The Research IT Services AI Studio provides service-based AI solutions for data science and machine learning projects.
As more research domains move to intersect with data-intensive computation and nearly every field of discovery is transitioning from data-poor to data-rich, techniques such as machine learning and AI are driving scientific and technological advancement in diverse areas such as astrophysics, particle physics, biology, meterology, medicine, finance, healthcare and social sciences.
The AI Studio
By working closely with other RITS service teams, the AI Studio service is backed up by first class resources and support in the form of the Research Data Storage service and the research computing platforms Legion, Grace and Myriad.
Dr Sanaz Jabbari leads the AI Studio service, which is available to both novice and experienced data scientists. For researchers who are experienced programmers and machine learning savvy, the service provides advice on issues such as model selection, parameter tuning, or achieving a higher performance. For researchers new to data science, the AI Studio provides a consultation service that can help determine what sort of predictions and analysis are possible from their data and what type of data they need to collect.
Below are some of the projects the AI Studio has been involved in:
- Catastrophe modelling for tsunamis in the Indian Ocean
Our task is 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 in 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 also there are other information in the map such as contours and other written information in text and digits. Our task is to identify these target digits from the rest of the information, localise them, find their coordinates and provide the 3-dimensional coordinates of these data points. To accomplish this, we need to implement a pipeline of Image processing tasks, including object detection, localisation, and digit recognition.
- NLP Economics
A project with the Economics department to extract and parse information from the OCRed health reports available on the Wellcome Library. The extracted information such as the number of health visitors per year and per area, will be later used by the Economics team to form a hypothesis ont he health of the population based on the governmental stratefies, throughout the past century.
- Oceanic Exchanges
A collaboration with the School of Laws, Arts and Humanities, and Social and Historical Sciences (SLASH), we are working with the Oceanic Exchanges project to enable the analysis of large collections of newspaper articles, from multiple countries, on UCL's high performance computing platforms.
Our collaboration with the School of Education, PopChat uses web-based technologies and pedagogical research to improve English comprehension of kids in primary and secondary schools in the Philippines, through music, song lyrics and rhymes. We built the software for the game and will be involved at a later stage in the post-launch data analysis.
- Critical Care & Bed Occupancy Models
Our project with UCLH, together we are building tools and systems to allow the patient data to be used for research, and ultimately, for real-time patient care. At this stage, RSDG is developing the data infrastructure, 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.
- FASt-Mal Laboratory Information Management System
Our collaboration with BEAMS, the project's aim is to translate state-of-the-art robotics and maching-learning research into a benchtop prototype capable of Fast, Accurate, Scalable malaria diagnosis. The project aims to overcome diagnostic challenges by replacing human-expert optical-microscopt with a robotic automated computer-expert system that assesses similar digital-optical-microscopy representations of the disease. RSDG is developing the information management system for the project, storing acquired images with all metadata, allowing human experts to annotate images for tranining and test datasets, and interfacing with the machine learning software being developed by UCL Computer Science.
Contact the AI Studio
Please e-mail Dr Sanaz Jabbari (firstname.lastname@example.org) if you would like to discuss a project. RITS also run regular drop-in sessions for all research staff and research students to provide quick consultations on any tricky data science related problems.