Query Optimization using Machine and Deep Learning

In this project we will investigate and develop novel techniques that employ Machine Learning (ML) and Deep Learning (DL) for the optimal execution of queries in a relational DBMS. The research will be conducted with close collaboration with the team of IBM that develops Db2, the well-known relational DBMS of IBM. The goal is to integrate the produced ‘learned’ optimizer in Db2.

Industry-coached STEM experiential learning for social and environmental sustainability

Creating an inclusive environment where different innovators can feel welcome and exploit their talents is an ethical imperative no company can ignore. The scientific literature also provides clear evidence that diverse teams are more creative and high-performing, and that the engineering industry has a diversity problem. The general objective of this proposal is to research methodologies, outcomes and best practices for STEM experiential-learning environments that engage student teams in community-driven projects that address societal-impactful, sustainability problems.

Self-tuning servers within IBM cloud

Modern cloud-based applications are deployed as isolated processes in containers or virtual machines. These applications frequently require tuning by the application developer (or a DevOps engineer) in order to extract the requisite performance. For example, a Java application executing within a Docker container may have radically better performance if the host JVM runs with a specific garbage collector policy, or if the Docker container has the appropriate amount of memory and virtual CPU resources. This application-specific tuning is today a manual process.

Automatic Classification of Security Events

IBM QRadar needs to be able to categorize events generated by hundreds of different network devices in order to function as a Security Information and Event Management (SIEM). This categorization is currently a manual process and our aim is to automate this task. We have a database of over 579,000 events coming from over 300 devices that have been manually classified over the years. We also have the classification categories: 18 high level categories, broken down into 500+ subcategories; these categories broadly correspond to security threats.

Safe Harbour for Military, Veteran and Family Health Research Data

The Canadian Institute for Military and Veteran Health Research (CIMVHR), affiliated research partners at universities across Canada, and IBM Canada Ltd. have identified a significant and universal issue facing health researchers that applies to Canadian military, Veteran and family health (MVFH) research and health research for the Canadian population at large.

Digital speech analysis: prediction and differential diagnosis of PTSD symptoms and severity

Occupational stress conveys risk of Posttraumatic Stress Disorder (PTSD).

Ahead of Time Compiled Code Generation

Compilers are large software projects consisting of many separate but common components like code generators, garbage collectors, and runtime diagnostic tools, to name but a few. Historically compiler developers have had to write each of these components from scratch. The Eclipse OMR project was created to provide generic components for use in new compilers and language runtime environments. OMR has enough flexibility to accommodate a wide range of programming languages without sacrificing performance, portability, or robustness.

Improved Numerical Combustion Models for Predicting and Reducing Pollutant Emissions in Gas Turbine Engines

Gas turbine engines are the primary propulsion device for today’s aircraft. These engines operate on liquid hydrocarbon-based fuels and as such can yield a range of undesirable pollutants including gaseous emissions such as nitrogen oxides (NOx), carbon monoxide (CO), green-house gases (GHG, largely CO2, really a combustion product) and unburned hydrocarbons (UHC), as well as nanometer-sized carbonaceous particulate matter or soot.

Improved Numerical Combustion Models for Predicting and Reducing Pollutant Emissions in Gas Turbine Engines

Gas turbine engines are the primary propulsion device for today’s aircraft. These engines operate on liquid hydrocarbon-based fuels and as such can yield a range of undesirable pollutants including gaseous emissions such as nitrogen oxides (NOx), carbon monoxide (CO), green-house gases (GHG, largely CO2, really a combustion product) and unburned hydrocarbons (UHC), as well as nanometer-sized carbonaceous particulate matter or soot.

Electrochemical Fischer-Tropsch Synthesis of Renewable Liquid Fuels from CO2

Despite a rapid decline of electricity costs, there is still demand for energy-dense liquid fuels, such as in heavy freight and air transportation. Liquid fuels can be synthesized from a mixture of carbon monoxide and hydrogen called synthesis gas (syngas). However, this process requires high temperatures and pressures, and is itself responsible for significant greenhouse gas emissions. We propose the use of electrocatalysis to produce these liquid fuels.

Pages