Sage Journals: Discover world-class research

Abstract

Attribute and class noises are the two important sources of Corruptions (noise) contained in real-world datasets which may deteriorate data interpretation and accuracy. Class noise has potentially serious negative impacts compared to attribute noise, however, the existing major class noise detection methods are not able to address this problem efficiently. To overcome issues related to detection and the elimination of class noise, we suggest a new noise filtering approach able to identify and remove class noise, called Multi-Iterative Partitioning Class Noise Filter (MIPCNF). Since there is no single filter that consistently outperforms its counterparts in all database types and in different levels of noise, our approach relies on an algorithm in which several rounds of class noise detection are performed on different partitions of the data using several classifiers. Therefore, we use different filtering strategies: iterative noise filter, partitioning filter and ensemble-based filter. The experimental results, on 14 real-world datasets, and statistical analysis, show that our method is not only overcoming the higher noise but also over-performing latest class noise detection and elimination strategies in different levels of noise.

Keywords

Class noise Noise Detection Noise Elimination Partitioning Filter Large Data

Get full access to this article

View all access options for this article.

References

S.B.

Kotsiantis ,

Zaharakis and

Pintelas , Supervised machine learning: A review of classification techniques, Emerging artificial intelligence applications in computer engineering 160 (2007), 3–24.

E.M.

Knorr , T.Ng. Raymond and

Tucakov , Distance-based outliers: Algorithms and applications, The International Journal on Very Large Data Bases VLDB 8(3-4) (2000), 237–253.

Ramaswamy ,

Rastogi and

Shim , Efficient algorithms for mining outliers from large data sets, ACM Sigmod Record 29(2) (2000), 427–438.

M.M.

Breunig , H.P.Kriegel,

R.T.

Ng and

Sander , LOF: Identifying density-based local outliers, In ACM Sigmod Record 29(2) (2000), 93–104.

Thongkam ,

Xu ,

Zhang and

Huang , Support vector machine for outlier detection in breast cancer survivability prediction, Advanced Web and Network Technologies, and Applications, Springer Berlin Heidelberg 4977(1) (2008), 99–109.

Scholkop ,

Williamson ,

Smola ,

Shawe-Taylor and

Platt , Support vector method for novelty detection, Advances in Neural Information Processing Systems 12(1) (1999), 582–588.

Hayton ,

Scholkopf ,

Tarassenko and

Anuzis , Support vector novelty detection applied to jet engine vibration spectra, Advances in Neural Information Processing Systems 13(4) (2000), 946–952.

Scholkopf ,

J.C.

Platt ,

J.C.

Shawe-Taylor ,

A.J.

Smola and

R.C.

Williamson , Estimating the support of a high-dimensional distribution, Neural Comput 13(7) (2001), 1443–1471.

Hoffmann , Kernel PCA for novelty detection, Pattern Recognit 40(3) (2007), 863–874.

10.

Chandola ,

Banerjee and

Kumar , Anomaly detection: A survey, ACM Comput Surv 41(3) (2009), 15:1–15:58.

11.

J.W.

Sun ,

F.Y.

Zhao ,

C.J.

Wang and

S.F.

Chen , Identifying and correcting mislabeled training instances, Future generation communication and networking, IEEE 1(1) (2007), 244–250.

12.

Barandela and

Gasca , Decontamination of training samples for supervised pattern recognition methods, Joint IAPR International Workshops on Statistical Techniques in Pattern Recognition (SPR) and Structural and Syntactic Pattern Recognition (SSPR), Springer, 1876, 2000, pp. 621–630.

13.

Jeatrakul ,

K.W.

Wong and

C.C.

Fung , Data cleaning for classification using misclassification analysis, Journal of Advanced Computational Intelligence and Intelligent Informatics 14(3) (2010), 297–302.

14.

Zhu ,

Wu and

Chen , Eliminating class noise in large datasets, Proceedings of the International Conference on Machine Learning 3(1) (2003), 920–927.

15.

Frenay and

Verleysen , Classification in the presence of label noise: A survey, transactions on neural networks and learning systems, 25(5) (2014), 845–869.

16.

Zhu and

Wu , Class noise vs. attribute noise: A quantitative study, Artif Intell Rev 22(3) (2004), 177–210.

17.

T.M.

Khoshgoftaar and

Rebours , Generating multiple noise elimination filters with the ensemble-partitioning filter, Proceedings of the International Conference on Information Reuse and Integration, 2004, pp. 369–375.

18.

Sáez ,

Galar ,

Luengo and

Herrera , Analyzing the presence of noise in multi-class problems: Alleviating its influence with the one-vs-one decomposition, Knowledge and Information Systems 38(1) (2014), 179–206.

19.

Zhu ,

Wu and

Chen , Bridging local and global data cleansing: Identifying class noise in large distributed data datasets, Data Mining and Knowledge Discovery 12(2-3) (2006), 275–308.

20.

T.M.

Khoshgoftaar and

Rebours , Improving software quality prediction by noise filtering techniques, Computer Science and Technology 22(3) (2007), 387–396.

21.

T.M.

Khoshgoftaar and

Rebours , Noise elimination with partitioning filter for software quality estimation, International Journal of Computer Applications in Technology 27(4) (2006), 246–258.

22.

R.J.

Hickey , Noise modelling and evaluating learning from examples, Artif Intell 82(1-2) (1996), 157–179.

23.

R.A.

Servedio , Smooth boosting and learning with malicious noise, Journal of Machine Learning Research 4(3) (2003), 633–648.

24.

Biggio ,

Nelson and

Laskov , Support vector machines under adversarial label noise, Proceedings of Asian Conference on Machine Learning 20(1) (2011), 97–112.

25.

Hu ,

Wang and

Gao , Joint state and fault estimation for time-varying nonlinear systems with randomly occurring faults and sensor saturations, Automatica 97 (2018), 150–160.

26.

Bi and

D.R.

Jeske , The efficiency of logistic regression compared to normal discriminant analysis under class- conditional classification noise, Jornal of Multivariate Anal 101(7) (2010), 1622–1637.

27.

Sánchez ,

Pla and

Ferri , Prototype selection for the nearest neighbour rule through proximity graphs, Pattern Recognit Lett 18(6) (1997), 507–513.

28.

D.R.

Wilson and

T.R.

Martinez , Reduction techniques for instance based learning algorithms, Mach Learn 38(3) (2000), 257–286.

29.

Okamoto and

Nobuhiro , An average-case analysis of the k-nearest neighbor classifier for noisy domains, Proceedings of the Int Joint Conf Artif Intell 1(1) (1997), 238–243.

30.

R.A.

McDonald ,

D.J.

Hand and

I.A.

Eckley , An empirical comparison of three boosting algorithms on real data sets with artificial class noise, Multiple Classifier Systems, Springer (2003), 35–44.

31.

Melville ,

Shah ,

Mihalkova and

R.J.

Mooney , Experiments on ensembles with missing and noisy data, Multiple Classifier Systems, Springer (2004), 293–302.

32.

Jiang , Some theoretical aspects of boosting in the presence of noisy data, Proceedings of the Eighteenth International Conference on Machine Learning, 2001.

33.

Abellan and

A.R.

Masegosa , Bagging decision trees on data sets with classification noise, Foundations of Information and Knowledge Systems, Springer (2010), 248–265.

34.

J.R.

Quinlan , Induction of decision trees, Mach Learn 1(1) (1986), 81–106.

35.

C.E.

Brodley and

M.A.

Friedl , Identifying mislabeled training data, J Artif Intell Res 11(1) (1999), 131–167.

36.

G.L.

Libralon ,

A.C.P.D.L.

Carvalho and

A.C.

Lorena , Preprocessing for noise detection in gene expression classification data, J Brazil Comput Soc 15(1) (2009), 3–11.

37.

Nematzadeh ,

Ibrahim and

Selamat , Class Noise Detection Using Classification Filtering Algorithms, Foundations of Information and Knowledge SystemsProc. International Conference on Computational Intelligence in Information System, Springer, 2016, pp. 121–130.

38.

J.A.

Sáez ,

Krawczyk and

Woźniak , On the influence of class noise in medical data classification: Treatment using noise filtering methods, Applied Artificial Intelligence 30(6) (2016), 590–609.

39.

de Jesús Martínez Felip ,

Manuel Felipe Riverón ,

Alberto Martínez Castro and

Pogrebnyak , Noisy image block matching based on dissimilarity measure in discrete cosine transform domain, Journal of Intelligent & Fuzzy Systems 36(4) (2019), 3169–3176.

40.

Anagha ,

Balasundaram and

Meena , On robust twin support vector regression in primal using squared pinball loss, Journal of Intelligent & Fuzzy Systems 35(5) (2018), 5231–5239.

41.

Zeng and

T.R.

Martinez , Using decision trees and soft labeling to filter mislabeled data, Journal of Intelligent Systems 17(4) (2011), 331–354.

42.

Rebbapragada ,

C.E.

Brodley ,

Sulla-Menashe and

M.A.

Friedl , Active label correction, Proceedings of the IEEE 12th International Conference on Data Mining (ICDM), 2012, pp. 1080–1085.

43.

A.L.

Miranda ,

L.P.

Garcia ,

A.C.

Carvalho and

A.C.

Lorena , Use of classification algorithms in noise detection and elimination, Hybrid Artificial Intelligence Systems, Springer, 2009, pp. 417–424.

44.

Cuendet ,

Hakkani-Tur and

Shriberg , Automatic labeling inconsistencies detection and correction for sentence unit segmentation in conversational speech, Machine Learning for Multimodal Interaction, Springer-Verlag, 2007, pp. 144–155.

45.

Gamberger ,

Boskovic ,

Lavrac and

Groselj , Experiments with noise filtering in a medical domain, ICML (1999), 143–151.

46.

J.A.

Saez ,

Galar ,

Luengo and

Herrera , INFFC: An iterative class noise filter based on the fusion of classifiers with noise sensitivity control, Information Fusion 27(1) (2016), 19–32.

47.

Devijver , On the editing rate of the MULTIEDIT algorithm, Pattern Recogn Lett 4(1) (1986), 9–12.

48.

Sanchez ,

Barandela ,

Marques ,

Alejo and

Badenas , Analysis of new techniques to obtain quality training sets, Pattern Recogn Lett 24(1) (2003), 1015–1022.

49.

Wilson , Asymptotic properties of nearest neighbor rules using edited data, IEEE Trans Syst Man Cybernet 2(3) (1972), 408–421.

50.

Tomek , An experiment with the edited nearest-neighbor rule, IEEE Trans Syst Man Cybernet 6(6) (1976), 448–452.

51.

Alcalá-Fdez ,

Fernández ,

Luengo ,

Derrac ,

Garciá ,

Sánchez and

Herrera , Keel data-mining software tool: Data set repository, integration of algorithms and experimental analysis framework, Journal of Multiple-Valued Logic and Soft Computing 17(1) (2011), 2–3.

52.

Lichman , UCI machine learning repository, IEEE Trans Syst Man Cybernet (2013).

53.

W.L.

Zhang ,

Guo ,

Shen ,

D.G.

Li and

J.K.

Li , An energy-efficient algorithm for multi-site application partitioning in MCC, Sustainable Computing: Informatics and Systems 18 (2018), 45–53.

54.

Natarajan ,

Vairavasundaram and

Ravi , Optimized fuzzy-based group recommendation with parallel computation, Journal of Intelligent & Fuzzy Systems 36(5) (2019), 4189–4199.

55.

M.F.A.

Hady and

Schwenker , Combining committee-based semi-supervised learning and active learning, Journal of Computer Science and Technology, Springer 25(4) (2010), 681–698.

56.

Treerattanapitak and

Jaruskulchai , Possibilistic exponential fuzzy clustering, Journal of Computer Science and Technology, Springer Science & Business Media 28(2) (2013), 311–321.

57.

Zhao ,

Li ,

Liu and

Fan , A multi-objective interval valued fuzzy clustering algorithm with spatial information for noisy image segmentation, Journal of Intelligent & Fuzzy Systems 36(6) (2019), 5333–5344.

MIPCNF: Multi-iterative partitioning class noise filter

Abstract

Keywords

Get full access to this article

References