Machine learning can be used to predict employee events around retention, promotion or movement. This project explores how to generate better predictions by exploring correlations and exploiting them through features that increase predictive strength. Furthermore, the project explores how to reliably fine-tune the predictive model to a particular data set in the presence of interdependence […]

This project examines the peer review process of a leading Canadian academic journal focused on international development, with the goal to better understand how research knowledge is made accessible and relevant – or not – for policy makers and practitioners. The intern will analyze systematically the texts of submitted articles, comments provided by the scholars […]

Pivot Legal Society seeks to improve the lives and the health of people who are homeless, use drugs, and/or engage in sex work through law and policy reform. Beginning in 2017 Pivot begun a large scale project to expand its knowledge base and networks with the goal of creating inclusive communities and promoting respect for […]

Commercial Mortgage-Backed Securities have traditionally been an extremely illiquid and inefficiently priced instruments. Our model, whether implemented through direct portfolio optimization services for clients or through a money management business, will help make this market more efficient and liquid. In particular, using the output of the model, we are able to advise our clients to […]

The creative industry is one of the vital pillars of the Canadian economy. Furthering the careers of women in business, technical and creative roles in Vancouver can help promote the economic growth of BC creative industry and advancing women into higher roles. Our project is to track the real-time data of the female staff in […]

Machine learning (ML) applications have shown remarkable performance in vanous intelligent tasks but high computational intensity and large memory requirements have hindered its widespread ubhzation in embedded and Internet of things devices due to resource constraints. Many optimization techniques have been proposed previously for domain specific architectures. These optimizations will affect an embedded device differently. […]

This project aims to develop a tool for cities and municipalities to use to negotiate and evaluate how large real estate development projects coming into communities, especially vulnerable neighbourhoods, can provide benefits back to that community. The specific focus of these benefits is on providing work and training opportunities for local residents, as well as […]

The Hey Neighbour! pilot program evaluation intends to draw conclusions about the potential of social policy interventions into urban neighbourhoods. First, we will review the multidisciplinary research trends and approaches related to the question of improving social quality in urban neighbourhoods and communities. This will include review of the terminology, definitions of related terminology, overlapping […]

This project involves the testing and characterization of new piezoelectric vibration sensors developed by the research group led by Prof. Bahreyni at the Intelligent Sensors Laboratory. These piezoelectric sensors have now been combined with another type of sensor – one with a capacitive transduction mechanism to improve the low-frequency sensitivity and noise performance. I shall […]

This Project is an continuation of our SIGGRAPH Asia 2017 paper on “Learning to Group Graphical Patterns”. The paper introduced a novel deep learning approach for grouping discrete patterns common in graphical designs. The approach was based on a convolutional neural network architecture that learns a grouping measure defined over a pair of pattern elements. […]

The project involves the modeling of the metabolism of TB. I developed an algorithmic pipeline called MetaMerge, which allowed me to reconcile differences in format, nomenclature, and annotation, between two models of TB metabolism. MONGOOSE, another doctoral project of mine, is a tool for analyzing metabolic network models in exact arithmetic, resulting in consistent, reproducible […]

The objective of this proposal is to study Littlewood cyclotomic polynomials of odd degree. In algebra, the cyclotomic polynomial is one such that has all its roots on the unit circle. Since all the coefficients of Littlewood polynomials are -1 or +1, its associates a finite binary sequence with -1 or +1 entries. Therefore, their […]