Prediction of Breast Cancer through Tolerance-based Intuitionistic Fuzzy-rough Set Feature Selection and Artificial Neural Network

Abstract

The importance of diagnosing breast cancer is one of the most significant issues in medical science. Diagnosing whether the cancer is benign or malignant is extremely essential in ascertaining the type of cure, moreover, to bringing down bills. This study aims to use the tolerance-based intuitionistic fuzzy-rough set approach to pick attributes and data processing with help of machine learning for the classification of breast cancer. The main purpose of selecting a feature is to make a subset of input variables by removing irrelevant variables or variables that lack predictive information. This study shows how to eliminate redundant data in big data and achieve more efficient results. Rough set theory has already been used successfully to set down attributes, but this theory is insufficient to reduce the properties of a real- value dataset because it will possibly drop knowledge through the decomposition procedure. and this prevents us from getting the right results. In this study, we used the tolerance based intuitive fuzzy rough method for attribute selection. In this technique, lower and upper approaches are used to intuitive fuzzy sets from rough sets to remove uncertainty due to having simultaneous membership, non-membership, and hesitation degrees and obtain better results. The used method is demonstrated to be better performing in the shape of chosen attributes.

Keywords

• Fuzzy-Rough set
• Intuitionistic
• Feature- selection
• Breast cancer

References

1. [1] Agarwal, R., “https://towardsdatascience.com/the-5-feature-selection-algorithms-every-data-scientist-need -to-know-3a6b566efd2”, Access date: 27.07.2019.
2. [2] Jensen, R., Shen, Q., “Fuzzy-Rough Sets Assisted Attribute Selection”, IEEE Transactions On Fuzzy Systems, Feb; 15(1): 73, (2007).
3. [3] Jensen, R., Shen, Q., “Fuzzy-Rough Attribute Reduction with Application to Web Categorization”, Fuzzy Sets and Systems, 141(3): 469-485, (2004).
4. [4] Jensen, R., Shen, Q., “Computational intelligence and feature selection”, rough and fuzzy approaches, Hoboken, New Jersey, John Wiley & Sons, 8: (2008).
5. [5] Pawlak, Z., “Rough sets”, International Journal of Parallel Programming, 11(5): 341–356, (1982).
6. [6] Pawlak, Z., “Rough sets, theoretical aspects of reasoning about data”, Dordrecht, Netherlands: Springer Science, Business Media, 9: (2007).
7. [7] Pawlak, Z., Skowron, A., “Rough sets: Some extensions. Information Sciences” 177(1): 28–40, (2012).
8. [8] Slowinski, R., Vanderpooten, D., "Similarity Relation as a Basis for Rough Approximations", Advances in Machine Intelligence and Soft Computing, P. Wang, ed., Duke Univ. Press, (IV): 17-33, (1997).

9. [9] Han, Jiawei, Lee, J.G., Kamber, M., "An overview of clustering methods in geographic data analysis", Geographic Data Mining and Knowledge Discovery 2, 149-170, (2009).
10. [10] Tan, K.P., Liu, H.G., Liang, P.H., Bioorganic and Medicinal Chemistry Letters, 20(12): 3569-3572, (2010).
11. [11] Dubois, D., Prade, H., "Putting Rough Sets and Fuzzy Sets Together", Intelligent Decision Support, 203-232, (1992).
12. [12] Dubois, D., Prade, H., Farreny, H., Martin, R., Clouaire, Testemale, C., “Possibility Theory An Approach to Computerized Processing of Uncertainty”, Plenum Press, New York, (1988).
13. [13] Dubois, D., Prade, H., “Twofold fuzzy sets and rough sets-Some issues in knowledge representation”, Fuzzy Sets & Systems, 23: p3-ndash, 18, (1987).
14. [14] Atanassov, K. T., “Intuitionistic fuzzy sets”, In Intuitionistic fuzzy sets, Physica, Heidelberg, 1-137, (1999).
15. [15] Bustince, H., Burillo, P., “Vague sets are intuitionistic fuzzy sets”, Fuzzy Sets and Systems, 79 (3): 403-405, (1996).
16. [16] Elena, E., Castiñeira, Torres-Blanc, C., Cubillo, S., “Measuring contradiction on A-IFS defined in finite universes”, Knowledge-Based Systems, 24 (8): 1297-1309, (2011).
17. [17] Deschrijver, G., Etienne E., Kerre, “On the position of intuitionistic fuzzy set theory in the framework of theories modelling imprecision”, Information Sciences, 177 (8): 1860-1866, (2017).
18. [18] Dymova, L., Sevastjanov, P., “An interpretation of intuitionistic fuzzy sets in terms of evidence theory: Decision making aspect”, Knowledge-Based Systems, 23 (8): 772-782, (2010).
19. [19] Mukherjee, S., Basu, K., “Solution of a class of Intuitionistic Fuzzy Assignment Problem by using similarity measures”, Knowledge-Based Systems, 27: 170-179, (2012).
20. [20] Feng, Q., Li, R., “Discernibility Matrix Based Attribute Reduction in Intuitionistic Fuzzy Decision Systems”, Paper presented at the RSFDGrC, (2013).
21. [21] Tiwari, A.K., Shreevastava, Sh., Som, T., Shukla, K.K., “Tolerance-based intuitionistic fuzzy-rough set approach for attribute reduction”, Expert Syst, 101(C July): 205–212, (2018).
22. [22] Skowron, A., Stepaniuk, J., "Tolerance Approximation Spaces", Fundamenta Informaticae, 27 (2): 245-253, (1996).
23. [23] Jurio, A., Paternain, D., Bustince, H., Guerra, C., Beliakov, G., “A construction method of Atanassov's intuitionistic fuzzy sets for image processing”, IEEE International Conference Intelligent Systems, London, 337-342, (2010).