Grant: Discovery Grants Program - Individual
University of Regina
$40,000.00
Interestingness measures analysis, expectation-based data mining and animated plans
FY 2011-12
Summary
In my research, I will look for new ways of discovering knowledge using computers.
First and foremost, I will create new ways for computer programs to identify the most interesting conclusions that can be drawn from vast collections of data called databases. A variety of methods have been developed to automatically analyze databases. These methods are typically based on mathematical formulas called measures of interest. Unfortunately, these methods find too many relationships among the data for people to understand easily. Researchers have devised ways by which software can select some of the information, but these ways need to be modified to produce fewer conclusions. As well, they need to be adapted for use in specific fields, tasks, and people. One attractive way of proceeding is to take a group of existing and new measures and analyze their relationships mathematically and experimentally.
Secondly, and more specifically, I would like to find ways of keeping computers from reporting obvious information about time and space as newly discovered relationships. People understand relationships involving time and space very well. So, the computer should only report relationships about time and space that are not known to people. My approach will be based on keeping track of what people already know and what they might expect to be true, given knowledge already reported. Then, a new discovery made by software acting on a database will only be reported if it is something that a person might not expect from what was already reported.
Thirdly, I will try to make it easier to create animations. Now, it takes hours of painstaking effort to create short animations using software. I will change the software to allow background characters to be animated more easily. Individual non-player characters in current computer games and crowds of background characters in current movies are animated by creating a software agent for every character and having the agent play the animation most suited to the character's current situation. I will extend this idea by allowing the agent to create plans involving many steps and then execute these plans while playing suitable animations.
Program
Discovery Grants Program - Individual
Recipient
Location
Saskatchewan, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
121504-2009
Name nom
Hamilton, Howard
Department département
Computer Science
Organization id
17
Institution établissement
University of Regina
Province en
Saskatchewan
Province fr
Saskatchewan
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2011
Competition year année de concours
2009
Award amount
40000
Program id
RGPIN
Program nane en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
Discovery grants programs
Group fr
Programmes de subventions à la découverte
Committee code
331
Committee name en
Computing and Information Sciences - B
Committee name fr
Informatique - B
Area of application code
802
Area of application group en
Information and communication services
Area of application group fr
Services d'information et de télécommunications
Area of application en
Information systems and technology
Area of application fr
Systèmes d'information et technologie de l'information
Research subject code
2805
Research subject group en
Artificial intelligence
Research subject group fr
Intelligence artificielle
Research subject en
Learning and inference theories
Research subject fr
Théories de l'apprentissage et l'inférence
Partie
3
Nb partie
5
Application title
Interestingness measures analysis, expectation-based data mining and animated plans
Keyword
NSERC
Application summary
In my research, I will look for new ways of discovering knowledge using computers.
First and foremost, I will create new ways for computer programs to identify the most interesting conclusions that can be drawn from vast collections of data called databases. A variety of methods have been developed to automatically analyze databases. These methods are typically based on mathematical formulas called measures of interest. Unfortunately, these methods find too many relationships among the data for people to understand easily. Researchers have devised ways by which software can select some of the information, but these ways need to be modified to produce fewer conclusions. As well, they need to be adapted for use in specific fields, tasks, and people. One attractive way of proceeding is to take a group of existing and new measures and analyze their relationships mathematically and experimentally.
Secondly, and more specifically, I would like to find ways of keeping computers from reporting obvious information about time and space as newly discovered relationships. People understand relationships involving time and space very well. So, the computer should only report relationships about time and space that are not known to people. My approach will be based on keeping track of what people already know and what they might expect to be true, given knowledge already reported. Then, a new discovery made by software acting on a database will only be reported if it is something that a person might not expect from what was already reported.
Thirdly, I will try to make it easier to create animations. Now, it takes hours of painstaking effort to create short animations using software. I will change the software to allow background characters to be animated more easily. Individual non-player characters in current computer games and crowds of background characters in current movies are animated by creating a software agent for every character and having the agent play the animation most suited to the character's current situation. I will extend this idea by allowing the agent to create plans involving many steps and then execute these plans while playing suitable animations.