Hostname: page-component-cd9895bd7-gvvz8 Total loading time: 0 Render date: 2024-12-27T09:18:06.106Z Has data issue: false hasContentIssue false
  • English
  • Français

Handling class overlapping to detect noisy instances in classification

Published online by Cambridge University Press:  10 July 2018

Shivani Gupta  and
Atul Gupta
Shivani Gupta
Affiliation:
Indian Institute of Information Technology, Design and Manufacturing Jabalpur, Jabalpur, Madhya Pradesh 482001, India e-mail: [email protected], [email protected]
Atul Gupta
Affiliation:
Indian Institute of Information Technology, Design and Manufacturing Jabalpur, Jabalpur, Madhya Pradesh 482001, India e-mail: [email protected], [email protected]
Get access Rights & Permissions [Opens in a new window]

Abstract

Automated machine classification will play a vital role in the machine learning and data mining. It is probable that each classifier will work well on some data sets and not so well in others, increasing the evaluation significance. The performance of the learning models will intensely rely on upon the characteristics of the data sets. The previous outcomes recommend that overlapping between classes and the presence of noise has the most grounded impact on the performance of learning algorithm. The class overlap problem is a critical problem in which data samples appear as valid instances of more than one class which may be responsible for the presence of noise in data sets.

The objective of this paper is to comprehend better the data used as a part of machine learning problems so as to learn issues and to analyze the instances that are profoundly covered by utilizing new proposed overlap measures. The proposed overlap measures are Nearest Enemy Ratio, SubConcept Ratio, Likelihood Ratio and Soft Margin Ratio. To perform this experiment, we have created 438 binary classification data sets from real-world problems and computed the value of 12 data complexity metrics to find highly overlapped data sets. After that we apply measures to identify the overlapped instances and four noise filters to find the noisy instances. From results, we found that 60–80% overlapped instances are noisy instances in data sets by using four noise filters. We found that class overlap is a principal contributor to introduce class noise in data sets.

Type
Research Article
Information
The Knowledge Engineering Review , Volume 33 , 2018 , e8
Copyright
© Cambridge University Press, 2018 

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Alcal-Fdez, J., Fernndez, A., Luengo, J., Derrac, J., Garca, S., Snchez, L. & Herrera, F. 2011. Keel data-mining software tool: data set repository, integration of algorithms and experimental analysis framework. Journal of Multiple-Valued Logic and Soft Computing 17, 255–287.Google Scholar
Baumgartner, R. & Somorjai, R. L. 2006. Data complexity assessment in undersampled classification of high-dimensional biomedical data. Pattern Recognition Letters 27(12), 1383–1389.Google Scholar
Basu, M. & Ho, T. K. (eds) 2006. Data Complexity in Pattern Recognition. Springer Science and Business Media.Google Scholar
Bernad-Mansilla, E. & Ho, T. K. 2005. Domain of competence of XCS classifier system in complexity measurement space. IEEE Transactions on Evolutionary Computation 9(1), 82–104.Google Scholar
Brodley, C. E. & Friedl, M. A. 1999. Identifying mislabeled training data. Journal of Artificial Intelligence Research 11, 131–167.Google Scholar
Cortes, C. & Vapnik, V. 1995. Support-vector networks. Machine Learning 20(3), 273–297.Google Scholar
Cover, T. & Hart, P. 1967. Nearest neighbor pattern classification. IEEE Transactions on Information Theory 13(1), 21–27.Google Scholar
Derrac, J., Triguero, I., Garca, S. & Herrera, F. 2012. Integrating instance selection, instance weighting, and feature weighting for nearest neighbor classifiers by coevolutionary algorithms. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics) 42(5), 1383–1397.Google Scholar
Devijver, P. A. 1986. On the editing rate of the multiedit algorithm. Pattern Recognition Letters 4(1), 9–12.Google Scholar
Domingos, P. & Pazzani, M. 1997. On the optimality of the simple Bayesian classifier under zero-one loss. Machine learning 29(2–3), 103–130.CrossRefGoogle Scholar
Gamberger, D., Lavrac, N. & Groselj, C. 1999. Experiments with noise filtering in a medical domain. In 16th International Conference on Machine Learning (ICML99), 143–151.Google Scholar
Hattori, K. & Takahashi, M. 2000. A new edited k-nearest neighbor rule in the pattern classification problem. Pattern Recognition 33(3), 521–528.Google Scholar
He, H. & Garcia, E. A. 2009. Learning from imbalanced data. IEEE Transactions on Knowledge and Data Engineering 21(9), 1263–1284.Google Scholar
Jain, A. K., Duin, R. P. W. & Mao, J. 2000. Statistical pattern recognition: a review. IEEE Transactions on Pattern Analysis and Machine Intelligence 22(1), 4–37.CrossRefGoogle Scholar
Jeatrakul, P., Wong, K. W. & Fung, C. C. 2010. Data cleaning for classification using misclassification analysis. Journal of Advanced Computational Intelligence and Intelligent Informatics 14(3), 297–302.Google Scholar
Khoshgoftaar, T. M., Zhong, S. & Joshi, V. 2005. Enhancing software quality estimation using ensemble-classifier based noise filtering. Intelligent Data Analysis 9(1), 3–27.Google Scholar
Kretzschmar, R., Karayiannis, N. B. & Eggimann, F. 2003. Handling class overlap with variance-controlled neural networks. In Proceedings of the International Joint Conference on Neural Networks, 2003, 1, 517–522. IEEE.CrossRefGoogle Scholar
Luengo, J. & Herrera, F. 2012. Shared domains of competence of approximate learning models using measures of separability of classes. Information Sciences 185(1), 43–65.Google Scholar
Mollineda, R. A., Snchez, J. S. & Sotoca, J. M. 2005. Data characterization for effective prototype selection. In Iberian Conference on Pattern Recognition and Image Analysis, 27–34. Springer.Google Scholar
Orriols-Puig, A., Macia, N. & Ho, T. K. 2010. Documentation for the Data Complexity Library in C++ 196, Universitat Ramon Llull, La Salle.Google Scholar
Quinlan, J. R. 2014. C4. 5: Programs for Machine Learning. Elsevier.Google Scholar
Salvador, G. & Herrera, F. 2008. An extension on statistical comparisons of classifiers over multiple data setsi for all pairwise comparisons, Journal Machine Learning Research, 9, 2677–2694. Google Scholar
Snchez, J. S., Barandela, R., Marqus, A. I., Alejo, R. & Badenas, J. 2003. Analysis of new techniques to obtain quality training sets. Pattern Recognition Letters 24(7), 1015–1022.Google Scholar
Snchez, J. S., Mollineda, R. A. & Sotoca, J. M. 2007. An analysis of how training data complexity affects the nearest neighbor classifiers. Pattern Analysis and Applications 10(3), 189–201.CrossRefGoogle Scholar
Snchez, J. S., Pla, F. & Ferri, F. J. 1997. Prototype selection for the nearest neighbour rule through proximity graphs. Pattern Recognition Letters 18(6), 507–513.Google Scholar
Tomek, I. 1976. An experiment with the edited nearest-neighbor rule. IEEE Transactions on Systems, Man, and Cybernetics 6(6), 448–452.Google Scholar
Verbaeten, S. & Van Assche, A. 2003. Ensemble methods for noise elimination in classification problems. In 4th International Workshop on Multiple Classifier Systems (MCS 2003), LNCS 2709, 317–325. Springer.Google Scholar
Wilson, D. L. 1972. Asymptotic properties of nearest neighbor rules using edited data. IEEE Transactions on Systems, Man, and Cybernetics 2(3), 408–421.Google Scholar
Zhu, X. & Wu, X. 2004. Class noise vs. attribute noise: a quantitative study. Artificial Intelligence Review 22(3), 177–210.Google Scholar