Efficient Mining of Agro-Meteorological Data

Data mining refers to non-trivial extraction of implicit, previously unknown, and potentially useful information from data. In this project, the intern will apply data mining techniques to agro-meteorological data provided by Manitoba Agriculture, Food and Rural Initiatives (MAFRI). Specifically, he plans to develop mathematical solutions to analyze both current and historic weather data as well as related information such as crop yields, soil inventories, and crop management practices.

Streaming Workload Characterization and Multi-level Client Clustering

This project is part of a larger research project which investigates the applicability of the peer-to-peer (P2P) computing paradigm in designing large-scale content distribution systems. To develop an efficient content distribution system, it is essential to understand the workload that will be distributed, the behavior of content consumers and the environment in which the system will operate.

Multi-class Problem Decomposition Using Genetic Programming

Behavioural detectors for intrusion detection require training in order to correctly characterize the operation of a service – protocol combination. Implicit in this is the assumption that the learning algorithm will scale to large datasets and provide simple solutions. This work will address both requirements under a Genetic Programming context through the use of a combined multi-objective, host-parasite model. It has already been demonstrated that both schemes are appropriate independently.

Mobile IP Infrastructure for Medical Data Transmission

Currently, EMS paramedics record patient information such as history, medical assessment, and treatments rendered onsite with pen and paper. They then convert this information to a paper-based call report and hand it over to the hospital along with the patient. This method is time-consuming and error prone. It causes delay for data analysis and lengthens paramedic turn-around time. This project will produce a data collection tool based on the mobile IP infrastructure which will reduce clerical errors, improve data analysis and medical care.

A Defense System Against DDoS Attacks

Distributed Denial of Service (DDoS) attacks are widely regarded as a major threat to the Internet because of their ability to make a service unavailable and create a huge volume of unwanted traffic. Unwanted traffic control is one of the most important challenges of Bell Canada. Current countermeasures cannot assure higher quality of service under a tremendous increase in unwanted traffic.

Semantic Forwarding Engine for Content-based Routing

This project is about content-based networks. In content-based networks, the decisions regarding the forwarding of data are done by inspecting the actual information contents. The forwarding process is guided by properties of the payload data. This is in contrast with traditional networks where forwarding is guided only by the destination addresses contained in packets.

Embedding Undirected Graphs onto Extended Grids

D-Wave Systems is currently involved in the research and development of quantum computing technology. Quantum computers allow for not just a fast computer, but potentially, a change in the computational complexity of problems. Graph theory plays a crucial role in the development and understanding of the capabilities and behaviour of the quantum computing hardware being developed, both from an operational and an applications perspective.

Software Componentization

Current software development and refactoring practices promote the modularization of software and encourage the interoperation of software components. The emergence of service oriented architectures is now providing the incentive to promote even more modularity and interoperation between multi-vendor, multi-language, and multi-environment software. This project aims to develop a better understanding of these growing interoperation constraints in the context of large web applications.

Investigation and Development of Globally Convergent Methods for Solving Multiple Non-Linear Functions

Aurel Systems Inc. offers a commercial dynamic process simulation program called CADSIM Plus™ (www.aurelsystems.com). At several places in the program sets of nonlinear equations must be solved or nonlinear functions must be minimized (for example, solving pressure flow networks, solving for independent variables given sets of user defined dependent variables, solving for both temperatures on a heat exchanger with condensation or flash).

Estimation of Joint Distribution from Marginal Totals with Applications to Database Marketing

In many customer surveys and database marketing applications such as segmentation, profiling and predicting consumers’ choices, the joint distributions of covariates of interests are required. However, for variety of reasons, such as protection of clients’ confidentiality, the data are often available only in marginal frequency distribution format. This makes it difficult to use the covariates in a meaningful way where joint distributions are required for analysis decision making.