index.json

[{"authors":["isaac-neal"],"categories":null,"content":"","date":1669852800,"expirydate":-62135596800,"kind":"term","lang":"en","lastmod":1669852800,"objectID":"522695d76ddd2f2967f945c542771e3b","permalink":"https://sohanseth.github.io/author/isaac-neal/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/author/isaac-neal/","section":"authors","summary":"","tags":null,"title":"Isaac Neal","type":"authors"},{"authors":["abbas-rizvi"],"categories":null,"content":"","date":-62135596800,"expirydate":-62135596800,"kind":"term","lang":"en","lastmod":-62135596800,"objectID":"5a04a791619774198a43d53546dfe664","permalink":"https://sohanseth.github.io/author/abbas-rizvi/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/author/abbas-rizvi/","section":"authors","summary":"","tags":null,"title":"Abbas Rizvi","type":"authors"},{"authors":["ahad-abdalla"],"categories":null,"content":"Ahad is a PhD student in the Centre for Inflammation Research. His research is focused on systems immunology aspects of lung injury using the human ex vivo lung perfusion model\n","date":-62135596800,"expirydate":-62135596800,"kind":"term","lang":"en","lastmod":-62135596800,"objectID":"df946963e23f81a6b712296ab4b1a5d9","permalink":"https://sohanseth.github.io/author/ahad-abdalla/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/author/ahad-abdalla/","section":"authors","summary":"Ahad is a PhD student in the Centre for Inflammation Research. His research is focused on systems immunology aspects of lung injury using the human ex vivo lung perfusion model","tags":null,"title":"Ahad Abdalla","type":"authors"},{"authors":["alex-adams"],"categories":null,"content":"Alex is a PhD student on the MRC Precision Medicine CDT Programme at the University of Edinburgh. Her research involves applying data science techniques, analysing spectroscopy data, stratifying benign and malignant lung cancer.\n","date":-62135596800,"expirydate":-62135596800,"kind":"term","lang":"en","lastmod":-62135596800,"objectID":"8c9c11b9e5d92f5536f30bd0db7382d1","permalink":"https://sohanseth.github.io/author/alex-adams/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/author/alex-adams/","section":"authors","summary":"Alex is a PhD student on the MRC Precision Medicine CDT Programme at the University of Edinburgh. Her research involves applying data science techniques, analysing spectroscopy data, stratifying benign and malignant lung cancer.","tags":null,"title":"Alex Adams","type":"authors"},{"authors":["achakrab"],"categories":null,"content":"Find me at https://anitcd.github.io/.\n","date":-62135596800,"expirydate":-62135596800,"kind":"term","lang":"en","lastmod":-62135596800,"objectID":"3c3c7b2344e11af9830114cbbd2c0781","permalink":"https://sohanseth.github.io/author/anirban-chakraborty/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/author/anirban-chakraborty/","section":"authors","summary":"Find me at https://anitcd.github.io/.","tags":null,"title":"Anirban Chakraborty","type":"authors"},{"authors":["eke-chima"],"categories":null,"content":"","date":-62135596800,"expirydate":-62135596800,"kind":"term","lang":"en","lastmod":-62135596800,"objectID":"264f7f0daf40546022f73401070dc97a","permalink":"https://sohanseth.github.io/author/chima-eke/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/author/chima-eke/","section":"authors","summary":"","tags":null,"title":"Chima Eke","type":"authors"},{"authors":["dagmara-panas"],"categories":null,"content":"Data Scientist, once-Neuroscientist, all-round-geek (and sleep enthusiast) with a varied background. Experience ranging from basic research through building and deploying ML models in a business environment - to guiding tours on river Cam. Interested in applying Data Science for societal improvement (but generally into any problem solving, so I suppose my character alignment is \u0026lsquo;chaotic good\u0026rsquo; ;))\n","date":-62135596800,"expirydate":-62135596800,"kind":"term","lang":"en","lastmod":-62135596800,"objectID":"a47d6272a94c14607bd95598ebe10bd2","permalink":"https://sohanseth.github.io/author/daga-panas/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/author/daga-panas/","section":"authors","summary":"Data Scientist, once-Neuroscientist, all-round-geek (and sleep enthusiast) with a varied background. Experience ranging from basic research through building and deploying ML models in a business environment - to guiding tours on river Cam.","tags":null,"title":"Daga Panas","type":"authors"},{"authors":["dlipschutz"],"categories":null,"content":"Research associate with experience in Data Science and Statistical and Epidemiological Modelling both in Academia and in Industry. I have an overarching interest in using my quantitative skills to solve questions relating to healthcare and infectious diseases.\n","date":-62135596800,"expirydate":-62135596800,"kind":"term","lang":"en","lastmod":-62135596800,"objectID":"4ae68c7487b896472da0e9b515e8023b","permalink":"https://sohanseth.github.io/author/debby-lipschutz/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/author/debby-lipschutz/","section":"authors","summary":"Research associate with experience in Data Science and Statistical and Epidemiological Modelling both in Academia and in Industry. I have an overarching interest in using my quantitative skills to solve questions relating to healthcare and infectious diseases.","tags":null,"title":"Debby Lipschutz","type":"authors"},{"authors":["Iris Szu-Szu Ho"],"categories":null,"content":"","date":-62135596800,"expirydate":-62135596800,"kind":"term","lang":"en","lastmod":-62135596800,"objectID":"418e3285c1f8364d0cb80c24f3c1ee14","permalink":"https://sohanseth.github.io/author/iris-ho/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/author/iris-ho/","section":"authors","summary":"","tags":null,"title":"Iris Ho","type":"authors"},{"authors":["karthik-mohan"],"categories":null,"content":"Data Scientist, with close to six years of experience in developing data science solutions - from conceptualization to building data pipelines to modelling and reporting, for businesses across various industries such as sportswear retail, mass media, oil and gas, automobiles among others. Experienced in a wide range of tools and techniques used in an industry setting. I believe one of the most important skills for a data scientist is adaptability. I am interested in making a positive impact on society using the power of data and machine learning.\n","date":-62135596800,"expirydate":-62135596800,"kind":"term","lang":"en","lastmod":-62135596800,"objectID":"6a9933445b29e324b839929e709c28df","permalink":"https://sohanseth.github.io/author/karthik-mohan/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/author/karthik-mohan/","section":"authors","summary":"Data Scientist, with close to six years of experience in developing data science solutions - from conceptualization to building data pipelines to modelling and reporting, for businesses across various industries such as sportswear retail, mass media, oil and gas, automobiles among others.","tags":null,"title":"Karthik Mohan","type":"authors"},{"authors":["kieran-richards"],"categories":null,"content":"Kieran is a statistician, with experience developing scalable Bayesian methods with a wide range of applications including epidemiology, oceanography and stormsurge prediction. He is interested in developing probabilistic models and supporting methodologies which aim to have a positive impact by delivering explainable uncertainty quantification.\n","date":-62135596800,"expirydate":-62135596800,"kind":"term","lang":"en","lastmod":-62135596800,"objectID":"49608af8362e6f1d869e0b3bcdd40ba1","permalink":"https://sohanseth.github.io/author/kieran-richards/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/author/kieran-richards/","section":"authors","summary":"Kieran is a statistician, with experience developing scalable Bayesian methods with a wide range of applications including epidemiology, oceanography and stormsurge prediction. He is interested in developing probabilistic models and supporting methodologies which aim to have a positive impact by delivering explainable uncertainty quantification.","tags":null,"title":"Kieran Richards","type":"authors"},{"authors":[""],"categories":null,"content":"","date":-62135596800,"expirydate":-62135596800,"kind":"term","lang":"en","lastmod":-62135596800,"objectID":"3c8aaa5d8ebb1b55ee9dc52641fe319b","permalink":"https://sohanseth.github.io/author/lara-johnson/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/author/lara-johnson/","section":"authors","summary":"","tags":null,"title":"Lara Johnson","type":"authors"},{"authors":["Luwei-wang"],"categories":null,"content":"Personal webpage\n","date":-62135596800,"expirydate":-62135596800,"kind":"term","lang":"en","lastmod":-62135596800,"objectID":"a7446ced0aaf6bc52a0b8a30c1c6c902","permalink":"https://sohanseth.github.io/author/luwei-wang/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/author/luwei-wang/","section":"authors","summary":"Personal webpage","tags":null,"title":"Luwei Wang","type":"authors"},{"authors":["maxmillan-ries"],"categories":null,"content":"PhD Student at the College of Informatics/ACRC, with an additional 2 years of experience as a data scientist, developing data science solutions in the fields of Computer Vision and industry (e.g. ASML).\n","date":-62135596800,"expirydate":-62135596800,"kind":"term","lang":"en","lastmod":-62135596800,"objectID":"5031d7eca10bbea96c84a52e60533234","permalink":"https://sohanseth.github.io/author/maxmillan-ries/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/author/maxmillan-ries/","section":"authors","summary":"PhD Student at the College of Informatics/ACRC, with an additional 2 years of experience as a data scientist, developing data science solutions in the fields of Computer Vision and industry (e.","tags":null,"title":"Maxmillan Ries","type":"authors"},{"authors":["nada-almoudi"],"categories":null,"content":"Nada is a PhD student in the Informatics school and a member of the Institute for Adaptive and Neural Computation at the University of Edinburgh. Her research focuses on the development of machine learning algorithms and other AI-based approaches to analyse and interpret brain medical imaging data, with the goal of improving diagnosis, treatment, and patient outcomes.\n","date":-62135596800,"expirydate":-62135596800,"kind":"term","lang":"en","lastmod":-62135596800,"objectID":"f1cef8a7d0761a5f5975c33a91d5e170","permalink":"https://sohanseth.github.io/author/nada-almoudi/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/author/nada-almoudi/","section":"authors","summary":"Nada is a PhD student in the Informatics school and a member of the Institute for Adaptive and Neural Computation at the University of Edinburgh. Her research focuses on the development of machine learning algorithms and other AI-based approaches to analyse and interpret brain medical imaging data, with the goal of improving diagnosis, treatment, and patient outcomes.","tags":null,"title":"Nada Almoudi","type":"authors"},{"authors":["nia-jenkins"],"categories":null,"content":"","date":-62135596800,"expirydate":-62135596800,"kind":"term","lang":"en","lastmod":-62135596800,"objectID":"1d6155b3b14bcc9af79753f03f15f708","permalink":"https://sohanseth.github.io/author/nia-jenkins/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/author/nia-jenkins/","section":"authors","summary":"","tags":null,"title":"Nia Jenkins","type":"authors"},{"authors":[""],"categories":null,"content":"","date":-62135596800,"expirydate":-62135596800,"kind":"term","lang":"en","lastmod":-62135596800,"objectID":"3bd79bf82c2fe21fcd1b00299a53bfcc","permalink":"https://sohanseth.github.io/author/nick-homer/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/author/nick-homer/","section":"authors","summary":"","tags":null,"title":"Nick Homer","type":"authors"},{"authors":[""],"categories":null,"content":"","date":-62135596800,"expirydate":-62135596800,"kind":"term","lang":"en","lastmod":-62135596800,"objectID":"2528eab4d44ecb72aff328b686ba6108","permalink":"https://sohanseth.github.io/author/nikos-avramidis/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/author/nikos-avramidis/","section":"authors","summary":"","tags":null,"title":"Nikos Avramidis","type":"authors"},{"authors":["saeeda-gouhari"],"categories":null,"content":"Saeeda is a PhD student of the Edinburgh Earth, Ecology and Environment Doctoral Training Partnership (E4 DTP) at the University of Edinburgh. Her research project involves project looking at how monitoring and evaluation of overseas development assistance could be supported using Earth Observation and Geospatial Data.\n","date":-62135596800,"expirydate":-62135596800,"kind":"term","lang":"en","lastmod":-62135596800,"objectID":"b39b2b4d177c193d5fddcdb284f0f47b","permalink":"https://sohanseth.github.io/author/saeeda-gouhari/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/author/saeeda-gouhari/","section":"authors","summary":"Saeeda is a PhD student of the Edinburgh Earth, Ecology and Environment Doctoral Training Partnership (E4 DTP) at the University of Edinburgh. Her research project involves project looking at how monitoring and evaluation of overseas development assistance could be supported using Earth Observation and Geospatial Data.","tags":null,"title":"Saeeda Gouhari","type":"authors"},{"authors":["samuel-fielding"],"categories":null,"content":"","date":-62135596800,"expirydate":-62135596800,"kind":"term","lang":"en","lastmod":-62135596800,"objectID":"6e21d9b64db04ea31fa322ccdc90253d","permalink":"https://sohanseth.github.io/author/samuel-fielding/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/author/samuel-fielding/","section":"authors","summary":"","tags":null,"title":"Samuel Fielding","type":"authors"},{"authors":[""],"categories":null,"content":"","date":-62135596800,"expirydate":-62135596800,"kind":"term","lang":"en","lastmod":-62135596800,"objectID":"f2edd4286368b01e32acbd6b401ef792","permalink":"https://sohanseth.github.io/author/sean-o-heir/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/author/sean-o-heir/","section":"authors","summary":"","tags":null,"title":"Seán Ó Héir","type":"authors"},{"authors":["sinziana-radulescu"],"categories":null,"content":"Sinziana is a PhD student in the Centre for Medical Informatics. Her research is focused on exploring the interplay between multimorbidity, polypharmacy and frailty in ICU patients.\n","date":-62135596800,"expirydate":-62135596800,"kind":"term","lang":"en","lastmod":-62135596800,"objectID":"e81b321e461b756ba711c87422bfec3c","permalink":"https://sohanseth.github.io/author/sinziana-radulescu/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/author/sinziana-radulescu/","section":"authors","summary":"Sinziana is a PhD student in the Centre for Medical Informatics. Her research is focused on exploring the interplay between multimorbidity, polypharmacy and frailty in ICU patients.","tags":null,"title":"Sinziana Radulescu","type":"authors"},{"authors":["admin"],"categories":null,"content":"I am the Lead Data Scientist (Senior Research Fellow equivalent) at the School of Informatics, University of Edinburgh. I lead the Data Science Unit (DSU) for Science, Health, People and Environment (SHaPE).\nAffiliations/Collaborations:\n Advanced Care Research Centre (ACRC) AI and Multimorbidity: Clustering in Individuals Space and Clinical Context Centre for Statistics Computational Social Science Data for Children Collaborative with UNICEF Functional Materials Group ICU-HEART Shankar-Hari Group The New Real Translational Healthcare Technologies  News:\n 01.09.2023: Luwei, Max and Sean join as PhD students 01.09.2023: Papers in BMC Medicine, The Lancet Digital Health and AI Surgery 01.08.2023: Kieran and Debbie join as PDRAs 10.03.2023: Paper accepted at IEEE Transactions on Biomedical Engineering 08.03.2023: Saeeda joins as PhD Student 07.02.2023: Paper accepted at IEEE Transactions on Biomedical Engineering 09.01.2023: Nada joins as PhD Student  ","date":-62135596800,"expirydate":-62135596800,"kind":"term","lang":"en","lastmod":-62135596800,"objectID":"2525497d367e79493fd32b198b28f040","permalink":"https://sohanseth.github.io/author/sohan-seth/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/author/sohan-seth/","section":"authors","summary":"I am the Lead Data Scientist (Senior Research Fellow equivalent) at the School of Informatics, University of Edinburgh. I lead the Data Science Unit (DSU) for Science, Health, People and Environment (SHaPE).","tags":null,"title":"Sohan Seth","type":"authors"},{"authors":["Nia C. Jenkins","Katjana Ehrlich","Andras Kufcsak","Stephanos Yerolatsitis","Susan Fernandes","Irene Young","Katie Hamilton","Harry A. C. Wood","Tom Quinn","Vikki Young","Ahsan R. Akram","James M. Stone","Robert R. Thomson","Keith Finlayson","Kevin Dhaliwal","Sohan Seth"],"categories":null,"content":"","date":1672531200,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1672531200,"objectID":"1377aab42daacc0f2522951f2697a9e1","permalink":"https://sohanseth.github.io/publication/jenkins-computational-2023/","publishdate":"2023-03-22T19:28:37.890503Z","relpermalink":"/publication/jenkins-computational-2023/","section":"publication","summary":"","tags":null,"title":"Computational Fluorescence Suppression in Shifted Excitation Raman Spectroscopy","type":"publication"},{"authors":["Rui-Zhi Zhang","Sohan Seth","James Cumby"],"categories":null,"content":"","date":1672531200,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1672531200,"objectID":"1d8a2c10bde421699a7cf66a268df67c","permalink":"https://sohanseth.github.io/publication/zhang-grouped-2023/","publishdate":"2023-01-05T07:28:55.457524Z","relpermalink":"/publication/zhang-grouped-2023/","section":"publication","summary":"Grouped Representation of Interatomic Distances (GRID) accurately quantifies similarity between crystal structures and can be used to predict physical properties. ,  Determining how similar two materials are in terms of both atomic composition and crystallographic structure remains a challenge, the solution of which would enable generalised machine learning using crystal structure data. We demonstrate a new method of describing crystal structures based on interatomic distances, termed the Grouped Representation of Interatomic Distances (GRID). This fast to compute descriptor can equally be applied to crystalline or disordered materials, and encodes additional information beyond pairwise distances, such as coordination environments. Combined with earth mover's distance as a measure of similarity, we show that GRID is able to quantitatively compare materials involving both short- and long-range structural variation. Using this new material descriptor, we show that it can accurately predict bulk moduli using a simple nearest-neighbour model, and that the resulting similarity shows good generalisability across multiple materials properties.","tags":null,"title":"Grouped representation of interatomic distances as a similarity measure for crystal structures","type":"publication"},{"authors":["Alexandra C. Adams","Andras Kufcsak","Katjana Ehrlich","Kevin Dhaliwal","Sohan Seth"],"categories":null,"content":"","date":1672531200,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1672531200,"objectID":"3408c099c7ec2922d892c11e65974ed1","permalink":"https://sohanseth.github.io/publication/adams-simultaneous-2023/","publishdate":"2023-03-22T19:28:37.905713Z","relpermalink":"/publication/adams-simultaneous-2023/","section":"publication","summary":"","tags":null,"title":"Simultaneous Spectral Temporal Modelling for a Time-Resolved Fluorescence Emission Spectrum","type":"publication"},{"authors":["Isaac Neal","Sohan Seth","Gary Watmough","Mamadou S. Diallo"],"categories":null,"content":"","date":1669852800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1669852800,"objectID":"52f5f469474f8884d5295940a172d865","permalink":"https://sohanseth.github.io/publication/neal-census-independent-2022/","publishdate":"2022-05-17T12:23:22.215734Z","relpermalink":"/publication/neal-census-independent-2022/","section":"publication","summary":"Abstract Knowledge of population distribution is critical for building infrastructure, distributing resources, and monitoring the progress of sustainable development goals. Although censuses can provide this information, they are typically conducted every 10 years with some countries having forgone the process for several decades. Population can change in the intercensal period due to rapid migration, development, urbanisation, natural disasters, and conflicts. Census-independent population estimation approaches using alternative data sources, such as satellite imagery, have shown promise in providing frequent and reliable population estimates locally. Existing approaches, however, require significant human supervision, for example annotating buildings and accessing various public datasets, and therefore, are not easily reproducible. We explore recent representation learning approaches, and assess the transferability of representations to population estimation in Mozambique. Using representation learning reduces required human supervision, since features are extracted automatically, making the process of population estimation more sustainable and likely to be transferable to other regions or countries. We compare the resulting population estimates to existing population products from GRID3, Facebook (HRSL) and WorldPop. We observe that our approach matches the most accurate of these maps, and is interpretable in the sense that it recognises built-up areas to be an informative indicator of population.","tags":null,"title":"Census-independent population estimation using representation learning","type":"publication"},{"authors":["Jonathan E. Millar","Lucile Neyton","Sohan Seth","Jake Dunning","Laura Merson","Srinivas Murthy","Clark D. Russell","Sean Keating","Maaike Swets","Carole H. Sudre","Timothy D. Spector","Sebastien Ourselin","Claire J. Steves","Jonathan Wolf","Annemarie B. Docherty","Ewen M. Harrison","Peter J. M. Openshaw","Malcolm G. Semple","J. Kenneth Baillie"," ISARIC-4C","Consortium Lead Investigator","J. Kenneth Baillie","Chief Investigator","Malcolm G. Semple","Co-Lead Investigator","Peter J. M. Openshaw","ISARIC Clinical Coordinator","Gail Carson"," Co-Investigators","Beatrice Alex","Benjamin Bach","Wendy S. Barclay","Debby Bogaert","Meera Chand","Graham S. Cooke","Annemarie B. Docherty","Jake Dunning","Anna da Silva Filipe","Tom Fletcher","Christopher A. Green","Ewen M. Harrison","Julian A. Hiscox","Antonia YW Ho","Peter W. Horby","Samreen Ijaz","Saye Khoo","Paul Klenerman","Andrew Law","Wei Shen Lim","Alexander J. Mentzer","Laura Merson","Alison M. Meynert","Mahdad Noursadeghi","Shona C. Moore","Massimo Palmarini","William A. Paxton","Georgios Pollakis","Nicholas Price","Andrew Rambaut","David L. Robertson","Clark D. Russell","Vanessa Sancho-Shimizu","Janet T. Scott","Louise Sigfrid","Tom Solomon","Shiranee Sriskandan","David Stuart","Charlotte Summers","Richard S. Tedder","Emma C. Thomson","Ryan S. Thwaites","Lance C. W. Turtle","Maria Zambon","Project Managers","Hayley Hardwick","Chloe Donohue","Jane Ewins","Wilna Oosthuyzen","Fiona Griffiths","Data Analysts","Lisa Norman","Riinu Pius","Tom M. Drake","Cameron J. Fairfield","Stephen Knight","Kenneth A. Mclean","Derek Murphy","Catherine A. Shaw"," Data","Information System Manager","Jo Dalton","Michelle Girvan","Egle Saviciute","Stephanie Roberts","Janet Harrison","Laura Marsh","Marie Connor","Data integration"," presentation","Gary Leeming","Ross Hendry","Material Management","William Greenhalf","Victoria Shaw","Sarah McDonald","Local Principal Investigators","Kayode Adeniji","Daniel Agranoff","Ken Agwuh","Dhiraj Ail","Ana Alegria","Brian Angus","Abdul Ashish","Dougal Atkinson","Shahedal Bari","Gavin Barlow","Stella Barnass","Nicholas Barrett","Christopher Bassford","David Baxter","Michael Beadsworth","Jolanta Bernatoniene","John Berridge","Nicola Best","Pieter Bothma","David Brealey","Robin Brittain-Long","Naomi Bulteel","Tom Burden","Andrew Burtenshaw","Vikki Caruth","David Chadwick","Duncan Chambler","Nigel Chee","Jenny Child","Srikanth Chukkambotla","Tom Clark","Paul Collini","Graham Cooke","Catherine Cosgrove","Jason Cupitt","Maria-Teresa Cutino-Moguel","Paul Dark","Chris Dawson","Samir Dervisevic","Phil Donnison","Sam Douthwaite","Ingrid DuRand","Ahilanadan Dushianthan","Tristan Dyer","Cariad Evans","Chi Eziefula","Chrisopher Fegan","Adam Finn","Duncan Fullerton","Sanjeev Garg","Atul Garg","Jo Godden","Arthur Goldsmith","Clive Graham","Elaine Hardy","Stuart Hartshorn","Daniel Harvey","Peter Havalda","Daniel B. Hawcutt","Maria Hobrok","Luke Hodgson","Anita Holme","Anil Hormis","Michael Jacobs","Susan Jain","Paul Jennings","Agilan Kaliappan","Vidya Kasipandian","Stephen Kegg","Michael Kelsey","Jason Kendall","Caroline Kerrison","Ian Kerslake","Oliver Koch","Gouri Koduri","George Koshy","Shondipon Laha","Susan Larkin","Tamas Leiner","Patrick Lillie","James Limb","Vanessa Linnett","Jeff Little","Michael MacMahon","Emily MacNaughton","Ravish Mankregod","Huw Masson","Elijah Matovu","Katherine McCullough","Ruth McEwen","Manjula Meda","Gary Mills","Jane Minton","Mariyam Mirfenderesky","Kavya Mohandas","Quen Mok","James Moon","Elinoor Moore","Patrick Morgan","Craig Morris","Katherine Mortimore","Samuel Moses","Mbiye Mpenge","Rohinton Mulla","Michael Murphy","Megan Nagel","Thapas Nagarajan","Mark Nelson","Igor Otahal","Mark Pais","Selva Panchatsharam","Hassan Paraiso","Brij Patel","Justin Pepperell","Mark Peters","Mandeep Phull","Stefania Pintus","Jagtur Singh Pooni","Frank Post","David Price","Rachel Prout","Nikolas Rae","Henrik Reschreiter","Tim Reynolds","Neil Richardson","Mark Roberts","Devender Roberts","Alistair Rose","Guy Rousseau","Brendan Ryan","Taranprit Saluja","Aarti Shah","Prad Shanmuga","Anil Sharma","Anna Shawcross","Jeremy Sizer","Richard Smith","Catherine Snelson","Nick Spittle","Nikki Staines","Tom Stambach","Richard Stewart","Pradeep Subudhi","Tamas Szakmany","Kate Tatham","Jo Thomas","Chris Thompson","Robert Thompson","Ascanio Tridente","Darell Tupper-Carey","Mary Twagira","Andrew Ustianowski","Nick Vallotton","Lisa Vincent-Smith","Shico Visuvanathan","Alan Vuylsteke","Sam Waddy","Rachel Wake","Andrew Walden","Ingeborg Welters","Tony Whitehouse","Paul Whittaker","Ashley Whittington","Meme Wijesinghe","Martin Williams","Lawrence Wilson","Sarah Wilson","Stephen Winchester","Martin Wiselka","Adam Wolverson","Daniel G. Wooton","Andrew Workman","Bryan Yates","Peter Young"],"categories":null,"content":"","date":1669852800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1669852800,"objectID":"6a44c1bf2d2bafdff83498ff98fcac4a","permalink":"https://sohanseth.github.io/publication/millar-distinct-2022/","publishdate":"2022-05-17T12:23:22.22437Z","relpermalink":"/publication/millar-distinct-2022/","section":"publication","summary":"Abstract COVID-19 is clinically characterised by fever, cough, and dyspnoea. Symptoms affecting other organ systems have been reported. However, it is the clinical associations of different patterns of symptoms which influence diagnostic and therapeutic decision-making. In this study, we applied clustering techniques to a large prospective cohort of hospitalised patients with COVID-19 to identify clinically meaningful sub-phenotypes. We obtained structured clinical data on 59,011 patients in the UK (the ISARIC Coronavirus Clinical Characterisation Consortium, 4C) and used a principled, unsupervised clustering approach to partition the first 25,477 cases according to symptoms reported at recruitment. We validated our findings in a second group of 33,534 cases recruited to ISARIC-4C, and in 4,445 cases recruited to a separate study of community cases. Unsupervised clustering identified distinct sub-phenotypes. First, a core symptom set of fever, cough, and dyspnoea, which co-occurred with additional symptoms in three further patterns: fatigue and confusion, diarrhoea and vomiting, or productive cough. Presentations with a single reported symptom of dyspnoea or confusion were also identified, alongside a sub-phenotype of patients reporting few or no symptoms. Patients presenting with gastrointestinal symptoms were more commonly female, had a longer duration of symptoms before presentation, and had lower 30-day mortality. Patients presenting with confusion, with or without core symptoms, were older and had a higher unadjusted mortality. Symptom sub-phenotypes were highly consistent in replication analysis within the ISARIC-4C study. Similar patterns were externally verified in patients from a study of self-reported symptoms of mild disease. The large scale of the ISARIC-4C study enabled robust, granular discovery and replication. Clinical interpretation is necessary to determine which of these observations have practical utility. We propose that four sub-phenotypes are usefully distinct from the core symptom group: gastro-intestinal disease, productive cough, confusion, and pauci-symptomatic presentations. Importantly, each is associated with an in-hospital mortality which differs from that of patients with core symptoms.","tags":null,"title":"Distinct clinical symptom patterns in patients hospitalised with COVID-19 in an analysis of 59,011 patients in the ISARIC-4C study","type":"publication"},{"authors":["Gary R. Watmough","Magnus Hagdorn","Jodie Brumhead","Sohan Seth","Enrique Delamónica","Charlotte Haddon","William C. Smith"],"categories":null,"content":"","date":1669852800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1669852800,"objectID":"a61a40bdfdde348110f17655e6974c8e","permalink":"https://sohanseth.github.io/publication/watmough-using-2022/","publishdate":"2022-05-17T12:23:22.225528Z","relpermalink":"/publication/watmough-using-2022/","section":"publication","summary":"Abstract Physical access to health facilities is an important factor in determining treatment seeking behaviour and has implications for targets within the Sustainable Development Goals, including the right to health. The increased availability of high-resolution land cover and road data from satellite imagery offers opportunities for fine-grained estimations of physical access which can support delivery planning through the provision of more realistic estimates of travel times. The data presented here is of travel time to health facilities in Uganda, Zimbabwe, Tanzania, and Mozambique. Travel times have been calculated for different facility types in each country such as Dispensaries, Health Centres, Clinics and Hospitals. Cost allocation surfaces and travel times are provided for child walking speeds but can be altered easily to account for adult walking speeds and motorised transport. With a focus on Uganda, we describe the data and method and provide the travel maps, software and intermediate datasets for Uganda, Tanzania, Zimbabwe and Mozambique.","tags":null,"title":"Using open-source data to construct 20 metre resolution maps of children’s travel time to the nearest health facility","type":"publication"},{"authors":["Olivia V Swann","Nazir I Lone","Ewen M Harrison","Laurie A Tomlinson","Alex J Walker","Michael J Seaborne","Louisa Pollock","James Farrell","Peter S Hall","Sohan Seth","Thomas C Williams","Jennifer Preston","J. Samantha Ainsworth","Freya F Semple","J Kenneth Baillie","Srinivasa V Katikireddi","Ashley Akbari","Ronan Lyons","Colin R Simpson","Malcolm G Semple","Ben Goldacre","Sinead Brophy","Aziz Sheikh","Annemarie B Docherty"],"categories":null,"content":"","date":1667260800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1667260800,"objectID":"bbd3597b1ab06a006d723563cb1b8447","permalink":"https://sohanseth.github.io/publication/swann-studying-2022-1/","publishdate":"2023-09-29T15:04:20.563102Z","relpermalink":"/publication/swann-studying-2022-1/","section":"publication","summary":"Introduction SARS-CoV-2 infection rarely causes hospitalisation in children and young people (CYP), but mild or asymptomatic infections are common. Persistent symptoms following infection have been reported in CYP but subsequent healthcare use is unclear. We aim to describe healthcare use in CYP following community-acquired SARS-CoV-2 infection and identify those at risk of ongoing healthcare needs.   Methods and analysis We will use anonymised individual-level, population-scale national data linking demographics, comorbidities, primary and secondary care use and mortality between 1 January 2019 and 1 May 2022. SARS-CoV-2 test data will be linked from 1 January 2020 to 1 May 2022. Analyses will use Trusted Research Environments: OpenSAFELY in England, Secure Anonymised Information Linkage (SAIL) Databank in Wales and Early Pandemic Evaluation and Enhanced Surveillance of COVID-19 in Scotland (EAVE-II). CYP aged ≥4 and textless18 years who underwent SARS-CoV-2 reverse transcription PCR (RT-PCR) testing between 1 January 2020 and 1 May 2021 and those untested CYP will be examined. The primary outcome measure is cumulative healthcare cost over 12 months following SARS-CoV-2 testing, stratified into primary or secondary care, and physical or mental healthcare. We will estimate the burden of healthcare use attributable to SARS-CoV-2 infections in the 12 months after testing using a matched cohort study of RT-PCR positive, negative or untested CYP matched on testing date, with adjustment for confounders. We will identify factors associated with higher healthcare needs in the 12 months following SARS-CoV-2 infection using an unmatched cohort of RT-PCR positive CYP. Multivariable logistic regression and machine learning approaches will identify risk factors for high healthcare use and characterise patterns of healthcare use post infection.   Ethics and dissemination This study was approved by the South-Central Oxford C Health Research Authority Ethics Committee (13/SC/0149). Findings will be preprinted and published in peer-reviewed journals. Analysis code and code lists will be available through public GitHub repositories and OpenCodelists with meta-data via HDR-UK Innovation Gateway.","tags":null,"title":"Studying the Long-term Impact of COVID-19 in Kids (SLICK). Healthcare use and costs in children and young people following community-acquired SARS-CoV-2 infection: protocol for an observational study using linked primary and secondary routinely collected healthcare data from England, Scotland and Wales","type":"publication"},{"authors":["Olivia V Swann","Nazir I Lone","Ewen M Harrison","Laurie A Tomlinson","Alex J Walker","Michael J Seaborne","Louisa Pollock","James Farrell","Peter S Hall","Sohan Seth","Thomas C Williams","Jennifer Preston","J. Samantha Ainsworth","Freya F Semple","J Kenneth Baillie","Srinivasa V Katikireddi","Ashley Akbari","Ronan Lyons","Colin R Simpson","Malcolm G Semple","Ben Goldacre","Sinead Brophy","Aziz Sheikh","Annemarie B Docherty"],"categories":null,"content":"","date":1667260800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1667260800,"objectID":"30d5ff9ec3c238a5e7cfe391116cb012","permalink":"https://sohanseth.github.io/publication/swann-studying-2022/","publishdate":"2022-11-24T21:07:15.359996Z","relpermalink":"/publication/swann-studying-2022/","section":"publication","summary":"Introduction SARS-CoV-2 infection rarely causes hospitalisation in children and young people (CYP), but mild or asymptomatic infections are common. Persistent symptoms following infection have been reported in CYP but subsequent healthcare use is unclear. We aim to describe healthcare use in CYP following community-acquired SARS-CoV-2 infection and identify those at risk of ongoing healthcare needs.   Methods and analysis We will use anonymised individual-level, population-scale national data linking demographics, comorbidities, primary and secondary care use and mortality between 1 January 2019 and 1 May 2022. SARS-CoV-2 test data will be linked from 1 January 2020 to 1 May 2022. Analyses will use Trusted Research Environments: OpenSAFELY in England, Secure Anonymised Information Linkage (SAIL) Databank in Wales and Early Pandemic Evaluation and Enhanced Surveillance of COVID-19 in Scotland (EAVE-II). CYP aged ≥4 and textless18 years who underwent SARS-CoV-2 reverse transcription PCR (RT-PCR) testing between 1 January 2020 and 1 May 2021 and those untested CYP will be examined. The primary outcome measure is cumulative healthcare cost over 12 months following SARS-CoV-2 testing, stratified into primary or secondary care, and physical or mental healthcare. We will estimate the burden of healthcare use attributable to SARS-CoV-2 infections in the 12 months after testing using a matched cohort study of RT-PCR positive, negative or untested CYP matched on testing date, with adjustment for confounders. We will identify factors associated with higher healthcare needs in the 12 months following SARS-CoV-2 infection using an unmatched cohort of RT-PCR positive CYP. Multivariable logistic regression and machine learning approaches will identify risk factors for high healthcare use and characterise patterns of healthcare use post infection.   Ethics and dissemination This study was approved by the South-Central Oxford C Health Research Authority Ethics Committee (13/SC/0149). Findings will be preprinted and published in peer-reviewed journals. Analysis code and code lists will be available through public GitHub repositories and OpenCodelists with meta-data via HDR-UK Innovation Gateway.","tags":null,"title":"Studying the Long-term Impact of COVID-19 in Kids (SLICK). Healthcare use and costs in children and young people following community-acquired SARS-CoV-2 infection: protocol for an observational study using linked primary and secondary routinely collected healthcare data from England, Scotland and Wales","type":"publication"},{"authors":["M. Fish","J. Rynne","A. Jennings","C. Lam","A. A. Lamikanra","J. Ratcliff","S. Cellone-Trevelin","E. Timms","J. Jiriha","I. Tosi","R. Pramanik","P. Simmonds","S. Seth","J. Williams","A. C. Gordon","J. Knight","D. J. Smith","J. Whalley","D. Harrison","K. Rowan","H. Harvala","P. Klenerman","L. Estcourt","D. K. Menon","D. Roberts","M. Shankar-Hari","the REMAP-CAP Immunoglobulin Domain UK Investigators"],"categories":null,"content":"","date":1661990400,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1661990400,"objectID":"f4b6adf3093aa9652bc052477705843f","permalink":"https://sohanseth.github.io/publication/fish-coronavirus-2022/","publishdate":"2022-09-22T10:07:08.783936Z","relpermalink":"/publication/fish-coronavirus-2022/","section":"publication","summary":"","tags":null,"title":"Coronavirus disease 2019 subphenotypes and differential treatment response to convalescent plasma in critically ill adults: secondary analyses of a randomized clinical trial","type":"publication"},{"authors":["Harry Alexander Charles Wood","Katjana Ehrlich","Stephanos Yerolatsitis","András Kufcsák","Tom Michael Quinn","Susan Fernandes","Dominic Norberg","Nia Caitlin Jenkins","Vikki Young","Irene Young","Katie Hamilton","Sohan Seth","Ahsan Akram","Robert Rodrick Thomson","Keith Finlayson","Kevin Dhaliwal","James Morgan Stone"],"categories":null,"content":"","date":1661990400,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1661990400,"objectID":"2cbf35f9a3ba64d972e6cc2167a089f6","permalink":"https://sohanseth.github.io/publication/wood-trimode-2022/","publishdate":"2022-09-22T10:07:08.792117Z","relpermalink":"/publication/wood-trimode-2022/","section":"publication","summary":"","tags":null,"title":"Tri‐mode optical biopsy probe with fluorescence endomicroscopy, Raman spectroscopy, and time‐resolved fluorescence spectroscopy","type":"publication"},{"authors":["C Turnbull","A Macleod","S Esposito","R Gorantla","S Seth","R Ramamoorthy","F Mehendale"],"categories":null,"content":"","date":1659312000,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1659312000,"objectID":"54e3bda1485fc0e039056f16168fa48f","permalink":"https://sohanseth.github.io/publication/turnbull-616-2022/","publishdate":"2022-11-24T21:07:15.368159Z","relpermalink":"/publication/turnbull-616-2022/","section":"publication","summary":"Abstract  Aim Orofacial clefts are the most common congenital anomaly to affect the craniofacial region. Surgical repair is usually performed in infancy; however, there are concerning inequalities in access to and quality of surgical care. Scoring aesthetic results after surgery is crucial when determining the success of a repair. A reliable and accurate scoring system utilising large numbers of unstandardised 2-dimentional (2D) photographs of ethnically diverse patients, which is inexpensive, widely accepted and easily applicable, does not exist. Artificial Intelligence (AI) has been applied in various surgical specialities with beneficial results; however, its advantages have not yet been harnessed in cleft care. We aimed to evaluate the potential use of routinely collected 2D photographs of patients with an orofacial cleft and determine if non-standardised data could be used for machine learning (ML) analysis in cleft research.   Method A database comprising over 5 million photographs, collected over 20 years, and developed by the international non-governmental organisation Smile Train, was described, and analysed using RStudio and Microsoft Excel.   Results Description and analysis of the dataset demonstrated that it is the largest and most ethnically inclusive and diverse dataset that currently exists. Preliminary AI analysis confirmed that ML could be used to analyse the data.   Conclusion The quality of routinely collected data presents challenges for use in research. Addressing such challenges helps ensure that findings are more representative of global burden of disease and will deliver outcomes that are more relevant to a diverse global population. Evidence based minimum standards to optimise future data collection have been identified.","tags":null,"title":"616 Addressing Challenges to Enable Better Use of Routinely Collected Clinical Photographs: Evaluating the Largest Cleft Dataset for Machine Learning Analysis","type":"publication"},{"authors":["Ruizhi Zhang","Sohan Seth","James Cumby"],"categories":null,"content":"","date":1648771200,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1648771200,"objectID":"ce6fefe2c91013da9e9958a22c7eb043","permalink":"https://sohanseth.github.io/publication/zhang-grouped-2022/","publishdate":"2022-05-17T12:26:38.673882Z","relpermalink":"/publication/zhang-grouped-2022/","section":"publication","summary":"Determining how similar two materials are in terms of both atomic composition and crystallographic structure remains a challenge, the solution of which would enable generalised machine learning using crystal structure data. We demonstrate a new method of describing crystal structures based on interatomic distances, termed the Grouped Representation of Interatomic Distances (GRID). This fast to compute descriptor can equally be applied to crystalline or disordered materials, and encodes additional information beyond pairwise distances, such as coordination environments. Combined with earth mover’s distance as a measure of similarity, we show that GRID is able to quantitatively compare materials involving both short- and long-range structural variation. Using this new material descriptor, we show that it can accurately predict bulk moduli using a simple nearest-neighbour model, and that the resulting similarity shows good generalisability across multiple materials properties.","tags":null,"title":"Grouped representation of interatomic distances as a similarity measure for crystal structures","type":"publication"},{"authors":["Damien Freitas","Roberto Rizzo","Florian Fusseis","Ian Butler","Sohan Seth","John Wheeler","Oliver Plümper","Hamed Amiri","Alireza Chogani","Christian Schlepütz","Federica Marone","Edward Ando"],"categories":null,"content":"","date":1646092800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1646092800,"objectID":"0cdcaa73191209cfa5fc05921f0ac07b","permalink":"https://sohanseth.github.io/publication/freitas-influence-2022/","publishdate":"2022-05-17T12:23:57.859022Z","relpermalink":"/publication/freitas-influence-2022/","section":"publication","summary":"\u0026lt;p\u0026gt;Tectonic-scale features happening at convergent plates are ultimately the outcome of microscopic, grain scale processes. In collision zones, prograde metamorphism occurs by gradual increase of pressure and temperature [1; 2]. Among the most important prograde mineral reactions are dehydration reactions, which are characterized by solid volume reduction, porosity creation, fluid release and high pore fluid pressures [3]. Most models linking dehydration and mechanical instabilities [4-6] involve feedback loops between coupled chemical, hydraulic and mechanical processes. Feedbacks control pore fluid pressure build-up and drainage, and provide efficient pathways for the transport of chemical components. Gypsum dehydration is crucial in the formation of detachment faults thin-skinned tectonics [7]. It is also used as a proxy for serpentine dehydration and the generation of intermediate depth seismic events/aseismic slip activity [8].\u0026lt;/p\u0026gt;\u0026lt;p\u0026gt;We performed a set of experimental gypsum dehydrations both at the TOMCAT microtomography beamline at the Swiss Light Source, and in the laboratory. Using a modified version of the Mjolnir triaxial rig [9] that allowed control of pore fluid pressure in the synchrotron microtomography setup enabled us to document how differential stress (\u0026amp;#8710;\u0026amp;#963;) and pore fluid pressure (P\u0026lt;sub\u0026gt;f\u0026lt;/sub\u0026gt;) influence the dehydration of Volterra alabaster gypsum to bassanite at a constant confining pressure and temperature in 4D.\u0026lt;/p\u0026gt;\u0026lt;p\u0026gt;We derived data on mineral phase transformation and formation of pore networks by applying a deep-learning algorithm in ORS Dragonfly\u0026amp;#174; software, which reduced data processing times, minimized interpretation biases, and allowed analysing larger volumes. The results exhibit an extremely high accuracy compared to standard procedures. The analysis of phase proportions (gypsum, bassanite and porosity) of segmented volumes correlates very well to theoretical predictions indicating a correct segmentation from the algorithms and self-consistency of the generated datasets. Comparing results obtained\u0026amp;#160; at various \u0026amp;#8710;\u0026amp;#963; and P\u0026lt;sub\u0026gt;f\u0026lt;/sub\u0026gt; to the light of mechanical data and additional in-house experiments allows us to better interpret their effect on reaction duration, magnitude and textural evolution of the rock. Transient phenomena as well as individual grain transformation and growth are now traceable in a fully automated way.\u0026lt;/p\u0026gt;\u0026lt;p\u0026gt;Our data further our understanding of gypsum dehydration: We found that \u0026amp;#8710;\u0026amp;#963; greatly influences the assemblage of the bassanite needles, which tend to grow nearly vertical at \u0026amp;#8710;\u0026amp;#963; \u0026amp;#8773; 0. Increasing \u0026amp;#8710;\u0026amp;#963; significantly increases sample compaction. On the contrary, increasing P\u0026lt;sub\u0026gt;f \u0026lt;/sub\u0026gt;decreases the bulk deformation and slows down the reaction. As pores grow around bassanite needles, the control of the orientation of needles by differential stress can influence the overall pore network and thus introduce anisotropies during transient and final stages of the reaction. Our data confirm that \u0026amp;#8710;\u0026amp;#963; and P\u0026lt;sub\u0026gt;f\u0026lt;/sub\u0026gt; greatly influence transient and final rock texture, which has implications on drainage during nappe emplacements.\u0026lt;/p\u0026gt;\u0026lt;p\u0026gt;\u0026lt;strong\u0026gt;References\u0026lt;/strong\u0026gt;: [1] Hacker et al., 2003, /10.1029/2001JB001129; [2] Peacock, 2001, 10.1130/0091-7613(2001)029\u0026lt;0299:ATLPOD\u0026gt;2.0.CO;2 [3] Llana-Funez et al. 2012, /10.1007/s00410-012-0726-8; [4] Raleigh and Paterson, 1965;/10.1029/JZ070i016p03965\u0026amp;#160; [5] Dobson et al., 2002; /10.1126/science.1075390 [6] Jung et al., 2004; /10.2747/0020-6814.46.12.1089 [7] Hubbert and Rubey, 1959;/10.1130/0016-7606(1959)70[115:ROFPIM]2.0.CO;2 [8] Rutter et al. 2009; /10.1016/j.jsg.2008.09.008 [9] Butler 2020, /10.1107/S160057752001173X.\u0026lt;/p\u0026gt;","tags":null,"title":"Influence of pore fluid pressure and differential stress on gypsum dehydration and rock texture revealed by 4D synchrotron X-ray tomography","type":"publication"},{"authors":["Qihao Jiang","Sohan Seth","Theresa Scharl","Tim Schroeder","Alois Jungbauer","Simone Dimartino"],"categories":null,"content":"","date":1646092800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1646092800,"objectID":"dc2bfc71b0f0c78f50b16f0ea5005445","permalink":"https://sohanseth.github.io/publication/jiang-prediction-2022/","publishdate":"2022-05-17T12:23:22.223728Z","relpermalink":"/publication/jiang-prediction-2022/","section":"publication","summary":"","tags":null,"title":"Prediction of the performance of pre‐packed purification columns through machine learning","type":"publication"},{"authors":["Isaac Neal","Sohan Seth","Gary Watmough","Mamadou S. Diallo"],"categories":null,"content":"","date":1633046400,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1633046400,"objectID":"426cb9f30c183a44c5f99d1b921549a7","permalink":"https://sohanseth.github.io/publication/neal-census-independent-2021/","publishdate":"2023-09-29T15:04:20.547463Z","relpermalink":"/publication/neal-census-independent-2021/","section":"publication","summary":"Knowledge of population distribution is critical for building infrastructure, distributing resources, and monitoring the progress of sustainable development goals. Although censuses can provide this information, they are typically conducted every ten years with some countries having forgone the process for several decades. Population can change in the intercensal period due to rapid migration, development, urbanisation, natural disasters, and conflicts. Census-independent population estimation approaches using alternative data sources, such as satellite imagery, have shown promise in providing frequent and reliable population estimates locally. Existing approaches, however, require significant human supervision, for example annotating buildings and accessing various public datasets, and therefore, are not easily reproducible. We explore recent representation learning approaches, and assess the transferability of representations to population estimation in Mozambique. Using representation learning reduces required human supervision, since features are extracted automatically, making the process of population estimation more sustainable and likely to be transferable to other regions or countries. We compare the resulting population estimates to existing population products from GRID3, Facebook (HRSL) and WorldPop. We observe that our approach matches the most accurate of these maps, and is interpretable in the sense that it recognises built-up areas to be an informative indicator of population.","tags":["Computer Science - Machine Learning"],"title":"Census-Independent Population Estimation using Representation Learning","type":"publication"},{"authors":[],"categories":[],"content":"","date":1621377862,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1621377862,"objectID":"c68674de51582e8496b78970079120b8","permalink":"https://sohanseth.github.io/project/cisc/","publishdate":"2021-05-18T23:44:22+01:00","relpermalink":"/project/cisc/","section":"project","summary":"Develope stable, consistent, operationalisable, reproducible, and explaninable clusters of multimorbidities. We will analyze these clusters in Clinical Practice Research Datalink and validate them in DataLoch to find their genetic basis and in Scottish Longitudinal Study to infer their socio-economic basis.","tags":[],"title":"Understanding Clusters of Multimorbidity using Machine Learning","type":"project"},{"authors":["Yili Yang","Sohan Seth","Ian B. Butler","Florian Fusseis"],"categories":null,"content":"","date":1619827200,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1619827200,"objectID":"aae23e54f6764583c473d3218c1af8a0","permalink":"https://sohanseth.github.io/publication/yang-fast-2021/","publishdate":"2021-05-20T08:53:25.01945Z","relpermalink":"/publication/yang-fast-2021/","section":"publication","summary":"","tags":null,"title":"Fast Segmentation of 4D Microtomography Volumes from Core-flooding Experiments in Porous Rock using Convolutional Neural Network","type":"publication"},{"authors":["James Cumby"],"categories":null,"content":"","date":1616763600,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1616763600,"objectID":"f0912a471a1b72828d6fb57238495b2d","permalink":"https://sohanseth.github.io/d2d/cumby/","publishdate":"2021-03-26T22:29:15Z","relpermalink":"/d2d/cumby/","section":"d2d","summary":"Crystalline materials form the basis of many of the technologies we rely on, ranging from the silicon transistors powering our computers to the sugar powering us. The principal tool for determining the arrangement of atoms in a material (X-ray diffraction) was discovered just over a century ago, and in that time chemists have built up vast databases of materials which continue to grow exponentially. In this talk, I will discuss the information that is contained within diffraction data, its impact in understanding the physical properties of materials, and how it is impacting the way chemists make new materials. In relation to my own research, I will highlight how atomic structure data can be used to discover new materials, and some of the challenges in harnessing these data.","tags":[],"title":"Atomic Insights From a Grain of Salt","type":"d2d"},{"authors":[],"categories":null,"content":"","date":1611655225,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1611655225,"objectID":"a3de93c4416403ae88e161798389570f","permalink":"https://sohanseth.github.io/talk/anc2021/","publishdate":"2021-01-26T14:08:25+01:00","relpermalink":"/talk/anc2021/","section":"talk","summary":"Decisions including access to services, distribution of vaccines, disaster relief, and many others are informed based on the most up to date population estimates for an area, and many Sustainable Development Goals (SDGs) indicators established by the United Nations (UN) depend on the total population count or population count of a specific group. Traditional population data source, i.e., census data, is not adequate for this purpose since censuses are conducted typically decennially. Census-independent population estimation or bottom-up approach estimates population through microcensus and remote sensing. This involves using local population survey data, i.e., microcensus, and remote sensing data, e.g., satellite images, to learn an association between the visual features of an area that are informative of population, e.g., number of buildings, type of land, distance to road etc., and the respective population, and to extrapolate this knowledge across an entire country or region. I will present some challenges and preliminary results of our ongoing work with Data for Children Collaborative and UNICEF in Mozambique.","tags":[],"title":"Estimating Population Density from Remote Sensing and Microcensus","type":"talk"},{"authors":["Isaac Neal","Sohan Seth","Gary Watmough","Mamadou Saliou Diallo"],"categories":null,"content":"","date":1609459200,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1609459200,"objectID":"a718fdfbde8fae49483f3fab2628bc96","permalink":"https://sohanseth.github.io/publication/neal-towards-2021/","publishdate":"2021-04-29T20:47:12.617896Z","relpermalink":"/publication/neal-towards-2021/","section":"publication","summary":"Reliable and frequent population estimation is key for making policies around vaccination and planning infrastructure delivery. Since censuses lack the spatio-temporal resolution required for these tasks, census-independent approaches, using remote sensing and microcensus data, have become popular. We estimate intercensal population count in two pilot districts in Mozambique. To encourage sustainability, we assess the feasibility of using publicly available datasets to estimate population. We also explore transfer learning with existing annotated datasets for predicting building footprints, and training with additional `dot' annotations from regions of interest to enhance these estimations. We observe that population predictions improve when using footprint area estimated with this approach versus only publicly available features.","tags":null,"title":"Towards Sustainable Census-Independent Population Estimation in Mozambique","type":"publication"},{"authors":["Gary Watmough","Sohan Seth"],"categories":[],"content":"","date":1604620800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1604620800,"objectID":"4d9dbf52e2bb77fe4c14a0fc1272ab55","permalink":"https://sohanseth.github.io/project/cpa2s/","publishdate":"2020-11-06T00:00:00Z","relpermalink":"/project/cpa2s/","section":"project","summary":"Develop understanding on the causes of childhood poverty. We are focussing on whether children’s physical accessibility to services, such as health facilities or schools contribute to their deprivation.","tags":[],"title":"Child Poverty and Access to Services in Uganda","type":"project"},{"authors":["Olivia V Swann","Karl A Holden","Lance Turtle","Louisa Pollock","Cameron J Fairfield","Thomas M Drake","Sohan Seth","Conor Egan","Hayley E Hardwick","Sophie Halpin","Michelle Girvan","Chloe Donohue","Mark Pritchard","Latifa B Patel","Shamez Ladhani","Louise Sigfrid","Ian P Sinha","Piero L Olliaro","Jonathan S Nguyen-Van-Tam","Peter W Horby","Laura Merson","Gail Carson","Jake Dunning","Peter J M Openshaw","J Kenneth Baillie","Ewen M Harrison","Annemarie B Docherty","Malcolm G Semple"],"categories":null,"content":"","date":1596240000,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1596240000,"objectID":"fcef46323ff3ee17a30b5ec73f36ed6b","permalink":"https://sohanseth.github.io/publication/swann-clinical-2020/","publishdate":"2021-02-07T20:57:34.265159Z","relpermalink":"/publication/swann-clinical-2020/","section":"publication","summary":"Abstract  Objective To characterise the clinical features of children and young people admitted to hospital with laboratory confirmed severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection in the UK and explore factors associated with admission to critical care, mortality, and development of multisystem inflammatory syndrome in children and adolescents temporarily related to coronavirus disease 2019 (covid-19) (MIS-C).   Design Prospective observational cohort study with rapid data gathering and near real time analysis.   Setting 260 hospitals in England, Wales, and Scotland between 17 January and 3 July 2020, with a minimum follow-up time of two weeks (to 17 July 2020).   Participants 651 children and young people aged less than 19 years admitted to 138 hospitals and enrolled into the International Severe Acute Respiratory and emergency Infections Consortium (ISARIC) WHO Clinical Characterisation Protocol UK study with laboratory confirmed SARS-CoV-2.   Main outcome measures Admission to critical care (high dependency or intensive care), in-hospital mortality, or meeting the WHO preliminary case definition for MIS-C.   Results  Median age was 4.6 (interquartile range 0.3-13.7) years, 35% (225/651) were under 12 months old, and 56% (367/650) were male. 57% (330/576) were white, 12% (67/576) South Asian, and 10% (56/576) black. 42% (276/651) had at least one recorded comorbidity. A systemic mucocutaneous-enteric cluster of symptoms was identified, which encompassed the symptoms for the WHO MIS-C criteria. 18% (116/632) of children were admitted to critical care. On multivariable analysis, this was associated with age under 1 month (odds ratio 3.21, 95% confidence interval 1.36 to 7.66; P=0.008), age 10-14 years (3.23, 1.55 to 6.99; P=0.002), and black ethnicity (2.82, 1.41 to 5.57; P=0.003). Six (1%) of 627 patients died in hospital, all of whom had profound comorbidity. 11% (52/456) met the WHO MIS-C criteria, with the first patient developing symptoms in mid-March. Children meeting MIS-C criteria were older (median age 10.7 (8.3-14.1) v 1.6 (0.2-12.9) years; Ptextless0.001) and more likely to be of non-white ethnicity (64% (29/45) v 42% (148/355); P=0.004). Children with MIS-C were five times more likely to be admitted to critical care (73% (38/52) v 15% (62/404); Ptextless0.001). In addition to the WHO criteria, children with MIS-C were more likely to present with fatigue (51% (24/47) v 28% (86/302); P=0.004), headache (34% (16/47) v 10% (26/263); Ptextless0.001), myalgia (34% (15/44) v 8% (21/270); Ptextless0.001), sore throat (30% (14/47) v (12% (34/284); P=0.003), and lymphadenopathy (20% (9/46) v 3% (10/318); Ptextless0.001) and to have a platelet count of less than 150 × 10 9 /L (32% (16/50) v 11% (38/348); Ptextless0.001) than children who did not have MIS-C. No deaths occurred in the MIS-C group.    Conclusions Children and young people have less severe acute covid-19 than adults. A systemic mucocutaneous-enteric symptom cluster was also identified in acute cases that shares features with MIS-C. This study provides additional evidence for refining the WHO MIS-C preliminary case definition. Children meeting the MIS-C criteria have different demographic and clinical features depending on whether they have acute SARS-CoV-2 infection (polymerase chain reaction positive) or are post-acute (antibody positive).   Study registration ISRCTN66726260.","tags":null,"title":"Clinical characteristics of children and young people admitted to hospital with covid-19 in United Kingdom: prospective multicentre observational cohort study","type":"publication"},{"authors":["Jonathan E Millar","Lucile Neyton","Sohan Seth","Jake Dunning","Laura Merson","Srinivas Murthy","Clark D Russell","Sean Keating","Maaike Swets","Carole H Sudre","Timothy D Spector","Sebastien Ourselin","Claire J Steves","Jonathan Wolf","ISARIC-4C Investigators","Annemarie B Docherty","Ewen M Harrison","Peter JM Openshaw","Malcolm G Semple","J. Kenneth Baillie"],"categories":null,"content":"","date":1596240000,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1596240000,"objectID":"508799d96b3df54a1e20010348a7c376","permalink":"https://sohanseth.github.io/publication/millar-robust-2020/","publishdate":"2021-02-07T20:57:34.265907Z","relpermalink":"/publication/millar-robust-2020/","section":"publication","summary":"Abstract Severe COVID-19 is characterised by fever, cough, and dyspnoea. Symptoms affecting other organ systems have been reported. The clinical associations of different patterns of symptoms can influence diagnostic and therapeutic decision-making: for example, significant differential therapeutic effects in sub-groups of patients with different severities of respiratory failure have already been reported for the only treatment so far shown to reduce mortality in COVID-19, dexamethasone. We obtained structured clinical data on 68914 patients in the UK (the ISARIC Coronavirus Clinical Characterisation Consortium, 4C) and used a principled, unsupervised clustering approach to partition the first 33468 cases according to symptoms reported at recruitment. We validated our findings in a second group of 35446 cases recruited to ISARIC-4C, and in separate cohort of community cases. A core symptom set of fever, cough, and dyspnoea co-occurred with additional symptoms in three patterns: fatigue and confusion, diarrhoea and vomiting, or productive cough. Presentations with a single reported symptom of dyspnoea or confusion were common, and a subgroup of patients reported few or no symptoms. Patients presenting with gastrointestinal symptoms were more commonly female, had a longer duration of symptoms before presentation, and had lower 30-day mortality. Patients presenting with confusion, with or without core symptoms, were older and had a higher unadjusted mortality. Symptom clusters were highly consistent in replication analysis using a further 35446 individuals subsequently recruited to ISARIC-4C. Similar patterns were externally verified in 4445 patients from a study of self-reported symptoms of mild disease. The large scale of ISARIC-4C study enabled robust, granular discovery and replication of patient clusters. Clinical interpretation is necessary to determine which of these observations have practical utility. We propose that four patterns are usefully distinct from the core symptom groups: gastro-intestinal disease, productive cough, confusion, and pauci-symptomatic presentations. Importantly, each is associated with an in-hospital mortality which differs from that of patients with core symptoms. These observations deepen our understanding of COVID-19 and will influence clinical diagnosis, risk prediction, and future mechanistic and clinical studies.","tags":null,"title":"Robust, reproducible clinical patterns in hospitalised patients with COVID-19","type":"publication"},{"authors":["Milly Lo"],"categories":null,"content":"","date":1583499600,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1583499600,"objectID":"45298c1c85a740fd5e7f17d126e4ae0c","permalink":"https://sohanseth.github.io/d2d/lo/","publishdate":"2021-02-07T22:34:51Z","relpermalink":"/d2d/lo/","section":"d2d","summary":"Much of the routine data generated during the provision of medical care in critical care units is discarded rather than fully used to help clinicians improve treatments. Multi-centre ‘intensive-care big-data’ initiatives such as the adult BrainIT group have successfully improved adult brain trauma care with new research ideas and data-driven improvement interventions. With the support of a prestigious EU grant, I have successfully set- up a new paediatric brain trauma ‘big-data’ initiative (KidsBrainIT) that uses high-quality bedside physiological data from patients recruited in 15 PICU in 5 countries to better understand the importance of bespoke management improvements (e.g. treatment of increased brain pressure from brain swelling). I am using KidsBrainIT as a proof-of-concept to demonstrate the benefits of data-intensive informatics in improvement research and to translate this concept into IMPACT-ACE that will ultimately improve patient care, safety and outcome in the broader critical-care setting and other medical specialities in the future. In this talk, I will summarise the challenges we have overcome using this research approach and how we may make better use of big data generated routinely within critical care units.","tags":[],"title":"IMPACT-ACE: Gold Panning in the Under-used Critical Care Data Stream","type":"d2d"},{"authors":["James Cumby","Sohan Seth"],"categories":[],"content":"","date":1583020800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1583020800,"objectID":"ebfe53410227a450529a31de4d11f691","permalink":"https://sohanseth.github.io/project/crystal/","publishdate":"2020-03-01T00:00:00Z","relpermalink":"/project/crystal/","section":"project","summary":"Develop new concise and informative crystal structure descriptors, focussed on maintaining chemical interpretability and generalisability.","tags":[],"title":"Interpretable Descriptors for Materials Machine Learning","type":"project"},{"authors":["Katerina Boufea","Sohan Seth","Nizar N. Batada"],"categories":null,"content":"","date":1583020800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1583020800,"objectID":"baad960c55c7bdc2a78415e86efbe074","permalink":"https://sohanseth.github.io/publication/boufea-scid-2020/","publishdate":"2021-02-07T20:57:34.264503Z","relpermalink":"/publication/boufea-scid-2020/","section":"publication","summary":"","tags":null,"title":"scID Uses Discriminant Analysis to Identify Transcriptionally Equivalent Cell Types across Single-Cell RNA-Seq Data with Batch Effect","type":"publication"},{"authors":["Simone Dimartino"],"categories":null,"content":"","date":1579870800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1579870800,"objectID":"dcf55f29a652717f8295e2043f160809","permalink":"https://sohanseth.github.io/d2d/demartino/","publishdate":"2021-02-07T22:32:03Z","relpermalink":"/d2d/demartino/","section":"d2d","summary":"Perfectly ordered structures have been reported to drastically outperform traditional packing in a variety of applications in chemistry and engineering. While this used to be a rather theoretical concept, 3D printing now enables the fabrication of such ordered structures, with complex geometry, and with resolution at the micron scale.\nIn this lecture I will present a holistic toolbox to design, manufacture and characterize such structures. In my research group we blend a range of modelling and experimental methods, from fluid dynamics to machine learning, from materials science to engineering practice. I will demonstrate how our approach to 3D printing delivers optimized structures and materials with improved performance, with specific focus on applications in the separation sciences (e.g. chromatography) and biotechnology sectors (e.g. bioreactors).\nHopefully this talk will spark your interest on this topic, and make you realize how 3D printed structures could complement and boost your research, regardless of its background and scope!","tags":[],"title":"3-D printing of Ordered Structures: Applications in Chemistry and Engineering","type":"d2d"},{"authors":[],"categories":null,"content":"","date":1579600846,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1579600846,"objectID":"24bfe2402438e38d075c28784c377e96","permalink":"https://sohanseth.github.io/talk/anc2020/","publishdate":"2021-04-30T14:26:46+01:00","relpermalink":"/talk/anc2020/","section":"talk","summary":"Archetypal analysis is an unsupervised learning tool commonly used in exploratory data analysis dimensionality reduction interpretation and visualization. We extend this idea to find archetypal distributions given a set of probability distributions. This is useful for example when we report the uncertainty in a measurement alongside the measured value. We propose a principled approach to tackle this situation using partial membership model. We discuss the connection between the proposed approach and existing extensions of archetypal analysis namely probabilistic archetypal analysis kernel archetypal analysis interval archetypal analysis and statistical archetypal analysis and apply this approach to both synthetic and real data to investigate its properties and effectiveness.","tags":[],"title":"Archetypal Distribution","type":"talk"},{"authors":["Annemarie Docherty"],"categories":null,"content":"","date":1574427600,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1574427600,"objectID":"404e728138a2b3b688718f8a8a73bc0a","permalink":"https://sohanseth.github.io/d2d/docherty/","publishdate":"2021-02-07T22:29:15Z","relpermalink":"/d2d/docherty/","section":"d2d","summary":"We admit around 10,000 patients to Intensive Care Units (ICUs) in Scotland every year, with conditions such as sepsis, cardiac arrest and trauma. These patients are critically unwell, and despite best care, approximately 18% of patients admitted to ICU will die during their hospital admission. Significant amounts of data are collected on every patient admitted to the ICU including not only characteristics such as age, sex, and comorbidity, but also beat to beat information on heart rate, blood pressure and other markers of critical illness. This information helps us as clinicians in our diagnosis and management of each individual critically ill patient.\nHowever, there are as yet unrealised potential uses for this data to improve outcomes for our whole population. Analysis of routine text healthcare data will enable us to characterise different healthcare phenotypes, identifying patients at risk of adverse events, or who may benefit from different interventions. Analysis of high-frequency physiological patient data could enable us to detect and potentially predict adverse events early and implement management changes quickly and effectively.\nCollaboration between data scientists and clinicians using this routinely collected healthcare data could transform the way that patients are managed in the ICU and ultimately improve outcomes for this critically unwell population.","tags":[],"title":"ICU-HEART: Using Routine Healthcare Data to Improve Outcomes in ICU","type":"d2d"},{"authors":["Gary Watmough"],"categories":null,"content":"","date":1570798800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1570798800,"objectID":"9459c03f66cbbe8fc6b9bc675f9b0c2b","permalink":"https://sohanseth.github.io/d2d/watmough/","publishdate":"2021-02-07T22:26:23Z","relpermalink":"/d2d/watmough/","section":"d2d","summary":"Tracking the progress of the Sustainable Development Goals and targeting interventions requires frequent, up-to-date data on social, economic and ecosystem conditions. My research seeks to examine the role that remotely sensed satellite data could have in mapping and monitoring socioeconomic conditions by exploring how household wellbeing and deprivation can be predicted from land use maps and building roof material type both derived from fine spatial resolution satellite data. We demonstrate that satellite data can predict wellbeing in Kenya with between 51 and 62% accuracy. Prediction accuracy was higher when using a multi-level approach to linking households to landscapes and most land use changes between 2005 and 2014 were observed in homesteads of the poorest households. High-resolution satellite data could provide a faster and cheaper way to track several SDGs but work so far across several research groups and countries has been based on secondary data analysis. However, a challenge lies in upscaling the work to regional and national levels to make it relevant to policy makers. We are exploring various approaches including CNNs to identify how we might best move forward.","tags":[],"title":"Mapping Deprivation in Rural Areas from Earth Observation Data","type":"d2d"},{"authors":[],"categories":null,"content":"","date":1568192427,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1568192427,"objectID":"c99788e7a696789ae88b54fb3384698c","permalink":"https://sohanseth.github.io/talk/cladag2019/","publishdate":"2021-05-10T20:44:27+01:00","relpermalink":"/talk/cladag2019/","section":"talk","summary":"Given a set of observations, archetypal analysis finds 'extreme' examples, i.e., archetypes that represent the observations well. Following the geometric formulation proposed by Cutler and Breiman (1994) this is achieved by approximating the convex hull of the set of observations with the archetypes such that the observations can be explained as convex combinations of the archetypes; an analogy being the colors red, green and blue that can explain the color spectrum as convex combinations of these archetypal colors. Archetypal analysis can be seen as a matrix factorization problem, and is closely related to other 'prototype' finding approaches, e.g., k-means clustering and topic modelling.\nThe standard approach of finding archetypes assumes that the observations are real valued, which, unfortunately, is not compatible with many practical situations. For example, one may ask to find archetypal responses for a set of binary questions, or archetypal document given a set of word count vectors of a set of documents.  In this talk, I will revisit archetypal analysis from the basic principles, and discuss a probabilistic framework that accommodates these scenarios, i.e., data types such as integers, categorical, and stochastic vector. This formulation is equivalent to performing archetypal analysis in the continuous parameter space of the probability distribution than in the discrete observation space, and for a range of exponential family distributions, such as Bernoulli, Poisson, and multinomial, the resulting optimization problem can be efficiently solved using majorization-minimization. For categorical variables, e.g., multiple-option questions, I will introduce an extension of this approach to a generative framework using Dirichlet prior over the mixing parameters for which the approximate posterior distribution can be efficiently inferred using variational Bayes', and associated hyperparameters help finding a suitable number of archetypes.\nI will show the application of these formulations for finding archetypal tourists based on binary survey data, archetypal disaster-affected countries based on disaster count data, archetypal customers using German credit data, archetypal images using SUN image attribute data, and archetypal behaviour from Big Five personality data. I will also present an appropriate visualization tool to summarize the archetypal analysis solution, and address some recent developments in this area and some open questions. ","tags":[],"title":"Probabilistic Archetypal Analysis","type":"talk"},{"authors":[],"categories":null,"content":"","date":1568106054,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1568106054,"objectID":"f20b5347cba41cfbb0330a25bd579d82","permalink":"https://sohanseth.github.io/talk/napoli2019/","publishdate":"2021-05-10T20:53:54+01:00","relpermalink":"/talk/napoli2019/","section":"talk","summary":"It is commonly accepted that 'all models are wrong but some are useful'. An aspect of statistical modelling is, therefore, to understand the limitations of the fitted model since this may help in extending the model to a more suitable one. This process is known as model criticism. Model criticism uses statistical tests to assess various aspects of the fitted model in order to identify its deficiencies. This is usually carried out, by Posterior Predictive Check, in the observation space by assessing if replicated data generated under the fitted model looks similar to the observed data. I will describe an alternative approach, referred to as the Aggregated Posterior Check, that pulls the data back into the space of latent variables, and carries out model criticism in the latent space. The principle of this approach is that if the model fits, then posterior inferences should match the prior assumptions. I will demonstrate the method with examples of model criticism in latent space applied to factor analysis, linear dynamical systems and Gaussian processes on three real world examples from image analysis, time series modelling, and time series extrapolation.","tags":[],"title":"Model Criticism in Latent Space","type":"talk"},{"authors":["Sohan Seth","Iain Murray","Christopher K. I. Williams"],"categories":null,"content":"","date":1567296000,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1567296000,"objectID":"b9f012f050f92d94374871a703fdec4a","permalink":"https://sohanseth.github.io/publication/seth-model-2019/","publishdate":"2021-02-07T20:57:34.263344Z","relpermalink":"/publication/seth-model-2019/","section":"publication","summary":"Model criticism is usually carried out by assessing if replicated data generated under the fitted model looks similar to the observed data, see e.g. Gelman, Carlin, Stern, and Rubin (2004, p. 165). This paper presents a method for latent variable models by pulling back the data into the space of latent variables, and carrying out model criticism in that space. Making use of a model's structure enables a more direct assessment of the assumptions made in the prior and likelihood. We demonstrate the method with examples of model criticism in latent space applied to factor analysis, linear dynamical systems and Gaussian processes.","tags":["factor analysis","Gaussian processes","latent variable models","linear dynamical systems","model criticism"],"title":"Model Criticism in Latent Space","type":"publication"},{"authors":[],"categories":null,"content":"","date":1566381628,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1566381628,"objectID":"5c7f4ecdda9a6fb5c3687fe3c0e67784","permalink":"https://sohanseth.github.io/talk/boston2019/","publishdate":"2021-05-18T14:18:28+01:00","relpermalink":"/talk/boston2019/","section":"talk","summary":"Solitary pulmonary nodules are common, often incidental findings on chest CT scans. The investigation of pulmonary nodules is time-consuming and often leads to protracted follow-up with ongoing radiological surveillance, however, clinical calculators that assess the risk of the nodule being malignant exist to help in the stratification of patients. Furthermore recent advances in interventional pulmonology include the ability to both navigate to nodules and also to perform autofluorescence endomicroscopy. In this study we assessed the efficacy of incorporating additional information from label-free fibre-based optical endomicrosopy of the nodule on assessing risk of malignancy. Using image analysis and machine learning approaches, we find that this information does not yield any gain in predictive performance in a cohort of patients. Further advances with pulmonary endomicroscopy will require the addition of molecular tracers to improve information from this procedure.","tags":[],"title":"Can We Assess Lung Nodule by Just Looking at It?","type":"talk"},{"authors":["Florian Fusseis"],"categories":null,"content":"","date":1558098000,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1558098000,"objectID":"84aa326525c77c50edb47a6172488628","permalink":"https://sohanseth.github.io/d2d/fusseis/","publishdate":"2021-02-07T22:22:13Z","relpermalink":"/d2d/fusseis/","section":"d2d","summary":"X-ray microtomography is an imaging technique that enables reconstructing the internal structure of objects based on variations in x-ray absorption and phase contrast. The x-rays produced by synchrotron light sources are even bright enough to see through pressure vessels and capture changes to the internal structure of rock samples during geological processes in experiments. Time-resolved (4D) microtomography, which produces vast amounts of image data, is currently revolutionising experimental geosciences. These data allow the quantification and interpretion of grain (i.e. micron-) scale processes in rocks. Where combined with more conventional mechanical, chemical, hydraulic and thermal data, they enable significant advances in our understanding of tectonic processes. These advances are currently curtailed by our lacking ability to optimize tomographic data acquisition, streamline data processing and most importantly, mine, combine and interpret the experimental data. In this talk I will outline our group’s experimental work with (synchrotron-based) 4D x-ray microtomography and describe our interfaces with data science. I will report on our current data analysis strategies and discuss our stumbling blocks in data processing and interpretation.","tags":[],"title":"How Sleep-deprivation at Synchrotrons Advances Plate Tectonics","type":"d2d"},{"authors":["Rupert Myers","Zoë Petard"],"categories":null,"content":"","date":1553259600,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1553259600,"objectID":"9e9337657d65764964814cab72737086","permalink":"https://sohanseth.github.io/d2d/myers/","publishdate":"2021-02-07T22:18:42Z","relpermalink":"/d2d/myers/","section":"d2d","summary":"Modern society is unsustainable. This fact highlights the imperative for transformational change to the industrial system and the materials basis of modern society, i.e., the ‘total materials system’. ‘Computational industrial ecology’ is an emerging approach that aims to leverage data and modelling tools to quantify the total materials system in order to understand how to improve its efficiency and reduce its environmental burdens. The Industrial Ecology Team is currently working towards this aim by developing a data structure for sustainability science data, a relational database to efficiently contain these data for querying, and an algorithm to unify these data into a model of the total materials system. In this seminar, we will introduce industrial ecology, discuss current research activities, and identify some potential areas for future research.","tags":[],"title":"Computational Industrial Ecology","type":"d2d"},{"authors":["Lev Sarkisov"],"categories":null,"content":"","date":1552050000,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1552050000,"objectID":"51bdf9c643b451cf8f4159d68e0721ef","permalink":"https://sohanseth.github.io/d2d/sarkisov/","publishdate":"2021-02-07T21:45:44Z","relpermalink":"/d2d/sarkisov/","section":"d2d","summary":"The discovery of new classes of porous adsorbents such as metal-organic frameworks (MOFs) has opened access to a very large number of porous structures with a wide range of functionalities, which can be potentially exploited in different separation applications. Experimental evaluation of all these materials for specific applications is not feasible, and as a result, this prompted the development of high throughput computational screening methods. In this presentation, I will reflect on the development of the multiscale strategies that combine molecular simulations and pressure swing adsorption modelling and optimization to predict performance of the materials on the process scale. Specifically, I will focus on the challenges associated with the interface between molecular and process levels of description and demonstrate that the emerging picture is quite complex. As a case study, a well-known 4-step vacuum swing adsorption (VSA) cycle with light product pressurization (LPP), and Zeolite 13X as adsorbent in application to carbon dioxide removal from a typical flue gas stream (15% CO2, 85% N2, 1 atm) will be considered. I will discuss (a) the effect of the protocol for fitting experimental adsorption data with analytical adsorption models (e.g. dual-site Langmuir model), (b) influence of the pellet porosity and (c) influence of the pellet size on the process performance and material raking. Another aspect of the multiscale strategies we intend to explore is the accuracy of the molecular force fields, particularly in reproducing nitrogen isotherms, and how this affects predictions for the performance of the material in a process and the resulting ranking.","tags":[],"title":"From Crystal to Adsorption Column: Challenges in Multiscale Computational Screening of Materials for Adsorption Separation Processes","type":"d2d"},{"authors":["Debaditya Choudhury","Michael G Tanner","Sarah McAughtrie","Fei Yu","Bethany Mills","Tushar R Choudhary","Sohan Seth","Thomas H Craven","James M Stone","Ioulia K Mati","Colin J Campbell","Mark Bradley","Christopher K I Williams","Kevin Dhaliwal","Timothy A Birks","Robert R Thomson"],"categories":null,"content":"","date":1546300800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1546300800,"objectID":"d58477879a07546e5a3d51284ff397a8","permalink":"https://sohanseth.github.io/publication/choudhury-endoscopic-2019/","publishdate":"2021-02-07T20:57:34.294731Z","relpermalink":"/publication/choudhury-endoscopic-2019/","section":"publication","summary":"","tags":null,"title":"Endoscopic sensing of distal lung physiology","type":"publication"},{"authors":["Alexander Przybylski","Edwin van Beek","Kevin Dhaliwal","Aziz Sheikh","Azin Salimian","Sohan Seth","Giorgos Papanastasiou","Jeremy Walker","Nik Hirani"],"categories":null,"content":"","date":1546300800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1546300800,"objectID":"a97c96dcb16d180f5bec10cfa6e81d35","permalink":"https://sohanseth.github.io/publication/przybylski-stratification-2019/","publishdate":"2021-04-29T20:44:34.446463Z","relpermalink":"/publication/przybylski-stratification-2019/","section":"publication","summary":"","tags":null,"title":"Stratification of Fibrotic Lung Disease: Integration of Molecular Endotyping and Quantitative CT via Machine Learning","type":"publication"},{"authors":[],"categories":null,"content":"","date":1537786815,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1537786815,"objectID":"457c965f028c1614f1fcff304bc9d895","permalink":"https://sohanseth.github.io/talk/cmi2018/","publishdate":"2021-05-10T20:04:15+01:00","relpermalink":"/talk/cmi2018/","section":"talk","summary":"We address the task of estimating bacterial and cellular load in the human distal lung with fibered confocal fluorescence microscopy (FCFM). In pulmonary FCFM some cells can display autofluorescence, and they appear as disc like objects in the FCFM images, whereas bacteria, although not autofluorescent, appear as bright blinking dots when exposed to a targeted smartprobe. Estimating bacterial and cellular load becomes a challenging task due to the presence of background from autofluorescent human lung tissues, i.e., elastin, and imaging artifacts from motion etc. We create a database of annotated images for both these tasks where bacteria and cells were annotated, and use these databases for supervised learning. We extract image patches around each pixel as features, and train a classifier to predict if a bacterium or cell is present at that pixel. We apply our approach on two datasets for detecting bacteria and cells respectively. For the bacteria dataset, we show that the estimated bacterial load increases after introducing the targeted smartprobe in the presence of bacteria. For the cell dataset, we show that the estimated cellular load agrees with a clinician’s assessment.","tags":[],"title":"Estimating Bacterial and Cellular Load in FCFM Imaging","type":"talk"},{"authors":["Sohan Seth","Ahsan R. Akram","Kevin Dhaliwal","Christopher K. I. Williams"],"categories":null,"content":"","date":1514764800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1514764800,"objectID":"ff22ae295886b8bd8c4488c414f90f35","permalink":"https://sohanseth.github.io/publication/seth-estimating-2018/","publishdate":"2021-02-07T20:57:34.261418Z","relpermalink":"/publication/seth-estimating-2018/","section":"publication","summary":"We address the task of estimating bacterial and cellular load in the human distal lung with fibered confocal fluorescence microscopy (FCFM). In pulmonary FCFM some cells can display autofluorescence, and they appear as disc like objects in the FCFM images, whereas bacteria, although not autofluorescent, appear as bright blinking dots when exposed to a targeted smartprobe. Estimating bacterial and cellular load becomes a challenging task due to the presence of background from autofluorescent human lung tissues, i.e., elastin, and imaging artifacts from motion etc. We create a database of annotated images for both these tasks where bacteria and cells were annotated, and use these databases for supervised learning. We extract image patches around each pixel as features, and train a classifier to predict if a bacterium or cell is present at that pixel. We apply our approach on two datasets for detecting bacteria and cells respectively. For the bacteria dataset, we show that the estimated bacterial load increases after introducing the targeted smartprobe in the presence of bacteria. For the cell dataset, we show that the estimated cellular load agrees with a clinician’s assessment.","tags":["logistic regression","bacteria","cell","FCFM imaging","lung","radial basis function network","supervised learning"],"title":"Estimating Bacterial and Cellular Load in FCFM Imaging","type":"publication"},{"authors":[],"categories":null,"content":"","date":1499949031,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1499949031,"objectID":"789c8eddf421855b7b883a5e2ea136f5","permalink":"https://sohanseth.github.io/talk/miua2017/","publishdate":"2021-05-10T21:28:31+01:00","relpermalink":"/talk/miua2017/","section":"talk","summary":"We address the task of detecting bacteria and estimating bacterial load in the human distal lung with fibered confocal fluorescence microscopy (FCFM) and a targeted smartprobe. Bacteria appear as bright dots in the image when exposed to a smartprobe, but they are often difficult to detect due to the presence of background autofluorescence inherent to human lungs. In this study, we create a database of annotated image frames where a clinician has labelled bacteria, and use this database for supervised learning to build a suitable bacterial load estimation software.","tags":[],"title":"Estimating Bacterial Load in FCFM Imaging","type":"talk"},{"authors":["Debaditya Choudhury","Michael G. Tanner","Sarah McAughtrie","Fei Yu","Bethany Mills","Tushar R. Choudhary","Sohan Seth","Thomas Craven","James M. Stone","Loulia K. Mati","Colin J. Campbell","Mark Bradley","Christopher K. I. Williams","Kevin Dhaliwal","Timothy A. Birks","Robert R. Thomson"],"categories":null,"content":"","date":1491004800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1491004800,"objectID":"2400fed9d1f3143c404c448a5e7806bc","permalink":"https://sohanseth.github.io/publication/choudhury-endoscopic-2017/","publishdate":"2021-02-07T20:57:34.2957Z","relpermalink":"/publication/choudhury-endoscopic-2017/","section":"publication","summary":"","tags":null,"title":"Endoscopic sensing of pH in the distal lung (Conference Presentation)","type":"publication"},{"authors":["Sohan Seth","Ahsan R. Akram","Kevin Dhaliwal","Christopher K. I. Williams"],"categories":null,"content":"","date":1483228800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1483228800,"objectID":"a52935ae5502483d9e70ed9cdcd68faf","permalink":"https://sohanseth.github.io/publication/seth-estimating-2017/","publishdate":"2021-02-07T20:57:34.260341Z","relpermalink":"/publication/seth-estimating-2017/","section":"publication","summary":"We address the task of detecting bacteria and estimating bacterial load in the human distal lung with fibered confocal fluorescence microscopy (FCFM) and a targeted smartprobe. Bacteria appear as bright dots in the image when exposed to a smartprobe, but they are often difficult to detect due to the presence of background autofluorescence inherent to human lungs. In this study, we create a database of annotated image frames where a clinician has labelled bacteria, and use this database for supervised learning to build a suitable bacterial load estimation software.","tags":null,"title":"Estimating Bacterial Load in FCFM Imaging","type":"publication"},{"authors":["D. Choudhury","M. G. Tanner","S. McAughtrie","F. Yu","B. Mills","T. R. Choudhary","S. Seth","T. H. Craven","J. M. Stone","I. K. Mati","C. J. Campbell","M. Bradley","C. K. I. Williams","K. Dhaliwal","T. A. Birks","R. R. Thomson"],"categories":null,"content":"","date":1480550400,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1480550400,"objectID":"619e308b2a0298e6647c1ace482a75d3","permalink":"https://sohanseth.github.io/publication/choudhury-endoscopic-2016/","publishdate":"2021-02-07T20:57:34.260833Z","relpermalink":"/publication/choudhury-endoscopic-2016/","section":"publication","summary":"Previously unobtainable measurements of alveolar pH were obtained using an endoscope-deployable optrode. The pH sensing was achieved using functionalized gold nanoshell sensors and surface enhanced Raman spectroscopy (SERS). The optrode consisted of an asymmetric dual-core optical fiber designed for spatially separating the optical pump delivery and signal collection, in order to circumvent the unwanted Raman signal generated within the fiber. Using this approach, we demonstrate a ~100-fold increase in SERS signal-to-fiber background ratio, and demonstrate multiple site pH sensing with a measurement accuracy of ± 0.07 pH units in the respiratory acini of an ex vivo ovine lung model. We also demonstrate that alveolar pH changes in response to ventilation.","tags":null,"title":"Endoscopic sensing of alveolar pH","type":"publication"},{"authors":["Sohan Seth","Ahsan R. Akram","Paul McCool","Jody Westerfeld","David Wilson","Stephen McLaughlin","Kevin Dhaliwal","Christopher K. I. Williams"],"categories":null,"content":"","date":1470009600,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1470009600,"objectID":"0ae65bd49e03a72820698a2fff20c34a","permalink":"https://sohanseth.github.io/publication/seth-assessing-2016/","publishdate":"2021-02-07T20:57:34.262091Z","relpermalink":"/publication/seth-assessing-2016/","section":"publication","summary":"Solitary pulmonary nodules are common, often incidental findings on chest CT scans. The investigation of pulmonary nodules is time-consuming and often leads to protracted follow-up with ongoing radiological surveillance, however, clinical calculators that assess the risk of the nodule being malignant exist to help in the stratification of patients. Furthermore recent advances in interventional pulmonology include the ability to both navigate to nodules and also to perform autofluorescence endomicroscopy. In this study we assessed the efficacy of incorporating additional information from label-free fibre-based optical endomicrosopy of the nodule on assessing risk of malignancy. Using image analysis and machine learning approaches, we find that this information does not yield any gain in predictive performance in a cohort of patients. Further advances with pulmonary endomicroscopy will require the addition of molecular tracers to improve information from this procedure.","tags":null,"title":"Assessing the utility of autofluorescence-based pulmonary optical endomicroscopy to predict the malignant potential of solitary pulmonary nodules in humans","type":"publication"},{"authors":["Sohan Seth","Manuel J. A. Eugster"],"categories":null,"content":"","date":1462060800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1462060800,"objectID":"3c7cd1d95464f1966f8c167c42d5fe2e","permalink":"https://sohanseth.github.io/publication/seth-archetypal-2016/","publishdate":"2021-04-29T20:44:34.427726Z","relpermalink":"/publication/seth-archetypal-2016/","section":"publication","summary":"Archetypal analysis is a popular exploratory tool that explains a set of observations as compositions of few 'pure' patterns. The standard formulation of archetypal analysis addresses this problem for real valued observations by finding the approximate convex hull. Recently, a probabilistic formulation has been suggested which extends this framework to other observation types such as binary and count. In this article we further extend this framework to address the general case of nominal observations which includes, for example, multiple-option questionnaires. We view archetypal analysis in a generative framework: this allows explicit control over choosing a suitable number of archetypes by assigning appropriate prior information, and finding efficient update rules using variational Bayes'. We demonstrate the efficacy of this approach extensively on simulated data, and three real world examples: Austrian guest survey dataset, German credit dataset, and SUN attribute image dataset.","tags":null,"title":"Archetypal Analysis for Nominal Observations","type":"publication"},{"authors":["Paul Blomstedt","Ritabrata Dutta","Sohan Seth","Alvis Brazma","Samuel Kaski"],"categories":null,"content":"","date":1462060800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1462060800,"objectID":"4b2658a1a476866136b44c7963025559","permalink":"https://sohanseth.github.io/publication/blomstedt-modelling-based-2016/","publishdate":"2021-02-07T20:57:34.263939Z","relpermalink":"/publication/blomstedt-modelling-based-2016/","section":"publication","summary":"","tags":null,"title":"Modelling-based experiment retrieval: a case study with gene expression clustering","type":"publication"},{"authors":["Sohan Seth","Manuel J. A. Eugster"],"categories":null,"content":"","date":1451606400,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1451606400,"objectID":"5f1060ff4cccd5099123c02310c46a05","permalink":"https://sohanseth.github.io/publication/seth-probabilistic-2016/","publishdate":"2021-02-07T20:57:34.259157Z","relpermalink":"/publication/seth-probabilistic-2016/","section":"publication","summary":"Archetypal analysis represents a set of observations as convex combinations of pure patterns, or archetypes. The original geometric formulation of finding archetypes by approximating the convex hull of the observations assumes them to be real–valued. This, unfortunately, is not compatible with many practical situations. In this paper we revisit archetypal analysis from the basic principles, and propose a probabilistic framework that accommodates other observation types such as integers, binary, and probability vectors. We corroborate the proposed methodology with convincing real-world applications on finding archetypal soccer players based on performance data, archetypal winter tourists based on binary survey data, archetypal disaster-affected countries based on disaster count data, and document archetypes based on term-frequency data. We also present an appropriate visualization tool to summarize archetypal analysis solution better.","tags":["Archetypal analysis","Binary observation","Convex hull","Majorization–minimization","Probabilistic modeling","Visualization"],"title":"Probabilistic archetypal analysis","type":"publication"},{"authors":[],"categories":null,"content":"","date":1415088012,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1415088012,"objectID":"5185e8641e1d728414a7f37c7dbe7b24","permalink":"https://sohanseth.github.io/talk/iconip2014/","publishdate":"2021-05-10T21:44:12+01:00","relpermalink":"/talk/iconip2014/","section":"talk","summary":"We study the task of retrieving relevant experiments given a query experiment. By experiment, we mean a collection of measurements from a set of ‘covariates’ and the associated ‘outcomes’. While similar experiments can be retrieved by comparing available ‘annotations’, this approach ignores the valuable information available in the measurements themselves. To incorporate this information in the retrieval task, we suggest employing a retrieval metric that utilizes probabilistic models learned from the measurements. We argue that such a metric is a sensible measure of similarity between two experiments since it permits inclusion of experiment-specific prior knowledge. However, accurate models are often not analytical, and one must resort to storing posterior samples which demands considerable resources. Therefore, we study strategies to select informative posterior samples to reduce the computational load while maintaining the retrieval performance. We demonstrate the efficacy of our approach on simulated data with simple linear regression as the models, and real world datasets.","tags":[],"title":"Retrieval of Experiments by Efficient Comparison of Marginal Likelihood","type":"talk"},{"authors":[],"categories":null,"content":"","date":1410451210,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1410451210,"objectID":"8c0393e4b6285232464571d61fe97b93","permalink":"https://sohanseth.github.io/talk/lsoldm2014/","publishdate":"2021-05-10T21:19:10+01:00","relpermalink":"/talk/lsoldm2014/","section":"talk","summary":"We study the task of retrieving relevant experiments given a query experiment. By experi- ment, we mean a collection of measurements from a set of ‘covariates’ and the associated ‘out- comes’. While similar experiments can be retrieved by comparing available ‘annotations’, this approach ignores the valuable information available in the measurements themselves. To incor- porate this information in the retrieval task, we suggest employing a retrieval metric that utilizes probabilistic models learned from the measurements. We argue that such a metric is a sensible measure of similarity between two experiments since it permits inclusion of experiment-specific prior knowledge. However, accurate models are often not analytical, and one must resort to storing posterior samples which demands considerable resources. Therefore, we study strate- gies to select informative posterior samples to reduce the computational load while maintaining the retrieval performance. We demonstrate the efficacy of our approach on simulated data with simple linear regression as the models, and real world datasets.","tags":[],"title":"Retrieval of Experiments by Efficient Comparison of Marginal Likelihoods","type":"talk"},{"authors":[],"categories":null,"content":"","date":1410017415,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1410017415,"objectID":"50a58124731ee15509aa72d8c5b68f68","permalink":"https://sohanseth.github.io/talk/mlsb2014/","publishdate":"2021-05-10T21:08:15+01:00","relpermalink":"/talk/mlsb2014/","section":"talk","summary":"","tags":[],"title":"Differential Analysis of Whole-genome Shotgun Sequences","type":"talk"},{"authors":["Rosha Pokharel","Sohan Seth","Jose C. Principe"],"categories":null,"content":"","date":1404172800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1404172800,"objectID":"7f0dc971200a8ba7fc1df21f07e2bf5e","permalink":"https://sohanseth.github.io/publication/pokharel-quantized-2014/","publishdate":"2021-02-07T20:57:34.26718Z","relpermalink":"/publication/pokharel-quantized-2014/","section":"publication","summary":"","tags":null,"title":"Quantized mixture kernel least mean square","type":"publication"},{"authors":["Sohan Seth","Niko Välimäki","Samuel Kaski","Antti Honkela"],"categories":null,"content":"","date":1398902400,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1398902400,"objectID":"846cb015826e819265aa72dfae1ead18","permalink":"https://sohanseth.github.io/publication/seth-exploration-2014/","publishdate":"2021-02-07T20:57:34.262754Z","relpermalink":"/publication/seth-exploration-2014/","section":"publication","summary":"Motivation: Over the recent years, the field of whole metagenome shotgun sequencing has witnessed significant growth due to the high-throughput sequencing technologies that allow sequencing genomic samples cheaper, faster, and with better coverage than before. This technical advancement has initiated the trend of sequencing multiple samples in different conditions or environments to explore the similarities and dissimilarities of the microbial communities. Examples include the human microbiome project and various studies of the human intestinal tract. With the availability of ever larger databases of such measurements, finding samples similar to a given query sample is becoming a central operation. Results: In this paper, we develop a content-based exploration and retrieval method for whole metagenome sequencing samples. We apply a distributed string mining framework to efficiently extract all informative sequence k-mers from a pool of metagenomic samples and use them to measure the dissimilarity between two samples. We evaluate the performance of the proposed approach on two human gut metagenome data sets as well as human microbiome project metagenomic samples. We observe significant enrichment for diseased gut samples in results of queries with another diseased sample and very high accuracy in discriminating between different body sites even though the method is unsupervised. Availability: https://github.com/HIITMetagenomics/dsm-framework. Contact: sohan.seth@hiit.fi, antti.honkela@hiit.fi","tags":null,"title":"Exploration and retrieval of whole-metagenome sequencing samples","type":"publication"},{"authors":["Il Memming Park","Sohan Seth","Steven Van Vaerenbergh"],"categories":null,"content":"","date":1398902400,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1398902400,"objectID":"f490af36d8217ac157e61c67c8e9e46c","permalink":"https://sohanseth.github.io/publication/park-probabilistic-2014/","publishdate":"2021-02-07T20:57:34.267824Z","relpermalink":"/publication/park-probabilistic-2014/","section":"publication","summary":"","tags":null,"title":"Probabilistic kernel least mean squares algorithms","type":"publication"},{"authors":["Sohan Seth","Niko Valimaki","Antti Honkela","Samuel Kaski"],"categories":null,"content":"","date":1388534400,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1388534400,"objectID":"c40c0f3ec96f804f54512a5e2df31cd7","permalink":"https://sohanseth.github.io/publication/seth-differential-2014/","publishdate":"2021-04-29T20:44:34.445559Z","relpermalink":"/publication/seth-differential-2014/","section":"publication","summary":"","tags":null,"title":"Differential analysis of whole-genome shotgun sequences","type":"publication"},{"authors":["Sohan Seth","José C. Príncipe"],"categories":null,"content":"","date":1388534400,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1388534400,"objectID":"2561f3a0233fc85f4cde1a86bbdd271c","permalink":"https://sohanseth.github.io/publication/seth-learning-2014/","publishdate":"2021-02-07T20:57:34.28946Z","relpermalink":"/publication/seth-learning-2014/","section":"publication","summary":"","tags":null,"title":"Learning dependence from samples","type":"publication"},{"authors":["Sohan Seth","John Shawe-Taylor","Samuel Kaski"],"categories":null,"content":"","date":1388534400,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1388534400,"objectID":"a0ed6f212602051b0627d647f8b2a1d0","permalink":"https://sohanseth.github.io/publication/loo-retrieval-2014/","publishdate":"2021-02-07T20:57:34.26658Z","relpermalink":"/publication/loo-retrieval-2014/","section":"publication","summary":"","tags":null,"title":"Retrieval of Experiments by Efficient Comparison of Marginal Likelihoods","type":"publication"},{"authors":["Rosha Pokharel","Sohan Seth","Jose C. Principe"],"categories":null,"content":"","date":1375315200,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1375315200,"objectID":"5df9d07f34fbe0b859253d7605280e25","permalink":"https://sohanseth.github.io/publication/pokharel-mixture-2013/","publishdate":"2021-02-07T20:57:34.268524Z","relpermalink":"/publication/pokharel-mixture-2013/","section":"publication","summary":"","tags":null,"title":"Mixture kernel least mean square","type":"publication"},{"authors":["Lin Li","Il Memming Park","Austin Brockmeier","Badong Chen","Sohan Seth","Joseph T. Francis","Justin C. Sanchez","Jose C. Principe"],"categories":null,"content":"","date":1372636800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1372636800,"objectID":"f6db8f7e9274afad0b8b80e650632b8c","permalink":"https://sohanseth.github.io/publication/li-adaptive-2013/","publishdate":"2021-02-07T20:57:34.276539Z","relpermalink":"/publication/li-adaptive-2013/","section":"publication","summary":"","tags":null,"title":"Adaptive Inverse Control of Neural Spatiotemporal Spike Patterns With a Reproducing Kernel Hilbert Space (RKHS) Framework","type":"publication"},{"authors":["Il Memming Park","Sohan Seth","Antonio R.C. Paiva","Lin Li","Jose C. Principe"],"categories":null,"content":"","date":1372636800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1372636800,"objectID":"bd1e4913ea2d274c8e3f572436d916b9","permalink":"https://sohanseth.github.io/publication/park-kernel-2013/","publishdate":"2021-02-07T20:57:34.269236Z","relpermalink":"/publication/park-kernel-2013/","section":"publication","summary":"","tags":null,"title":"Kernel Methods on Spike Train Space for Neuroscience: A Tutorial","type":"publication"},{"authors":["B. Fadlallah","S. Seth","A. Keil","J. Principe"],"categories":null,"content":"","date":1349049600,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1349049600,"objectID":"9f7a914e61240ffe2615f0ffa8454dcb","permalink":"https://sohanseth.github.io/publication/fadlallah-quantifying-2012/","publishdate":"2021-02-07T20:57:34.278203Z","relpermalink":"/publication/fadlallah-quantifying-2012/","section":"publication","summary":"","tags":null,"title":"Quantifying Cognitive State From EEG Using Dependence Measures","type":"publication"},{"authors":["B. H. Fadlallah","A. J. Brockmeier","S. Seth","Lin Li","A. Keil","J. C. Principe"],"categories":null,"content":"","date":1343779200,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1343779200,"objectID":"42b78bdd6cb35dd19fcab4ba27d2829f","permalink":"https://sohanseth.github.io/publication/fadlallah-association-2012/","publishdate":"2021-02-07T20:57:34.282166Z","relpermalink":"/publication/fadlallah-association-2012/","section":"publication","summary":"","tags":null,"title":"An Association Framework to Analyze Dependence Structure in Time Series","type":"publication"},{"authors":["Il Memming Park","Sohan Seth","Murali Rao","José C. Príncipe"],"categories":null,"content":"","date":1343779200,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1343779200,"objectID":"177b5a7ddd9c1169af66931b1d15aff9","permalink":"https://sohanseth.github.io/publication/park-strictly-2012/","publishdate":"2021-02-07T20:57:34.277396Z","relpermalink":"/publication/park-strictly-2012/","section":"publication","summary":"Exploratory tools that are sensitive to arbitrary statistical variations in spike train observations open up the possibility of novel neuroscientific discoveries. Developing such tools, however, is difficult due to the lack of Euclidean structure of the spike train space, and an experimenter usually prefers simpler tools that capture only limited statistical features of the spike train, such as mean spike count or mean firing rate. We explore strictly positive-definite kernels on the space of spike trains to offer both a structural representation of this space and a platform for developing statistical measures that explore features beyond count or rate. We apply these kernels to construct measures of divergence between two point processes and use them for hypothesis testing, that is, to observe if two sets of spike trains originate from the same underlying probability law. Although there exist positive-definite spike train kernels in the literature, we establish that these kernels are not strictly definite and thus do not induce measures of divergence. We discuss the properties of both of these existing nonstrict kernels and the novel strict kernels in terms of their computational complexity, choice of free parameters, and performance on both synthetic and real data through kernel principal component analysis and hypothesis testing.","tags":null,"title":"Strictly Positive-Definite Spike Train Kernels for Point-Process Divergences","type":"publication"},{"authors":["Sohan Seth","José C. Príncipe"],"categories":null,"content":"","date":1341100800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1341100800,"objectID":"6952ec3e522ae690c1066f11e9e47f8a","permalink":"https://sohanseth.github.io/publication/seth-conditional-2012/","publishdate":"2021-02-07T20:57:34.287092Z","relpermalink":"/publication/seth-conditional-2012/","section":"publication","summary":"Estimating conditional dependence between two random variables given the knowledge of a third random variable is essential in neuroscientific applications to understand the causal architecture of a distributed network. However, existing methods of assessing conditional dependence, such as the conditional mutual information, are computationally expensive, involve free parameters, and are difficult to understand in the context of realizations. In this letter, we discuss a novel approach to this problem and develop a computationally simple and parameter-free estimator. The difference between the proposed approach and the existing ones is that the former expresses conditional dependence in terms of a finite set of realizations, whereas the latter use random variables, which are not available in practice. We call this approach conditional association, since it is based on a generalization of the concept of association to arbitrary metric spaces. We also discuss a novel and computationally efficient approach of generating surrogate data for evaluating the significance of the acquired association value.","tags":null,"title":"Conditional Association","type":"publication"},{"authors":["Badong Chen","Songlin Zhao","Sohan Seth","Jose C. Principe"],"categories":null,"content":"","date":1338508800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1338508800,"objectID":"21a046f8c4d3d9ce7f840a919fe84c1c","permalink":"https://sohanseth.github.io/publication/chen-online-2012/","publishdate":"2021-02-07T20:57:34.273299Z","relpermalink":"/publication/chen-online-2012/","section":"publication","summary":"","tags":null,"title":"Online efficient learning with quantized KLMS and L1 regularization","type":"publication"},{"authors":["Bilal H. Fadlallah","Sohan Seth","Andreas Keil","Jose C. Principe"],"categories":null,"content":"","date":1330560000,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1330560000,"objectID":"792e2488c2c22da4b2851b3f488192df","permalink":"https://sohanseth.github.io/publication/fadlallah-analyzing-2012/","publishdate":"2021-02-07T20:57:34.286203Z","relpermalink":"/publication/fadlallah-analyzing-2012/","section":"publication","summary":"","tags":null,"title":"Analyzing dependence structure of the human brain in response to visual stimuli","type":"publication"},{"authors":["S. Seth","J. C. Principe"],"categories":null,"content":"","date":1325376000,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1325376000,"objectID":"65cf758b7804b4a9bc03650d9e0bf1b8","permalink":"https://sohanseth.github.io/publication/seth-assessing-2012/","publishdate":"2021-02-07T20:57:34.280615Z","relpermalink":"/publication/seth-assessing-2012/","section":"publication","summary":"","tags":null,"title":"Assessing Granger Non-Causality Using Nonparametric Measure of Conditional Independence","type":"publication"},{"authors":["Lin Li","Il Memming Park","Sohan Seth","Justin C. Sanchez","José C. Principe"],"categories":null,"content":"","date":1325376000,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1325376000,"objectID":"2b870511871ea39a9a87032be9828e30","permalink":"https://sohanseth.github.io/publication/li-functional-2012/","publishdate":"2021-02-07T20:57:34.278981Z","relpermalink":"/publication/li-functional-2012/","section":"publication","summary":"","tags":null,"title":"Functional Connectivity Dynamics Among Cortical Neurons: A Dependence Analysis","type":"publication"},{"authors":["Lin Li","Il Memming Park","Sohan Seth","John S. Choi","Joseph T. Francis","Justin C. Sanchez","Jose C. Principe"],"categories":null,"content":"","date":1314835200,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1314835200,"objectID":"273dd568dfa7dc29070b9ffc1fd5115e","permalink":"https://sohanseth.github.io/publication/lin-li-adaptive-2011/","publishdate":"2021-02-07T20:57:34.282916Z","relpermalink":"/publication/lin-li-adaptive-2011/","section":"publication","summary":"","tags":null,"title":"An adaptive decoder from spike trains to micro-stimulation using kernel least-mean-squares (KLMS)","type":"publication"},{"authors":["Sohan Seth","Murali Rao","Il Park","José C. Principe"],"categories":null,"content":"","date":1312156800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1312156800,"objectID":"a34708186423348fceedf7eb29959d57","permalink":"https://sohanseth.github.io/publication/seth-unified-2011/","publishdate":"2021-02-07T20:57:34.275695Z","relpermalink":"/publication/seth-unified-2011/","section":"publication","summary":"","tags":null,"title":"A Unified Framework for Quadratic Measures of Independence","type":"publication"},{"authors":["B. H. Fadlallah","S. Seth","A. Keil","J. C. Principe"],"categories":null,"content":"","date":1312156800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1312156800,"objectID":"d16627bafb9e59cde1a755fe88771408","permalink":"https://sohanseth.github.io/publication/fadlallah-robust-2011/","publishdate":"2021-02-07T20:57:34.281388Z","relpermalink":"/publication/fadlallah-robust-2011/","section":"publication","summary":"","tags":null,"title":"Robust EEG preprocessing for dependence-based condition discrimination","type":"publication"},{"authors":["Sohan Seth","Austin J. Brockmeier","John S. Choi","Mulugeta Semework","Joseph T. Francis","Jose C. Principe"],"categories":null,"content":"","date":1309478400,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1309478400,"objectID":"a8d4d1641a9a9f21a7e42410b9b5cf8f","permalink":"https://sohanseth.github.io/publication/seth-evaluating-2011/","publishdate":"2021-02-07T20:57:34.284558Z","relpermalink":"/publication/seth-evaluating-2011/","section":"publication","summary":"","tags":null,"title":"Evaluating dependence in spike train metric spaces","type":"publication"},{"authors":["Sohan Seth","Austin J. Brockmeier","Jose C. Principe"],"categories":null,"content":"","date":1304208000,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1304208000,"objectID":"da4917b8570fc4b1cac927163d25016b","permalink":"https://sohanseth.github.io/publication/seth-metric-2011/","publishdate":"2021-02-07T20:57:34.291106Z","relpermalink":"/publication/seth-metric-2011/","section":"publication","summary":"","tags":null,"title":"A metric approach toward point process divergence","type":"publication"},{"authors":["Il Park","Sohan Seth","Murali Rao","Jose C. Principe"],"categories":null,"content":"","date":1304208000,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1304208000,"objectID":"13e4fc6c3710fbd221cd6dc0b76e47b7","permalink":"https://sohanseth.github.io/publication/park-estimation-2011/","publishdate":"2021-02-07T20:57:34.287948Z","relpermalink":"/publication/park-estimation-2011/","section":"publication","summary":"","tags":null,"title":"Estimation of symmetric chi-square divergence for point processes","type":"publication"},{"authors":["Murali Rao","Sohan Seth","Jianwu Xu","Yunmei Chen","Hemant Tagare","José C. Príncipe"],"categories":null,"content":"","date":1293840000,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1293840000,"objectID":"8093adfed723b3015eedcaaa60e9b0ff","permalink":"https://sohanseth.github.io/publication/rao-test-2011/","publishdate":"2021-02-07T20:57:34.272443Z","relpermalink":"/publication/rao-test-2011/","section":"publication","summary":"","tags":null,"title":"A test of independence based on a generalized correlation function","type":"publication"},{"authors":["Sohan Seth","Jose C. Principe"],"categories":null,"content":"","date":1291161600,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1291161600,"objectID":"d5439e9b12f72bcd8a084b530f0ceb22","permalink":"https://sohanseth.github.io/publication/seth-variable-2010/","publishdate":"2021-02-07T20:57:34.274119Z","relpermalink":"/publication/seth-variable-2010/","section":"publication","summary":"","tags":null,"title":"Variable Selection: A Statistical Dependence Perspective","type":"publication"},{"authors":["Sohan Seth","Jose C. Principe"],"categories":null,"content":"","date":1280620800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1280620800,"objectID":"46fa2fb2ae5af6f2ac55594e8a1b812e","permalink":"https://sohanseth.github.io/publication/seth-conditional-2010-1/","publishdate":"2021-02-07T20:57:34.296606Z","relpermalink":"/publication/seth-conditional-2010-1/","section":"publication","summary":"","tags":null,"title":"A conditional independence perspective of variable selection","type":"publication"},{"authors":["Sohan Seth","Jose C. Principe"],"categories":null,"content":"","date":1280620800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1280620800,"objectID":"42a3f8aac57f59dfe8cc51e9e21096ee","permalink":"https://sohanseth.github.io/publication/seth-test-2010/","publishdate":"2021-02-07T20:57:34.283775Z","relpermalink":"/publication/seth-test-2010/","section":"publication","summary":"","tags":null,"title":"A Test of Granger Non-causality Based on Nonparametric Conditional Independence","type":"publication"},{"authors":["Lin Li","Il Park","S Seth","J C Sanchez","J C Principe"],"categories":null,"content":"","date":1280620800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1280620800,"objectID":"725ae93f05869943140375172270dc4f","permalink":"https://sohanseth.github.io/publication/lin-li-neuronal-2010/","publishdate":"2021-02-07T20:57:34.290221Z","relpermalink":"/publication/lin-li-neuronal-2010/","section":"publication","summary":"","tags":null,"title":"Neuronal functional connectivity dynamics in cortex: An MSC-based analysis","type":"publication"},{"authors":["Sohan Seth","Jose C. Principe"],"categories":null,"content":"","date":1267401600,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1267401600,"objectID":"25ab8ac73f070c35b834d2d894198f2c","permalink":"https://sohanseth.github.io/publication/seth-conditional-2010/","publishdate":"2021-02-07T20:57:34.285396Z","relpermalink":"/publication/seth-conditional-2010/","section":"publication","summary":"","tags":null,"title":"A conditional distribution function based approach to design nonparametric tests of independence and conditional independence","type":"publication"},{"authors":["Weifeng Liu","Puskal Pokharel","Jianwu Xu","Sohan Seth"],"categories":null,"content":"","date":1262304000,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1262304000,"objectID":"afba89c2d03e82b73ccf03db7cd3de78","permalink":"https://sohanseth.github.io/publication/principe-correntropy-2010/","publishdate":"2021-02-07T20:57:34.288752Z","relpermalink":"/publication/principe-correntropy-2010/","section":"publication","summary":"","tags":null,"title":"Correntropy for Random Variables: Properties and Applications in Statistical Inference","type":"publication"},{"authors":["Lin Li","S. Seth","Il Park","J.C. Sanchez","J.C. Principe"],"categories":null,"content":"","date":1251763200,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1251763200,"objectID":"92697e4eccddbaf4fabafbe925097c6c","permalink":"https://sohanseth.github.io/publication/lin-li-estimation-2009/","publishdate":"2021-02-07T20:57:34.292852Z","relpermalink":"/publication/lin-li-estimation-2009/","section":"publication","summary":"","tags":null,"title":"Estimation and visualization of neuronal functional connectivity in motor tasks","type":"publication"},{"authors":["Sohan Seth","Jose C. Principe"],"categories":null,"content":"","date":1251763200,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1251763200,"objectID":"0f90c69eb8d4d5762a7c0c383f97156f","permalink":"https://sohanseth.github.io/publication/seth-estimation-2009/","publishdate":"2021-02-07T20:57:34.293703Z","relpermalink":"/publication/seth-estimation-2009/","section":"publication","summary":"","tags":null,"title":"Estimation of density ratio and its application to design a measure of dependence","type":"publication"},{"authors":["JungPhil Kwon","S. Seth","A. Keil","J.C. Principe"],"categories":null,"content":"","date":1251763200,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1251763200,"objectID":"861cefbe458c28ab94733fd2177b99a3","permalink":"https://sohanseth.github.io/publication/jungphil-kwon-estimation-2009/","publishdate":"2021-02-07T20:57:34.291905Z","relpermalink":"/publication/jungphil-kwon-estimation-2009/","section":"publication","summary":"","tags":null,"title":"Estimation of instantaneous power in the EEG to assess brain connectivity with high temporal resolution","type":"publication"},{"authors":["Sohan Seth","Jose C. Principe"],"categories":null,"content":"","date":1243814400,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1243814400,"objectID":"abfcca4d6c4291119ec98f3b1878f8a0","permalink":"https://sohanseth.github.io/publication/seth-speeding-2009/","publishdate":"2021-02-07T20:57:34.274893Z","relpermalink":"/publication/seth-speeding-2009/","section":"publication","summary":"","tags":null,"title":"On speeding up computation in information theoretic learning","type":"publication"},{"authors":["Sohan Seth","Il Park","Jose C. Principe"],"categories":null,"content":"","date":1238544000,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1238544000,"objectID":"b3b92ca7819c942ac3a05ac6fe1e7730","permalink":"https://sohanseth.github.io/publication/seth-new-2009/","publishdate":"2021-02-07T20:57:34.297541Z","relpermalink":"/publication/seth-new-2009/","section":"publication","summary":"","tags":null,"title":"A new nonparametric measure of conditional independence","type":"publication"},{"authors":["Sohan Seth","Jose C. Principe"],"categories":null,"content":"","date":1204329600,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1204329600,"objectID":"bd55daf866249613169f286a128f1e8a","permalink":"https://sohanseth.github.io/publication/seth-compressed-2008/","publishdate":"2021-02-07T20:57:34.271674Z","relpermalink":"/publication/seth-compressed-2008/","section":"publication","summary":"","tags":null,"title":"Compressed signal reconstruction using the correntropy induced metric","type":"publication"},{"authors":["Sohan Seth","Mustafa C. Ozturk","Jose C. Principe"],"categories":null,"content":"","date":1185926400,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1185926400,"objectID":"5dc7b82a74ed54cd38f3261fdfe1a06f","permalink":"https://sohanseth.github.io/publication/seth-signal-2007/","publishdate":"2021-02-07T20:57:34.279766Z","relpermalink":"/publication/seth-signal-2007/","section":"publication","summary":"","tags":null,"title":"Signal Processing with Echo State Networks in the Complex Domain","type":"publication"},{"authors":["Nabarun Bhattacharyya","Sohan Seth","Bipan Tudu","Pradip Tamuly","Arun Jana","Devdulal Ghosh","Rajib Bandyopadhyay","Manabendra Bhuyan"],"categories":null,"content":"","date":1180656000,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1180656000,"objectID":"5fa03b1f5a0a67b2f84732a21dc717aa","permalink":"https://sohanseth.github.io/publication/bhattacharyya-monitoring-2007/","publishdate":"2021-02-07T20:57:34.270877Z","relpermalink":"/publication/bhattacharyya-monitoring-2007/","section":"publication","summary":"","tags":null,"title":"Monitoring of black tea fermentation process using electronic nose","type":"publication"},{"authors":["Nabarun Bhattacharyya","Sohan Seth","Bipan Tudu","Pradip Tamuly","Arun Jana","Devdulal Ghosh","Rajib Bandyopadhyay","Manabendra Bhuyan","Santanu Sabhapandit"],"categories":null,"content":"","date":1172707200,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1172707200,"objectID":"eb146a19be932d7907aa26983af7990e","permalink":"https://sohanseth.github.io/publication/bhattacharyya-detection-2007/","publishdate":"2021-02-07T20:57:34.27006Z","relpermalink":"/publication/bhattacharyya-detection-2007/","section":"publication","summary":"","tags":null,"title":"Detection of optimum fermentation time for black tea manufacturing using electronic nose","type":"publication"},{"authors":["Sohan Seth","Gary Watmough"],"categories":[],"content":"","date":-62135596800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":-62135596800,"objectID":"85ca0498f5210a4ee7062f39f2a840ed","permalink":"https://sohanseth.github.io/project/pep/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/project/pep/","section":"project","summary":"Develop sustainable machine learning models to improve intercensal population estimates in Mozambique. We are using satellite images and microcensus data to estimate population in rural and semi-unban areas independent of census data. ","tags":[],"title":"Census-Independent Population Density Estimation in Mozambique","type":"project"},{"authors":["Bruce Guthrie","Alan Marshall","Sohan Seth"],"categories":[],"content":"","date":-62135596800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":-62135596800,"objectID":"afe09518a526c0376ad5a24db90795a5","permalink":"https://sohanseth.github.io/project/acrc/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/project/acrc/","section":"project","summary":"Develop, validate and disseminate a suite of new risk prediction models for a set of adverse outcomes such as mortality, increased care needs or hospitalisation. In the context of population ageing and resource constrained services, risk prediction tools have great potential to ensure the delivery of the right care to the right person in the most cost-effective way.","tags":[],"title":"Data-driven Insight and Prediction in Later Life Care","type":"project"},{"authors":["Sohan Seth"],"categories":[],"content":"","date":-62135596800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":-62135596800,"objectID":"2f22f8fb0b6f1aec565e63263ba1c80c","permalink":"https://sohanseth.github.io/project/prism/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/project/prism/","section":"project","summary":"Develop machine learning models for analysing fluorescence, Raman, and time-resolved spectroscopy signals in the context of interventional pulmonology, in particular cancer delineation.","tags":[],"title":"Machine Learning for Spectroscopy","type":"project"},{"authors":["Florian Fusseis","Ian Butler","John Wheeler","Sohan Seth","Stephen Elphick"],"categories":[],"content":"","date":-62135596800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":-62135596800,"objectID":"c0f60516c41474ab7764f46e4a3ab274","permalink":"https://sohanseth.github.io/project/midgard/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/project/midgard/","section":"project","summary":"Develop segmentation algorithms for very large scale 4D microtomography images without human supervision. The segmented images will inform critical parameters to understand the mechanism of rock deformation.","tags":[],"title":"Segmentation of Micro-tomography Images for Understanding Deformation of Rocks","type":"project"}]