Classification and integration of multitype data

Jon Atli Benediktsson*, Johannes R. Sveinsson, Kolbeinn Arnason

*Corresponding author for this work

Research output: Contribution to conferencePaperpeer-review

1 Citation (Scopus)

Abstract

Neural network approaches and statistical classification methods based on consensus from several data sources are considered with respect to classification and integration of multitype data. The consensus theoretic methods need weighting mechanisms to control the influence of each data source in the combined classification. The weights are optimized in order to improve the combined classification accuracies. A non-linear method which utilizes a neural network is used and trained on a feature reduced input set. This non-linear method gives excellent results in experiments along with other neural network models.

Original languageEnglish
Pages177-179
Number of pages3
Publication statusPublished - 1998
EventProceedings of the 1998 IEEE International Geoscience and Remote Sensing Symposium, IGARSS. Part 1 (of 5) - Seattle, WA, USA
Duration: 6 Jul 199810 Jul 1998

Conference

ConferenceProceedings of the 1998 IEEE International Geoscience and Remote Sensing Symposium, IGARSS. Part 1 (of 5)
CitySeattle, WA, USA
Period6/07/9810/07/98

Fingerprint

Dive into the research topics of 'Classification and integration of multitype data'. Together they form a unique fingerprint.

Cite this