Circular Economy of Medical Waste: Novel Intelligent Medical Waste Management Framework Based on Extension Linear Diophantine Fuzzy FDOSM and Neural Network Approach

Abstract

The COVID-19 pandemic has caused overwhelming levels of medical waste, resulting in constant threats to environmental pollution. Furthermore, many environmental issues related to medical waste have emerged. This study aims to propose an application that allows the identification and classification of hospitals that generate overwhelming levels of medical waste aftermath of the COVID-19 pandemic by using Multi-Criteria Decision-Making methods (MCDM). MCDM was designed on the integration of the Analytic Hierarchy Process (AHP), linear diophantine fuzzy set-fuzzy decision by opinion score method (LDFN-FDOSM), and Artificial Neural Network (ANN) analysis. Ten hospital managers were interviewed to determine the volume of medical waste generated by the hospitals they manage. Five types of medical waste were identified: general waste, sharps waste, pharmaceutical waste, infectious waste, and pathological waste. Among these five types, pharmaceutical waste is appointed as one that most impacts the environment. After that 313 experts in the health sector with experience in sustainability techniques were targeted to determine the best and worst technique for the Circular Economy to manage medical waste using the neural network approach. Findings also revealed that incineration technique, microwave technique, pyrolysis technique, autoclave chemical technique, vaporised hydrogen peroxide, dry heat, ozone, and ultraviolet light were the most vital and effective methods to dispose of medical waste during the pandemic. Additionally, ozone was ranked first as the most Circular Economy-related method for medical waste disposal. Among the implications of this study for governments, policymakers, and practitioners identify actions that hospitals may consider regarding the Circular Economy concept. Another implication is the supportive role of policymakers in transitioning most pollutant hospitals to becoming more sustainable.

Evaluation of the Routing Algorithms for NoC-Based MPSoC: A Fuzzy Multi-Criteria Decision-Making Approach

“…Since of these issues, it's tough to choose the optimal option since the outcomes may be unpredictable or inaccurate. Furthermore, the choice of the MCDM approach may alter the ultimate conclusion because of the variety of ways in which the methods manage ambiguity [17]. In order to get dependable and robust outcomes, it is essential to take into account the decision context and the causes of uncertainty while attempting to handle ambiguity in MCDM approaches.…”

“…One of the key advantages of FDOSM is its ability to handle fuzzy data and uncertain information, which can be particularly useful in complex decision-making scenarios where data may be incomplete or imprecise [17]. In addition, by avoiding two preferences, FDOSM ensures that decisionmakers do not express contradictory or conflicting preferences when evaluating alternatives [32].…”

“…Procedures including objective validation, subject validation, sensitivity analysis, Spearman's rank correlation, and a comparison analysis are the most used method for validation [17], [79]. This research used objective validation, sensitivity analysis, and Spearman's rank correlation techniques to guarantee a rigorous categorisation scheme was applied to the DM alternatives (routing algorithms) A scale assessment shows that each group contained five alternatives.…”