Category: blog

Posted on

AI Safety Summit workshop

Horizon Transitional Assistant Professor Horia Maior shares his experience of facilitating a workshop on Ethics and Responsible Innovation in the application of AI within the nuclear energy sector at the AI Summit hosted by the UK Atomic Energy Authority and the Robotics and AI Collaboration (RAICo)..

“Together with Dr Virginia Portillo and Dr Pepita Barnard I had the privilege of facilitating a workshop on Ethics and Responsible Innovation in the application of AI within the nuclear energy sector.

The summit was nothing short of inspiring. It was an incredible opportunity to delve into the critical discussions surrounding AI safety and ethics, particularly in an industry as crucial as nuclear energy.

But what made the summit truly remarkable was the chance to connect with a diverse group of passionate researchers and practitioners. From academia and industry to the public sector, the breadth of knowledge, enthusiasm, and willingness to collaborate was genuinely inspiring.

I must also shout out to my University of Nottingham colleagues Jack Chaplin, and Giovanna Martinez Arellano who delivered two other enlightening workshops on AI Safety and AI Assurance, as well as colleagues from the Omnifactory® for the amazing facility tour provided on the day.

Reflecting on these amazing few days, I’m filled with gratitude for the opportunity to contribute to such vital conversations, to learn, network, and collaborate, and advance the ethical use of AI across different sectors.

Thank huge thank you to Horizon Digital Economy Research, UKRI Trustworthy Autonomous Systems (TAS) Hub and Responsible Ai UK  for supporting our work!

Thanks also to the UK Atomic Energy Authority, RAICo, the University of Nottingham, Phill Mulvana MSc FIET CMgr MCMI, David Branson III and everyone involved for an unforgettable summit.

 

Posted on

Privacy-preserving & machine-learned catchment models for national dietary surveillance via digital footprint data

Horizon’s Transitional Assistant Professor, Georgiana Nica-Avram has co-authored a paper ‘Privacy-preserving & machine-learned catchment models for national dietary surveillance via digital footprint data’ which was submitted to the 2022 IEEE International Conference on Big Data.

Abstract

Big data from food retail stores is increasingly being used for population dietary surveillance, epidemiological studies of diet-related diseases, and evaluations of public health interventions. However, for retail data to be useful it is necessary to understand the spatio-temporal variation of when and where food is purchased and consumed. While some customers willingly share home location data with retailers as part of loyalty programs such data is typically too fine-grained/sensitive to be applied for research purposes. The aim of this study was to analyse differences between privacy-preserving models and actual retail catchments, and investigate if machine learning techniques could improve the accuracy of such catchment models. Based on a UK-wide sample of 4 million grocery store loyalty card holders, covering 485 million transactions over 29 months (2019-2021) and distributed across 33,000 neighbourhoods (Lower Super Output Areas, or LSOA), the study demonstrates how models trained on geolocated data perform at predicting, per store, catchment areas which contain 50, 80, and 95% of its customers’ primary location. Through comparative assessment of machine learning approaches, we find better performance from tree-based models (RF, XGB) with the best performance from an XGB model achieving an R2 of 0.72 and MAE of 1.06. To conclude, we review variable importance measures using SHAP values and discuss the relative merits of including specific features when modeling catchment areas. © 2022 IEEE.