This $170,000 federal Project Grant award from the National Science Foundation's Computer and Information Science and Engineering (CISE) program (CFDA 47.070) aims to develop robust and human-aligned deep learning techniques for analyzing medical sensor time-series data. The primary goals are to: 1) identify input confounders that lead to spurious correlations in time-series data, 2) design knowledge-editing strategies to correct these spurious correlations, and 3) investigate the techniques in medical applications such as Parkinson's disease monitoring and fall detection for the elderly. The research outcomes will produce open-source tools to benefit sensor-based medical monitoring and diagnosis tasks. The project will also foster broader participation from undergraduate and graduate students, particularly in the Hispanic community in South Texas, through dedicated research, education, and outreach initiatives. North Carolina State University is the sole award recipient, with the project period running from Sep 1, 2024 to Aug 31, 2027.
Mod # | Description | Reason For Modification | Federal Obligation (Click to sort descending) | Date (Click to sort ascending) |
|---|---|---|---|---|
| Not listed | $170.0k | 7/30/24 |