Innovative Projects Realized

Advanced geoscience targeting through focused machine learning

With the majority of the easy mineral resource targets having already been found, the mining industry is being forced to re-evaluate methodologies for conducting exploration programs. Future targets are likely to be deeper, with little or no surface expression, and may be concealed from conventional exploration techniques by overburden, permafrost or other geologically complex environments. In order to locate such targets, a holistic multidisciplinary approach is required to identify trends across multiple characteristic features, including geology, geophysics and geochemistry. Quantifying and correlating georeferenced features from such a wide array of data types can be best handled using machine learning algorithms. These algorithms can be trained on a sub-sample of known mineral deposit locations such that they are able to identify the trends in the multi-parameter data set which are associated with mineralization. Once the relevant trend has been identified, a machine learning algorithm is able to predict new mineralization zones from the full data set. Many different machine learning algorithms exist, each with advantages and disadvantages. Tailoring an algorithm to this specific application requires an understanding of both the data, as well as the theory supporting machine learning. Such a marriage of expertise can lead to vast improvements in performance and a more reliable outcome in predicting future mineralization zones.

Logistics and operations simulation of logging debris supply for bioenergy production

Logging operations in British Columbia produce an estimated 15.5 megatonnes per year (MT/yr) (oven dry basis) of forest residues. Traditionally this logging slash has been piled and burnt on site. Due to the rising concerns around climate change and increasing demand for energy, these harvest residuals are becoming a desirable fuel source for sustainable bioenergy production. However, due to the logistical complexities, high cost, and fossil fuel intensity of collection and transportation, careful planning is necessary to provide these fuels to local energy facilities in an economically feasible and environmentally benign manner. This research proposes the optimal procurement strategy for delivering 100 000 Bone Dry Tonnes (BDT’s) per year of harvest residuals to a 112 megawatt (MW) Howe Sound Pulp and Paper power facility located near Vancouver, BC. A new transportation and logistics simulation model has been developed which implements high resolution real data from the supply operations in the region.

FOREX Geocoding System for Foreign Currency Market Monitoring

An existing Forex currency trading system has demonstrated a proof of concept on a static data set. The current project proposes to implement the trading system for real-time applications taking advantage of available geospatial information which can influence currency markets. The novel methodology will be based on building a high-dimensional weighted autocorrelation model between real-time news and their spatio-temporal geographic locations. This would require development of sophisticated methods in the areas of data mining, geocoding and spatio-temporal pattern matching. The developed technology will be incorporated into CTS Forex trading software which will improve its monitoring and predictive capabilities by allowing to change the system trading behavior, i.e. exiting the trade, moving the stop loss and take profit in real-time.

Application of Data Mining Methods for Detecting Irregularities in Securities Market

Current procedure for monitoring securities market in Canada relies heavily on tips from outside and hard coded rules and thresholds. This approach leaves many suspicious cases out of investigation (i.e. false negatives). We introduce a data mining approach to identify irregularities in securities market. These irregularities are known as suspicious cases that might be associated with fraudulent activities and need to be investigated by auditors. Developing such methods requires a deep understanding of strategies that investment componies employ. During this internship, Koosha will work on building strategies for investments in securities market at FreeThink Capital, a hedge fund based in Edmonton. FreeThink Capital uses statistical analysis to understand the market and build investment strategies. Koosha will focus on time series analysis methods to detect patterns in securities market. This internship provides him an understanding of investoors’ approach and various investment strategies in securities market.

Colorimetric test strips for oil/fuel/ethanol mixtures

There is a need for customers to use a simple test method to determine if the fuel blends they are using are of the proper composition for fuel efficiency, environment- friendliness and engine cylinder compatibility. But it is difficult to determine the composition of oil/fuel/ethanol mixtures without detailed and expensive chemical analysis. It is because the different hydrocarbons in oils or in fuels are hard to differentiate by physical change or by simple chemical reactions such as pH change. In order to perform a simple test such as a colorimetric analysis, it may be necessary to find out the additives present in the oils and fuels for detection. There are many colorimetric tests available in the literature for the detection of these additives. However, these tests are all tedious that are not amendable to the simple test format such as the test strip. On the other hand, nanomaterials have been synthesized to test for viscosity and wettability of organic liquids. However, these nanomaterials have not been used to test oil/fuel/ethanol mixtures. Therefore, in this proposal, a series of nanomaterials called inverse opal films will be prepared. They will be treated and coated with different organosilanes to change the surface properties for liquid wetting. These treated nanomaterials will be used to determine the oil/fuel mixture ratios based on the color change when the different liquids wet the nanopores created in the inverse opal films. This method can easily be adapted in the test strip format, which is a userfriendly method with low cost and low power consumption.

Extracting information from Emails

The project will attempt to extract useful information from emails as well as attempt to classify emails as meeting intent or not. The proposed project deals with attempting to leverage current machine learning and natural language processing techniques to build a prototype that can solve the above problems. This will benefit the company by not having to use manual solutions. Currently the company uses the mechanical turk which requires actual humans extracting information from the emails. The prototype would eliminate the need for this and reduce their costs.

Creative BC: Strategic Design Process Research and Plan Development

Creative BC is an independent provincial agency tasked with overseeing the development and promotion of B.C.’s creative industries. In addition to administering tax credits and providing production support for filmmakers and television producers, it intends to work with the digital media, music and publishing industries to co-develop and implement a strategy for the creative sector. To fulfill its new mandate under the provincial B.C. Creative Futures plan, Creative BC is engaging an Interdisiplinary Graduate Studies student (ISGP) researcher who will lead a research, design and experimental process to craft an innovation-centered growth plan for the cultural and creative industries in British Columbia. Their goal is to build an innovative and sustainable creative sector that results in local pride and global attention. With an effective strategy they will be able to recruit and retain top creative thinkers and leaders and ultimately influence public policy.

Experimental investigation of patterning a nanostructured bioadsorbable stent by femtosecond laser ablation

The proposed project complements the current work of the partner organization with polymeric materials. The evaluation of ultrashort laser interaction with solid matter of surface textured metal-like materials would help the partner organization obtain detailed process knowledge; a distinct advantage for broadening its service offering to address a different market segment.

Cable Simulation Methods Using Nonlinear Finite Elements

Cable systems play an important role in many large scale simulation applications. Examples include marine systems, mining machinery, and cranes. The high fidelity and efficient modelling and simulation of these systems can enhance the applications and usability dynamic modelling environments. In this project we particularly target to develop models and efficient algorithms based on nonlinear finite element representation of the cables in largescale multibody simulation models. We will investigate core modeling and implementation aspects that are directly related to practical applications. The partner organization, CMLabs will greatly benefit from this project. The proposed work is of direct relevance to their current work, can have applications in many projects, and will also open up possibilities to broaden the applications of CMLabs’ software platform Vortex.

Effect of exposure to hydrocarbons on reproductive functions in select marine organisms

The partner organization, Oceans Ltd, offers diagnostic services to detect and monitor the effects of environmental contaminants on marine ecosystems, mainly using fish as biomonitoring tools. The company wishes to seize an opportunity for capacity building and diversification by exploring new bioindicator technologies based on the effects of hydrocarbons on the reproduction of marine invertebrates. The Mercier Laboratory will provide key expertise on the general biology and reproduction of marine invertebrates, which will be instrumental in exploring this avenue. The intern will use this knowledge to assist Oceans Ltd develop indicators of oil exposure that relate to reproductive functions in selected cold-water species. Specifically, the intern will be involved in carrying out the hydrocarbon exposures and subsequent biomarker analyses as part of his graduate (MSc) studies.

This research project was undertaken and completed with a grant from and the financial assistance of Petroleum Research Newfoundland & Labrador.

Techna Guided Therapeutics Cluster

The Guided Therapeutics (GTx) Core of the Techna Institute is developing innovative imaging technology and therapeutic approaches, and translating those advances to commercial and clinical applications. Working with our industrial partners Precision X-Ray and Elekta, the Mitacs-supported interns will develop new capabilities and tools for preclinical image-guided radiation therapy devices and radiosurgical techniques. With Precision X-Ray, the interns will work on developing the ability to use optical imaging to undertake unique preclinical studies in radiation therapy. The interns will also refine the radiation delivery methods of the preclinical irradiator to allow for dose painting. With Elekta, the interns will use a novel magnetic resonance imaging technique to better visualize the fine structures of nerve bundles near a tumour, and use that information to guide a Gamma Knife system in radiosurgery. Novel quality assurance and dosimetry tools will be developed to meet the needs of both industrial partners.

Mapping Building Conditions – perhaps a bit more – for what purpose

Despite advancement in asbestos education and knowledge, there remains a shortcoming in area of management of asbestos exposure, which results in human health impact. This shortcoming was documented in a study carried out in Minneapolis, Minnesota (Alexander et al 2012). Alexander and colleagues examined the population exposed to asbestos and looked into evidence of lung changes consistent with asbestos exposure. Their investigation demonstrated a strong relation between asbestos exposure due to poor detection and management practices, and measurable human lung modifications. Unfortunately, despite the invested efforts to reduce asbestos exposure, Ontario still allows the import and utilization of asbestos products (2013, April). The goal of this research project is to target issues concerning accurate classification of ACM conditions, thereby improving the well-being of workers health, and hence preventing future harm from asbestos. This project is in partnership with ECOH Management Inc. The industry partner is interested in developing a hazard mapping system that will assist in visually identifying the position and extent of contamination imposed by asbestos containing materials (ACM) on asbestos abatement projects. This project seeks to develop a miniature mapping system that can be used in dictating potential risk to construction workers’ health, as well as to understand the modes/mechanism of actions of these asbestos-like fibers in order to make better informed risk assessment and regulatory decisions. The industry partner, ECOH Management, is interested in developing a mapping system that will help expand the knowledge of identified ACM on site and thereby assist the industry partner in making better informed decision.