Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Interpretable Fuzzy Systems For Forward Osmosis Desalination

Qusai Khaled, Uzay Kaymak, Laura Genga

TL;DR

A human-in-the-loop approach for developing interpretable FRBS to predict forward osmosis desalination productivity, which achieved comparable predictive performance to cluster-based FRBS while maintaining semantic interpretability and meeting structural complexity constraints.

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.

Interpretable Fuzzy Systems For Forward Osmosis Desalination

TL;DR

A human-in-the-loop approach for developing interpretable FRBS to predict forward osmosis desalination productivity, which achieved comparable predictive performance to cluster-based FRBS while maintaining semantic interpretability and meeting structural complexity constraints.

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.
Paper Structure (13 sections, 13 equations, 4 figures, 5 tables)

This paper contains 13 sections, 13 equations, 4 figures, 5 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Design Methodology for Interpretable FRBs
  4. Human in the Loop (HITL) Phase
  5. Data-driven phase
  6. Predicting the performance of forward osmosis desalination
  7. Forward Osmosis Desalination
  8. Dimensionality Reduction
  9. Rule base construction
  10. Estimating the consequents
  11. Tuning the consequents
  12. Comparison to clustering based fuzzy systems
  13. Conclusion and Future research

Figures (4)

  • Figure 1: Example of fuzzy sets satisfying the distinguishability criteria, plotted in continuous lines, compared to sets violating distinguishability, visualized with dashed lines.
  • Figure 2: Visualization depicting the skewness of dataset features relative to the flux $F_x$. DSM: Draw solution molarity, DST: Draw solution temperature, DSV: Draw solution velocity, FST: Feed solution temperature, FSV: Feed solution velocity.
  • Figure 3: Results of GRABS simplification.
  • Figure 4: Fuzzy sets created for $\Delta P$ using grid partitioning GP, Gustaffson-Kessel clustering GK, Fuzzy C-Means FCM and particle swarm optimization PSO.