Completed Projects
-
Medical AI Projects
These projects are related to the design, development, and validation
of AI in various medical applications.
-
Social Media and Social Network Analytics
-
Geo-Visualization of Spatio-temporal Patterns and Disease Trends
This project, funded by the Centre for Infectious Disease Epidemiology
and Research (CIDER), aims to develop geo-visualization techniques that
allow the interactive exploration of spatio-temporal patterns and
disease trends.
The GeoVast system automatically highlights regions with
abnormally high concentration of incidences and performs hot spots
prediction.
This project involves collaboration between Saw Swee Hock School of
Public Health and NUS School of Computing.
-
Flagship Project on Ocular Imaging
The project is funded by ASTAR Exploit Technologies to fully automate
the Singapore Eye Vessel Assessment System (SIVA). This system brings
together various technologies from image processing and artificial
intelligence to construct vascular models from retinal images.
Subsequently, these models of blood vessels can be queried for a
variety of measurements which have been shown to be correlated to
diseases such as stroke, diabetes, hypertension etc. This project
is a collaboration between Singapore Eye Research Institute (SERI) and
NUS School of Computing.
-
Gaze Tracking for Visual Field Testing in Glaucoma
Funded by ASTAR Biomedical Engineering Programme, this project is a joint collaboration between
NUS School of Computing, Singapore Eye Research Institute (SERI) and
Singapore-Stanford Biodesign Science and Engineering Institute.
We aim to develop a portable perimetry device
that can test a patient's field of vision while tracking
the patient's gaze with gaze-tracking technology based on video images of
the eye. This device would remove the need for the patient to fixate
constantly on a central target by placing the stimulus in the correct
area of visual field to be tested based on the patient's gaze.
-
SiRIAN: Singapore Retinal Imaging and Archival Network
The SiRIAN programme, funded by ASTAR SBIC, is
focused on linking retinal image features
with demographic and clinical data for risk prediction.
This project involves collaboration between Centre of Eye Research
Australia (CERA), I2R and NUS School of Computing.
-
Knowledge Discovery in Biological and Clinical Data
This is an I2R-SoC joint research project funded by ASTAR. The project
aims to construct a knowledge discovery and data mining platform
for biological and clinical researchers to extract new knowledge and
value-added information from diverse data sets.
In particular, we have
developed a taxonomy of artifacts observed in molecular databases,
methods that recognize micro RNA precursors from genomic sequences,
and techniques to discover network motifs and increase the reliability of
interactions in protein-protein interaction networks.
-
RetinaMiner: Mining Changes in Retinal Images
This project is funded by ASTAR SERC.
The vascular structure of a retina image has been shown to reflect the
cardio-vascular states of the human body. Careful study of the changes
in retina images can enable clinicians to monitor, predict, and manage
diseases at an early stage.
This project aims to develop methods to precisely extract
and tracks vascular structures from digital retinal images
to compute vessel caliber, branch angles and tortuosity.
Retinal images over multiple time points are registered to detect changes.
These data are tagged using XML for subsequently querying of changes.
Techniques to discover spatio-temporal patterns
that highlight the interesting changes that occur in these vascular
structures are developed.
-
RETINA: a RETinal INformation Analysis system
This is an NUS-NSTB funded project. The objective of the project
is to employ a combination of innovative image processing
and mining techniques to automate the preliminary
analysis and screening of specific diabetic and age-related eye diseases from
digitized retinal photographs of diabetic patients. This project is a
joint collaboration between National Healthcare Group Polyclinics,
Tan Tock Seng Hospital and NUS School of Computing.
-
InteliClean: a Knowledge-Based Framework
for Intelligient Data Cleaning
This project integrates de-duplicating strategies and methods
into a general purpose and complete data cleaning system.
The objective is to obtain a set of higher quality data for mining and
warehousing.
-
Next Generation Electronic Business Hubs
Supported by the NUS Academic Research Fund, this project aims
to design an Electronic Business Hub
(EBH) to provide business partners, government services, and
customers with a portal, or an interactive "window," into their
collaborative business environment. The hub will be able to integrate front
and back office applications, supply chain and e-business capabilities.
Users will be able to seamlessly access internal and external applications,
hosted services and business content via a single, easy-to-use
Web-based environment.