Applying machine learning techniques for demand forecasting in retail

An important component to every growing retail business is demand forecasting which can affect the strategic plans of a business. The impact extends across the business’ function including budgeting, financial planning, price optimization, sales and marketing plans, capacity planning, staff management, risk assessment and mitigation plans.
In this project, we want to apply machine learning technologies to improve the accuracy and granularity of retail demand forecast.

Advancing Climate-Ready Fisheries in BC and Canada

Climate change is rearranging the distribution of ocean life and threatening the viability of world-wild fisheries that people depend on for food, income and well-being. While ample evidence shows the impacts of climate change on fisheries, British Columbia (BC) and Canada are lagging behind in developing the science and solutions needed to help west coast fisheries be more responsive and resilient.

Network anomaly detection of Building Automation Systems

This project aims to monitor the communications among the devices connected in a building automation system. It is important to detect any changes in the normal communication pattern of the devices. Such changes often signify a change of operational behavior, caused either by a failure or an impending breakdown. In the worst-case scenario, anomalies deviated from normal communication pattern may indicate the system is under a cyberattack, which would have serious consequences to the people inside and the building itself.

Species traits as clues for who will win or lose: Large mammal responses to landscape change

Resource extraction has caused extensive landscape change that impacts wildlife. This is especially true in Alberta, Canada, where forestry, oil and gas and similar industries stretch across the province. While these industries are known to negatively affect some wildlife species, other species benefit from the features that these industries introduce, such as roads. In consequence, wildlife communities in human-modified landscapes consist of ‘winner’ and ‘loser’ species.

Anatomy Detection of Cats and Dogs using Localization

The proposed work is an application of artificial intelligence and medical imaging. When positioning a dog to have an X-ray image taken of its paw, a neural network trained in canine anatomy can be configured to inform radiologists if the patient’s paw is improperly placed or even drive motorized hardware to automatically center the patient’s anatomy with respect to the imaging hardware. Diagnostic X-ray images like DICOMs contain header information about the subject including species, anatomy imaged, and the orientation of the image.

Broken Promises: Museum Exhibit Development during the Covid-19 Pandemic

Broken Promises is the capstone output of Landscapes of Injustice, a multi-year, intersectoral project exploring the dispossession of Japanese Canadians during the 1940s. The project illustrates the violation of human and civil rights at a time of perceived insecurity; measures taken in the name of national defence; the enduring harm of mass displacement, and loss of home and property; and human resilience. The traveling exhibit is one of the major research outputs of the project.

Evaluating and optimizing rural and urban lesbian, gay, bisexual, transgender, queer, intersex, and Two-Spirit (LGBTQI2S) engagement with hospice and palliative care in the Island Health Region - Year two

Existing research focused on the experiences of gay and lesbian older adults with the health care system report that there is a general distrust and reluctance to access healthcare based upon the cumulative effect of discrimination over the life course. At present, while 75% of Canadians have indicated they would like to die at home, 45% of Vancouver Island residents die of in acute care. Clearly there exists a service gap and it appears possible that such a gap may be larger in the LGBTQI2S community.

Fin whales of the Gitga’at First Nation: Site fidelity, distribution, and abundance within a proposed shipping lane

A rare inland population of fin whale uses the remote Kitimat Fjord System (KFS) in northern British Columbia (in the marine territory of the Gitga’at First Nation). This is the only fjord system, both historically and currently, that this predominantly offshore species has used within Canadian waters. Fin whales returned to the KFS only recently, at the same time as industrial development planning accelerated for northern BC coast.

Assessing temporal and spatial patterns of bowhead whale presence and underwater noise in the western Canadian Arctic

Understanding when and where bowhead whales occur is ecologically, culturally and politically important in the context of a rapidly changing climate, with some of the greatest impacts happening in the Arctic. Decreases in sea ice allow for increased shipping and its associated underwater noise in one of the last acoustically pristine habitats in the world. Bowheads, the only endemic Arctic mysticete and a cultural keystone species for the Inuit, are vocal, their survival depends on sound, thus vulnerable to increasing noise.

Radar-based Real-Time Detection of Overdose Incidents in Small Public Spaces

This project aims to train machine learning models that use millimetre-wave radar data to non-invasively detect health incidents, such as overdoses in public bathroom stalls.

Pages