Innovative Projects Realized

A Dynamic Predictive Lead Scoring System for Inside Sales

Lead scoring is essential for lead management. The result of lead scoring is a list consists of leads with scores assigned indicating how likely each lead can be converted into the next stage of sales process. The Lamb or Spam and the Rule-Based are the two lead scoring methods that have been discussed in the literature. As various machine learning algorithms and artificial intelligence started to reemerge, predictive lead scoring models seem to be the next promising solution for lead scoring activity. This research project aims to develop a dynamic predictive lead scoring system that leverages on predictive analytics to automate lead scoring process based on historical customer data for a more accurate and reliable result. The outcome of this research project will demonstrate the value of application of data-driven predictive analytics in inside sales by offering business practitioners a model that can help optimize resource allocation and ultimately improve company success.

Game Metrics for Physiology-Based Health Games

In this proposed internship project, a new methodology towards the use of game metrical data to rate

player’s behavior and motivate behavioural change will be explored. Together with the Ayogo Games

(a game development company which takes special interest in the development of serious and health

games, see http://ayogo.com/), a concept for an adaptable game based on different data sources should

be developed. Ayogo Games offers a unique possibility to work in a company with experience in both,

health and social game development. The internship brings complementary expertise and experience in

game metric collection and analysis to the collaborative project.

Investigating the affect of chlorine carbides on fracture toughness in zirconium alloys used for nuclear applications – Year two

Zirconium alloys are used extensively in nuclear reactor cores for key components such as fuel assemblies and pressure tubes. It is extremely important that the in-service behavior of these components is well characterized to ensure they remain fit-for-service. This work will investigate the relationship between harmful impurity elements, specifically chlorine, and the fracture toughness of a zirconium alloy, Zr-2.5Nb. It is known that chlorine results in the formation of tiny precipitates, which are particularly damaging because they tend to cluster and form elongated voids, termed fissures. Despite there significance there is a lack of mechanistic understanding concerning the formation of fissures, which this fellowship aims to remedy. The work is a collaboration with Canadian Nuclear Laboratory (CNL) who support the Canadian nuclear industry through their expertise on the in-reactor behavior of core components. This fellowship will be mutually beneficial to Queen’s University and CNL as Queen’s University is home to a new state-of-the-art nuclear materials characterization suite; and will be the centre of the bulk of the research carried out as part of this work. This will allow for high-impact publications and a more thorough understanding of the effect of chlorine on the fracture toughness Zr-2.5Nb

Investigating the affect of chlorine carbides on fracture toughness in zirconium alloys used for nuclear applications

Zirconium alloys are used extensively in nuclear reactor cores for key components such as fuel assemblies and pressure tubes. It is extremely important that the in-service behavior of these components is well characterized to ensure they remain fit-for-service. This work will investigate the relationship between harmful impurity elements, specifically chlorine, and the fracture toughness of a zirconium alloy, Zr-2.5Nb. It is known that chlorine results in the formation of tiny precipitates, which are particularly damaging because they tend to cluster and form elongated voids, termed fissures. Despite there significance there is a lack of mechanistic understanding concerning the formation of fissures, which this fellowship aims to remedy. The work is a collaboration with Canadian Nuclear Laboratory (CNL) who support the Canadian nuclear industry through their expertise on the in-reactor behavior of core components. This fellowship will be mutually beneficial to Queen’s University and CNL as Queen’s University is home to a new state-of-the-art nuclear materials characterization suite; and will be the centre of the bulk of the research carried out as part of this work. This will allow for high-impact publications and a more thorough understanding of the effect of chlorine on the fracture toughness Zr-2.5Nb

Shipping Container Code Classification and Prediction

BlueNode is a SaaS company focused on the sanitation and analysis of marine shipping data. The research project is focused on increasing the precision and accuracy of shipped goods processed through Canadian ports. Should the research prove the be successful, the technical methods used with be directly incorporated into the BlueNode system.

Smart Atlantic Buoy Redundancy Model

This research will provide a prediction of sea conditions at a given location based on measurements from meteorlogic and oceanographic ‘smart’ buoys in the general area. The motivation is to provide redundancy in the measurement of sea conditions for safe navigation within the Halifax Harbour when the main smart buoy in Halifax Harbour fails or is unavailable.
The current Halifax Harbour Smart buoy provides real-time wind and wave data that is used to determine if levels are within acceptable thresholds in order to move vessels within the harbour. Two additional buoys are operated in the harbour by other entities (Environment & Climate Change Canada (ECCC) and Fisheries and Oceans Canada (DFO). This research project will determine if a model can be derived from the additional two buoys to make a prediction about the expected measures from the Halifax Smart buoy.

Heat Transfer Analysis of an Electric Baseboard Heater using Computational Fluid Dynamics

This research is an attempt to understand a heat transfer challenge encountered in the Glen Dimplex electric baseboard heaters in details and provide recommendations to resolve that. This baseboard heater uses electricity to heat up an internal element which is designed to transfer the heat to the room’s air via a series of thin aluminum plates called fins. The poor heat transfer from heater fins to air results in low efficiency of the heater as well as the unwanted physical deformation of fins by thermal expansion. Using computer modeling, the heat transfer mechanisms inside the heater will be analyzed, the possible reasons for the heater’s low heat transfer performance will be identified, and recommendations to improve its performance will be given. Using these recommendations, Glen Dimplex would be able to redesign and improve its heaters consuming less electricity while providing higher heat output.

Managing Shared State for Video Games in a Networked Multi-core Environment

Video Games require a vast array of different computations to present the desired experience. These

computations must be completed consistently to make the software responsive to the user. The

industry trend towards many separate processors (multi-core) in the same physical device and the

emergence of network based ‘cloud’ computing have created many opportunities, but also many

challenges for the game industry.

The goal of this project is to create efficient techniques to organize and schedule the computations to

take advantage of all the processors available. These techniques must ensure that the results

produced correctly and are obtained quickly enough to satisfy responsiveness. Each of these

techniques will have a corresponding aspect that allows them to be used by programmers who are not

experts in utilizing multiple processors.

While this project focuses on games, the benefits will be applicable to many domains, especially in the

emerging field of mobile consumer-oriented applications.

Atmospheric water generation with nanostructured material

Atmospheric water harvesting allows arid regions with low rainfall or unsustainable/expensive groundwater resources to collect fresh water from the air to meet their needs. Typical water harvesting methods rely on a simple principle: humid air is forced through a mesh net, where water condenses and droplets drain away through gravity. However, these traditional approaches face limitations with respect to the rate at which water can condense and drain away from the surface. AWN Nanotech Inc. has developed an alternative configuration for water harvesting, relying on a nanomaterial-enhanced, functionalized porous substrate that
will promote water nucleation and actively “pump” the condensed water away from the surface for collection through capillary action. AWN requires the expertise developed at Polytechnique Montreal and McGill University in surface engineering and nanomaterial synthesis to refine design parameters for their new configuration and construct testable systems. This project will allow the development of a new, Canadian water harvesting system capable of revolutionizing how fresh water is supplied. With a worldwide market estimated at nearly 1 billion USD by 2020, not to mention the decreasing levels of Canadian fresh water sources, the successful outcome of this project will yield substantial benefits to the Canadian economy.

Décharges pulsées dans les liquides : synthèse de nanoparticules

“Les plasmas dans les milieux liquides” est un projet de recherche très original, en termes des applications dans différents domaines et en termes de physique fondamentale. Mon projet consiste à étudier les plasmas générés dans l’eau en utilisant une décharge électrique impulsionnelle. Pratiquement, nous allons étudier en premier temps les caractéristiques électriques de la décharge en déterminant son circuit électrique équivalent afin de remonter aux propriétés physiques de la décharge, telle que la densité électronique.
D’autre part, nous allons caractériser les nanoparticules synthétisées par cette décharge. En premier temps, nous utiliserons des électrodes en nickel et cobalt pour produire des nanoparticules d’oxyde de nickel et de cobalt. Ensuite, des nanoparticules contenant simultanément du cobalt et du nickel (i.e., nanoalliage) seront synthétisées. Nous étudierons l’effet de la tension appliquée, surtout la polarité (positive ou négative) et la largeur de la pulse (c’est à dire la durée de vie de plasma) sur les caractéristiques de la décharge et des nanoparticules produites. Le développement des procédés écologique permettant la production efficace des nanoparticules est un besoin dans les applications technologiques, surtout dans le domaine de stockage des données (e.g., disques durs) et de l’énergie (e.g., batteries).

Application of Different Machine Learning and Data Mining Algorithms in the Detection of Financial Fraud

Detection of financial fraud is a priority for financial institutions. There are a variety of techniques and models that can be used to address the problem of financial fraud. However, as fraudsters are becoming more inventive and adaptive, they have been able to penetrate the conventional protective methods. This is one of the main reasons for the growth in financial fraud activity, regardless of the efforts of financial institutions and government and law enforcement agencies. This project investigates the use of artificial intelligence and machine learning algorithms to detect financial fraud.

Detecting Credit Transaction Fraudulent Behavior Using Recurrent Neural Networks

Fraudulent activities are hard to detect, but they cost financial institutions millions of dollars in monetary losses and legal costs every year. Millions of dollars are being lost in credit transactions as criminals are finding new, more sophisticated ways to conduct financial crime. This research project examines novel ways of detecting fraudulent behavior using powerful tools such as Recurrent Neural Networks, a type of machine learning model that is well suited for sequence or historical data.