The PI currently has a funded NSF grant: 0812551 III-COR-Small: Beyond Feature Selection and Extraction - An Integrated Framework for High-Dimensional Data of Small Labeled Samples". This supplement proposal seeks REU supplemental funding for two undergraduate students to serve the following two purposes: (1) providing a unique research opportunity for the participating undergraduate students by allowing them to work on a set of well-defined research and development tasks for feature selection and extraction; (2) enhancing the study of the above project by delivering a high quality dimension reduction toolbox; and (3) involving undergraduate students to work on state-of-the-art research tasks and gain valuable experience that will encourage them to continue graduate study at ASU or other universities. The above project aims at studying the theoretical perspectives of dimension reduction for learning in the small sample context. We have one specific and challenging problem, which is suitable for undergraduate students: Developing a dimension reduction toolbox systematically to integrate popular existing algorithms to facilitate their application and performing comparative study. Although numerous dimension reduction and feature selection algorithms have been published, there is no toolbox that allows one to use it for research and development. The practical significance of this problem is three-fold: (1) Facilitating the objective comparison of popular existing algorithms to study characters and form guideline for their applications; (2) serving as a platform for benchmarking in new algorithm development for feature selection and extraction; and (3) assist the application of dimension reduction technique in solving real problems. To ensure the success of the project, the PI has outlined a plan for performing not only technology development but also systematic testing and usability study.
|Effective start/end date||9/1/08 → 8/31/12|
- National Science Foundation (NSF): $588,704.00
Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.