Bahar Yalcin Kavus
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Bahar Yalcin Kavus has a total of 36 co-authors. Here are the top co-authors by number of shared publications:
- Tolga Kudret Karaca
Department of Industrial Engineering, Istanbul Topkapi University, Istanbul, Türkiye
20 shared publications - Ertugrul Ayyildiz
Department of Industrial Engineering, Karadeniz Technical University, Trabzon, Turkiye
10 shared publications - Alev Taskin
Department of Industrial Engineering, Yildiz Technical University, Istanbul, Turkey
7 shared publications Ertugrul Ayyildiz
Karadeniz Technical University
4 shared publications- Gökalp Tulum
Department of Electrical and Electronics Engineering, Faculty of Engineering and Natural Sciences, Istanbul Topkapi University, Prof. Muammer Aksoy Cad. No. 10, Kazlıçeşme, Zeytinburnu, Istanbul 34020, Türkiye
4 shared publications - Onur Osman
Department of Electrical and Electronics Engineering, Istanbul Topkapi University, Istanbul, Turkey
4 shared publications
Latest Publications
- Open Access
- 27 October 2026
- Published by Springer Nature in Scientific Reports
Green infrastructure investment prioritization for urban ecosystem services and resilience: a decision-support framework
Green infrastructure (GI) investments are increasingly promoted as nature-based solutions that generate multiple ecosystem services and contribute to human well-being, climate adaptation, and urban resilience. However, prioritizing GI alternatives is a complex decision problem because different options provide diverse regulating, maintenance/habitat-related, cultural, ecological, technical, and socio-economic benefits under uncertainty. To provide a systematic ecosystem services basis, this study uses the Common International Classification of Ecosystem Services (CICES) as a guiding reference for screening the potential contributions of urban GI alternatives to human well-being. In particular, GI alternatives can be understood as ecosystem service bundles, where interactions and potential synergies among water regulation, biodiversity support, urban cooling, recreation, and public well-being shape their overall contribution to ecosystem management. To address this challenge, this study proposes an integrated Multi criteria Decision Aiding (MCDA) framework for prioritizing GI investment alternatives under uncertainty. The proposed framework combines the Modified Delphi approach, Intuitionistic Fuzzy Step-wise Weight Assessment Ratio Analysis (IF-SWARA), and Intuitionistic Fuzzy Multi-Attributive Border Approximation Area Comparison (IF-MABAC). The Modified Delphi approach is used to validate the criteria and alternatives and consolidate expert judgments, while IF-SWARA determines the relative importance of the evaluation criteria. IF-MABAC is then applied to rank GI investment alternatives. The findings show that Stormwater Management and Flood Mitigation receives the highest criterion weight (0.080), although the overall weight distribution is relatively balanced across the fifteen criteria. Following the IF-MABAC calculation, Constructed Wetlands emerge as the highest-ranked alternative (1.183), followed by Green Walls (0.309), Rain Gardens (0.173), Green Roofs (0.031), and Permeable Pavements (-0.220). Constructed Wetlands show positive relative performance on 12 of the 15 criteria, although trade-offs remain for cost-effectiveness, long-term replacement cost, and technical feasibility. The robustness analyses consistently preserve Constructed Wetlands as the leading alternative, while greater variation is observed among the lower-ranked options. The resulting prioritization is expert-based and context-specific and should therefore be interpreted as conditional on the selected criteria structure, consensus judgments, linguistic scale, and Kayseri planning context. Ultimately, the study contributes to ecosystem services research by offering a CICES-informed, transparent criteria architecture for supporting GI investment decisions rather than a purely methodological innovation.
- 27 October 2026
- Published by Springer Nature in Scientific Reports
Open AccessGreen infrastructure investment prioritization for urban ecosystem services and resilience: a decision-support framework
Green infrastructure (GI) investments are increasingly promoted as nature-based solutions that generate multiple ecosystem services and contribute to human well-being, climate adaptation, and urban resilience. However, prioritizing GI alternatives is a complex decision problem because different options provide diverse regulating, maintenance/habitat-related, cultural, ecological, technical, and socio-economic benefits under uncertainty. To provide a systematic ecosystem services basis, this study uses the Common International Classification of Ecosystem Services (CICES) as a guiding reference for screening the potential contributions of urban GI alternatives to human well-being. In particular, GI alternatives can be understood as ecosystem service bundles, where interactions and potential synergies among water regulation, biodiversity support, urban cooling, recreation, and public well-being shape their overall contribution to ecosystem management. To address this challenge, this study proposes an integrated Multi criteria Decision Aiding (MCDA) framework for prioritizing GI investment alternatives under uncertainty. The proposed framework combines the Modified Delphi approach, Intuitionistic Fuzzy Step-wise Weight Assessment Ratio Analysis (IF-SWARA), and Intuitionistic Fuzzy Multi-Attributive Border Approximation Area Comparison (IF-MABAC). The Modified Delphi approach is used to validate the criteria and alternatives and consolidate expert judgments, while IF-SWARA determines the relative importance of the evaluation criteria. IF-MABAC is then applied to rank GI investment alternatives. The findings show that Stormwater Management and Flood Mitigation receives the highest criterion weight (0.080), although the overall weight distribution is relatively balanced across the fifteen criteria. Following the IF-MABAC calculation, Constructed Wetlands emerge as the highest-ranked alternative (1.183), followed by Green Walls (0.309), Rain Gardens (0.173), Green Roofs (0.031), and Permeable Pavements (-0.220). Constructed Wetlands show positive relative performance on 12 of the 15 criteria, although trade-offs remain for cost-effectiveness, long-term replacement cost, and technical feasibility. The robustness analyses consistently preserve Constructed Wetlands as the leading alternative, while greater variation is observed among the lower-ranked options. The resulting prioritization is expert-based and context-specific and should therefore be interpreted as conditional on the selected criteria structure, consensus judgments, linguistic scale, and Kayseri planning context. Ultimately, the study contributes to ecosystem services research by offering a CICES-informed, transparent criteria architecture for supporting GI investment decisions rather than a purely methodological innovation.
- Open Access
- 14 August 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
A cluster-aware XAI-MCDM framework for province-level solar PV suitability screening in Turkey using real operational PV data
Identifying suitable regions for solar photovoltaic (PV) deployment is commonly addressed through GIS- and multi-criteria decision-making (MCDM)-based frameworks; however, criterion weights in such studies are often derived from expert judgement or purely statistical assumptions rather than from field-observed PV performance. This study proposes a cluster-aware explainable artificial intelligence–MCDM framework that converts operational PV generation data into interpretable meteorological criterion weights for province-level PV suitability screening. In the first stage, a leakage-controlled artificial neural network (ANN) was trained using 47,185 cleaned hourly observations from four operational PV plants in Turkey, including Adıyaman, Bolu, Çanakkale, and Konya. The target variable was defined as capacity-normalized hourly PV performance, and the predictor space was restricted to five transferable meteorological descriptors: solar-radiation-related information, air temperature, relative humidity, cloud cover, and wind speed. The ANN achieved a test R 2 of 0.782 and an nRMSE of 11.92%, indicating sufficient predictive reliability for explainability-based criterion weighting. Multi-XAI analysis, including SHAP, permutation importance, mutual information, and correlation-based relevance, identified the solar-radiation-related descriptor as the dominant driver of PV performance. The derived ANN-XAI weights were integrated with MEREC objective weights and transferred to a performance-priority MCDM ensemble composed of MARCOS, TOPSIS, and EDAS. In the second stage, the calibrated framework was extended to all 81 Turkish provinces using NASA POWER-based meteorological and solar-radiation proxy descriptors, together with applicability-domain risk assessment and solar–climate clustering. Clustering was used as an interpretation and robustness layer to identify comparable solar–climate regimes and to support within-cluster benchmarking rather than to replace the national MCDM ranking. The results identified Mersin as the most robust national candidate, while Burdur, Isparta, Karaman, Konya, Kayseri, Nevşehir, Niğde, and Aksaray formed a strong high-priority province portfolio. Cluster-wise analysis further showed that Turkey can be interpreted through distinct solar–climate regimes, enabling regional candidates to be evaluated within comparable climatic contexts. The proposed framework provides an explainable and data-driven decision-support tool for strategic province-level PV suitability screening, while its outputs should not be interpreted as final parcel-scale siting recommendations.
- 14 August 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Open AccessA cluster-aware XAI-MCDM framework for province-level solar PV suitability screening in Turkey using real operational PV data
Identifying suitable regions for solar photovoltaic (PV) deployment is commonly addressed through GIS- and multi-criteria decision-making (MCDM)-based frameworks; however, criterion weights in such studies are often derived from expert judgement or purely statistical assumptions rather than from field-observed PV performance. This study proposes a cluster-aware explainable artificial intelligence–MCDM framework that converts operational PV generation data into interpretable meteorological criterion weights for province-level PV suitability screening. In the first stage, a leakage-controlled artificial neural network (ANN) was trained using 47,185 cleaned hourly observations from four operational PV plants in Turkey, including Adıyaman, Bolu, Çanakkale, and Konya. The target variable was defined as capacity-normalized hourly PV performance, and the predictor space was restricted to five transferable meteorological descriptors: solar-radiation-related information, air temperature, relative humidity, cloud cover, and wind speed. The ANN achieved a test R 2 of 0.782 and an nRMSE of 11.92%, indicating sufficient predictive reliability for explainability-based criterion weighting. Multi-XAI analysis, including SHAP, permutation importance, mutual information, and correlation-based relevance, identified the solar-radiation-related descriptor as the dominant driver of PV performance. The derived ANN-XAI weights were integrated with MEREC objective weights and transferred to a performance-priority MCDM ensemble composed of MARCOS, TOPSIS, and EDAS. In the second stage, the calibrated framework was extended to all 81 Turkish provinces using NASA POWER-based meteorological and solar-radiation proxy descriptors, together with applicability-domain risk assessment and solar–climate clustering. Clustering was used as an interpretation and robustness layer to identify comparable solar–climate regimes and to support within-cluster benchmarking rather than to replace the national MCDM ranking. The results identified Mersin as the most robust national candidate, while Burdur, Isparta, Karaman, Konya, Kayseri, Nevşehir, Niğde, and Aksaray formed a strong high-priority province portfolio. Cluster-wise analysis further showed that Turkey can be interpreted through distinct solar–climate regimes, enabling regional candidates to be evaluated within comparable climatic contexts. The proposed framework provides an explainable and data-driven decision-support tool for strategic province-level PV suitability screening, while its outputs should not be interpreted as final parcel-scale siting recommendations.
- Open Access
- 5 August 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (15) , 7808
A Data-Driven Framework for Condition Monitoring and Early Warning of Low-Efficiency Events in Photovoltaic Systems
Reliable photovoltaic (PV) operation requires monitoring strategies that can detect performance degradation before it develops into persistent efficiency loss. This study proposes an interpretable data-driven framework for condition monitoring and early warning of low-efficiency events using only inverter-based electrical measurements. The novelty of this study lies in its focus on detecting low-efficiency operating conditions from inverter electrical data, rather than merely classifying individual PV fault types. Thirty-minute operational data from a 110 kW grid-connected PV plant in Kastamonu, Türkiye, covering January 2023–December 2025, were analyzed. Phase currents, phase voltages, total active power, and DC power were transformed into electrical health indicators, including mean current, mean voltage, current and voltage variability, phase imbalance index, and conversion efficiency. Correlation and imbalance analyses showed highly synchronized three-phase operation, with a mean phase imbalance index of 0.004865. Conversion efficiency remained stable, with an instantaneous mean of 0.964. Generalized Additive Model results explained 66.4% of efficiency variability and identified mean current as the dominant nonlinear determinant, while phase imbalance acted as a secondary but significant factor. A Random Forest classifier achieved 96.34% accuracy, 3.87% out-of-bag error, and 53.4% recall for rare low-efficiency events. Decision-tree rules indicated high risk when mean current fell below 9.4 A and very low risk above 12 A. The framework provides a practical, sensor-minimal, and interpretable approach for PV performance monitoring and proactive maintenance.
- 5 August 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (15) , 7808
Open AccessA Data-Driven Framework for Condition Monitoring and Early Warning of Low-Efficiency Events in Photovoltaic Systems
Reliable photovoltaic (PV) operation requires monitoring strategies that can detect performance degradation before it develops into persistent efficiency loss. This study proposes an interpretable data-driven framework for condition monitoring and early warning of low-efficiency events using only inverter-based electrical measurements. The novelty of this study lies in its focus on detecting low-efficiency operating conditions from inverter electrical data, rather than merely classifying individual PV fault types. Thirty-minute operational data from a 110 kW grid-connected PV plant in Kastamonu, Türkiye, covering January 2023–December 2025, were analyzed. Phase currents, phase voltages, total active power, and DC power were transformed into electrical health indicators, including mean current, mean voltage, current and voltage variability, phase imbalance index, and conversion efficiency. Correlation and imbalance analyses showed highly synchronized three-phase operation, with a mean phase imbalance index of 0.004865. Conversion efficiency remained stable, with an instantaneous mean of 0.964. Generalized Additive Model results explained 66.4% of efficiency variability and identified mean current as the dominant nonlinear determinant, while phase imbalance acted as a secondary but significant factor. A Random Forest classifier achieved 96.34% accuracy, 3.87% out-of-bag error, and 53.4% recall for rare low-efficiency events. Decision-tree rules indicated high risk when mean current fell below 9.4 A and very low risk above 12 A. The framework provides a practical, sensor-minimal, and interpretable approach for PV performance monitoring and proactive maintenance.
- Open Access
- 11 July 2026
- Published by Elsevier in Systems and Soft Computing
- Vol. 9
Solving the stochastic and dynamic capacitated vehicle routing problem utilizing advisory board reinforcement learning
- 11 July 2026
- Published by Elsevier in Systems and Soft Computing
- Vol. 9
Open AccessSolving the stochastic and dynamic capacitated vehicle routing problem utilizing advisory board reinforcement learning
- Open Access
- 1 July 2026
- Published by SAGE Publications in Science Progress
- Vol. 109 (3)
Prosthetic restoration material selection using an integrated Fermatean fuzzy MCDM method
Selecting an appropriate dental crown material requires the simultaneous consideration of clinical performance, aesthetics, cost, and patient-related expectations. This study aimed to support dentists in selecting the most suitable dental prosthetic restoration material under uncertainty. An integrated Fermatean fuzzy multi-criteria decision-making (MCDM) framework was employed by combining the CRITIC (Criteria Importance Through Intercriteria Correlation) method for weighting and the WASPAS (Weighted Aggregated Sum Product Assessment) method for ranking alternatives. Six restorative material alternatives were evaluated using eleven sub-criteria grouped under three main dimensions: mechanical, visual, and eco-nomic. The criteria were identified through literature review and expert opinion. The findings indicated that clinical longevity was the most important criterion in the evaluation process. Among the six alternatives, the resin nano-ceramic CAD/CAM material achieved the highest overall performance, followed by the lithium disilicate CAD/CAM and zirconia-based ceramic materials. Across the tested λ values and ±20% changes in the three highest-weighted criteria, the ranking order remained unchanged, indicating that the results were stable within the examined sensitivity scenarios, confirming the robustness of the proposed framework. The proposed framework provides a transparent decision-support tool for restorative dentistry and demonstrates the applicability of Fermatean fuzzy MCDM methods to dental material selection.
- 1 July 2026
- Published by SAGE Publications in Science Progress
- Vol. 109 (3)
Open AccessProsthetic restoration material selection using an integrated Fermatean fuzzy MCDM method
Selecting an appropriate dental crown material requires the simultaneous consideration of clinical performance, aesthetics, cost, and patient-related expectations. This study aimed to support dentists in selecting the most suitable dental prosthetic restoration material under uncertainty. An integrated Fermatean fuzzy multi-criteria decision-making (MCDM) framework was employed by combining the CRITIC (Criteria Importance Through Intercriteria Correlation) method for weighting and the WASPAS (Weighted Aggregated Sum Product Assessment) method for ranking alternatives. Six restorative material alternatives were evaluated using eleven sub-criteria grouped under three main dimensions: mechanical, visual, and eco-nomic. The criteria were identified through literature review and expert opinion. The findings indicated that clinical longevity was the most important criterion in the evaluation process. Among the six alternatives, the resin nano-ceramic CAD/CAM material achieved the highest overall performance, followed by the lithium disilicate CAD/CAM and zirconia-based ceramic materials. Across the tested λ values and ±20% changes in the three highest-weighted criteria, the ranking order remained unchanged, indicating that the results were stable within the examined sensitivity scenarios, confirming the robustness of the proposed framework. The proposed framework provides a transparent decision-support tool for restorative dentistry and demonstrates the applicability of Fermatean fuzzy MCDM methods to dental material selection.
- Open Access
- 20 May 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (10) , 5095
Autonomous Mobile Robot Selection in Smart Warehouses Considering Cybersecurity and Integration Requirements
Autonomous mobile robots (AMRs) are increasingly used in warehouse intralogistics to improve material flow, flexibility, productivity, and operational continuity. However, selecting an appropriate AMR is no longer limited to mechanical performance or acquisition cost, since modern warehouse robots operate as networked cyber-physical systems that must interact with enterprise software, fleet management platforms, communication infrastructures, and cybersecurity mechanisms. This study proposes an integrated Pythagorean fuzzy multi-criteria decision-making (MCDM) framework for evaluating AMR alternatives in warehouse operations by jointly considering economic, technical, physical, software-related, integration-oriented, and security-related criteria. Expert judgments obtained from eight specialists, including four academics and four private-sector professionals, were modeled using Pythagorean fuzzy numbers to capture uncertainty and hesitation in linguistic assessments. The Pythagorean Fuzzy Indifference Threshold-Based Attribute Ratio Analysis (PF-ITARA) method was employed to determine criterion weights based on threshold-sensitive discrimination among alternatives, while Pythagorean Fuzzy VIšekriterijumsko KOmpromisno Rangiranje (PF-VIKOR) was used to rank four AMR alternatives according to a compromise solution logic. The results show that investment cost, maneuverability, total cost of ownership, integration and validation requirements, and ease of programming and commissioning are the most influential criteria. Cybersecurity-related criteria, particularly data confidentiality, system integrity, monitoring and incident response readiness, authentication control, and role-based access control, also received notable importance levels. Among the evaluated alternatives, MiR250 achieved the best overall performance and emerged as the most suitable compromise solution, followed by OMRON LD-250, HIKROBOT Forklift AGV, and KUKA KMP 600-S diffDrive. The proposed framework provides a transparent and practically applicable decision-support tool for AMR procurement by integrating operational performance, digital interoperability, and cybersecurity readiness into a unified evaluation structure.
- 20 May 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (10) , 5095
Open AccessAutonomous Mobile Robot Selection in Smart Warehouses Considering Cybersecurity and Integration Requirements
Autonomous mobile robots (AMRs) are increasingly used in warehouse intralogistics to improve material flow, flexibility, productivity, and operational continuity. However, selecting an appropriate AMR is no longer limited to mechanical performance or acquisition cost, since modern warehouse robots operate as networked cyber-physical systems that must interact with enterprise software, fleet management platforms, communication infrastructures, and cybersecurity mechanisms. This study proposes an integrated Pythagorean fuzzy multi-criteria decision-making (MCDM) framework for evaluating AMR alternatives in warehouse operations by jointly considering economic, technical, physical, software-related, integration-oriented, and security-related criteria. Expert judgments obtained from eight specialists, including four academics and four private-sector professionals, were modeled using Pythagorean fuzzy numbers to capture uncertainty and hesitation in linguistic assessments. The Pythagorean Fuzzy Indifference Threshold-Based Attribute Ratio Analysis (PF-ITARA) method was employed to determine criterion weights based on threshold-sensitive discrimination among alternatives, while Pythagorean Fuzzy VIšekriterijumsko KOmpromisno Rangiranje (PF-VIKOR) was used to rank four AMR alternatives according to a compromise solution logic. The results show that investment cost, maneuverability, total cost of ownership, integration and validation requirements, and ease of programming and commissioning are the most influential criteria. Cybersecurity-related criteria, particularly data confidentiality, system integrity, monitoring and incident response readiness, authentication control, and role-based access control, also received notable importance levels. Among the evaluated alternatives, MiR250 achieved the best overall performance and emerged as the most suitable compromise solution, followed by OMRON LD-250, HIKROBOT Forklift AGV, and KUKA KMP 600-S diffDrive. The proposed framework provides a transparent and practically applicable decision-support tool for AMR procurement by integrating operational performance, digital interoperability, and cybersecurity readiness into a unified evaluation structure.
- Open Access
- 18 April 2026
- Published by MDPI AG in Mathematics
- Vol. 14 (8) , 1356
Hybrid Application of Multi-Criteria Decision-Making Methods for Municipal Investments: A Case Study Focusing on Equity in Istanbul
Equitable prioritization of public investments is increasingly critical as municipalities face constrained budgets, heterogeneous neighborhood needs, and demands for transparent decisions. This paper proposes a fairness-aware group multi-criteria decision-making (MCDM) framework for ranking municipal infrastructure investments when budgets are constrained, and neighborhood needs differ. Six alternatives are assessed in the Istanbul case study: flood risk mitigation, inclusive public realm and cooling, smart and energy-efficient municipal assets, walking and cycling infrastructure, healthcare access improvements, and seismic retrofitting of public buildings. The criteria system combines efficiency, implementability, socio-environmental performance, and equity-oriented priorities through five main dimensions and 23 sub-criteria. In addition to cost, feasibility, and service effectiveness, the framework incorporates fairness-related criteria such as baseline need and deficit severity, vulnerability-targeting effectiveness, minimum service guarantee for the worst-off, and priority for low-accessibility centers. Public acceptance and environmental performance are also included. Stakeholder panels provide expert judgments using intuitionistic fuzzy sets, capturing membership, non-membership, and hesitation to reflect uncertainty. Criteria weights are derived with Intuitionistic Fuzzy Step-wise Weight Assessment Ratio Analysis (IF-SWARA), enabling importance elicitation and group aggregation without forcing crisp consensus. Alternatives are then ranked using Intuitionistic Fuzzy Combined Compromise Solution (IF-CoCoSo), which blends additive and multiplicative compromise solutions to balance overall performance with equity objectives. Robustness is assessed through sensitivity analysis by varying the γ parameter within the IF-CoCoSo procedure. A municipal case study demonstrates that healthcare access improvements achieve the highest compromise performance, followed by flood risk mitigation and seismic retrofitting of public buildings, while smart and energy-efficient municipal assets rank last. The findings confirm that explicitly embedding fairness criteria can shift municipal priorities toward alternatives that more directly reduce deprivation, risk, and spatial inequality. The main contribution of this study is not merely empirical application, but the development of a fairness-aware group MCDM framework that operationalizes distributive justice in municipal investment prioritization through a structured set of criteria.
- 18 April 2026
- Published by MDPI AG in Mathematics
- Vol. 14 (8) , 1356
Open AccessHybrid Application of Multi-Criteria Decision-Making Methods for Municipal Investments: A Case Study Focusing on Equity in Istanbul
Equitable prioritization of public investments is increasingly critical as municipalities face constrained budgets, heterogeneous neighborhood needs, and demands for transparent decisions. This paper proposes a fairness-aware group multi-criteria decision-making (MCDM) framework for ranking municipal infrastructure investments when budgets are constrained, and neighborhood needs differ. Six alternatives are assessed in the Istanbul case study: flood risk mitigation, inclusive public realm and cooling, smart and energy-efficient municipal assets, walking and cycling infrastructure, healthcare access improvements, and seismic retrofitting of public buildings. The criteria system combines efficiency, implementability, socio-environmental performance, and equity-oriented priorities through five main dimensions and 23 sub-criteria. In addition to cost, feasibility, and service effectiveness, the framework incorporates fairness-related criteria such as baseline need and deficit severity, vulnerability-targeting effectiveness, minimum service guarantee for the worst-off, and priority for low-accessibility centers. Public acceptance and environmental performance are also included. Stakeholder panels provide expert judgments using intuitionistic fuzzy sets, capturing membership, non-membership, and hesitation to reflect uncertainty. Criteria weights are derived with Intuitionistic Fuzzy Step-wise Weight Assessment Ratio Analysis (IF-SWARA), enabling importance elicitation and group aggregation without forcing crisp consensus. Alternatives are then ranked using Intuitionistic Fuzzy Combined Compromise Solution (IF-CoCoSo), which blends additive and multiplicative compromise solutions to balance overall performance with equity objectives. Robustness is assessed through sensitivity analysis by varying the γ parameter within the IF-CoCoSo procedure. A municipal case study demonstrates that healthcare access improvements achieve the highest compromise performance, followed by flood risk mitigation and seismic retrofitting of public buildings, while smart and energy-efficient municipal assets rank last. The findings confirm that explicitly embedding fairness criteria can shift municipal priorities toward alternatives that more directly reduce deprivation, risk, and spatial inequality. The main contribution of this study is not merely empirical application, but the development of a fairness-aware group MCDM framework that operationalizes distributive justice in municipal investment prioritization through a structured set of criteria.
- Open Access
- 1 April 2026
- Published by SAGE Publications in Science Progress
- Vol. 109 (2)
Location selection of emergency support and logistics centers under complex urban infrastructure disruptions
Complex urban infrastructure disruptions can affect transportation, communication, and logistics systems simultaneously, forcing emergency operations to address both disaster relief and infrastructure restoration. This study proposes a multi-criteria decision framework under uncertainty to select Emergency Support and Logistics Center (ESLC) locations. The problem is modeled using five main criteria and 29 sub criteria covering demand and service level, logistics infrastructure and accessibility, cost and economy, risk and resilience, and governance and social factors. Criteria weights are obtained via the Best Worst Method (BWM), and candidate sites are ranked using Pythagorean Fuzzy Combinative Distance based Assessment (PF-CODAS), which evaluates alternatives through Pythagorean fuzzy (PF) membership and non-membership degrees and their distances from the Negative Ideal Solution (NIS). Results support a continuity-driven siting logic where Logistics “Infrastructure & Accessibility” is the dominant criterion and “Risk & Resilience” ranks second, reflecting the importance of network capability and hazard avoidance. The ranking identifies Hasdal (A3) as the best option (27.8005), followed by Hadımköy (A2) (10.1584) and Kurtköy (A5) (−2.2606). The proposed framework offers a transparent and reusable decision aid for ESLC planning in cities exposed to integrated infrastructure threats.
- 1 April 2026
- Published by SAGE Publications in Science Progress
- Vol. 109 (2)
Open AccessLocation selection of emergency support and logistics centers under complex urban infrastructure disruptions
Complex urban infrastructure disruptions can affect transportation, communication, and logistics systems simultaneously, forcing emergency operations to address both disaster relief and infrastructure restoration. This study proposes a multi-criteria decision framework under uncertainty to select Emergency Support and Logistics Center (ESLC) locations. The problem is modeled using five main criteria and 29 sub criteria covering demand and service level, logistics infrastructure and accessibility, cost and economy, risk and resilience, and governance and social factors. Criteria weights are obtained via the Best Worst Method (BWM), and candidate sites are ranked using Pythagorean Fuzzy Combinative Distance based Assessment (PF-CODAS), which evaluates alternatives through Pythagorean fuzzy (PF) membership and non-membership degrees and their distances from the Negative Ideal Solution (NIS). Results support a continuity-driven siting logic where Logistics “Infrastructure & Accessibility” is the dominant criterion and “Risk & Resilience” ranks second, reflecting the importance of network capability and hazard avoidance. The ranking identifies Hasdal (A3) as the best option (27.8005), followed by Hadımköy (A2) (10.1584) and Kurtköy (A5) (−2.2606). The proposed framework offers a transparent and reusable decision aid for ESLC planning in cities exposed to integrated infrastructure threats.
- Open Access
- 18 March 2026
- Published by MDPI AG in Algorithms
- Vol. 19 (3) , 230
A Multi-Agent Advisory Board Reinforcement Learning Framework for Adaptive Cooperative Control
This study proposes Advisory Board Reinforcement Learning (AdvB-RL), a cooperative reinforcement-learning framework that integrates multiple advisory neural networks to guide policy optimization. Unlike conventional single-agent architectures, AdvB-RL maintains a set of independently trained advisory networks that contribute to action selection through a dynamic aggregation mechanism. This design preserves diverse experiential knowledge while improving learning stability and the exploration–exploitation balance. The framework is evaluated on three benchmark control tasks, namely LunarLander-v2, CartPole-v1, and MountainCar-v0, using advisory board sizes of 1, 5, and 10 members against a Double Deep Q-Network (DDQN) baseline. The best-performing configuration, 10 AdvB, achieved 270.02 ± 24.74 on LunarLander-v2 versus 227.92 ± 86.02 for DDQN, 497.79 ± 5.18 on CartPole-v1 versus 304.37 ± 144.04, and −103.16 ± 15.46 on MountainCar-v0 versus −130.71 ± 31.64, indicating higher returns together with markedly lower variability. Across the three environments, these results show that increasing the number of advisory members improves both reward consistency and overall robustness, with the 10-member setting providing the strongest performance. Within the tested configurations, the advisory board mechanism remains computationally feasible, while preliminary experiments beyond 10 advisors show diminishing returns relative to added complexity. Overall, AdvB-RL provides a robust and modular alternative to single-policy reinforcement learning for adaptive cooperative control.
- 18 March 2026
- Published by MDPI AG in Algorithms
- Vol. 19 (3) , 230
Open AccessA Multi-Agent Advisory Board Reinforcement Learning Framework for Adaptive Cooperative Control
This study proposes Advisory Board Reinforcement Learning (AdvB-RL), a cooperative reinforcement-learning framework that integrates multiple advisory neural networks to guide policy optimization. Unlike conventional single-agent architectures, AdvB-RL maintains a set of independently trained advisory networks that contribute to action selection through a dynamic aggregation mechanism. This design preserves diverse experiential knowledge while improving learning stability and the exploration–exploitation balance. The framework is evaluated on three benchmark control tasks, namely LunarLander-v2, CartPole-v1, and MountainCar-v0, using advisory board sizes of 1, 5, and 10 members against a Double Deep Q-Network (DDQN) baseline. The best-performing configuration, 10 AdvB, achieved 270.02 ± 24.74 on LunarLander-v2 versus 227.92 ± 86.02 for DDQN, 497.79 ± 5.18 on CartPole-v1 versus 304.37 ± 144.04, and −103.16 ± 15.46 on MountainCar-v0 versus −130.71 ± 31.64, indicating higher returns together with markedly lower variability. Across the three environments, these results show that increasing the number of advisory members improves both reward consistency and overall robustness, with the 10-member setting providing the strongest performance. Within the tested configurations, the advisory board mechanism remains computationally feasible, while preliminary experiments beyond 10 advisors show diminishing returns relative to added complexity. Overall, AdvB-RL provides a robust and modular alternative to single-policy reinforcement learning for adaptive cooperative control.
- Open Access
- 26 February 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Estimation of liquefaction-induced settlement of shallow foundation by machine learning with imbalanced data
Estimating the level of earthquake-induced liquefaction settlements in shallow foundations is essential for assessing seismic risk and designing effective soil improvement strategies. Reliable predicting methods of vertical deformations and tilting in buildings founded on shallow liquefiable soils enable the development of seismic-resilient and cost-effective foundation solutions while supporting informed decision-making in earthquake insurance and mitigation planning. This study presents a comparative analysis of machine learning and deep learning models for classifying liquefaction-induced building settlements using a systematically compiled database of documented case studies. The dataset integrates building characteristics, geotechnical parameters, and seismic intensity indicators. Different kinds of resampling methods working at data level, cost-sensitive learning strategies, and algorithm-level advancements were studied in detail to treat extremely skewed class distribution. A SHAP-based feature selection method was applied as an extension to identify the most influential predictors, optimizing model efficiency without sacrificing predictive performance. Moreover, to improve classification reliability, dynamic threshold tuning and ensemble learning with weighted voting was employed. The result points out that data-driven feature selection and threshold optimization can better classify seismic damage, thus offering geotechnical earthquake engineering applications a methodology that is both interpretable and computationally efficient.
- 26 February 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Open AccessEstimation of liquefaction-induced settlement of shallow foundation by machine learning with imbalanced data
Estimating the level of earthquake-induced liquefaction settlements in shallow foundations is essential for assessing seismic risk and designing effective soil improvement strategies. Reliable predicting methods of vertical deformations and tilting in buildings founded on shallow liquefiable soils enable the development of seismic-resilient and cost-effective foundation solutions while supporting informed decision-making in earthquake insurance and mitigation planning. This study presents a comparative analysis of machine learning and deep learning models for classifying liquefaction-induced building settlements using a systematically compiled database of documented case studies. The dataset integrates building characteristics, geotechnical parameters, and seismic intensity indicators. Different kinds of resampling methods working at data level, cost-sensitive learning strategies, and algorithm-level advancements were studied in detail to treat extremely skewed class distribution. A SHAP-based feature selection method was applied as an extension to identify the most influential predictors, optimizing model efficiency without sacrificing predictive performance. Moreover, to improve classification reliability, dynamic threshold tuning and ensemble learning with weighted voting was employed. The result points out that data-driven feature selection and threshold optimization can better classify seismic damage, thus offering geotechnical earthquake engineering applications a methodology that is both interpretable and computationally efficient.