With the increasing popularity of Internet, online advertising becomes a new marketing opportunity by instant globally advertisements (ads). At the basis, the process of online advertising can be considered as a buyer/seller relationship, where the two of the key participants are publishers (i.e. seller) and advertisers (i.e. buyer). Publishers make money through hosting websites with advertisements, while advertisers pay for having their ads displayed on publishers' websites.
This project studies Machine Learning algorithms for multi-category document classification. The purpose is to effectively predict user’s behavior based on the contextualization of the advertising and the associated document and therefore, to increase the click rate and the success of a dynamical advertising campaign. Due to the nature of the World Wide Web, the feature sets for the classification is extremely large. However, many learning algorithms don’t perform well with large number of features or attributes.
UNIMIN extracts and produces feldspar at two adjacent sites located north of Havelock, Ontario. In recent years, there have been occasional complaints from nearby residents concerning high levels of dust deposition on their properties. The residents believe that the dust originates from the mine site. In response, UNIMIN has invested heavily in several dust control strategies. However, the relative efficacy of these strategies has not been quantified for the given site conditions.
Different from traditional online advertising, dynamic media campaigns show different impressions (visitors to a web page) with different advertisement based on the characteristics of the impression. Infer Engine is a system that optimizes bidding for media campaigns by maximizing total profit for every impression. The theoretical foundation of the Engine is a by statistics based learning theory for predictive models and mathematics analysis for optimization. The proposed project is on performance valuation of the Infer Engine with different learning algorithms.
Predictive modeling is a statistical data mining approach that builds a prediction function from the observed data. The function is then used to estimate a value of a dependent variable for new data. Then objective of the project is to develop predictive models by machine learning approach and data mining techniques from the large volum of data collected at the partner site. The intension is to study applications of some most recent adademic reserach restuls to an industry product, a real-time analytics and data-intensive platfome.
Aircraft/Avionics System certification is awarded by aviation regulatory bodies to applicants after they have demonstrated that the design of the system meets airworthiness requirements. Airworthiness requirements are a complex set of requirements, standards, and regulations. Demonstration of compliance to airworthiness requirements can be accomplished through testing, reviews, similarity of installation and/or usage and other means.
An important concept in industry and science is the occurrence of rare events: events that occur with low probabilities but have significant impacts. Examples of rare events include the chance of an automobile insurance holder filing a claim or credit card accounts are compromised. The proposed project investigates applications of machine learning algorithms in the analysis and prediction of the occurrence of rare events.
The proposed research project will result in the development of a background and scoping document to inform and assist climate change adaptation planning for the City of Peterborough and Peterborough County. It will be directed with the involvement and guidance of a municipal working group.
This internship will enable a targeted collaboration to be developed between Alcohol Countermeasure Systems Corp. and Trent University, associated with designing and constructing a new generation of alloptical breath alcohol sensors. The high-sensitivity, high-selectivity breathalysers that will emerge from this collaboration are expected to become a valued diagnostic tool within many sectors, from professional to recreational.