Due to the advancement of technology, data is becoming richer in features and instances, but not all features and instances help to improve classification performance in data mining. Data reduction helps to alleviate the difficulty of learning techniques when the data is large, and rough sets have been widely used for data reduction. Semi-monolayer covering rough set is an efficient and high-quality rough set model in set-valued information systems. In this paper, a new data reduction scheme is proposed from the perspective of incremental updating of semi-monolayer covering rough set (abbr. FSMCDE). Firstly, in the set-valued decision system, based on the fact that the lower approximation set gradually increases with the features until it remains stable, the limit for the lower approximation set of semi-monolayer covering rough set to remain stable is proved, and the incremental updating theory of the lower approximation set is designed. Secondly, the features are continuously added to the set-valued system, and the incremental algorithm is used to update the lower approximation set until it reaches the limit, completing the collaborative reduction of features and instances. Furthermore, to reduce the blindness of adding features during incremental updating, Fisher score is introduced to form the final collaborative reduction algorithm of features and instances. The experimental results show that FSMCDE can efficiently accomplish the collaborative reduction of features and instances, and effectively improve the classification performance.

Ruimin Li. Collaborative Reduction of Features and Instances in the Set-valued Decision System. Academic Journal of Computing & Information Science (2024), Vol. 7, Issue 3: 13-20. https://doi.org/10.25236/AJCIS.2024.070302.

[1] Idri A, Benhar H, Fernández-Alemán J L, et al. A systematic map of medical data preprocessing in knowledge discovery[J]. Computer Methods and Programs in Biomedicine. 2018, 162: 69-85.

[2] Buza K, Nanopoulos A, Schmidt-Thieme L. INSIGHT: Efficient and Effective Instance Selection for Time-Series Classification[C]. In Advances in Knowledge Discovery and Data Mining: 15th Pacific-Asia Conference, PAKDD 2011, Shenzhen, China, May 24-27, 2011, Proceedings, Part II 15, pp. 149-160. Springer Berlin Heidelberg, 2011.

[3] Cai J, Luo J, Wang S, et al. Feature selection in machine learning: A new perspective[J]. Neurocomputing. 2018, 300: 70-79.

[4] Pawlak Z, Skowron A. Rudiments of rough sets[J]. Information Sciences. 2007, 177(1): 3-27.

[5] Sun L, Zhang X, Qian Y, et al. Feature selection using neighborhood entropy-based uncertainty measures for gene expression data classification[J]. Information Sciences. 2019, 502: 18-41.

[6] R. J, M. A, N. M P. Effective instance selection using the fuzzy-rough lower approximation[C]. 2019 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE). IEEE, 2019.

[7] Verbiest N, Cornelis C, Herrera F. FRPS: A Fuzzy Rough Prototype Selection method[J]. Pattern Recognition. 2013, 46(10): 2770-2782.

[8] Anaraki J, Samet S, Lee J, et al. SUFFUSE: Simultaneous Fuzzy-Rough Feature- Sample Selection[J]. Journal of Advances in Information Technology. 2015, 6: 103-110.

[9] Derrac J, Cornelis C, García S, et al. Enhancing evolutionary instance selection algorithms by means of fuzzy rough set based feature selection[J]. Information Sciences. 2012, 186(1): 73-92.

[10] Shu W, Shen H. Updating attribute reduction in incomplete decision systems with the variation of attribute set[J]. International Journal of Approximate Reasoning. 2014, 55(3): 867-884.

[11] Wu Z, Chen N, Gao Y. Semi-monolayer cover rough set: Concept, property and granular algorithm [J]. Information Sciences. 2018, 456: 97-112.

[12] Wu Z, Wang H, Chen N, et al. Semi-monolayer covering rough set on set-valued information systems and its efficient computation[J]. International Journal of Approximate Reasoning. 2021, 130: 83-106.

[13] Guan Y, Wang H. Set-valued information systems[J]. Information Sciences. 2006, 176(17): 2507-2525.

[14] Li J, Cheng K, Wang S, et al. Feature Selection: A Data Perspective[J]. ACM Comput. Surv. 2017, 50(6): 94.