Incremental updating reduction for relation decision systems with dynamic conditional relation sets

In real applications, the feature set in a relation decision system often varies with time resulting in a dynamic relation decision system where the existing attribute reduction methods become time-consuming and not suitable. How to efficiently update the reduc-tion with prior information of attribute reduction is an important task. Aim at this, we firstly propose an incremental updating mechanism for the positive region and right neigh-bor of a relation decision system when the conditional relation set has increased or decreased. By integrating the proposed incremental updating mechanism of positive region and right neighbor to the positive region-based reduction method, a novel incremental updating reduction algorithm for relation decision systems with dynamic conditional rela-tion sets is designed. The proposed incremental updating reduction algorithm can speed up the reduction of relation decision systems with dynamic conditional relation sets. Specially, it can deal with the reduction of dynamic decision systems whose decision rela-tions aren't equivalence relations, such as incomplete decision systems with missing deci-sion values. The experimental study carried out on UCI datasets show the good performance the proposed algorithm.(c) 2023 Elsevier Inc. All rights reserved.