Test case prioritization and ranking play a crucial role in software testing by improving fault detection efficiency and ensuring software reliability.While prioritization selects the most relevant test cases for opti...Test case prioritization and ranking play a crucial role in software testing by improving fault detection efficiency and ensuring software reliability.While prioritization selects the most relevant test cases for optimal coverage,ranking further refines their execution order to detect critical faults earlier.This study investigates machine learning techniques to enhance both prioritization and ranking,contributing to more effective and efficient testing processes.We first employ advanced feature engineering alongside ensemble models,including Gradient Boosted,Support Vector Machines,Random Forests,and Naive Bayes classifiers to optimize test case prioritization,achieving an accuracy score of 0.98847 and significantly improving the Average Percentage of Fault Detection(APFD).Subsequently,we introduce a deep Q-learning framework combined with a Genetic Algorithm(GA)to refine test case ranking within priority levels.This approach achieves a rank accuracy of 0.9172,demonstrating robust performance despite the increasing computational demands of specialized variation operators.Our findings highlight the effectiveness of stacked ensemble learning and reinforcement learning in optimizing test case prioritization and ranking.This integrated approach improves testing efficiency,reduces late-stage defects,and improves overall software stability.The study provides valuable information for AI-driven testing frameworks,paving the way for more intelligent and adaptive software quality assurance methodologies.展开更多
Annual haze in Northern Thailand has become increasingly severe,impacting health and the environment.How-ever,the sources of the haze remain poorly quantified due to limited observational data on aerosol molecular tra...Annual haze in Northern Thailand has become increasingly severe,impacting health and the environment.How-ever,the sources of the haze remain poorly quantified due to limited observational data on aerosol molecular tracers.This study comprehensively investigates chemical composition of PM_(2.5),including both inorganic and organic compounds throughout haze and post-haze periods in 2019 at a rural site of Northern Thailand.Average PM_(2.5) concentrations during haze and post-haze period were 87±36 and 21±11μg/m^(3),respectively.Organic matter was the dominant contributor in PM_(2.5) mass,followed by water soluble inorganic ions and mineral dust.Molecular markers,including levoglucosan,dehydroabietic acid,and 4-nitrocatechol,and ions(Cl^(-),and K^(+)),were used to characterize low haze(PM_(2.5)<100μg/m^(3))and episodic haze(PM_(2.5)>100μg/m^(3)).Low haze is associated with local aerosols from agricultural waste burning,while episodic haze is linked to aged aerosols from mixed agricultural waste,softwood,and hardwood burning.Source apportionment incorporating these molecular markers in receptor modelling(Positive matrix factorization),identified three distinct biomass burning sources:mixed,local,and aged biomass burnings,contributing 31,19 and 13%of PM_(2.5) during haze period.During post-haze period,contributions shifted,with local biomass burning(32%)comparable to secondary sulfate(34%)and mixed dust and traffic sources(26%).These findings demonstrate that both regional and local sources con-tribute to severe haze,highlighting the need for integrated policies for cross-border cooperation as well as stricter regulations to reduce biomass burning in Northern Thailand and Southeast Asia.展开更多
Functionally graded cellular structures(FGCSs)have a multitude of applications to a wide range of industries.Utilising the ever-progressing technology of additive manufacturing(AM),FGCSs can be applied to control mate...Functionally graded cellular structures(FGCSs)have a multitude of applications to a wide range of industries.Utilising the ever-progressing technology of additive manufacturing(AM),FGCSs can be applied to control material grading and achieve the desired mechanical properties.The current study explores the design and optimisation of FGCSs for AM,with a focus on improving the compression and impact performance of below knee(BK)prosthetic limbs made of thermoplastic polyurethane(TPU).A multiscale research methodology integrating topology optimization(TO),finite element analysis(FEA),and design of experiments(Do E)was adopted to optimise lattice structures in terms of stiffness and lightweight properties.Two-unit cell designs were considered in the study:Schwarz P gyroid and body-centered cubic(BCC).Response surface methodology(RSM)was implemented to analyse the effect of minimum and maximum cell wall thickness,cell size,and unit cell type on the mechanical performance of TPU FGCS structures.The results indicated that a Schwarz P FGCS structure with cell size,minimum and maximum cell wall thickness of 6,0.9 and 2.8 mm,respectively,could be optimal for a compromise between performance and weight.In this optimized case,stiffness and volume fraction values of 684 N/mm and 0.64 were obtained,respectively.The study also presents a proof-of-concept design for a BK prosthetic damper,highlighting the potential of FGCSs to enhance patient comfort,reduce manufacturing costs,and enable personalised designs through 3D scanning and AM.The obtained results could be a step forward towards the incorporation of AM technologies in prosthetics,offering a pathway to lightweight,cost-effective,and functionally tailored solutions.展开更多
轨旁储能装置(wayside energy storage device,WESD)具有大容量、大功率、转换高效等优势,为未来轨道交通节能运行提供了新的解决方案。针对发生延误后多列车调度和节能运行优化问题,提出了一种综合考虑节能运行和旅客需求的调度优化方...轨旁储能装置(wayside energy storage device,WESD)具有大容量、大功率、转换高效等优势,为未来轨道交通节能运行提供了新的解决方案。针对发生延误后多列车调度和节能运行优化问题,提出了一种综合考虑节能运行和旅客需求的调度优化方法。将轨旁储能与列车运行状态切换控制、时刻表调整相结合,在考虑坡度的情况下对同一供电区段内多个列车的到发时间、运行速度和牵引、惰行、制动等运行状态进行协同调控优化,以提高再生制动能量的直接利用率,有效降低对WESD的容量要求。仿真结果表明,所提方法可以降低WESD的累计储能容量,实现列车节能运行。展开更多
文摘Test case prioritization and ranking play a crucial role in software testing by improving fault detection efficiency and ensuring software reliability.While prioritization selects the most relevant test cases for optimal coverage,ranking further refines their execution order to detect critical faults earlier.This study investigates machine learning techniques to enhance both prioritization and ranking,contributing to more effective and efficient testing processes.We first employ advanced feature engineering alongside ensemble models,including Gradient Boosted,Support Vector Machines,Random Forests,and Naive Bayes classifiers to optimize test case prioritization,achieving an accuracy score of 0.98847 and significantly improving the Average Percentage of Fault Detection(APFD).Subsequently,we introduce a deep Q-learning framework combined with a Genetic Algorithm(GA)to refine test case ranking within priority levels.This approach achieves a rank accuracy of 0.9172,demonstrating robust performance despite the increasing computational demands of specialized variation operators.Our findings highlight the effectiveness of stacked ensemble learning and reinforcement learning in optimizing test case prioritization and ranking.This integrated approach improves testing efficiency,reduces late-stage defects,and improves overall software stability.The study provides valuable information for AI-driven testing frameworks,paving the way for more intelligent and adaptive software quality assurance methodologies.
文摘Annual haze in Northern Thailand has become increasingly severe,impacting health and the environment.How-ever,the sources of the haze remain poorly quantified due to limited observational data on aerosol molecular tracers.This study comprehensively investigates chemical composition of PM_(2.5),including both inorganic and organic compounds throughout haze and post-haze periods in 2019 at a rural site of Northern Thailand.Average PM_(2.5) concentrations during haze and post-haze period were 87±36 and 21±11μg/m^(3),respectively.Organic matter was the dominant contributor in PM_(2.5) mass,followed by water soluble inorganic ions and mineral dust.Molecular markers,including levoglucosan,dehydroabietic acid,and 4-nitrocatechol,and ions(Cl^(-),and K^(+)),were used to characterize low haze(PM_(2.5)<100μg/m^(3))and episodic haze(PM_(2.5)>100μg/m^(3)).Low haze is associated with local aerosols from agricultural waste burning,while episodic haze is linked to aged aerosols from mixed agricultural waste,softwood,and hardwood burning.Source apportionment incorporating these molecular markers in receptor modelling(Positive matrix factorization),identified three distinct biomass burning sources:mixed,local,and aged biomass burnings,contributing 31,19 and 13%of PM_(2.5) during haze period.During post-haze period,contributions shifted,with local biomass burning(32%)comparable to secondary sulfate(34%)and mixed dust and traffic sources(26%).These findings demonstrate that both regional and local sources con-tribute to severe haze,highlighting the need for integrated policies for cross-border cooperation as well as stricter regulations to reduce biomass burning in Northern Thailand and Southeast Asia.
基金financially supported and funded by the Deanship of Scientific Research at Imam Mohammad Ibn Saud Islamic University(IMSIU)(No.IMSIU-DDRSP2503)。
文摘Functionally graded cellular structures(FGCSs)have a multitude of applications to a wide range of industries.Utilising the ever-progressing technology of additive manufacturing(AM),FGCSs can be applied to control material grading and achieve the desired mechanical properties.The current study explores the design and optimisation of FGCSs for AM,with a focus on improving the compression and impact performance of below knee(BK)prosthetic limbs made of thermoplastic polyurethane(TPU).A multiscale research methodology integrating topology optimization(TO),finite element analysis(FEA),and design of experiments(Do E)was adopted to optimise lattice structures in terms of stiffness and lightweight properties.Two-unit cell designs were considered in the study:Schwarz P gyroid and body-centered cubic(BCC).Response surface methodology(RSM)was implemented to analyse the effect of minimum and maximum cell wall thickness,cell size,and unit cell type on the mechanical performance of TPU FGCS structures.The results indicated that a Schwarz P FGCS structure with cell size,minimum and maximum cell wall thickness of 6,0.9 and 2.8 mm,respectively,could be optimal for a compromise between performance and weight.In this optimized case,stiffness and volume fraction values of 684 N/mm and 0.64 were obtained,respectively.The study also presents a proof-of-concept design for a BK prosthetic damper,highlighting the potential of FGCSs to enhance patient comfort,reduce manufacturing costs,and enable personalised designs through 3D scanning and AM.The obtained results could be a step forward towards the incorporation of AM technologies in prosthetics,offering a pathway to lightweight,cost-effective,and functionally tailored solutions.
文摘轨旁储能装置(wayside energy storage device,WESD)具有大容量、大功率、转换高效等优势,为未来轨道交通节能运行提供了新的解决方案。针对发生延误后多列车调度和节能运行优化问题,提出了一种综合考虑节能运行和旅客需求的调度优化方法。将轨旁储能与列车运行状态切换控制、时刻表调整相结合,在考虑坡度的情况下对同一供电区段内多个列车的到发时间、运行速度和牵引、惰行、制动等运行状态进行协同调控优化,以提高再生制动能量的直接利用率,有效降低对WESD的容量要求。仿真结果表明,所提方法可以降低WESD的累计储能容量,实现列车节能运行。
