An enhanced fuzzy min-max (EFMM) network is proposed for pattern classification in this paper. The aim is to overcome a number of limitations of the original fuzzy min-max (FMM) network and improve its classification performance. The key contributions are three heuristic rules to enhance the learning algorithm of FMM. First, a new hyperbox expansion rule to eliminate the overlapping problem during the hyperbox expansion process is suggested. Second, the existing hyperbox overlap test rule is extended to discover other possible overlapping cases. Third, a new hyperbox contraction rule to resolve possible overlapping cases is provided. Efficacy of EFMM is evaluated using benchmark data sets and a real medical diagnosis task. The results are better than those from various FMM-based models, support vector machine-based, Bayesian-based, decision tree-based, fuzzy-based, and neural-based classifiers. The empirical findings show that the newly introduced rules are able to realize EFMM as a useful model for undertaking pattern classification problems.

Over the last few decades, pattern classification has become one of the most important fields of artificial intelligence because it constitutes an essential component in many real-world applications. Artificial neural networks and fuzzy logic are the two most widely used models in pattern classification. To build an efficient and powerful model, researchers have introduced hybrid models that combine both fuzzy logic and artificial neural networks. Among the existing hybrid models, the family of Fuzzy Min-Max (FMM) neural networks offers a premier model for undertaking pattern classification problems. While the original FMM model is useful in terms of its capability of online learning, it suffers from several limitations in its learning procedure. Therefore, researchers have proposed numerous improvements to overcome the limitations over the years. In this paper, we conduct a comprehensive survey on the developments of FMM-based models for pattern classification. To allow researchers in selecting the most suitable FMM variants and to provide a proper guideline for future developments, this study divides the FMM variants into two main categories, namely FMM variants with and without contraction. This division facilitates understanding of the improvements on the original FMM model, as well as enables identification of the limitations that still exist in various FMM-based models. We also summarize the use of FMM and its variants in solving different benchmark and real-world pattern classification problems. In addition, future trends and research directions of FMM-based models are highlighted.

At present, pattern classification is one of the most important aspects of establishing machine intelligence systems for tackling decision-making processes. The fuzzy min–max (FMM) neural network combines the operations of an artificial neural network and fuzzy set theory into a common framework. FMM is considered one of the most useful neural networks for pattern classification. This paper aims to 1) analyze the FMM neural network in terms of its impact in addressing pattern classification problems; 2) examine models that are proposed based on the original FMM model (i.e., existing FMM-based variants); 3) identify the challenges associated with FMM and its variants, and; 4) discuss future trends and make recommendations for improvement. The review is conducted based on a methodical protocol. Through a rigorous searching and filtering process, the relevant studies are extracted and comprehensively analyzed to adequately address the defined research questions. The findings indicate that FMM plays a critical role in providing solutions to pattern classification issues. The FMM model and a number of FMM-based variants are identified and systematically analyzed with respect to their aims, improvements introduced and results achieved. In addition, FMM and its variants are critically analyzed with respect to their benefits and limitations. This paper shows that the existing FMM-based variants still encounter issues in terms of the learning process (expansion, overlap test, and contraction), which influence the classification performance. Based on the review findings, research opportunities are suggested to propose a new model to enhance the number of existing FMM models, particularly in terms of their learning process by minimizing hyperbox overlap pertaining to different classes as well as avoiding membership ambiguity of the overlapped region. In short, this review provides a comprehensive and critical reference for researchers and practitioners to leverage FMM and its variants for undertaking pattern classification tasks.