Consistency Measure of Multiple Classifiers for Land Cover Classification by Remote Sensing Image

Authors:
Peijun Du;Guangli Li;Wei Zhang;Xiaomei Wang;Hao Sun
Affiliations:
Department of Remote Sensing and Geographical Information Science, China University of Mining and Technology, Xuzhou City, P.R. China 221116;Department of Remote Sensing and Geographical Information Science, China University of Mining and Technology, Xuzhou City, P.R. China 221116;Department of Remote Sensing and Geographical Information Science, China University of Mining and Technology, Xuzhou City, P.R. China 221116;Department of Remote Sensing and Geographical Information Science, China University of Mining and Technology, Xuzhou City, P.R. China 221116;Department of Remote Sensing and Geographical Information Science, China University of Mining and Technology, Xuzhou City, P.R. China 221116
Venue:
MCS '09 Proceedings of the 8th International Workshop on Multiple Classifier Systems
Year:
2009

Citing 7
Cited 0

Improving Identification of Difficult Small Classes by Balancing Class Distribution

AIME '01 Proceedings of the 8th Conference on AI in Medicine in Europe: Artificial Intelligence Medicine
A study of the behavior of several methods for balancing machine learning training data

ACM SIGKDD Explorations Newsletter - Special issue on learning from imbalanced datasets
Data Mining: Practical Machine Learning Tools and Techniques, Second Edition (Morgan Kaufmann Series in Data Management Systems)

Data Mining: Practical Machine Learning Tools and Techniques, Second Edition (Morgan Kaufmann Series in Data Management Systems)
The class imbalance problem: A systematic study

Intelligent Data Analysis
SMOTE: synthetic minority over-sampling technique

Journal of Artificial Intelligence Research
Exploratory undersampling for class-imbalance learning

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
An empirical analysis of under-sampling techniques to balance a protein structural class dataset

ICONIP'06 Proceedings of the 13th international conference on Neural information processing - Volume Part III

Quantified Score

Hi-index	0.00

Visualization

Abstract

Nowadays, multiple classifier system is widely used for land cover classification by remote sensing imagery. The performance of combined classifier is closely related to the selection of member classifiers, so it is necessary to analyze the diversity and consistency of member classifiers. In our study, consistency measures are studied and experimented from three levels: general consistency measure, binary prior measure and consistency of errors, and the result shows that it is feasible to find the effective set of member classifiers by some consistency measures. In land cover classification by remotely sensed classifiers, we can select optimal member classifiers by integrating different consistency criterions.