Hybrid weighted fuzzy production rule extraction utilizing modified harmony search and BPNN
Abstract Weighted Fuzzy Production Rules (WFPRs) are vital for Clinical Decision Support Systems (CDSSs), significantly impacting diagnostic accuracy and bridging the gap between data-driven insights and actionable clinical decisions through knowledge engineering. This paper proposes an integrated a...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-03-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-95406-y |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850153941513273344 |
|---|---|
| author | Feng Qin Azlan Mohd Zain Kai-Qing Zhou De-Bing Zhuo |
| author_facet | Feng Qin Azlan Mohd Zain Kai-Qing Zhou De-Bing Zhuo |
| author_sort | Feng Qin |
| collection | DOAJ |
| description | Abstract Weighted Fuzzy Production Rules (WFPRs) are vital for Clinical Decision Support Systems (CDSSs), significantly impacting diagnostic accuracy and bridging the gap between data-driven insights and actionable clinical decisions through knowledge engineering. This paper proposes an integrated approach combining the Dynamic Dimension Adjustment Harmony Search (DDA-HS) Algorithm and Back Propagation Neural Networks (BPNNs) to enhance WFPR extraction accuracy. DDA-HS dynamically adjusts search space dimensions through fitness evaluations, optimizing initial weights in BPNNs and leveraging an absorbing Markov chain to enhance transition probabilities, supporting exploration and avoiding local optima in high-dimensional spaces. Evaluated against existing optimization methods including Harmony Search (HS), Cuckoo Search (CS), Adaptive Global Optimal Harmony Search (AGOHS), and Harmony Search with Cuckoo Search (HSCS) Algorithms, DDA-HS achieves 74.48% accuracy for BPNN classification and 77.08% for WFPR classification on the PIMA dataset, representing improvements of 3.6% and 6.5%, respectively. WFPR extraction enhances BPNN interpretability by revealing feature influences on decision-making, improving both accuracy and transparency. The proposed method offers a robust framework for reliable and interpretable CDSSs in healthcare. |
| format | Article |
| id | doaj-art-b06151cf44b84f8fb357a7eb61e6db1d |
| institution | OA Journals |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-b06151cf44b84f8fb357a7eb61e6db1d2025-08-20T02:25:35ZengNature PortfolioScientific Reports2045-23222025-03-0115111910.1038/s41598-025-95406-yHybrid weighted fuzzy production rule extraction utilizing modified harmony search and BPNNFeng Qin0Azlan Mohd Zain1Kai-Qing Zhou2De-Bing Zhuo3Faculty of Computing, Universiti Teknologi MalaysiaFaculty of Computing, Universiti Teknologi MalaysiaSchool of Communication and Electronic Engineering, Jishou UniversitySchool of Civil Engineering and Architecture, Jishou UniversityAbstract Weighted Fuzzy Production Rules (WFPRs) are vital for Clinical Decision Support Systems (CDSSs), significantly impacting diagnostic accuracy and bridging the gap between data-driven insights and actionable clinical decisions through knowledge engineering. This paper proposes an integrated approach combining the Dynamic Dimension Adjustment Harmony Search (DDA-HS) Algorithm and Back Propagation Neural Networks (BPNNs) to enhance WFPR extraction accuracy. DDA-HS dynamically adjusts search space dimensions through fitness evaluations, optimizing initial weights in BPNNs and leveraging an absorbing Markov chain to enhance transition probabilities, supporting exploration and avoiding local optima in high-dimensional spaces. Evaluated against existing optimization methods including Harmony Search (HS), Cuckoo Search (CS), Adaptive Global Optimal Harmony Search (AGOHS), and Harmony Search with Cuckoo Search (HSCS) Algorithms, DDA-HS achieves 74.48% accuracy for BPNN classification and 77.08% for WFPR classification on the PIMA dataset, representing improvements of 3.6% and 6.5%, respectively. WFPR extraction enhances BPNN interpretability by revealing feature influences on decision-making, improving both accuracy and transparency. The proposed method offers a robust framework for reliable and interpretable CDSSs in healthcare.https://doi.org/10.1038/s41598-025-95406-yWFPRsCDSSsDDA-HSBPNNsOptimizationInterpretability |
| spellingShingle | Feng Qin Azlan Mohd Zain Kai-Qing Zhou De-Bing Zhuo Hybrid weighted fuzzy production rule extraction utilizing modified harmony search and BPNN Scientific Reports WFPRs CDSSs DDA-HS BPNNs Optimization Interpretability |
| title | Hybrid weighted fuzzy production rule extraction utilizing modified harmony search and BPNN |
| title_full | Hybrid weighted fuzzy production rule extraction utilizing modified harmony search and BPNN |
| title_fullStr | Hybrid weighted fuzzy production rule extraction utilizing modified harmony search and BPNN |
| title_full_unstemmed | Hybrid weighted fuzzy production rule extraction utilizing modified harmony search and BPNN |
| title_short | Hybrid weighted fuzzy production rule extraction utilizing modified harmony search and BPNN |
| title_sort | hybrid weighted fuzzy production rule extraction utilizing modified harmony search and bpnn |
| topic | WFPRs CDSSs DDA-HS BPNNs Optimization Interpretability |
| url | https://doi.org/10.1038/s41598-025-95406-y |
| work_keys_str_mv | AT fengqin hybridweightedfuzzyproductionruleextractionutilizingmodifiedharmonysearchandbpnn AT azlanmohdzain hybridweightedfuzzyproductionruleextractionutilizingmodifiedharmonysearchandbpnn AT kaiqingzhou hybridweightedfuzzyproductionruleextractionutilizingmodifiedharmonysearchandbpnn AT debingzhuo hybridweightedfuzzyproductionruleextractionutilizingmodifiedharmonysearchandbpnn |