Students will be expected to work in teams of up to 4 members on course projects. Students are welcome to (and usually do) come up with their own projects; alternately they may also choose from a list of projects that are proposed by various collaborators. The list of proposed projects will be presented in the first week of September. We list some of these below. We expect at least some of these projects to lead to papers, or to contribute to other applications or projects.
This year the MLSP course is being conducted in collaboration with NASA. As part of this collaboration, NASA scientists will provide us with several case studies. Students working on these case studies will be required to complete a set of prescribed analyses, as well as devise additional analyses of their own.
The list of 6 case studies will be put up here shortly.
For this project we will work with Dr. Marcel Bergerman of the robotics institute to develop voice-based control for agricultural field robots. A more detailed description of the project will be put up here shortly.
One of the standard tests for detecting Alzheimers early is a "finger tap" test, where subjects are asked to drum on a sensor with their fingers. The equipment for this tends to be expensive. For this project we will develop techniques to run the test using an IPAD. We will have to devise appropriate sensing and classification methods to detect the tapping patterns, and classifiers that can predict Alzheimers based on these patterns. The project will be run in collaboration with the deputy corner of Fayette county. Additional details will be put up here shortly.
Consider a person interacting with a robot or any other such interactive device. It is often hard to know if the person is addressing the device (or merely conversing with someone else). In this project we will use a combination of audio and visual cues to automatically detect if the subject's focus of attention is the robot.
More project ideas will be put up here in the coming days.