A process mining approach in big data analysis and modeling decision making risks for measuring environmental health...

Area of Science:

• Environmental Health Science
• Data Science
• Decision Science

Background:

• Assessing institutional environmental health is complex, often involving large datasets and risk factors.
• Existing methods may lack the flexibility to integrate diverse criteria and handle uncertainty effectively.
• A need exists for a unified, data-driven approach to evaluate and manage environmental health in public settings.

Purpose of the Study:

• To introduce a novel process-mining framework for assessing institutional environmental health.
• To develop and validate the Institutional Environmental Health Index (IEHI) software.
• To demonstrate the IEHI's utility in identifying institutions requiring sanitation prioritization.

Main Methods:

• Developed an ontology-based Multi-Criteria Group Decision-Making (MCGDM) model.
• Integrated fuzzy modeling and consensus evaluation principles.
• Employed Fuzzy Ordered Weighting Average (OWA) and Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) for computation.
• Utilized Group Fuzzy Decision-Making software for practical application.

Main Results:

• The IEHI successfully analyzed big data from environmental health investigations.
• The index generated a single, interpretable number reflecting environmental health status.
• Identified institutions with critical sanitation needs and those meeting standards.
• Demonstrated high flexibility and practicality in a case study of 20 mosques.

Conclusions:

• The IEHI provides a robust framework for quantifying environmental health in various institutions.
• It enhances e-health assessment through efficient big data and risk analysis.
• The methodology supports more realistic and data-informed decision-making in environmental health management.