZM |
| Organisation | State Agency of Ukraine for Exclusion Zone Management |
| Country | Ukraine |
| Sector | Public |
| PI Contribution | UoB's School of Physics/Interface Analysis Centre (IAC) has already developed and validated the necessary hardware and software that together comprises the radiation detector modules and the cloud-based AI-enabled "Overwatch" analytics and visualisation system. Therefore, the system architecture/design is 'ready-to-go' and just requires the additional units to be assembled ahead of deployment in Ukraine. The costs associated with this project are solely for the manufacture of five units to be sent to Ukraine. The project team have an impressive track record in the production, deployment and subsequent commercialisation of the industrially applicable technologies developed. |
| Collaborator Contribution | We wish to show our willingness to act as 'end-users' for this project. To facilitate this, we will work alongside the ISPNPP-UoB team as we have done before during other successful deployments of technology. |
| Impact | This project sought to implement UoB 'on-edge' radiation detection capabilities to the ChEZ, replacing the infrastructure that was damaged during the Russian occupation of the Zone from February 2022. The project also sought to transfer knowledge and capabilities to Ukrainian national agencies responsible for in-zone monitoring. |
| Start Year | 2022 |
| Description | The AI City - Amazon Web Services |
| Organisation | Amazon.com |
| Department | Amazon Web Services |
| Country | United States |
| Sector | Private |
| PI Contribution | Following the successful implementation of a city-wide IoT enabled and AI assisted radiation monitoring and anomaly detection provision, (that has attracted the attention of UK and overseas Governments) this IAA project will advance and deploy an expanded static and vehicular-based network of low-cost and resilient environmental sensors. By assimilating the real-time and multi-variable data into the University of Bristol's (UoB) unique and cutting-edge AI/MLbased self-learning analysis, trend identification, cause/correlation attribution, and visualisation platform, the system will allow scientists, policymakers, citizens, and other stakeholders to understand, predict and manage natural and anthropogenic environmental factors, triggers, and effects. |
| Collaborator Contribution | In the course of your initiative, we envisage providing you with the technical and product support which will enable you to make the best possible use of our services to achieve your research aims - namely our Artificial Intelligence (AI) and Machine Learning (ML) platforms. The university's AWS Partner University status provides academics with access to AWS Certification opportunities. We anticipate liaising closely with you and with your project team to ensure that your training and skills needs are appropriately addressed and enhanced. To best support your utilization of the AWS solution portfolio during your project, AWS is willing to offer 6-months of pro-bono AWS Prepayment Cloud-Credits as well as ongoing support throughout its duration by our in-house technical development team - therefore ensuring your project gets the most out of the unique features that AWS can offer. We value the in-kind support of AWS in relation to your proposal to be at a value of approximately £8,000. |
| Impact | The deployment of mobile and resilient sensor-based monitoring systems within BCC vehicles, with data delivered (in realtime) directly to an online portal for expert (and non-expert) visualisation and interpretation. |
| Start Year | 2022 |
| Description | The AI City - Sellafield |
| Organisation | Sellafield Ltd |
| Country | United Kingdom |
| Sector | Private |
| PI Contribution | Following the successful implementation of a city-wide IoT enabled and AI assisted radiation monitoring and anomaly detection provision, (that has attracted the attention of UK and overseas Governments) this IAA project will advance and deploy an expanded static and vehicular-based network of low-cost and resilient environmental sensors. By assimilating the real-time and multi-variable data into the University of Bristol's (UoB) unique and cutting-edge AI/MLbased self-learning analysis, trend identification, cause/correlation attribution, and visualisation platform, the system will allow scientists, policymakers, citizens, and other stakeholders to understand, predict and manage natural and anthropogenic environmental factors, triggers, and effects. |
| Collaborator Contribution | Deploy the systems developed by the UoB team on Sellafield Site during the testing phase of the project, with the view to implementing such technology on our site once it has reached technical maturity at the conclusion of the grant. |
| Impact | The deployment of mobile and resilient sensor-based monitoring systems within BCC vehicles, with data delivered (in realtime) directly to an online portal for expert (and non-expert) visualisation and interpretation. |
| Start Year | 2022 |
| Description | Applying Fast machine Learning for Medical Imaging - Clinician Workshop |
| Form Of Engagement Activity | Participation in an activity, workshop or similar |
| Part Of Official Scheme? | No |
| Geographic Reach | Local |
| Primary Audience | Professional Practitioners |
| Results and Impact | The major activity is to hold 2 half-day workshops where we bring together healthcare experts and particle physicists. This will include radiographers, radiologists, surgeons etc and particle physicists with machine learning experience. The approximate size would be 6-8 people from each group. The objective is knowledge exchange between the two domains with a view to understanding where there is a clear path to translating the algorithms and technology into benefits for medical professionals (and subsequently patients). |
| Year(s) Of Engagement Activity | 2023 |
| Description | Development through Data Science for Somaliland Phase 2 - Data Science teaching |
| Form Of Engagement Activity | Participation in an activity, workshop or similar |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Undergraduate students |
| Results and Impact | -) teach data science to a large body of students to help economic development. We aimed to grow the numbers. last year we had ~80 students. This year we had near to 700 coming from more institutes. -) We wanted to expand the number of sessions and the scope of the course. We indeed increased the teaching sessions from 15 to 19. Similarly, we increased the number of industry lectures from 10 to 15. |
| Year(s) Of Engagement Activity | 2023 |