26 September 2014
BII wins best booth display award at A*STAR Scientific Conference 2014

This year's A*STAR Scientific Conference 2014 (ASC) with the theme "Science for a Better Future" was held at The Chevrons on 25 - 26 September 2014.

The conference, which features eminent overseas speakers and scientific leaders from A*STAR provided a platform for cross sharing of new ideas and advancements in science and research and development. There were also presentations showcasing the latest research by A*STAR scientists.

We are happy to announce that BII won the Best Booth Display Award at this year's conference. BII showcased the Hand Pose Estimation demo (by Xu Chi and Ashwin from the Machine Learning For Bioimage Analysis group) and the FluSurver (by Raphael from the Protein Sequence Analysis Group). Congratulations once again to those (and their group members) who set up and manned the booths and explained to the visitors their displays at the ASC 2014!

About Hand Pose Estimation
We tackle the practical problem of hand pose estimation from single noisy depth images, which amounts to estimate the precise finger joint locations in 3D. Since a finger has three joints plus finger tip, altogether we end up having 20 joint 3D locations to estimate from a single depth image. By exercising and developing our own variant of the random forest learning method, our system is able to work with Kinect-type consumer-grade depth cameras and reliably produces pose estimations of general motions efficiently (up to over 60 frames per second). More detailed information of this project can be found here.

About FluSurver
The FluSurver is a research tool developed to help the influenza research community with the identification, analysis and interpretation of mutations in influenza sequences. It allows researchers, clinician scientists and surveillance labs to rapidly screen their influenza sequences for potentially interesting mutations to identify candidates for phenotypic changes or special epidemiological relevance. For the latter, we provide geographic and temporal frequency of occurrence as well as co-occurrence of mutations. For phenotypic changes we utilize our in-house database of curated literature annotations for mutation effects such as drug resistance, host receptor specificity, virulence, antigenic drift and antibody escape mutants. We also show the position of the mutation(s) in structural models and highlight if mutations are close to common drug, host receptor or antibody binding sites or if a glycosylation motif is lost or created through a mutation. The FluSurver has already been instrumental in the discovery of new influenza strain variants with altered antiviral susceptibility, host specificity, glycosylation and antigenic properties.

Feedback Login Site Map