A Simplified Adaptive Fuzzy Min-Max Neural Network for pattern classification

neural network, as a prominent hyperbox classifier, has undergone significant research over the past three decades. Despite its effectiveness, the conventional FMM algorithm relies on a fixed expansion coefficient, which often leads to suboptimal performance because it cannot adapt to varying data distributions. Additionally, the membership function in FMM typically depends on sensitive parameters that need to be preset, further complicating its practical application. To address these limitations and improve the adaptability and classification accuracy of FMM, we propose a Simplified Adaptive Fuzzy Min-Max Neural Network (SAFMM) for pattern classification, where all parameters are adaptively chosen. Our contributions are twofold: Firstly, a novel FMM learning algorithm is introduced, where hyperboxes expand adaptively instead of using a fixed coefficient, and cluster and class-specific hyperboxes are simultaneously applied to avoid overlap. Secondly, considering uneven data distributions within hyperboxes, a new adaptive membership function based on data core is defined for classification. The proposed SAFMM model is evaluated on benchmark datasets and areal- world case of magnetic flux leakage (MFL) defect depth estimation in pipeline non-destructive testing (NDT). Experimental results demonstrate that SAFMM can generate fewer hyperboxes while ensuring classification accuracy and exhibits an absolute advantage for quick classification as the dataset size increases.