The goals of this project with the Economics department is to extract and parse information from health reports available in the Wellcome library, which have been OCR’ed from printed copy. The extracted information includes details such as the number of health visitors per year and per area, and will be later used by the Economics team to form a hypothesis on the health of the population based on the governmental strategies used throughout the past century.
Critical Care & Bed occupancy models
In this project with UCLH, we are building tools and systems to allow routinely collected patient data to be used for research, and ultimately, for real-time patient care. Others in the Research Software Development Group have been building the code data infrastructure to extract, transform and map data, preparing it for research use. We are now at the stage that we can retrieve the data needed for training and building models that can improve the operational flow of the hospital, such as predicting bed occupancy within the critical care unit.
Strictly speaking in this collaboration with Computer Science we are not working on the AI aspects; that is the focus of the researchers. RSDG is developing the information management system for the project, storing acquired images with all metadata, allowing human experts to annotate images for training and test datasets, and interfacing with the machine learning software being developed by UCL Computer Science. This is the crucial ‘plumbing’ work needed to enable the research to scale and be reproducible. The project's aim is to translate state-of-the-art robotics and machine-learning research into a benchtop prototype capable of Fast, Accurate and Scalable malaria diagnosis. It aims to overcome diagnostic challenges by replacing human-expert optical microscopy with a robotic automated computer-expert system that assesses similar digital-optical-microscopy representations of the disease.
- PI: Delmiro Fernandez-Reyez
- Funding: EPSRC GCRF
- RSDG team: Jonathan Cooper, Asif Tamuri, Roland Guichard
- Duration: Aug 2017 - Apr 2020
- Languages and Technologies: Python, OMERO
- Project website: uclfastmal.wordpress.com
Popchat (phase 1)
A collaboration with the Institute of Education, PopChat uses web-based technologies and pedagogical research to improve English comprehension of children in primary and secondary schools in the Philippines, through music, song lyrics and rhymes. We built prototype online games for the children to play, and will be involved at a later stage in post-launch data analysis.
- PI: Dr Kaska Porayska-Pomsta and Tunde Olatunji
- Funding: Newton Fund
- RSDG team: Raquel Alegre, Roma Kaplaukh
- Duration: 2018 - 2019
- Languages and Technologies: Scala, MongoDB
Catastrophe modelling for tsunamis in the Indian Ocean
Our task was to automatically extract bathymetry data from scanned maps provided by the Department of Statistics team. They require certain digitised information from the maps, in order to develop a model to forecast effects of tsunamis on the coasts of India, and to some extent Pakistan and Iran. The bathymetry information is marked in the map in a consistent format (a digit, and subscript digit), but the maps contain many other details, both written (further text and digits) and diagrammatic (such as contours). Our task is to identify the target digits from the rest of the information, localise them, find their coordinates and provide the 3-dimensional coordinates of these data points as input for the models. To accomplish this, we needed to implement a pipeline of image processing tasks, including object detection, localisation, and digit recognition.
- PI: Professor Serge Guillas
- Funding: EPSRC IAA Discovery to Use
- RSDG team: Sanaz Jabbari, Raquel Alegre
- Duration: August 2018 - January 2019
- Languages and technologies: Python, Azure Custom Vision Service
This Digital Humanities project aims to trace global information networks in historical newspaper archives. Our role was to development tools for running the researchers’ queries on the massive text archives, using UCL's high-performance computing platforms.