[Turing-Southampton] Presenting the Turing Fellow Research Projects | Registration open!!!

Wed Oct 6 15:21:45 BST 2021

***apologies if you receive this more than once***

As part of the Turing Fellow Research Projects event series taking place across the Institute's university partner network, I'm pleased to announce the final four presentations being hosted by our Southampton Fellows in collaboration with Newcastle University and The University of Manchester.

Details and registration links for all events are below.

Friday 15 October, 11:00-12:00

Register here<https://eur03.safelinks.protection.outlook.com/?url=https%3A%2F%2Fus02web.zoom.us%2Fwebinar%2Fregister%2FWN_zZig_L9USoqZx7nhWVZkkw&data=04%7C01%7CTuring-Southampton%40ecs.soton.ac.uk%7C9836823369754da6800808d988d4a074%7C4a5378f929f44d3ebe89669d03ada9d8%7C0%7C0%7C637691269063654952%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&sdata=ljyWHDWiyAPXENbQEKWTmxP83X9fwTjJcyVy4uJME5Q%3D&reserved=0>

Machine learning of seismicity induced by hydraulic fracturing

Thomas Gernon<https://eur03.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.turing.ac.uk%2Fpeople%2Fresearchers%2Fthomas-gernon&data=04%7C01%7Csdd1%40soton.ac.uk%7C162f7399e248465b47fb08d984b89f13%7C4a5378f929f44d3ebe89669d03ada9d8%7C0%7C0%7C637686751035534735%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&sdata=pyG5w9%2FYv71%2B1gHiW07z%2BCnV1xMLZwJ2hqL1Pw9dmiE%3D&reserved=0>

In this talk, Tom Gernon will describe how machine learning can be applied to forecast earthquakes triggered by underground fluid injection, and thereby improve real-time regulation practices in fracking and wastewater disposal regions. As an example, he will show

how Bayesian networks can be used to model joint conditional dependencies between both natural (e.g. geology, seismicity) and operational (e.g. injection volumes, rates, and depth) parameters. This approach is key to unlocking spatial complexity and is applicable

to geothermal and carbon capture and storage projects including those in the UK.

Open-source Private Data Integration

George Konstantinidis<https://eur03.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.turing.ac.uk%2Fpeople%2Fresearchers%2Fgeorge-konstantinidis&data=04%7C01%7Csdd1%40soton.ac.uk%7C162f7399e248465b47fb08d984b89f13%7C4a5378f929f44d3ebe89669d03ada9d8%7C0%7C0%7C637686751035534735%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&sdata=%2BUQSSuQzWvXk9Yq8lDXvCLEbkOzLkpi4TUGhukn%2BLkY%3D&reserved=0>

In this talk George is going to present the latest developments on the new area of collaborative data privacy. In these scenarios the service provider is considered a friend and not an adversary to the data owner, thus privacy enforcement is collaborative and does not rely

on encryption or distortion of data. Instead, this area investigates and develops mechanisms for users to encode their custom requirements, data consent, privacy preferences and data policies in a machine-processable language to form data usage contracts that can

be automatically (or algorithmically) respected.  George will discuss the formal foundations of the area, connections to data privacy, algorithms and open source implementations for supporting these automated agreements in data management. He will present results

on real and synthetic datasets and discuss extensions ranging from blockchains to clinical research, to AI reasoning and Knowledge Graphs.

Monday 18 October, 10:30-12:00

Joint with Newcastle University

Register here<https://eur03.safelinks.protection.outlook.com/?url=https%3A%2F%2Fus02web.zoom.us%2Fwebinar%2Fregister%2FWN_yLHXVa2TQe-uyaMcFHQnEQ&data=04%7C01%7CTuring-Southampton%40ecs.soton.ac.uk%7C9836823369754da6800808d988d4a074%7C4a5378f929f44d3ebe89669d03ada9d8%7C0%7C0%7C637691269063664912%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&sdata=wcv1WXjjulJYCBpnW6se3ZDdYB%2FeFObKQ3Hzxllci8k%3D&reserved=0>

Mapping biology from mouse to man using transfer learning

Ben MacArthur<https://eur03.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.turing.ac.uk%2Fpeople%2Fresearchers%2Fben-macarthur&data=04%7C01%7Csdd1%40soton.ac.uk%7C162f7399e248465b47fb08d984b89f13%7C4a5378f929f44d3ebe89669d03ada9d8%7C0%7C0%7C637686751035544728%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&sdata=knjPICPqRbZBarUFKI27bqrsYKnlr49Z5toqAZUhDwo%3D&reserved=0>

In this talk Ben MacArthur will outline how tools from machine learning can be combined with experiments to better understand how biology can be mapped between species and thereby improve the biomedical research and development pipeline.

As an example, he will show how transfer learning can be used to determine when biology learnt from one organism (the mouse) can be effectively transferred be to another (the human) and when it cannot.

Decision support algorithms for Emergency Departments

Neil White<https://eur03.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.turing.ac.uk%2Fpeople%2Fresearchers%2Fneil-white&data=04%7C01%7Csdd1%40soton.ac.uk%7C162f7399e248465b47fb08d984b89f13%7C4a5378f929f44d3ebe89669d03ada9d8%7C0%7C0%7C637686751035554723%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&sdata=GnYP2HwJYDNxeFOGBa%2FsK52oGjZeEx%2FAnqHo%2Fc8L7XU%3D&reserved=0>

In this talk, Neil White and Chris Duckworth will describe the outcomes of the TriagED project. Emergency departments (EDs) are facing unprecedented levels of overcrowding, which delays and impacts patient care. By analysing data collected from EDs, we can use machine learning models

to predict patient outcomes (e.g. whether a patient was discharged or admitted to hospital). These models will predict the patient outcome as early as possible in the hospital visit, with an aim to improve the efficiency of EDs and help allocate resources in downstream care.

Clinical settings are, however, dynamic environments and the reasons for attending the ED and their severity can change with time (i.e. data drift). This can have serious ramifications for any machine learning model implemented.  We demonstrate how explainable machine learning can be used

to monitor data drift for a predictive model deployed within a hospital ED. We use the COVID-19 pandemic as an extreme case of data drift, which has brought a severe change in operational circumstances. Furthermore we show how emergent health risks can be identified by using the

relative importance of model features.

4P Healthcare

Paolo Missier<https://eur03.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.turing.ac.uk%2Fpeople%2Fresearchers%2Fpaolo-missier&data=04%7C01%7Csdd1%40soton.ac.uk%7C162f7399e248465b47fb08d984b89f13%7C4a5378f929f44d3ebe89669d03ada9d8%7C0%7C0%7C637686751035554723%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&sdata=gvseM6yesoU74nSWnyyQ2QdxsQH%2BU%2FNfWzsbH%2B%2FRW58%3D&reserved=0>, Newcastle University

Our project at Newcastle University sets out to investigate how self-monitoring using wearable devices may help detect the early onset of metabolic diseases, potentially leading to early interventions to benefit both individuals and the health care system.

Focusing on Type 2 Diabetes (T2D) and on wrist-worn accelerometery traces of physical activity, in this talk we will cover two angles of this research.  Firstly, we show that suitable features can be either engineered, or learnt from the raw traces using autoencoders, and

that such features can in fact be used to discriminate T2D patients from healthy controls. We have further validated the representation learning approach on a second dataset of T2D patients, provided by the DIRECT IMI consortium.  Motivated by the scarcity of high-quality traces associated with metabolic conditions such as T2D, we then explored the idea of generating synthetic traces and in fact to simulate "a day in life of a virtual T2D patient", by learning generative models from the available traces. We report on promising initial results and suggest further research in this area.

Wednesday 3 November, 13:15-14:30

Register here<https://eur03.safelinks.protection.outlook.com/?url=https%3A%2F%2Fus02web.zoom.us%2Fwebinar%2Fregister%2FWN_XeILjhwERlGOKKaHc9TI_w&data=04%7C01%7CTuring-Southampton%40ecs.soton.ac.uk%7C9836823369754da6800808d988d4a074%7C4a5378f929f44d3ebe89669d03ada9d8%7C0%7C0%7C637691269063664912%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&sdata=sjwy4WtR7HiqAyjFdcotAXTXPh9dLFhMtGlsJaQX3CQ%3D&reserved=0>

Data science approaches to applied mathematical modelling

Marika Taylor<https://eur03.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.turing.ac.uk%2Fpeople%2Fresearchers%2Fmarika-taylor&data=04%7C01%7Csdd1%40soton.ac.uk%7C162f7399e248465b47fb08d984b89f13%7C4a5378f929f44d3ebe89669d03ada9d8%7C0%7C0%7C637686751035564717%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&sdata=1cbNspxvtZuOmdnxGiOdwTmtu%2FjRhH4XgvEFCNSpB90%3D&reserved=0>

In this talk Marika Taylor will describe new relationships between tessellations and codes used for quantum error correction, focussing on tessellations of negatively curved (hyperbolic) spaces. The motivations for constructing such codes will be explored - these range

from fundamental physics to understanding the geometry underlying quantum machine learning.

Jazz as Social Machine

Thomas Irvine<https://eur03.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.turing.ac.uk%2Fpeople%2Fresearchers%2Fthomas-irvine&data=04%7C01%7Csdd1%40soton.ac.uk%7C162f7399e248465b47fb08d984b89f13%7C4a5378f929f44d3ebe89669d03ada9d8%7C0%7C0%7C637686751035574712%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&sdata=kQ%2FfYoJv6qO9VlrrPDp96RHeYP3CV6sKy48QK9jAUGk%3D&reserved=0>

Making jazz with machine learning agents turns out to be complicated. Using insights from Web Science, Science and Technology Studies and musicological jazz studies, I survey the techniques currently in use, and explore what it is about jazz's data that makes

machine learning jazz more of a "social" problem than other challenges in the growing field of Music Information Retrieval.

Tuesday 23 November, 14:00-15:30

Joint with The University of Manchester

Register here<https://teams.microsoft.com/registration/-XhTSvQpPk2-iWadA62p2A,1bh6qC4isUeT-gmiMP7McA,tfrNasdn50-4SBzv6YT4tw,bim-TalsAUSNJvHouy6iYg,zLVSjJcH4Eqt2ilJ3rgl2g,u3tnKBmtu0auqx8zwV8YFQ?mode=read&tenantId=4a5378f9-29f4-4d3e-be89-669d03ada9d8>

A Multidisciplinary Study of Predictive Artificial Intelligence Technologies in the Criminal Justice System

Pamela Ugwudike<https://eur03.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.turing.ac.uk%2Fpeople%2Fresearchers%2Fpamela-ugwudike&data=04%7C01%7Csdd1%40soton.ac.uk%7C162f7399e248465b47fb08d984b89f13%7C4a5378f929f44d3ebe89669d03ada9d8%7C0%7C0%7C637686751035584705%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&sdata=I1wOubQwOsAzYr2u1KI%2BNqHwJgbFYaHoK13sVnUsZ5U%3D&reserved=0>

Description to follow

Topological complexity of neural networks

Jacek Brodzki<https://eur03.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.turing.ac.uk%2Fpeople%2Fresearchers%2Fjacek-brodzki&data=04%7C01%7Csdd1%40soton.ac.uk%7C162f7399e248465b47fb08d984b89f13%7C4a5378f929f44d3ebe89669d03ada9d8%7C0%7C0%7C637686751035594700%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&sdata=aLT%2BPxPRq1JNN%2FH2Cn61dzpo0H1O1JqRlIHBlNSY5%2Bk%3D&reserved=0>

Description to follow

Anonymisation and Provenance: Expression Data Environments With PROV

Adriane Chapman<https://eur03.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.turing.ac.uk%2Fpeople%2Fresearchers%2Fadriane-chapman&data=04%7C01%7Csdd1%40soton.ac.uk%7C162f7399e248465b47fb08d984b89f13%7C4a5378f929f44d3ebe89669d03ada9d8%7C0%7C0%7C637686751035594700%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&sdata=1KQblaQxr5vbtNhuLnCIHerqt8KYmjMIDuXT87oYo6g%3D&reserved=0> and Mark Elliot<https://eur03.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.research.manchester.ac.uk%2Fportal%2Fmark.elliot.html&data=04%7C01%7CTuring-Southampton%40ecs.soton.ac.uk%7C9836823369754da6800808d988d4a074%7C4a5378f929f44d3ebe89669d03ada9d8%7C0%7C0%7C637691269063674862%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&sdata=gs8nxXqtT%2FpxZ66DF23HS4%2FeP8%2BjbSkdl7rW8spMln0%3D&reserved=0>, The University of Manchester

Description to follow

Background
In 2018 over 300 Turing Fellows were appointed at the Institute following an open call. Some of these received additional funding to deliver research projects that have had substantial impact in the areas of data science and artificial intelligence. The Institute and its university partners are delighted to host the events which will showcase the breadth of research and demonstrate the impact of these research projects. Events will be added to the website over the coming weeks, visit regularly for more information.

Details of all university partner presentations and how to register can be found here<https://eur03.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.turing.ac.uk%2Fpresenting-turing-fellow-research-projects&data=04%7C01%7Csdd1%40soton.ac.uk%7C78704f84846d4514be6108d925b3852b%7C4a5378f929f44d3ebe89669d03ada9d8%7C0%7C0%7C637582275258788662%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&sdata=vNT7mDg1hsmsm1SgWeV1twE4ojgIZ0yVVjsGXLwIYzc%3D&reserved=0> - we look forward to seeing you there.

Please feel free to disseminate more widely.

Best wishes

Susan
_________________________________
Susan Davies
Coordination Manager, Web Science Institute<https://www.southampton.ac.uk/wsi/index.page?>
University Liaison Manager, The Alan Turing Institute<https://www.southampton.ac.uk/wsi/alan-turing-institute/alan-turing-institute.page>
Web Science Institute
University of Southampton
Southampton SO17 1BJ
M 07768 266464
https://www.southampton.ac.uk/wsi<https://www.southampton.ac.uk/wsi/index.page>

My working days are Monday to Thursday.

-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.ecs.soton.ac.uk/pipermail/turing-southampton/attachments/20211006/3743462e/attachment-0001.html 