KNN Data Filling Algorithm for Incomplete Interval-Valued Fuzzy Soft Sets

Abstract As a generalization of the fuzzy soft set, interval-valued set is viewed as more resilient and powerful tool for dealing with uncertain information. However, lower or upper membership degree, both them, may be missed during data collection transmission procedure, which could present challenges processing. The existing filling algorithm incomplete sets has low accuracy high error rate leads to wrong results involves subjectivity due setting threshold. Therefore, solve these problems, we propose KNN sets. An attribute-based combining rule first designed determine whether involving degree should ignored filled avoids subjectivity. will according their K complete nearest neighbors. To verify validity feasibility method, conduct randomized experiments on real dataset Shanghai Five-Four Hotel Data simulated datasets. experimental illustrate that our proposed method outperform average rate.