This study introduces a Landscape Information Modeling±Stable Diffusion(LIM±SD)-based digital workflow for ecological engineered landscaping(EEL)design,focusing on urban river wetlands.It explores how studen...This study introduces a Landscape Information Modeling±Stable Diffusion(LIM±SD)-based digital workflow for ecological engineered landscaping(EEL)design,focusing on urban river wetlands.It explores how students from diverse academic backgrounds perform EEL tasks using the LIM±SD approach.A total of 30 participants,including industrial design postgraduates and landscape architecture undergraduates and postgraduates,completed the design tasks.The efficacy of their designs was assessed through expert evaluations on site appropriateness,aesthetics,spatial layout,and eco-engineering techniques of the design proposals,as well as the parametric simulation which calculated the vegetation coverage rate and proportion of riparian areas for each design.Moreover,evaluation of participants’subjective design experiences was conducted via questionnaires.Results indicated that landscape architecture postgraduates outperformed others applying ecological engineering principles.The study also elucidated discrepancies between LIM models and SD-generated renderings,as well as the uncertainty of SDgenerated renderings,suggesting improvements are needed to align digital outputs with ecological design criteria.展开更多
目的探究“非遗+AI”新模式下湖南土特产包装的创新设计形式,传承和发展非遗文化,提升土特产包装的文化内涵,提高传统包装的科技含量,以适应当代消费者不断提升的审美和消费需求。方法通过问卷调查、深度访谈等方法,分析“非遗+AI”模...目的探究“非遗+AI”新模式下湖南土特产包装的创新设计形式,传承和发展非遗文化,提升土特产包装的文化内涵,提高传统包装的科技含量,以适应当代消费者不断提升的审美和消费需求。方法通过问卷调查、深度访谈等方法,分析“非遗+AI”模式与当代湖南土特产包装的设计现状,了解消费者对包装设计的不同需求,总结设计策略,并基于“非遗+AI”新模式下机器学习和深度学习技术,借助SD(Stable Diffusion,稳定扩散模型)架构下的Lora模型(Low-RankAdaptation of Large Language Models,大语言模型的低秩适用方法),进行踏虎凿花在岳阳王鸽土特产包装设计中的创新应用实践。结果生成出紧跟新时代数字技术,驱动非遗文化活态传承的包装设计图案,从而实现湖南土特产包装的创新设计探索。结论基于“非遗+AI”模式下的SD模型技术,对泸溪踏虎凿花进行创新转化并应用在湖南土特产岳阳王鸽包装设计中,既活化了传统手工艺的表达形式,又创新了土特产的包装表现手法,为其他非遗文化元素和产品包装的有机融合提供了新路径。展开更多
The distribution of material phases is crucial to determine the composite’s mechanical property.While the full structure-mechanics relationship of highly ordered material distributions can be studied with finite numb...The distribution of material phases is crucial to determine the composite’s mechanical property.While the full structure-mechanics relationship of highly ordered material distributions can be studied with finite number of cases,this relationship is difficult to be revealed for complex irregular distributions,preventing design of such material structures to meet certain mechanical requirements.The noticeable developments of artificial intelligence(AI)algorithms in material design enables to detect the hidden structure-mechanics correlations which is essential for designing composite of complex structures.It is intriguing how these tools can assist composite design.Here,we focus on the rapid generation of bicontinuous composite structures together with the stress distribution in loading.We find that generative AI,enabled through fine-tuned Low Rank Adaptation models,can be trained with a few inputs to generate both synthetic composite structures and the corresponding von Mises stress distribution.The results show that this technique is convenient in generating massive composites designs with useful mechanical information that dictate stiffness,fracture and robustness of the material with one model,and such has to be done by several different experimental or simulation tests.This research offers valuable insights for the improvement of composite design with the goal of expanding the design space and automatic screening of composite designs for improved mechanical functions.展开更多
In this paper,certain delayed virus dynamical models with cell-to-cell infection and density-dependent diffusion are investigated.For the viral model with a single strain,we have proved the well-posedness and studied ...In this paper,certain delayed virus dynamical models with cell-to-cell infection and density-dependent diffusion are investigated.For the viral model with a single strain,we have proved the well-posedness and studied the global stabilities of equilibria by defining the basic reproductive number R_(0) and structuring proper Lyapunov functional.Moreover,we found that the infection-free equilibrium is globally asymptotically stable if R_(0)<1,and the infection equilibrium is globally asymptotically stable if R_(0)>1.For the multi-strain model,we found that all viral strains coexist if the corresponding basic reproductive number R^(e)_(j)>1,while virus will extinct if R^(e)_(j)<1.As a result,we found that delay and the density-dependent diffusion does not influence the global stability of the model with cell-to-cell infection and homogeneous Neumann boundary conditions.展开更多
In this paper, we derive a time-delayed and diffusive echinococcosis transmission model. We first address the well-posedness to the initial-value problem for the model and give the basic reproduction number TO0. In th...In this paper, we derive a time-delayed and diffusive echinococcosis transmission model. We first address the well-posedness to the initial-value problem for the model and give the basic reproduction number TO0. In the case of a bounded spatial domain, we establish the local stability as well as the global stability of the disease-free and disease equilibria of the model. The methods to prove the local and the global stability are to analyze the corresponding characteristic equations and construct Lyapunov functionals, respectively. In the case of an unbounded spatial domain, by applying Schauder＇s fixed point theorem and the limiting arguments, we show that when R0 〉 1, there exists a constant c＊ 〉 0 such that the model admits positive traveling wave solutions connecting the disease-free and endemic equilibrium for c 〉 c＊, and when R0 〉 1 and c 〈 c＊, the model has no positive traveling wave solutions connecting them.展开更多
The applications of machine learning(ML)in the medical domain are often hindered by the limited availability of high-quality data.To address this challenge,we explore the synthetic generation of echocardiography image...The applications of machine learning(ML)in the medical domain are often hindered by the limited availability of high-quality data.To address this challenge,we explore the synthetic generation of echocardiography images(echoCG)using state-of-the-art generative models.We conduct a comprehensive evaluation of three prominent methods:Cycle-consistent generative adversarial network(CycleGAN),Contrastive Unpaired Translation(CUT),and Stable Diffusion 1.5 with Low-Rank Adaptation(LoRA).Our research presents the data generation methodol-ogy,image samples,and evaluation strategy,followed by an extensive user study involving licensed cardiologists and surgeons who assess the perceived quality and medical soundness of the generated images.Our findings indicate that Stable Diffusion outperforms both CycleGAN and CUT in generating images that are nearly indistinguishable from real echoCG images,making it a promising tool for augmenting medical datasets.However,we also identify limitations in the synthetic images generated by CycleGAN and CUT,which are easily distinguishable as non-realistic by medical professionals.This study highlights the potential of diffusion models in medical imaging and their applicability in addressing data scarcity,while also outlining the areas for future improvement.展开更多
文摘This study introduces a Landscape Information Modeling±Stable Diffusion(LIM±SD)-based digital workflow for ecological engineered landscaping(EEL)design,focusing on urban river wetlands.It explores how students from diverse academic backgrounds perform EEL tasks using the LIM±SD approach.A total of 30 participants,including industrial design postgraduates and landscape architecture undergraduates and postgraduates,completed the design tasks.The efficacy of their designs was assessed through expert evaluations on site appropriateness,aesthetics,spatial layout,and eco-engineering techniques of the design proposals,as well as the parametric simulation which calculated the vegetation coverage rate and proportion of riparian areas for each design.Moreover,evaluation of participants’subjective design experiences was conducted via questionnaires.Results indicated that landscape architecture postgraduates outperformed others applying ecological engineering principles.The study also elucidated discrepancies between LIM models and SD-generated renderings,as well as the uncertainty of SDgenerated renderings,suggesting improvements are needed to align digital outputs with ecological design criteria.
文摘目的探究“非遗+AI”新模式下湖南土特产包装的创新设计形式,传承和发展非遗文化,提升土特产包装的文化内涵,提高传统包装的科技含量,以适应当代消费者不断提升的审美和消费需求。方法通过问卷调查、深度访谈等方法,分析“非遗+AI”模式与当代湖南土特产包装的设计现状,了解消费者对包装设计的不同需求,总结设计策略,并基于“非遗+AI”新模式下机器学习和深度学习技术,借助SD(Stable Diffusion,稳定扩散模型)架构下的Lora模型(Low-RankAdaptation of Large Language Models,大语言模型的低秩适用方法),进行踏虎凿花在岳阳王鸽土特产包装设计中的创新应用实践。结果生成出紧跟新时代数字技术,驱动非遗文化活态传承的包装设计图案,从而实现湖南土特产包装的创新设计探索。结论基于“非遗+AI”模式下的SD模型技术,对泸溪踏虎凿花进行创新转化并应用在湖南土特产岳阳王鸽包装设计中,既活化了传统手工艺的表达形式,又创新了土特产的包装表现手法,为其他非遗文化元素和产品包装的有机融合提供了新路径。
基金supported by the National Science Foundation CA-REER Grant(Grant No.2145392)the startup funding at Syracuse Uni-versity for supporting the research work.
文摘The distribution of material phases is crucial to determine the composite’s mechanical property.While the full structure-mechanics relationship of highly ordered material distributions can be studied with finite number of cases,this relationship is difficult to be revealed for complex irregular distributions,preventing design of such material structures to meet certain mechanical requirements.The noticeable developments of artificial intelligence(AI)algorithms in material design enables to detect the hidden structure-mechanics correlations which is essential for designing composite of complex structures.It is intriguing how these tools can assist composite design.Here,we focus on the rapid generation of bicontinuous composite structures together with the stress distribution in loading.We find that generative AI,enabled through fine-tuned Low Rank Adaptation models,can be trained with a few inputs to generate both synthetic composite structures and the corresponding von Mises stress distribution.The results show that this technique is convenient in generating massive composites designs with useful mechanical information that dictate stiffness,fracture and robustness of the material with one model,and such has to be done by several different experimental or simulation tests.This research offers valuable insights for the improvement of composite design with the goal of expanding the design space and automatic screening of composite designs for improved mechanical functions.
基金supported by NSFC(Nos.11671346 and U1604180)Key Scien-tific and Technological Research Projects in Henan Province(Nos.192102310089,18B110003)+1 种基金Foundation of Henan Educational Committee(No.19A110009)Grant of Bioinformatics Center of Henan University(No.2019YLXKJC02).
文摘In this paper,certain delayed virus dynamical models with cell-to-cell infection and density-dependent diffusion are investigated.For the viral model with a single strain,we have proved the well-posedness and studied the global stabilities of equilibria by defining the basic reproductive number R_(0) and structuring proper Lyapunov functional.Moreover,we found that the infection-free equilibrium is globally asymptotically stable if R_(0)<1,and the infection equilibrium is globally asymptotically stable if R_(0)>1.For the multi-strain model,we found that all viral strains coexist if the corresponding basic reproductive number R^(e)_(j)>1,while virus will extinct if R^(e)_(j)<1.As a result,we found that delay and the density-dependent diffusion does not influence the global stability of the model with cell-to-cell infection and homogeneous Neumann boundary conditions.
文摘In this paper, we derive a time-delayed and diffusive echinococcosis transmission model. We first address the well-posedness to the initial-value problem for the model and give the basic reproduction number TO0. In the case of a bounded spatial domain, we establish the local stability as well as the global stability of the disease-free and disease equilibria of the model. The methods to prove the local and the global stability are to analyze the corresponding characteristic equations and construct Lyapunov functionals, respectively. In the case of an unbounded spatial domain, by applying Schauder＇s fixed point theorem and the limiting arguments, we show that when R0 〉 1, there exists a constant c＊ 〉 0 such that the model admits positive traveling wave solutions connecting the disease-free and endemic equilibrium for c 〉 c＊, and when R0 〉 1 and c 〈 c＊, the model has no positive traveling wave solutions connecting them.
基金funded by the Science Committee of the Ministry of Science and Higher Education of the Republic of Kazakhstan(Grant No.AP13068032-Development of Methods and Algorithms for Machine Learning for Predicting Pathologies of the Cardiovascular System Based on Echocardiography and Electrocardiography).
文摘The applications of machine learning(ML)in the medical domain are often hindered by the limited availability of high-quality data.To address this challenge,we explore the synthetic generation of echocardiography images(echoCG)using state-of-the-art generative models.We conduct a comprehensive evaluation of three prominent methods:Cycle-consistent generative adversarial network(CycleGAN),Contrastive Unpaired Translation(CUT),and Stable Diffusion 1.5 with Low-Rank Adaptation(LoRA).Our research presents the data generation methodol-ogy,image samples,and evaluation strategy,followed by an extensive user study involving licensed cardiologists and surgeons who assess the perceived quality and medical soundness of the generated images.Our findings indicate that Stable Diffusion outperforms both CycleGAN and CUT in generating images that are nearly indistinguishable from real echoCG images,making it a promising tool for augmenting medical datasets.However,we also identify limitations in the synthetic images generated by CycleGAN and CUT,which are easily distinguishable as non-realistic by medical professionals.This study highlights the potential of diffusion models in medical imaging and their applicability in addressing data scarcity,while also outlining the areas for future improvement.
