Three-Way Decision of Granular-Ball Rough Sets Based on Fuzziness

Granular-ball computing (GBC) proposed by Xia adaptively generates a different neighborhood for each object, resulting in greater generality and flexibility. Moreover, GBC greatly improves the efficiency by replacing point input with granular-ball. However, traditional granular-ball classifiers may lead to risky classification on uncertain cases. In this paper, we introduce three-way decision (3WD) into GBC to construct a novel three-way decision of granular-ball rough sets (3WD-GBRS) from the perspective of uncertainty. This helps to construct reasonable multi-granularity spaces for handling complex decision problems with uncertainty. 3WD-GBRS is constructed in a data-driven method based on fuzziness, which avoids the subjective definition of certain risk parameters when calculating the threshold pairs. We further analyze the fuzziness loss of multilevel decision result in 3WD-GBRS. Extensive comparative experiments are conducted with 3 state-of-the-art GB-based classifiers and 1 classical machine learning classifiers on 6 public benchmark datasets. The results show that 3WD-GBRS almost outperforms other comparison methods in term of effectiveness and efficiency.