Web Search Solution with Law Foundation of B.C.

Team Members: Ross Shen, Shruti Sharma, Gini Choi, Shara Merrill, Valerian Janjua
Advisors: Jason Lee Elliott

With support from The Law Foundation of British Columbia and the Access to Justice framework, on the BC Human Rights Tribunal website, we made it easier for both complainants & respondents to find specifically relevant cases & extract info in a quick & easily understandable summary. Users should be able to find other similar cases to educate themselves on how the legal system operates (e.g. likely progress, timeline, outcome, etc), and educate themselves on what type of evidence they need to gather in order to make their case stronger and more credible.

Community Based Rehabilitation - Hope Health Action

Team: Shashank Thanalapati, Ali Arshad, Paul Ngo, Jeffrey, Henry Ye, Ming Gong

Advisor: Brian Fraser

HHA's Rehabilitation service is an extremely vital presence in Uganda and its role in supporting the less abled people has and will only do wonders. Managing all of this is a challenge by itself, and even more so if done manually with pen and paper. The CBR Project strives to nullify the need for physical documentation and change the way data was being taken, managed and accessed. Creating a web-based platform for managers and a mobile application for field workers was the task given to SFU. While the website had managerial and administrative features, the mobile devices were created with features that were required on site. Overall, we believe that this project's success could help HHA help Uganda and the 1.4 million refugees located there.

A Sim2Real Approach to Augment Underrepresented Data for Dynamic Emotion Expression Recognition

Team: Saba Akhyani, Mehryar Abbasi Boroujeni

Advisors: Angelica Lim, Mo Chen

Robots and artificial agents that interact with humans should be able to do so without bias and inequity, but facial perception systems have notoriously been found to work more poorly for certain groups of people than others. In our work, we aim to build a system that can perceive humans in a more transparent and inclusive manner. Specifically, we focus on dynamic expressions on the human face, which are difficult to collect for a broad set of people due to privacy concerns and the fact that faces are inherently identifiable. Furthermore, datasets collected from the Internet are not necessarily representative of the general population. We address this problem by offering a Sim2Real approach in which we use a suite of 3D simulated human models that enables us to create an auditable synthetic dataset. 

Baytree App

Team Members: Shiva Sanei, Cagla Istanbulluoglu, Noel Riopel

Advisors: Brian Fraser

The BayTree Centre is a non-profit organization in London, UK. Their mission is "To create supportive pathways towards social inclusion for children, women and families through education, workshops, mentoring and training programmes". This system supports the mentoring program by tracking mentor/mentee sessions and creating a personalized experience for them. Features include tracking meetings, monthly questionnaires, accessing resources, and user notifications. The system interfaces with their existing data collection and management system (Views). By the end of the semester the system is expected to be evaluated in the UK by The BayTree Centre and be ready to be deployed for active use.