Interpretable Fuzzy Systems For Forward Osmosis Desalination

2025-07-06

IEEE International Conference on Fuzzy Systems

AI Summary

This study addresses the limitations of conventional fuzzy rule systems in forward osmosis desalination, where low discriminability of fuzzy sets and poor semantic interpretability hinder their applicability in public health–related decision-making. To overcome these challenges, this work proposes a human-in-the-loop approach for constructing an interpretable fuzzy rule system that integrates expert-driven grid partitioning, domain-informed feature engineering, and an activation-strength–based rule pruning mechanism. The proposed method enhances both the discriminability of fuzzy sets and the transparency of generated rules while preserving semantic clarity and structural simplicity. Experimental results demonstrate that the system achieves prediction performance comparable to clustering-based fuzzy models, yet with significantly improved interpretability, thereby offering a reliable and transparent intelligent decision-support solution for water treatment applications.

Technology Category

• Machine Learning: Feature Construction/Reformulation
• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Computer Vision: Interpretability, Explainability, and Transparency

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Preserving interpretability in fuzzy rule-based systems (FRBS) is vital for water treatment, where decisions impact public health. While structural interpretability has been addressed using multi-objective algorithms, semantic interpretability often suffers due to fuzzy sets with low distinguishability. We propose a human-in-the-loop approach for developing interpretable FRBS to predict forward osmosis desalination productivity. Our method integrates expert-driven grid partitioning for distinguishable membership functions, domain-guided feature engineering to reduce redundancy, and rule pruning based on firing strength. This approach achieved comparable predictive performance to cluster-based FRBS while maintaining semantic interpretability and meeting structural complexity constraints, providing an explainable solution for water treatment applications.

Problem

• interpretable fuzzy systems
• forward osmosis desalination
• semantic interpretability
• fuzzy rule-based systems
• water treatment

Innovation

• interpretable fuzzy systems
• human-in-the-loop
• semantic interpretability
• forward osmosis desalination
• rule pruning