Prediction of cancer using customised fuzzy rough machine learning approaches

Chinnaswamy Arunkumar; Srinivasan Ramakrishnan

Prediction of cancer using customised fuzzy rough machine learning approaches

View Fulltext

Author(s): Chinnaswamy Arunkumar¹ and Srinivasan Ramakrishnan²
- Affiliations: 1: Department of Computer Science and Engineering , Amrita School of Engineering , Coimbatore, 641112, Amrita Vishwa Vidyapeetham , India ;
  2: Department of Information Technology , Dr. Mahalingam College of Engineering and Technology , Pollachi, 642003 , India
Source: Volume 6, Issue 1, February 2019, p. 13 – 18
DOI: 10.1049/htl.2018.5055 , Online ISSN 2053-3713

This is an open access article published by the IET under the Creative Commons Attribution-NonCommercial-NoDerivs License (http://creativecommons.org/licenses/by-nc-nd/3.0/)

Received 19/07/2018, Accepted 09/10/2018, Published 24/12/2018

This Letter proposes a customised approach for attribute selection applied to the fuzzy rough quick reduct algorithm. The unbalanced data is balanced using synthetic minority oversampling technique. The huge dimensionality of the cancer data is reduced using a correlation-based filter. The dimensionality reduced balanced attribute gene subset is used to compute the final minimal reduct set using a customised fuzzy triangular norm operator on the fuzzy rough quick reduct algorithm. The customised fuzzy triangular norm operator is used with a Lukasiewicz fuzzy implicator to compute the fuzzy approximation. The customised operator selects the least number of informative feature genes from the dimensionality reduced datasets. Classification accuracy using leave-one-out cross validation of 94.85, 76.54, 98.11, and 99.13% is obtained using a customised function for Lukasiewicz triangular norm operator on leukemia, central nervous system, lung, and ovarian datasets, respectively. Performance analysis of the conventional fuzzy rough quick reduct and the proposed method are performed using parameters such as classification accuracy, precision, recall, F-measure, scatter plots, receiver operating characteristic area, McNemar test, chi-squared test, Matthew's correlation coefficient and false discovery rate that are used to prove that the proposed approach performs better than available methods in the literature.

References

1. 1)
  - 2. Hannah Inbarani, H., Azar, A.T., Jothi, G.: ‘Supervised hybrid feature selection based on PSO and rough sets for medical diagnosis’, Comput. Methods Programs Biomed., 2014, 113, (1), pp. 175–185 (doi: 10.1016/j.cmpb.2013.10.007).
2. 2)
  - 16. Anarki, J.R., Eftekhari, M.: ‘Rough set based feature selection – a review’. Proc. 5th Conf. on Information and Knowledge Technology, Shiraz, Iran, 2013, pp. 301–306, doi: 10.1109/IKT.2013.6620083.
3. 3)
  - 8. Wang, A., An, N., Chen, G., et al: ‘Incremental wrapper based gene selection with Markov blanket’. Proc. IEEE Int. Conf. on Bioinformatics and Biomedicine (BIBM), Belfast, UK, 2014, pp. 74–79, doi: 10.1109/BIBM.2014.6999251.
4. 4)
  - 3. Aziz, R., Verma, C.K., Srivastava, N.: ‘A fuzzy based feature selection from independent component subspace for machine learning classification of microarray data’, Genom. Data, 2016, 8, pp. 4–15 (doi: 10.1016/j.gdata.2016.02.012).
5. 5)
  - 1. Bolon Canedo, V., Sanchez Marono, N., Alonso-Betanzos, A.: ‘Distributed feature selection, an application to microarray data classification’, Appl. Soft Comput., 2015, 30, pp. 136–150 (doi: 10.1016/j.asoc.2015.01.035).
6. 6)
  - 10. Zhang, X., Mei, C., Chen, D., et al: ‘A fuzzy rough set-based feature selection method using representative instances’, Knowl. Based Syst., 2018, 151, pp. 1–14 (doi: 10.1016/j.knosys.2018.04.016).
7. 7)
  - 5. Jensen, R., Parthalain, N.M.: ‘Towards scalable fuzzy–rough feature selection’, Inf. Sci., 2015, 323, pp. 1–15 (doi: 10.1016/j.ins.2015.06.025).
8. 8)
  - 19. Bhatt, R.B., Gopal, M.: ‘On fuzzy-rough sets approach to feature selection’, Pattern Recognit. Lett., 2005, 26, (7), pp. 965–975 (doi: 10.1016/j.patrec.2004.09.044).
9. 9)
  - 6. Jain, I., Jain, V.K., Jain, R.: ‘Correlation feature selection based improved-binary particle swarm optimization for gene selection and cancer classification’, Appl. Soft Comput., 2018, 62, pp. 203–215 (doi: 10.1016/j.asoc.2017.09.038).
10. 10)
  - 24. Boughorbel, S., Jarray, F., El-Anbari, M.: ‘Optimal classifier for imbalanced data using Matthews Correlation Coefficient metric’, PLoS ONE, 2017, 12, (6), pp. 1–17 (doi: 10.1371/journal.pone.0177678).
11. 11)
  - 23. http://datam.i2r.a-star.edu.sg/datasets/krbd, accessed 10 December 2011.
12. 12)
  - 12. Arunkumar, C., Ramakrishnan, S.: ‘A hybrid approach to feature selection using correlation coefficient and fuzzy rough quick reduct algorithm applied to cancer microarray data’. Proc. 10th Int. Conf. on Intelligent Systems and Control (ISCO 2016), Coimbatore, India, 2016, pp. 414–419, doi: 10.1109/ISCO.2016.7726921.
13. 13)
  - 11. Shahbeig, S., Rahideh, A., Helfroush, M.S., et al: ‘Gene selection from large-scale gene expression data based on fuzzy interactive multi-objective binary optimization for medical diagnosis’, Biocybernetics Biomed. Eng., 2018, 38, pp. 313–328 (doi: 10.1016/j.bbe.2018.02.002).
14. 14)
  - 15. Chawla, N., Kevin Bowyer, W., Lawrence Hall, O., et al: ‘SMOTE: synthetic minority over-sampling technique’, J. Artif. Intell. Res., 2002, 16, (1), pp. 321–357 (doi: 10.1613/jair.953).
15. 15)
  - 13. Arunkumar, C., Ramakrishnan, S.: ‘Modified fuzzy rough quick reduct algorithm for feature selection in cancer microarray data’, Asian J. Inf. Technol., 2016, 15, pp. 199–210, doi: 10.3923/ajit.2016.199.210.
16. 16)
  - 7. Maji, P., Garai, P.: ‘On fuzzy-rough attribute selection: criteria of max-dependency, max-relevance, min-redundancy, and max-significance’, Appl. Soft Comput., 2013, 13, pp. 3968–3980 (doi: 10.1016/j.asoc.2012.09.006).
17. 17)
  - 17. Radzikowska, A.M., Etieniie Kerre, E.: ‘An algebraic characterisation of fuzzy rough sets’. IEEE Int. Conf. on Fuzzy Systems, Budapest, Hungary, 2004, doi: 10.1109/FUZZY.2004.1375698.
18. 18)
  - 4. Kar, S., Sharma, K.D., Maitra, M.: ‘Gene selection from microarray gene expression data for classification of cancer subgroups employing PSO and adaptive K-nearest neighborhood technique’, Expert Syst. Appl., 2015, 42, (1), pp. 612–627 (doi: 10.1016/j.eswa.2014.08.014).
19. 19)
  - 18. Anarki, J.R., Eftekhari, M.: ‘Improving fuzzy-rough quick reduct for feature selection’. Proc. 19th Iranian Conf. on Electrical Engineering, Tehran, Iran, 2011, pp. 1–6.
20. 20)
  - 21. Apolloni, J., Leguizamon, G., Alba, E.: ‘Two hybrid wrapper-filter feature selection algorithms applied to high-dimensional microarray experiments’, Appl. Soft Comput., 2016, 38, pp. 922–932 (doi: 10.1016/j.asoc.2015.10.037).
21. 21)
  - 9. D'eer, L., Verbiest, N., Cornelis, C., et al: ‘A comprehensive study of implicator–conjunctor-based and noise-tolerant fuzzy rough sets: definitions, properties and robustness analysis’, Fuzzy Sets Syst., 2015, 275, pp. 1–38 (doi: 10.1016/j.fss.2014.11.018).
22. 22)
  - 20. Bhatt, R.B., Gopal, M.: ‘On the compact computational domain of fuzzy-rough sets’, Pattern Recognit. Lett., 2005, 26, (11), pp. 1632–1640 (doi: 10.1016/j.patrec.2005.01.006).
23. 23)
  - 22. Pang, S., Havukkala, I., Hu, Y., et al: ‘Classification consistency analysis for bootstrapping gene selection’, Neural Comput. Appl., 2007, 16, (6), pp. 527–539 (doi: 10.1007/s00521-007-0110-1).
24. 24)
  - 14. Arunkumar, C., Ramakrishnan, S.: ‘Attribute selection using fuzzy roughset based customized similarity measure for lung cancer microarray gene expression data’, Future Comput. Inf. J., 2018, 3, (1), pp. 131–142 (doi: 10.1016/j.fcij.2018.02.002).

Login

Not registered yet?

Share

Tools

Login to add to favourites

Key

Prediction of cancer using customised fuzzy rough machine learning approaches

References

Related content