Evaluation of Neural Pattern Classifiers for a Remote Sensing Application

Fischer, Manfred M. and Gopal, Sucharita and Staufer, Petra and Steinnocher, Klaus (1995): Evaluation of Neural Pattern Classifiers for a Remote Sensing Application. Published in: Geographical Systems , Vol. 4, No. 2 (1997): pp. 195-226.

Abstract

This paper evaluates the classification accuracy of three neural network classifiers on a satellite image-based pattern classification problem. The neural network classifiers used include two types of the Multi-Layer-Perceptron (MLP) and the Radial Basis Function Network. A normal (conventional) classifier is used as a benchmark to evaluate the performance of neural network classifiers. The satellite image consists of 2,460 pixels selected from a section (270 x 360) of a Landsat-5 TM scene from the city of Vienna and its northern surroundings. In addition to evaluation of classification accuracy, the neural classifiers are analysed for generalization capability and stability of results. Best overall results (in terms of accuracy and convergence time) are provided by the MLP-1 classifier with weight elimination. It has a small number of parameters and requires no problem-specific system of initial weight values. Its in-sample classification error is 7.87% and its out-of-sample classification error is 10.24% for the problem at hand. Four classes of simulations serve to illustrate the properties of the classifier in general and the stability of the result with respect to control parameters, and on the training time, the gradient descent control term, initial parameter conditions, and different training and testing sets.

• Item Type: MPRA Paper
• Language: English
• Keywords: Neural Classifiers, Classification of Multispectral Image Data, Pixel-by-Pixel Classification, Backpropagation, Sensitivity Analysis
• Subjects: C - Mathematical and Quantitative Methods > C4 - Econometric and Statistical Methods: Special Topics > C45 - Neural Networks and Related Topics

References

Benediktsson, J.A., Swain, P.H. and Ersory, O.K. (1990): Neural network approaches versus statistical methods in classification of multisource remote sensing data, IEEE Transactions on Geoscience and Remote Sensing, vol. 28(4), pp. 540-551.

Bischof, H., Schneider, W. and Pinz, AJ. (1992): Multispectral classification of Landsat-images using neural networks, IEEE Transactions on Geoscience and Remote Sensing, vol. 30 (3), pp. 482-490.

Bridle, J.S. (1989): Probabilistic interpretation of feedforward classification network outputs, with relationships to statistical pattern recognition, in Fougelman-Soulie, F. and Herault, J. (eds.): Neuro-Computing: Algorithms, Architectures and Applications, New York: Springer.

Civco, D.L. (1993): Artificial neural networks for land-cover classification and mapping, International Journal of Geographical Information Systems, vol. 7(2), pp. 173-186.

Dreyer, P. (1993): Classification of land cover using optimized neural nets on SPOT data, Photogrammetric Engineering and Remote Sensing, vol. 59(5), pp. 617-621.

Fischer, M.M. and Gopal, S. (1994): Artificial neural networks. a new approach to modelling interregional telecommunication flows, Journal of Regional Science (in press).

Gershenfield, N.A. and Weigend, A.S. (eds.) (1993): Time Series Prediction: Forecasting the Future and Understanding the Past. Reading (MA): Addison-Wesley.

Heerrnan, P.D., and Khazenie, N. (1992): Classification of multispectral remote sensing data using a backpropagation neural network, IEEE Transactions on Geoscience and Remote Sensing, vol. 30(1), pp. 81-88.

Hepner, G.F., Logan, T., Ritter, N. and Bryant, N. (1990): Artificial neural network classification using a minimal training set: Comparison to conventional supervised classification, Photogrammetric Engineering and Remote Sensing, vol. 56 (4), pp. 469-473.

Key, J., Maslanic, A. and Schweiger, AJ. (1989): Classification of merged AVHRR and SMMR Arctic data with neural networks, Photogrammetric Engineering and Remote Sensing, vol. 55(9), pp. 1331-1338.

Lee, J., Weger, R.C., Sengupta, S.K. and Welch, R.M. (1990): A neural network approach to cloud classification, IEEE Transactions on Geoscience and Remote Sensing, vol. 28(5), pp. 846-855.

Refenes, A.N., Zapranis, A. and Francis, G. (1994): Stock performance modeling using neural networks: A comparative study with regression models, Neural Networks, vol. 7(2), pp. 375-388.

Rumelhart, D.E., Hinton, G.E. and Williams, R.J. (1986): Learning internal representation by error propagation, in Rumelhart, D.E., McClelland, J.L. and PDP Research Group (eds.): Parallel Distributed Processing: Explorations in the Microstructures of Cognition, pp. 318-362. Cambridge (MA): MIT Press.

Salu, Y. and Tilton, J. (1993): Classification of multispectral image data by the binary diamond neural network and by nonparametric, pixel-by-pixel methods, IEEE Transactions on Geoscience and Remote Sensing, vol. 31(3), pp. 606-617.

Weigend, AS, Huberman, B.A and Rumelhart, D.E. (1991): Predicting sunspots and exchange rates with connectionist networks, in Eubank, S. and Casdagli, M (eds.): Proceedings of the 1990 NATO Workshop on Nonlinear Modelling and Forecasting, pp. 1-36. Redwood City (CA): Addison-Wesley.

Weigend, AS. (1993): Book Review: John A Hertz, Anders S. Krogh and Richard G. Palmer, Introduction to the Theory of Neural Computation, Artificial Intelligence, vol. 62, pp. 93-111.

White, H. (1989): Some asymptotic results for learning in single hidden-layer feedforward network models, Journal of the American Statistical Association, vol. 84, pp. 1003-1113.

Wilkinson, G.G., Fierens, F. and Kanellopoulos, I. (1994): Integration of neural and statistical approaches in spatial data classification, Geographical Systems - The International Journal of Geographical Information, Analysis, Theory and Decision (in press).