Image Rectification for 3D Stereoscopic Displays

3D, or Stereoscopic video technology has entered a new era. 3D stereoscopic effect has always relied on the viewers wearing special glasses to allow left and right image to be seen by each respective eye to create the stereoscopic effect of depth. Some industry players have started to investigate ways to create a 3D effect on the screen or display that does not the user to wear glasses. Spatial View Inc.

Water Pipeline Monitoring Using Wireless Sensor Networks

The intern will work closely with Pressure Pipe Inspection Company, a provider of critical water infrastructure management tools, to develop a new wireless data transmission system. The tasks will include 1) Rebuild Windows CE kernel for communication programming; 2) Data uploading program based on Winsock; 3) Data transmission software development between sites; 4) Design/Implement command function from the remote node. 5) Test the wireless data transmission system. 6) Improve the stability of the wireless system.

Analysis of Decision Support System Metrics

Octothorpe Software is a decision sciences company that offers systems which organizations can use to improve their performance. This MITACS ACCELERATE internship project will be focused on developing new methods and metrics that organizations can use to improve their competitiveness. This will be achieved by developing the procedures, processes and the tools for displaying and understanding the key factors to improving the organizations success.

Web Page Recommender System

The internship involves research into technology that can recommend web sites to a user. The user indicates web sites they like, and the recommender engine suggests pages with related content, or which people similar to the user liked. A recommender technology has been in development at Worio, a search engine company. What is proposed here are three machine learning projects that extend the recommender technology. First, learning a more sophisticated model of each user, by looking at all activity a user does, rather than just indicating preference.

Video Motion Detection and Tracking for Surveillance Applications

Surveillance is a growing need for many companies and organizations. The need to keep certain assets protected from theft, vandalism and other mischievous deeds is important to the well being of any organization. However, most places that require a security system have many cameras and areas that need to be monitored all at once. An autonomous system that automatically detects motion and can follow motion of interest can help alert the appropriate people that there is interesting activities occurring in certain cameras or areas.

Estimation of required efforts for information technology projects

The general objective of this research project is to enable a consulting firm to produce more accurate estimates for information technology (IT) projects. More specifically, the general objective consists of two sub-objectives, namely to: (1) determine the causes of estimation errors in the needs-analysis phase of IT projects; and (2) use new tools to correct such causes of error, thereby reducing the gap between current estimates and accurate appraisals.

Customer Segmentation Using Feature Set Generated from Customer Transaction Data

There is a high demand for automated fraud and money laundering detection and prevention systems since such activities costs millions to the financial industry every year. A key problem in detection techniques is the accurate and descriptive profiling of the accounts. Thus, it is important to identify the salient features in traction data that would enable us to accurately profile the accounts.

A Support System for Managing Failures of an Electronic Gaming Machine Environment

Computer systems, and in particular hosting servers such as Electronic Gaming Machines (EGM), have become very complex systems, and the requirement for 24/7 service requires fast correction of machine failures. Networks can include several thousands of devices, spread out over a geographic area of thousands of square kilometers. Maintenance and downtime can cost millions of dollars per year.

Keywords Detection in Handwritten Documents

The long-term aim of this project is to develop techniques and software for the processing of unconstrained handwritten documents. The short terms goals are 1) the enhancement, “de-noising” and removal of artifacts in degraded digital handwritten document images, 2) text-lines and words segmentation independent of scripts or symbols and 3) identification of a small set of keywords in handwritten document images for document classification, retrieval or other purposes.

Information Extraction from Unstructured Data

Information extraction from unstructured data is a wide and relatively recent domain. For this research project, the focus will be on the information extraction from finance reports and news, more precisely related to the commodities market. This includes Natural Language Processing (NLP), expert systems (such as ontology-based systems) and information fusion as tools for analysing qualitative information in finance and producing investment decisions. NLP is a science studying the automated understanding of natural human languages.