Construction of a Genetic Variant Store

This project proposes to explore and implement a method of storing and retrieving data relating to genetic variation across a population of individuals. Due to the large amount of genetic information each person possesses, such a database requires special attention to minimize the amount of data stored and to create efficient methods of accessing the data. This work will research and test different strategies to build a compact data store that will return results quickly. This data store will be incorporated into the PhenoTips software provided by Gene42 Inc.

Interactive preference elicitation application for book recommendations

Kobo is an online e-book retailer that provides recommendations for future purchases to its user base. One difficulty that recommendation systems face is what is known as the “cold-user” problem. In this scenario, when we know so little of a user’s preferences (for example, if they are new to the platform), we do not have any basis for recommendations. The goal of this project is to develop an interactive application that can elicit such preferences from users about whom we have little information, and that can help improve recommendations for power users.

Validation of the educational impact of a holographic lecture

UBC and Microsoft intend to collaborate on an applied research project where 3D models of the brain will be used to create an interactive Holographic lecture using Microsoft’s new augmented reality device, the HoloLens. The will form the basis for a lesson or “HoloLecture,” and will feature new interactions to take advantage of the HoloLens’s technology. The ability to manipulate the 3D objects and dynamically adapt them to a live lecture format will form the basis of a HoloLecture prototype that can be applied across disciplines.

Sentiment Analysis with Parsed Representation of News Articles

Information published by financial news agencies is used as one of the inputs to make investment decisions. News articles from multiple sources can be used to gauge market sentiment towards an industry or a specific company. Deep learning techniques have been successful in producing state of the art results on various benchmark datasets (Dai & Le, 2015; Miyato et al., 2016). Most of the popular algorithms extract features from words, sentences or paragraphs and represent them as fixed-length vectors (Mikolov et al., 2013; Le & Mikolov, 2014).

Machine Learning methods for Nova Scotia property value prediction

This project will develop and apply machine learning techniques to predict the valuation of the properties in Nova Scotia. The techniques will help Property Valuation Services Corporation (PVSC) assessors with more efficiently and accurately valuing properties. The ultimate goal is to help PVSC reduce the number of annual appeals – which is a costly undertaking. It will also reduce the need to send assessors directly to the property locations, instead they will use machine learning techniques to more accurately predict property values.

High power all-fiber Raman laser at 1.65 ?m

Fiber lasers have become the fastest-growing laser with a projected worldwide revenue up to $1.41 billion in 2017. In particular, fiber lasers at 1.65 ?m have drawn increasing attention with potential applications in chemical sensing, LIDAR and spectroscopy. All-fiber Raman lasing technology is a promising and efficient technology to achieve high power lasing at 1.65 ?m. However, there are limited all-fiber high power sources at 1.65 ?m that are commercially available.

Learning representations through stochastic gradient descent by minimizing the cross-validation error

Representations are fundamental to Artificial Intelligence. Typically, the performance of a learning system depends on its data representation. These data representations are usually hand-engineered based on some prior domain knowledge regarding the task. More recently, the trend is to learn these representations through deep neural networks as these can produce significant performance improvements over hand-engineered data representations. Learning representations reduces the human labour involved in any system design, and this allows in scaling of a learning system for difficult problems.

Characterizing topography of signal fidelity in a low-cost fNIRS device

High-performance athletes have learned that even after they have exhausted their bodies during training, they can continue to train their minds for an extra edge. Imagining your sport engages many of the same brain areas used to actually play your sport, and it has been shown that such mental practice can improve sport performance. However, simply sitting and imagining isn’t very engaging and doesn’t provide either the athlete nor their coaches with any information regarding how well they are engaging in mental imagery.

Estimation and Prediction of Censored Arrival Processes with Censoring for Replenishable Item Purchases

The aim of the project is to predict future customer demand for repeat-buying items based on available customer purchase records. However, the purchase history for a single customer may not be sufficient to base predictions on. Also, some purchase records might be missing due to sales events at competitors’ locations. Thus, treating each customer as a replicant of the average customer and averaging inter-purchase times to predict future demand will likely be an inadequate approach.

Investigating the challenges of designing and implementing human resource management systems in the context of a Quebec SME.

This research project will focus primarily on the analysis of information systems technology adoption in order to improve the design of information systems and the process used for their implementation. More preciously, the main objective will be to investigate the adoption of information systems designed for human resource management in order to identify improvement opportunities for the partner’s software solution and implementation process.

Pages