The number of academic studies addressing advancements in Multi-Criteria Group Decision-Making (MCDM) has been steadily increasing in recent years, with the Analytic Hierarchy Process (AHP) emerging as the most widely utilized method. However, traditional weight determination approaches in AHP are often inadequate for capturing the complexity, nonlinearity, and irregularity of real-world scenarios. Consequently, these methods are increasingly being substituted by optimization models, especially in MCGDM, where results from multiple experts must be aggregated. This paper presents a novel Fuzzy Non-Linear Programming (FNLP) model that enables extraction of weights from diverse types of fuzzy numbers simultaneously. Unlike conventional approaches that require aggregation operators, the proposed model directly derives crisp weights from the fuzzy decision matrices of multiple experts. Particle Swarm Optimization (PSO) algorithm is used to solve the proposed FNLP model. This innovative framework offers a streamlined and more accurate solution for weight determination, enhancing decision-making effectiveness in complex and uncertain environments. To validate the applicability of this, the model is employed in a problem of factors evaluation responsible for IoTs successful employment readiness in industries. The results match with practical implications.

Cardiovascular Disease (CVD) is a major reason for general mortality rate. According to WHO it is the leading cause of death worldwide, resulting in 17.9 million fatalities annually, or roughly 31% of the total mortality worldwide. Devices like ECG, echocardiogram, Holter monitor, cardiac MRI, etc. are used for detection of heart disease in hospitals. Usually, choosing the best features is challenging. In order to solve this problem, ideal Feature Selection (FS)-based Machine Learning (ML) techniques are suggested for early prediction. Using ML classifiers, the system, which consists of components for processing, storing, and gathering data, predicts patients heart problems. Least Absolute Shrinkage and Selection Operator (LASSO), SHapley Additive exPlanations (SHAP), Analysis of Variance (ANOVA), and Minimum Redundancy Maximum Relevance (mRMR) techniques are applied for feature extraction. Further, we used SHAP with Support Vector Machine (SVM), Logistic Regression (LR), Random Forest (RF), Extreme Gradient Boosting (XGBOOST), and Decision Tree (DT) for prediction. mRMR, LASSO, ANOVA are applied with Random Forest Classifier (RFC), Gradient Boost Classifier (GBC), Extra Tree Classifier (ETC), and Logistic Regression Classifier (LRC) for prediction. SHAP with SVM achieves highest accuracy with 86%. ANOVA with LRC achieves 85%. The suggested approach has the power to significantly reduce mortality from CVD and improve patient care, improving the lives of those who are impacted.

As the world embraces sustainable and smart solutions, agriculture is evolving through rapid technological advancements. Unmanned Aerial Vehicles (UAVs) are transforming smart farming, particularly for smallholder farmers, by reducing costs, saving time, and improving efficiency of agricultural tasks. This study aims to introduce a comprehensive group decision-making framework for selecting the most suitable UAV for agricultural purposes. Traditional Multi-Criteria Decision-Making (MCDM) methods face challenges with intricacies, non-linearity, limited exploration of solution space and weight distortion during defuzzification. To address these issues, this study introduces a novel Decomposed Fuzzy-based Non-Linear (DFNL) optimization model within Analytical Hierarchy Process (AHP), which directly extracts subjective crisp weights from DF-decisions. A hybrid metaheuristic algorithm is then proposed to solve this model efficiently. Additionally, objective weights are calculated using the CRiteria Importance Through Inter-criteria Correlation (CRITIC) method and qualitative data, enhancing the accuracy of the decision-making process. For ranking the UAV alternatives, the full Multiplicative form of the Multi-Objective Optimization by Ratio Analysis (MULTIMOORA) method is applied. The effectiveness of the proposed methodology is demonstrated through two extensive examples and validated via a case study focusing on the Indian subcontinent. Sensitivity analysis confirms its robustness and stability. The findings and novelties are supported by comparing with other extant models. This fusion of group decision-making methods and metaheuristic algorithms improves weight accuracy, reduces manual complexity, and adapts to uncertainty, offering policymakers actionable insights and a tailored approach for UAV selection.

Improving public transport quality significantly encourages users to shift from private vehicles, helping reduce traffic congestion, noise, and CO2 emissions in urban areas. Policymakers and researchers focus on identifying the key factors for enhancing public transport quality and finding practical solutions. However, traditional decision-making techniques often encounter limitations, such as difficulty in managing complex and non-linear relationships, inadequate solution space exploration, and defuzzification-caused weight distortion. To overcome these challenges, a novel Decomposed Fuzzy Set based Non-Linear (DFNL) optimization model is developed in this study. With this innovative model, Decomposed Fuzzy (DF) judgments lead straight to precise weights, eliminating information loss and improving precision. A hybrid metaheuristic algorithm combining Particle Swarm Optimization (PSO) and the Simplex Search Method (SSM) is proposed to solve the DFNL model effectively. Furthermore, a ranking technique called Multiplicative form of Multi-Objective Optimization by Ratio Analysis (MULTIMOORA) is incorporated for evaluating the solution for Urban Transport Sustainability (UTS). The proposed assessment is tested on two illustrative examples to demonstrate improved performance. A case study conducted in Kolkata, India, further validates its applicability. Comparative evaluations highlight its advantages over existing methods, while its resilience and stability are confirmed with sensitivity evaluations. By integrating metaheuristic algorithms with advanced group decision-making methodologies, this approach ensures enhanced accuracy of weight, streamlined computational complexity, and adaptability to uncertainty. The study offers practical and actionable insights for policymakers aiming to implement sustainable and resilient urban transport strategies.

This study includes a panoramic view of various existing techniques and approaches of Metaheuristic Optimization Algorithms (MOAs), specifically applied in solving decision-making problems. The synergy of MOAs and Multi-Criteria Decision-Making (MCDM) methods has already established many milestones in the literature. However, the review papers existing in the literature mostly segregates MOAs and MCDM, lacking behind a comprehensive exploration of their integration. This paper bridges the aforesaid gap by providing the recent publications of these two intricate domains arranged and explored with respect to their key contributions. The paper emphasizes on four highly cited Evolutionary Algorithms (EAs) to reduce the information overload. It provides in-depth exploration of practical applications, highlighting instances where synthesis of past achievements and current trends lay the groundwork for future explorations. The study claims that more than 85% of this work has been performed in the last decade only with Genetic Algorithm (GA)-MCDM leading this realm. It offers valuable insights for scholars and practitioners seeking to navigate the intricate developments in this interdisciplinary field.

Determining an acceptable solution across various factors poses a significant challenge in multiple-criteria group decision-making (MCGDM). Within the healthcare sector, where there is no tolerance for errors and mistakes, selecting a healthcare supplier is one of the most critical areas. Starting with the cardinal data-based methods, the recent approaches to solve such problems have grown to MCGDM methods. Recent advancements have emphasized hybrid MCGDM methods, as hybridized approaches tend to outperform individual methods. In response to this trend, this study describes a fusion of MCGDM and metaheuristic algorithms, as metaheuristics can handle the non-linearity, complexity and uncertainty better than the traditional MCGDM methods. Initially, the study introduces a novel MCGDM optimization model to directly obtain the crisp weights from the fuzzy decision matrices without aggregating the decisions received from multiple experts. Later, an algorithm is developed in the metaheuristic environment, leveraging a hybrid particle swarm optimization (PSO) method to solve the optimization model. By incorporating MCGDM principles into the metaheuristic system, this study enhances the supplier evaluation system of an Indian healthcare facility. The proposed method offers a convenient and robust solution for estimating the weights of suppliers and affecting criteria. The comparison results validate the algorithm. A sensitivity analysis ensures the robustness and efficiency of the method. By integrating the optimization process enables more accurate and reliable decision-making in the supplier selection sector.

In the post-COVID-19 era, the management of medical waste has become a precarious concern due to its potential risks to environment, patients, public and healthcare workers. Selecting the most suitable healthcare waste disposal technology (HWDT) is a complex task, complicated by multiple, often conflicting criteria. Optimization models are introduced to replace the traditional decision-making to encounter the limitations, such as weight distortion caused by defuzzification, uncertain nonlinear relationships of real-time models, and inadequate solution spaces exploration. This study introduces a novel hybrid SS-PSO algorithm to solve the optimization model for crisp weights directly from comparison matrices. The algorithm combines the strength of simplex search method (SSM) into particle swarm optimization (PSO). It is validated on three benchmark examples, achieving the lowest objective function values (0.2283, 4.4116, and 27.519) compared to existing methods, with enhanced consistency fitness. Later, to select the best HWDT, a multi-criteria decision-making (MCDM) technique called AHP-SS-PSO-TOPSIS (ASPT) is proposed. It integrates fuzzy analytical hierarchy process (AHP) and technique for order preference by similarity to ideal solution (TOPSIS) within a metaheuristic optimization framework. The integrated framework’s practical utility is demonstrated through a real case study in Indian subcontinent. The case study reveals that treatment effectiveness is the most important criteria with 21% weight. Autoclaving is the most appropriate technology for India to its low carbon emissions, energy efficiency, and cost-effectiveness. The sensitivity analysis has shown 91% stability on 21 distinct scenarios confirming the robustness and resilience of the ASPT method. The ranking results are compared with the other methods and similar rankings are obtained. Furthermore, the paper discusses the practical implications of this approach offering actionable insights for policymakers and healthcare administrators to adopt environmentally friendly and economically viable waste management technologies.

Renewable energy technologies and resources have witnessed a notable upsurge in research interest recently. Because of the complexity and ambiguity inherent in real-models, selecting optimal renewable energy technologies may be a laborious process for decision-makers. To address these issues, this study introduces a modified Multi-criteria Group Decision-Making (MCGDM) fuzzy optimization model to directly obtain the crisp weights from the fuzzy decision matrices. The model is solved using an algorithm created in a metaheuristic environment, employing a hybrid Particle Swarm Optimization (PSO) technique. This model is implemented in a real-world problem of selection of a suitable renewable energy source. The results indicate that wind energy emerges as the best non-conventional source within the given constraints. Comparison results confirm that the algorithm provides a similar ranking when selecting renewable energy technologies. By integrating the optimization process, the model enables more accurate and reliable decision-making results in the sector of renewable energy technologies and resources.

The original online version of this article was revised: “In this article the author’s name ‘Rishabh Rishabh’ was incorrectly written as ‘Rishabh’. The original article has been corrected.

Drug-drug interactions can prompt various health issues that take place when a person intakes multiple drugs simultaneously. Predicting these events in advance can save lives. A polynomial kernel SVM was proposed for predicting drug-drug interactions (DDIs) between a drug pair. A unique fingerprint of each drug was considered, and then, the fingerprints of every drug pair were combined into another unique fingerprint using a novel method which then acts as a feature vector for the machine learning model. The SVM implemented gave us an accuracy of 91.6%. Moreover, the proposed model could also predict novel interactions between drugs not present in the dataset.

The leading cause of deaths worldwide are cardiac-related illnesses. In 2019, approximately 32% of deaths worldwide were due to cardiovascular disease, and more than 75% of these occur in low- and middle-income countries. One of the main contributing factors to this is the patient not receiving the appropriate medications on time. This issue arises as a doctor must periodically examine more than 100 biological and chemical indicators of the patient. The goal of our work is to provide doctors with a decision support system that can recommend the appropriate drugs with practically applicable accuracy (80–95%). The computational models built were of two types—artificial neural network (ANN) and support vector classifier (SVC). In contrast to the ANN, the SVC had far little complexity. The ANN was tweaked and tuned according to the drug under study as each and every drug has its own complexity when it comes to prognosis. The general architecture included six hidden layers, of which four were ReLu + L2 (Regularized) and two were dropout layers (20% dropout) to deal with overfitting. The models were trained on a dataset of 117 attributes and were able to prognose 15 different heart-related drugs with high precision.