Garson's method trumps Olden's method in every case - How to determine relative importance of input-variables in nonlinear regression with artificial neural networks

Ecological Modelling

Volumn 309-310, Issue , 2015, Pages 60-63

  Fischer, Andreas ^a  

^a UNIVERSITY OF HEIDELBERG   (Germany)

Author keywords

Connection weight method; Garson's method; Method comparison; Nonlinear regression; Relative importance

Indexed keywords

NEURAL NETWORKS;

CONNECTION WEIGHTS; GARSON'S METHOD; METHOD COMPARISON; NON-LINEAR REGRESSION; RELATIVE IMPORTANCE;

REGRESSION ANALYSIS;

ARTIFICIAL NEURAL NETWORK; COMPARATIVE STUDY; ECOLOGICAL MODELING; NONLINEARITY; REGRESSION ANALYSIS;

EID: 84958170265     PISSN: 03043800     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.ecolmodel.2015.04.015     Document Type: Article

References (21)

1. Backhaus K., Erichson B., Plinke W., Weiber R. Multivariate Analysemethoden [Multivariate Data Analysis] 2006, Springer, Berlin.
2. Bishop C.M. Neural Networks for Pattern Recognition 1995, Clarendon Press, Oxford.
3. Cai J., Zheng P., Qaisar M., Luo T. Prediction and quantifying parameter importance in simultaneous anaerobic sulfide and nitrate removal process using artificial neural network. Environ. Sci. Pollut. Res. 2014, 1-8.
4. Fischer A. Nonlinear regression with neural networks: how to determine each input-variable's contribution in case of nonlinear and interactive effects. IEEE Trans. Neural Netw. Learn. Syst. 2015, (under review).
5. Fischer A. How to determine relevance of input-units in a Multi-Layer Perceptron (using the nnet package in R) 2014, Accessed March 12th 2015, URL: http://complexproblemsolver.blog.de/2014/11/29/how-to-determine-relevance-of-input-units-a-multi-layer-perceptron-using-the-nnet-package-r-19775643/.
6. Garson G.D. Interpreting neural-network connection weights. AI Expert 1991, 6(4):46-51.
7. Gevrey M., Dimopoulus I., Lek S. A comparison of methods to study the contribution of variables in artificial neural network models. Ecol. Model. 2003, 160:249-264.
8. Guo Y.M., Liu Y.G., Zeng G.M., Hu X.J., Xu W.H., Liu Y.Q., Liu S.M., Sun H.S., Ye J., Huang H.J. An integrated treatment of domestic wastewater using sequencing batch biofilm reactor combined with vertical flow constructed wetland and its artificial neural network simulation study. Ecol. Eng. 2014, 64:18-26.
9. Hornik K., Stinchcombe M., White H. Multilayer feedforward networks are universal approximators. Neural Netw. 1989, 2(5):359-366.
10. Ibrahim O.M. A comparison of methods for assessing the relative importance of input variables in artificial neural networks. J. Appl. Sci. Res. 2013, 9(11):5692-5700.
11. Kemp S.J., Zaradic P., Hansen F. An approach for determining relative input parameter importance and significance in artificial neural networks. Ecol. Model. 2007, 204:326-334.
12. Lek S., Delacoste M., Baran P., Dimopoulos I., Lauga J., Aulagnier S. Application of neural networks to modelling nonlinear relationships in ecology. Ecol. Model. 1996, 90:39-52.
13. Lek S., Guégan J.F. Artificial neural networks as a tool in ecological modelling, an introduction. Ecol. Model. 1999, 120(2):65-73.
14. Olden J.D., Joy M.K., Death R.G. An accurate comparison of methods for quantifying variable importance in artificial neural networks using simulated data. Ecol. Model. 2004, 178(3):389-397.
15. Olden J.D., Vander Zanden M.J., Johnson P.T. Assessing ecosystem vulnerability to invasive rusty crayfish (Orconectes rusticus). Ecol. Appl. 2011, 21(7):2587-2599.
16. Paliwal M., Kumar U.A. Assessing the contribution of variables in feed forward neural network. Appl. Soft Comput. 2011, 11:3690-3696.
17. Rey G.D., Fischer A. The expertise reversal effect concerning instructional explanations. Instr. Sci. 2013, 41:407-429.
18. Rey G.D., Wender K.F. Neuronale Netze. Eine Einführung in die Grundlagen, Anwendungen und Datenauswertung [Neural Networks. An Introduction in Basics, Applications and Data Analysis] 2008, Huber, Bern.
19. Rumelhart D.E., Durbin R., Golden R., Chauvin Y. Backpropagation: the basic theory. (Hrsg.), Backpropagation: Theory, Architectures, and Applications 1995, 1-34. Lawrence Erlbaum Associates, Hillsdale, NJ. Y. Chauvin, D.E. Rumelhart (Eds.).
20. Torgo L. Data Mining with R: Learning with Case Studies 2010, Chapman & Hall/CRC.
21. Venables W.N., Ripley B.D. Modern Applied Statistics with S 2002, Springer, New York. 4th edition.