Fuzzy Advantage Granular Ball Rough Set for Feature Selection via Deep Reinforcement Learning

Feature selection is a critical step in data mining, with the granular ball rough set model widely applied in this area. However, the randomness issue during the initialization of the existing fuzzy granular ball rough set algorithm may lead to the loss of samples during the feature measurement process. Additionally, it also lacks consistency in handling fuzzy samples in different regions of the granular ball, which further weakens the classification performance of high-dimensional fuzzy data. To this issue, we propose a fuzzy advantage granular ball rough set feature selection algorithm via deep reinforcement learning. First, to reduce the randomness in the generation process of granular balls, the center generation method is optimized by defining sample aggregation degree and spacing. Second, to enhance feature credibility, the granular ball advantage degree is constructed and integrated with purity to evaluate feature importance. Third, to improve the handling of fuzzy samples, a deep reinforcement learning mechanism is introduced to uniformly process the fuzzy samples. Finally, a feature selection algorithm (FGFSD) suitable for high-dimensional fuzzy data is proposed. Evaluated on 20 benchmarks, FGFSD achieves a feature reduction rate of 65% on low-dimensional datasets and up to 99.6% on high-dimensional datasets. Furthermore, it attains a mean accuracy of 0.9459, surpassing the suboptimal feature selection method's 0.9013 by 4.95%.