The use of entropy to measure structural diversity

@article{Masisi2008TheUO,
  title={The use of entropy to measure structural diversity},
  author={Lesedi Melton Masisi and Fulufhelo Vincent Nelwamondo and Tshilidzi Marwala},
  journal={2008 IEEE International Conference on Computational Cybernetics},
  year={2008},
  pages={41-45}
}
In this paper entropy based methods are compared and used to measure structural diversity of an ensemble of 21 classifiers. This measure is mostly applied in ecology, whereby species counts are used as a measure of diversity. The measures used were Shannon entropy, Simpsons and the Berger Parker diversity indexes. As the diversity indexes increased so did the accuracy of the ensemble. An ensemble dominated by classifiers with the same structure produced poor accuracy. Uncertainty rule from… CONTINUE READING
Highly Cited
This paper has 37 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 16 extracted citations

Diversity study of multi-objective genetic algorithm based on Shannon entropy

2014 Sixth World Congress on Nature and Biologically Inspired Computing (NaBIC 2014) • 2014
View 1 Excerpt
Highly Influenced

Statistics of hyperspectral data/image analysis: Entropy

2018 Colour and Visual Computing Symposium (CVCS) • 2018
View 1 Excerpt

Artificial Intelligence Techniques for Rational Decision Making

Advanced Information and Knowledge Processing • 2014

Temporal Illness Prediction using a Bayesian Model

Esben Pilgaard Møller, Thomas Kobber Panum, Bjarke Hesthaven Søndergaard
2014
View 2 Excerpts
Method Support

References

Publications referenced by this paper.
Showing 1-10 of 17 references

Information Theory Primer. s.l

T. D. Schneider
www.lecb.ncifcrf.gov/~toms, • 2007
View 4 Excerpts
Highly Influenced

Why the measurement of species diversity requires prior value judgements

S. Baumgartner
Department of economics, University of Heidelberg . Germany : s.n., • 2006
View 3 Excerpts
Highly Influenced

Dynamic Protein Classification: Adaptive Models Based on Incremental Learning Strategies. School of Electrical and Information Engineering, The University of the Witwatersrand, Theses

S. Mohamed
2006
View 1 Excerpt

Species Diversity

I. Harrison, M. Laverty, E. Sterling
s.l. : Connexions Project, • 2004
View 2 Excerpts

An experiment study on diversity for bagging and boosting with linear classifiers

L. I. Kuncheva, M. Duin, R.P.W. Skurichina
Information Fusion 3. • 2002
View 1 Excerpt