 Learning-Based Optimization of Hyperspectral Band Selection for Classification
C.O. Ayna, R. Mdrafi, Q. Du, A.C. Gurbuz Remote Sensing 15, no. 18: 4460. https://doi.org/10.3390/rs15184460 We propose a deep learning (DL) architecture composed of a constrained measurement learning network for band selection, followed by a classification network optimizing the final classification loss while learning to select the bands for this task. In this way, the proposed network directly learns to select bands that enhance the classification performance. For more, please check out our full manuscript here
0 Comments
IMPRESS Lab students Ahmed M. Alam and Mehedi Farhad presented a total of 4 papers at IEEE International Geosciences and Remote Sensing Symposium (IGARSS’23), at Pasadena, CA.
Dr. Gurbuz and Dr. Kurum organized a special session on Passive/Active Coexistence at IGARSS7/18/2023
IMPRESS Lab demonstrated our ground and UAS systems, sensors, and research outcomes at MSU Research Week to the general public and the students. Check out the news about our activity and my PhD student Mehedi Farhad's interview here
|
AuthorAli C. Gurbuz is an Assistant Professor in the Dept. of Electrical and Computer Engineering at Mississippi State University and director of Information Processing and Sensing (IMPRESS) lab Archives
September 2023
Categories |
RSS Feed
|
Social Media
|
Sponsors
|
Get in Touch
Simrall Electrical Engineering 406 Hardy Rd, Mississippi State, MS 39762 Phone: (662) 325-1530 Email: gurbuz [at] ece [dot] msstate [dot] edu |
