Affiliations: [a] School of Business, Nanjing Audit University, Nanjing, PR China | [b] School of Computer Science, Nanjing Audit University, Nanjing, PR China | [c] School of Management and Engineering, Nanjing University, Nanjing, PR China
Correspondence:
[*]
Corresponding author. Bing Huang, School of Computer Science, Nanjing Audit University, Nanjing 211815, PR China. E-mail: [email protected].
Abstract: Rule acquisition is significant in real life and extensively utilized in data mining. Currently, most studies have constructed rule acquisition algorithms based on the equivalence relation. However, these algorithms need to be more suitable for dominance-based decision systems and should consider applications in multi-scale environments. In this paper, we establish the dominance relation of the single-valued neutrosophic rough set model using the ranking method with the relative distance favorable degree. We then introduce this approach into a multi-scale environment to obtain the dominance relation of the multi-scale single-valued neutrosophic rough set model, resulting in two discernibility matrices and functions. We propose the algorithm for lower approximation optimal scale reduction and further examine the method of rule acquisition based on the discernibility matrix. Finally, we apply these algorithms to four random data sets to verify their effectiveness.
