Share Email Print
cover

Proceedings Paper

Using input feature information to improve ultraviolet retrieval in neural networks
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

In neural networks, the training/predicting accuracy and algorithm efficiency can be improved significantly via accurate input feature extraction. In this study, some spatial features of several important factors in retrieving surface ultraviolet (UV) are extracted. An extreme learning machine (ELM) is used to retrieve the surface UV of 2014 in the continental United States, using the extracted features. The results conclude that more input weights can improve the learning capacities of neural networks.

Paper Details

Date Published: 1 September 2017
PDF: 12 pages
Proc. SPIE 10405, Remote Sensing and Modeling of Ecosystems for Sustainability XIV, 1040506 (1 September 2017); doi: 10.1117/12.2274522
Show Author Affiliations
Zhibin Sun, USDA UV-B Monitoring and Research Program (United States)
Ni-Bin Chang, Colorado State Univ. (United States)
Wei Gao, USDA UV-B Monitoring and Research Program (United States)
Colorado State Univ. (United States)
Maosi Chen, USDA UV-B Monitoring and Research Program (United States)
Melina Zempila, USDA UV-B Monitoring and Research Program (United States)


Published in SPIE Proceedings Vol. 10405:
Remote Sensing and Modeling of Ecosystems for Sustainability XIV
Wei Gao; Ni-Bin Chang; Jinnian Wang, Editor(s)

© SPIE. Terms of Use
Back to Top