Loading...
Loading...
Contributors:
Dataset URI:
cbktg4r84fThis dataset provides the model parameters, complete fuzzy rule base, derived computational outputs, and reproducibility materials supporting the manuscript “FuzzyHen: An Interpretable Mamdani Framework for Integrated Environmental Heat-Risk Scoring in Reduced-Scale Laying-Hen Houses”. FuzzyHen is an interpretable Mamdani fuzzy inference framework developed to integrate environmental thermal indices into a continuous environmental heat-risk score for laying-hen housing research. The framework uses three redundancy-aware inputs: black globe humidity index (BGHI), temperature-humidity index (THI), and radiant thermal load (RTL). Each input is represented by five linguistic sets, resulting in a complete 125-rule base. Mamdani inference is implemented using minimum antecedent activation, maximum aggregation, and centroid defuzzification over a continuous 0–10 output universe. The deposited materials include a consolidated Excel workbook containing the mathematical model architecture, thermal-index equations, exact input and output membership-function parameters, weight scenarios, the complete 125-rule base, correlation audit, sensitivity analyses, leave-one-day-out robustness results, comparator analyses, computational integrity tests, software environment information, file inventory, data dictionary, and SHA-256 checksums. The accompanying reproducibility package contains the three author-generated source spreadsheets from the controlled reduced-scale experiment, the frozen Python implementation of the FuzzyHen pipeline, the transparent comparator analysis, full record-level derived outputs, machine-readable CSV files, software requirements, and cryptographic checksums. The experimental database comprises 68,792 valid environmental records obtained over 16 common experimental days from three fixed reduced-scale house–roof condition profiles. The dataset supports computational reproducibility and methodological inspection of FuzzyHen. It does not constitute physiological validation, commercial-farm validation, or evidence of generalized causal effects of roofing materials. House identity and roof condition were not independently replicated; therefore, application-level comparisons are restricted to the three observed fixed house–roof profiles.
Keyword(s):
Agricultural Engineering; Animal Science; Artificial Intelligence; Computer Science; Environmental Engineering.
MeSH Term(s):
Grants and Funding:
Associated Publication(s):
No Associated Publication Data Available
Supplementary Data:
No Supplementary Data Available
Related Dataset(s):
No Related Dataset Data Available
The National Library of Medicine (NLM) provides information about biomedical datasets. Inclusion on an NLM Web page does not imply endorsement of, or agreement with, the contents by NLM or the National Institutes of Health. Learn more: NLM Web Policies (nih.gov)