Adaptive T-S Fuzzy Semantic Hierarchical Quantification Algorithm via Regularized Fuzzy Error Entropy

Hierarchical quantification of health is crucial for personalized treatment. However, existing methods for hierarchical quantification adopt a separate optimization strategy for the premise and consequent parameters, which makes it difficult for the model to achieve globally optimal semantic expression. Moreover, traditional methods lack robustness in handling non-Gaussian noise, limiting the model’s generalization capability. To address these issues, this paper proposes an Adaptive T-S Fuzzy Semantic Hierarchical Quantification Algorithm via Regularized Fuzzy Error Entropy (ATS-RFEE). The algorithm transforms the traditional two-step parameter estimation into a joint optimization process with a feedback mechanism by introducing Fuzzy Error Entropy (RFEE) to re-weight the premise parameters of the T-S model, thereby enhancing its robustness. Furthermore, the Giono regularization method is adopted to identify the consequent parameters, and the rule outputs are adaptively adjusted using an iterative regression method, while the traditional defuzzification operation is omitted. Experimental results demonstrate the effectiveness of the proposed algorithm in improving the accuracy of blood pressure state quantification.