Multilevel image segmentation is a critical task in image analysis,which imposes high requirements on the global search capability and convergence efficiency of segmentation algorithms.In this paper,an improved Artifi...Multilevel image segmentation is a critical task in image analysis,which imposes high requirements on the global search capability and convergence efficiency of segmentation algorithms.In this paper,an improved Artificial Protozoa Optimization algorithm,termed the two-stage Taguchi-assisted Gaussian–Levy Artificial Protozoa Optimization(TGAPO)algorithm,is proposed and applied tomultilevel image segmentation.The proposed algorithm adopts a two-stage evolutionary mechanism.In the first stage,Gaussian perturbation is introduced to enhance local search capability;in the second stage,Levy flight is incorporated to expand the global search range;and finally,the Taguchi strategy is employed to further refine the optimal solution.Consequently,the global optimization performance and robustness of the algorithm are significantly improved.To evaluate the effectiveness of the proposed TGAPO algorithm,comparative experiments are conducted with representative optimization algorithms,including the Grey Wolf Optimizer(GWO)and Particle Swarm Optimization(PSO),in the context ofmultilevel image segmentation.The segmentation quality is assessed using the minimum cross-entropy function as the performance metric.Experimental results demonstrate that the TGAPO algorithm outperforms the comparison algorithms in terms of segmentation accuracy and convergence speed,and exhibits superior stability in high-threshold segmentation tasks.Furthermore,the proposedmethod achieves excellentmulti-threshold segmentation performance for color images and shows strong potential for practical applications.展开更多
Energy system optimization has become crucial for enhancing efficiency and environmental sustainability.This comprehensive review examines the synergistic application of Artificial Neural Networks(ANN)and Taguchi meth...Energy system optimization has become crucial for enhancing efficiency and environmental sustainability.This comprehensive review examines the synergistic application of Artificial Neural Networks(ANN)and Taguchi methods in optimizing diverse energy systems.While previous reviews have focused on these methods separately,this paper presents the first integrated analysis of both approaches across multiple energy applications.We systematically analyze their implementation in:Internal combustion engines,Thermal energy storage systems,Solar energy systems,Wind and tidal turbines,Heat exchangers,and hybrid energy systems.Our findings reveal that ANN models consistently achieve prediction accuracies exceeding 90%when compared to experimental data,while Taguchi-based methods combined with Grey Relational Analysis(GRA)or TOPSIS can improve system performance by up to 20%30%in multi-objective optimization scenarios.The review introduces novel frameworks for combining these methods and provides critical insights into their complementary strengths.Key statistical metrics,including determination coefficients and error analyses,validate the superior performance of integrated approaches.This work serves as a foundational reference for researchers and practitioners in energy system optimization,offering structured methodologies and future research directions.展开更多
Understanding the complex interaction between heat and mass transfer in non-Newtonian microflows is essential for the development and optimization of efficient microfluidic and thermal management systems.This study in...Understanding the complex interaction between heat and mass transfer in non-Newtonian microflows is essential for the development and optimization of efficient microfluidic and thermal management systems.This study investigates the magnetohydrodynamic(MHD)thermosolutal convection of a Casson fluid within an inclined,porous microchannel subjected to convective boundary conditions.The nonlinear,coupled equations governing momentum,energy,and species transport are solved numerically using the MATLAB bvp4c solver,ensuring high numerical accuracy and stability.To identify the dominant parameters influencing flow behavior and to optimize transport performance,a comprehensive hybrid optimization framework—combining a modified Taguchi design,Grey Relational Analysis(GRA),and Principal Component Analysis(PCA)—is proposed.This integrated strategy enables the simultaneous assessment of skin friction,Nusselt number,and Sherwood number,providing a rigorous multi-objective evaluation of system performance.Comparative validation with benchmark results from the literature confirms the accuracy and reliability of the present formulation and its numerical implementation.The results highlight the intricate coupling among flow slip,buoyancy effects,and convective transport mechanisms.Increased slip flow enhances axial velocity,while a higher solutal Biot number intensifies concentration gradients near the channel walls.Conversely,a lower thermal Biot number diminishes the temperature field,indicating weaker heat transfer across the boundaries.PCA results reveal that the first principal component(PC1)accounts for most of the system variance,demonstrating the dominant influence of coupled flow and transport parameters on overall system performance.展开更多
文摘Multilevel image segmentation is a critical task in image analysis,which imposes high requirements on the global search capability and convergence efficiency of segmentation algorithms.In this paper,an improved Artificial Protozoa Optimization algorithm,termed the two-stage Taguchi-assisted Gaussian–Levy Artificial Protozoa Optimization(TGAPO)algorithm,is proposed and applied tomultilevel image segmentation.The proposed algorithm adopts a two-stage evolutionary mechanism.In the first stage,Gaussian perturbation is introduced to enhance local search capability;in the second stage,Levy flight is incorporated to expand the global search range;and finally,the Taguchi strategy is employed to further refine the optimal solution.Consequently,the global optimization performance and robustness of the algorithm are significantly improved.To evaluate the effectiveness of the proposed TGAPO algorithm,comparative experiments are conducted with representative optimization algorithms,including the Grey Wolf Optimizer(GWO)and Particle Swarm Optimization(PSO),in the context ofmultilevel image segmentation.The segmentation quality is assessed using the minimum cross-entropy function as the performance metric.Experimental results demonstrate that the TGAPO algorithm outperforms the comparison algorithms in terms of segmentation accuracy and convergence speed,and exhibits superior stability in high-threshold segmentation tasks.Furthermore,the proposedmethod achieves excellentmulti-threshold segmentation performance for color images and shows strong potential for practical applications.
文摘Energy system optimization has become crucial for enhancing efficiency and environmental sustainability.This comprehensive review examines the synergistic application of Artificial Neural Networks(ANN)and Taguchi methods in optimizing diverse energy systems.While previous reviews have focused on these methods separately,this paper presents the first integrated analysis of both approaches across multiple energy applications.We systematically analyze their implementation in:Internal combustion engines,Thermal energy storage systems,Solar energy systems,Wind and tidal turbines,Heat exchangers,and hybrid energy systems.Our findings reveal that ANN models consistently achieve prediction accuracies exceeding 90%when compared to experimental data,while Taguchi-based methods combined with Grey Relational Analysis(GRA)or TOPSIS can improve system performance by up to 20%30%in multi-objective optimization scenarios.The review introduces novel frameworks for combining these methods and provides critical insights into their complementary strengths.Key statistical metrics,including determination coefficients and error analyses,validate the superior performance of integrated approaches.This work serves as a foundational reference for researchers and practitioners in energy system optimization,offering structured methodologies and future research directions.
文摘Understanding the complex interaction between heat and mass transfer in non-Newtonian microflows is essential for the development and optimization of efficient microfluidic and thermal management systems.This study investigates the magnetohydrodynamic(MHD)thermosolutal convection of a Casson fluid within an inclined,porous microchannel subjected to convective boundary conditions.The nonlinear,coupled equations governing momentum,energy,and species transport are solved numerically using the MATLAB bvp4c solver,ensuring high numerical accuracy and stability.To identify the dominant parameters influencing flow behavior and to optimize transport performance,a comprehensive hybrid optimization framework—combining a modified Taguchi design,Grey Relational Analysis(GRA),and Principal Component Analysis(PCA)—is proposed.This integrated strategy enables the simultaneous assessment of skin friction,Nusselt number,and Sherwood number,providing a rigorous multi-objective evaluation of system performance.Comparative validation with benchmark results from the literature confirms the accuracy and reliability of the present formulation and its numerical implementation.The results highlight the intricate coupling among flow slip,buoyancy effects,and convective transport mechanisms.Increased slip flow enhances axial velocity,while a higher solutal Biot number intensifies concentration gradients near the channel walls.Conversely,a lower thermal Biot number diminishes the temperature field,indicating weaker heat transfer across the boundaries.PCA results reveal that the first principal component(PC1)accounts for most of the system variance,demonstrating the dominant influence of coupled flow and transport parameters on overall system performance.
