Bringing Personalized Recommendation to the Legal Domain

Machine Learning has just started to be applied to the Legal Domain. ROSS Intelligence makes it possible for legal professionals to work faster and more effectively. Advanced Recommender Systems have not been previously applied in the Legal Domain. Yet state of the art models such as ones using Deep Collaborative Filtering have proven to be very effective on very sparse datasets. This project will evaluate the effectiveness of state-of-the-art Recommender System techniques applied to the legal domain in the hopes of improving the precision and recall of the current Q&A system.

Characterizing the role of probiotics in physiologically relevant ex vivo and in vivo models of infectious colitis

In the intestines of people living with inflammatory bowel diseases (IBDs), the balance of beneficial bacteria is shifted. Instead, the intestine is overloaded with potentially harmful bacteria – a phenomenon known as dysbiosis. This shift in bacterial populations is believed to be among the key contributors to the onset of inflammation observed in IBD patients.
Bioactive bacteria that help to re-establish equilibrium in the intestine are known as probiotics. They work by promoting the growth of beneficial bacteria while simultaneously warding off harmful bacteria.

Deloitte IP Factory: dTRAX Contract Management

Manual contract analysis and management is a laborious task. dTrax is Deloitte’s managed solution to this problem—it uses machine learning to automate the arduous contract management process and help users gain further insight from contracts. Specifically, dTrax will be used to standardize the intake of legal contracts, generate and edit contracts within a web interface, and identify and monitor changes in contracts. The proposed research project aims to improve dTrax by automating contract checking and analysis.

Development of electrospun micro/nano fibrous strain sensors with temperature sensing capabilities for wearable textile applications

Piezoresistive strain sensors respond to a mechanically induced deformation with a change in their electrical resistance. Large strain flexible strain sensors have been adopted for numerous applications including rehabilitation, health and sport performance monitoring as well as physiology and kinesiology applications. Although development of these flexible strain sensors has reached a level of maturity, design of a multifunctional strain sensor with temperature sensing capabilities and its integration with wearable textiles and electronics have still remained a challenge.

Methods for efficient and effective multi-document reading comprehension in the legal domain

ROSS enables legal professionals by providing tools that harnesses the power of artificial intelligence to make the research process more efficient. Advances within machine learning and natural language computing enable systems to achieve close to human performance. Many state-of-the-art methods have not been applied to the legal domain, leaving opportunity to enable development for the legal field and bring improvement to the efficiency and effectiveness of legal research. This project evaluates multiple approaches to multi-document comprehension and their performance in legal domain.

GaN Power Transistor Modelling and Experimental Verification

Crosslight Software Inc. is a leading provider of technology CAD (TCAD) tools for the design and simulation of semiconductor devices. They are specialized in innovative III-V compound materials which are considered as the next generation materials for power semiconductor devices. Crosslight has on-going activities in developing accurate simulation models for gallium nitride (GaN) material and devices. In particular, this is critical for the design of GaN based power transistors.

Recommendation system for retail shopping

People rely on recommendations from other people, friends’ word, news reports, and travel guide and so forth. Recommendation systems assist people to sift through available books, web pages, restaurants, and grocery products. [16]. We want to build a recommendation flow in the retail industry to serve Canadian citizens better. The system will understand the customers and help them to make better selections and improve their shopping experience.

Analysis of factors impacting views and revenue of digital assets on YouTube

This research project will focus on factors increasing viewership and revenue on Boat Rocker Media’s digital assets on YouTube. Combination of datasets from various sources such as YouTube revenue reporting, YouTube data and analytics Application Program Interfaces (API’s), and social media will be used in an explanatory analysis and statistical modeling to get new insights. The project will involve integration of data from various sources as well as data cleansing.

3D Imaging Development for Part Dimensional Measurement

Manual inspection method is still applied by mounting parts on customized checking fixtures and thus dimensions are checked with different gauges/feelers. Typically, it could take 10 -30 minutes to fully inspect the required spatial dimensions of one part. This project will develop an automated 3D dimensional inspection system for deep drawing parts. After manually mounting the part, the system will fully scan the whole part by 3D sensors/scanners.

Natural Language Interface for Ad Hoc Queries in Analytics

The main aim of this project is to design a database that provides a simplified way for individuals without the technical background to query information from the database. Such a database will operate on natural language, where the user asks the database a question about information retrieval and it presents the user with suitable answers. A database of this format aids users who are unfamiliar with scripting and database management languages, such as SQL, to use it seamlessly without the need for any prior training.