Abstract
This paper presents a new classification approach to deal with class imbalance in TLC patterns, which is due to the huge difference between the number of normal and pathological cases as a consequence of the rarity of LSD diseases. The proposed architecture is formed by two decision stages: the first is implemented by a one-class classifier aiming at recognizing most of the normal samples; the second stage is a hierarchical classifier which deals with the remaining outliers that are expected to contain the pathological cases and a small percentage of normal samples. We have also evaluated this architecture by a forest of classifiers, using the majority voting as a rule to generate the final classification. The results that were obtained proved that this approach is able to overcome some of the difficulties associated with class imbalance.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Keir, G., Winchester, B.G., Clayton, P.: Carbohydrate-deficient Glycoprotein Syndromes: Inborn Errors of Protein Glycosylation. Ann. Clin. Biochem. 36(Pt 1), 20–36 (1999)
Durand, G., Seta, N.: Protein Glycosylation and Diseases: Blood and Urinary Oligosaccharides as Markers for Diagnosis and Therapeutic Monitoring. Clin. Chem. 46, 795–805 (2000)
Scriver, S.R., Beaudet, A.L., Sly, W.S., Valle, D.: The Metabolic Bases of Inherited Disease, vol. 3. MCGraw-Hill, New-York (2001)
Friedman, R.B., Williams, M.A., Moser, H.W., Kolodny, E.H.: Improved Thin-Layer Chromatographic Method in the Diagnosis of Mannosidosis. Clinical Chemistry 24, 1576–1577 (1978)
Kurczynski, T.W., Kendzierski, K.S., Sewell, A.C., Kuczynski, T.W.: Urinary Oligosaccharides in Pregnant or Lactating Women: Pitfall in Screening. Clin. Chem. 39, 2346–2347 (1993)
Sewell, A.C.: Urinary Oligosaccharides. Techniques in Diagnostic Human Biochemical Genetics, 219–231 (1991)
Duvdevani-Bar, S., Edelman, S.: Visual Recognition and Categorization on the Basis of Similarities to Multiple Class Prototypes. Int. J. Comput. Vision 33, 201–228 (1999)
Pekalska, E., Duin, R.P.W.: Dissimilarity Representations Allow for Building Good Classifiers. Pattern Recogn. Lett. 23, 943–956 (2002)
Goldstone, R.L., Son, J.Y.: Similarity. In: Holyoak, K., Morrison, R. (eds.) Cambridge Handbook of Thinking and Reasoning, pp. 13–36. Cambridge University Press, Cambridge (2005)
Pekalska, E., Duin, R.P.W.: The Dissimilarity Representation for Pattern Recognition - Fundations and Applications, vol. 64. World Scientific Publishing, Singapore (2005)
Lavine, B.K.: Clustering and Classification of Analytical Data. In: Meyers, R.A. (ed.) Encyclopedia of Analytical Chemistry: Instrumentation and Applications, pp. 9689–9710. John Wiley & Sons, Chichester (2000)
Kubat, M., Holte, R., Matwin, S.: Learning when Negative Examples Abound. In: European Conference on Machine Learning, pp. 146–153 (1997)
Skurichina, M., Raudys, S., Duin, R.P.W.: K-Nearest Neighbors Directed Noise Injection in Multilayer Perceptron Training. IEEE Transactions on Neural Networks 11 (2000)
Chawla, N.V., Japkowicz, N., Kolcz, A.: Editorial: Special Issue: Learning from Imbalanced Data Sets. Sigkdd Explorations 6, 1–6 (2004)
Tax, D.M.J.: One-class Classification; Concept-learning in the Absence of Counter-examples. Ph.D. thesis: Delft University of Technology (2001)
Sousa, A.V., Mendonça, A.M., Campilho, A.: Chromatographic Pattern Classification. IEEE Trans. on Biomedical Engineering (2007), doi:10.1109/TBME.2008.919852
Paclik, P., Duin, R.P.W.: Dissimilarity-based Classification of Spectra: Computational Issues. Real-Time Imaging 9, 237–244 (2003)
Paclik, P., Duin, R.P.W.: Classifying Spectral Data using Relational Representation. In: Proc. of Spectral Imaging Workshop, Graz, Austria (2003)
Sousa, A.V., Mendonça, A.M., Campilho, A.: Dissimilarity-based Classification of Chromatographic Profiles. Pattern Analysis and Applications (2007), doi:10.1007/s10044-008-0113-2
Pekalska, E., Paclik, P., Duin, R.P.W.: A Generalized Kernel Approach to Dissimilarity-based Classifcation. Journal of Machine Learning Research 2, 175–211 (2001)
Ripley, B.D.: Pattern Recognition and Neural Networks. Cambridge University Press, Cambridge (2004)
Visa, S., Ralescu, A.: Learning Imbalanced and Overlapping Classes Using Fuzzy Sets. In: Workshop on Learning from Imbalanced Datasets II, ICML, Washington DC (2003)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Sousa, A.V., Mendonça, A.M., Campilho, A. (2008). Minimizing the Imbalance Problem in Chromatographic Profile Classification with One-Class Classifiers. In: Campilho, A., Kamel, M. (eds) Image Analysis and Recognition. ICIAR 2008. Lecture Notes in Computer Science, vol 5112. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-69812-8_41
Download citation
DOI: https://doi.org/10.1007/978-3-540-69812-8_41
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-69811-1
Online ISBN: 978-3-540-69812-8
eBook Packages: Computer ScienceComputer Science (R0)