Multisource Data Classification Using A Hybrid Semi-supervised Learning Scheme
- ORNL
- University of Minnesota
In many practical situations thematic classes can not be discriminated by spectral measurements alone. Often one needs additional features such as population density, road density, wetlands, elevation, soil types, etc. which are discrete attributes. On the other hand remote sensing image features are continuous attributes. Finding a suitable statistical model and estimation of parameters is a challenging task in multisource (e.g., discrete and continuous attributes) data classification. In this paper we present a semi-supervised learning method by assuming that the samples were generated by a mixture model, where each component could be either a continuous or discrete distribution. Overall classification accuracy of the proposed method is improved by 12% in our initial experiments.
- Research Organization:
- Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
- Sponsoring Organization:
- Work for Others (WFO)
- DOE Contract Number:
- DE-AC05-00OR22725
- OSTI ID:
- 1000414
- Resource Relation:
- Conference: IEEE International Geoscience & Remote Sensing Symposium, Boston, MA, USA, 20080706, 20080711
- Country of Publication:
- United States
- Language:
- English
Similar Records
A Hybrid Classification Scheme for Mining Multisource Geospatial Data
Semi-supervised machine-learning classification of materials synthesis procedures