Journal article
Comparison of Early Stopping Criteria for Neural-Network-Based Subpixel Classification
IEEE Geoscience and Remote Sensing Letters, Vol.8(1), pp.113-117
2011
Abstract
A neural-network-based subpixel classification is one of the most commonly used approaches to address spectral mixture problems. Neural-network subpixel-classification performance is directly related to the network-training protocols used. This letter examined early stopping criteria for network training of subpixel land-cover classification. A new stopping criterion is proposed that is based on the reduction of mean squared error (MSE) for a validation data set. We obtained excellent results by stopping the network training when the reduction of MSE between training iterations became marginal. Furthermore, the neural-network learning rate can be used as a threshold value to identify the stopping point. The approach appeared to be robust for both simulation data and actual remote-sensing data. Use of this criterion outperformed two other commonly used stopping criteria: a predefined number of training iterations and a cross-validation approach.
Details
- Title
- Comparison of Early Stopping Criteria for Neural-Network-Based Subpixel Classification
- Authors
- Yang Shao (Author) - University of North Carolina, United StatesG N Taff (Author) - University of North Carolina, United StatesStephen J Walsh (Author) - University of North Carolina, United States
- Publication details
- IEEE Geoscience and Remote Sensing Letters, Vol.8(1), pp.113-117
- Publisher
- IEEE (Institute of Electrical and Electronics Engineers)
- Date published
- 2011
- DOI
- 10.1109/LGRS.2010.2052782
- ISSN
- 1545-598X
- Organisation Unit
- University of the Sunshine Coast, Queensland
- Language
- English
- Record Identifier
- 99449400602621
- Output Type
- Journal article
Metrics
539 Record Views
InCites Highlights
These are selected metrics from InCites Benchmarking & Analytics tool, related to this output
- Collaboration types
- Domestic collaboration
- Web Of Science research areas
- Engineering, Electrical & Electronic
- Geochemistry & Geophysics
- Imaging Science & Photographic Technology
- Remote Sensing
UN Sustainable Development Goals (SDGs)
This output has contributed to the advancement of the following goals:
Source: InCites