The accuracy of numerical computation heavily relies on appropriate meshing,whichserves as the foundation for numerical computation.Although adaptive refinement methods areavailable,an adaptive numerical solution is l...The accuracy of numerical computation heavily relies on appropriate meshing,whichserves as the foundation for numerical computation.Although adaptive refinement methods areavailable,an adaptive numerical solution is likely to be ineffective if it originates from a poorly ini-tial mesh.Therefore,it is crucial to generate meshes that accurately capture the geometric features.As an indispensable input in meshing methods,the Mesh Size Function(MSF)determines the qual-ity of the generated mesh.However,the current generation of MSF involves human participation tospecify numerous parameters,leading to difficulties in practical usage.Considering the capacity ofmachine learning to reveal the latent relationships within data,this paper proposes a novel machinelearning method,Implicit Geometry Neural Network(IGNN),for automatic prediction of appro-priate MSFs based on the existing mesh data,enabling the generation of unstructured meshes thatalign precisely with geometric features.IGNN employs the generative adversarial theory to learnthe mapping between the implicit representation of the geometry(Signed Distance Function,SDF)and the corresponding MSF.Experimental results show that the proposed method is capableof automatically generating appropriate meshes and achieving comparable meshing results com-pared to traditional methods.This paper demonstrates the possibility of significantly decreasingthe workload of mesh generation using machine learning techniques,and it is expected to increasethe automation level of mesh generation.展开更多
Objective:To explore and analyze the clinical efficacy of flat mesh tension-free hernioplasty in the treatment of patients with inguinal hernia.Methods:A total of 60 patients with inguinal hernia were included and equ...Objective:To explore and analyze the clinical efficacy of flat mesh tension-free hernioplasty in the treatment of patients with inguinal hernia.Methods:A total of 60 patients with inguinal hernia were included and equally divided into an observation group(30 cases,flat mesh tension-free hernioplasty)and a control group(30 cases,mesh plug tension-free hernioplasty)based on differences in surgical plans.The visual analog scale(VAS)for postoperative pain,inflammatory markers(C-reactive protein,white blood cell count),and complication rates were compared between the two groups.Results:At 24 and 48 hours postoperatively,the VAS scores in the observation group were significantly lower than those in the control group(P<0.05).At 24 hours postoperatively,the levels of CRP and WBC were also lower in the observation group(P<0.05).The complication rate was slightly lower in the observation group(P>0.05).Conclusion:Flat mesh tension-free hernioplasty for inguinal hernia can alleviate postoperative pain and suppress inflammatory responses,with fewer complications,making it suitable for promotion at primary healthcare facilities.展开更多
从三维Mesh数据中分割建筑物立面以识别对象,是三维场景理解的关键,但现有方法多依赖高成本的精细标注数据。针对该问题,提出了一种半监督学习方法,引入一种基于对比学习和一致性正则化的半监督语义分割(semi-supervised semantic segme...从三维Mesh数据中分割建筑物立面以识别对象,是三维场景理解的关键,但现有方法多依赖高成本的精细标注数据。针对该问题,提出了一种半监督学习方法,引入一种基于对比学习和一致性正则化的半监督语义分割(semi-supervised semantic segmentation based on contrastive learning and consistency regularization,SS_CC)方法,用于分割三维Mesh数据的建筑物立面。在SS_CC方法中,改进后的对比学习模块利用正负样本之间的类可分性,能够更有效地利用类特征信息;提出的基于特征空间的一致性正则化损失函数,从挖掘全局特征的角度增强了对所提取建筑物立面特征的鉴别力。实验结果表明,所提出的SS_CC方法在F1分数、mIoU指标上优于当前一些主流方法,且在建筑物的墙面和窗户上的分割效果相对更好。展开更多
Separating oil/water mixtures via superhydrophobic stainless steel mesh(SSM)is a kind of efficient methods of treating oily wastewater,and the superhydrophobic SSM with a low cost,simple fabrication process and robust...Separating oil/water mixtures via superhydrophobic stainless steel mesh(SSM)is a kind of efficient methods of treating oily wastewater,and the superhydrophobic SSM with a low cost,simple fabrication process and robust usability remains a challenge.Herein,urushiol-based benzoxazine(U-D)with a strong substrate adhesion and low surface free energy was used to anchor SiO_(2) particles on the SSM surface to obtain a durable superhydrophobic SSM(PU-D/SiO_(2)/SSM)through a simple dip-coating process,meanwhile,epoxy resin was also introduced to further improve the adhesion between coating and SSM.PU-D/SiO_(2)/SSM could successfully separate various immiscible oil-water mixtures with a separation efficiency of over 96%and a flux up to 27100 L/m^(2) h only by gravity,respectively.Especially,the modified SSM could effectively remove water from water-in-oil emulsion with a separation efficiency of 99.7%.Moreover,PU-D/SiO_(2)/SSM had an outstanding reusability,whose water contact angle and separation efficiency only slightly decreased after 20 cycles of separating oil/water mixture.In addition,the modified SSM also displayed a satisfactory abrasion resistance,chemical stability and self-cleaning property.Thereby,the robust PU-D/SiO_(2)/SSM prepared by cheap raw materials and facile dip-coating method exhibits a high potential for separating oil/water mixtures.展开更多
基金co-supported by the Aeronautical Science Foundation of China(Nos.2018ZA52002 and 2019ZA052011)。
文摘The accuracy of numerical computation heavily relies on appropriate meshing,whichserves as the foundation for numerical computation.Although adaptive refinement methods areavailable,an adaptive numerical solution is likely to be ineffective if it originates from a poorly ini-tial mesh.Therefore,it is crucial to generate meshes that accurately capture the geometric features.As an indispensable input in meshing methods,the Mesh Size Function(MSF)determines the qual-ity of the generated mesh.However,the current generation of MSF involves human participation tospecify numerous parameters,leading to difficulties in practical usage.Considering the capacity ofmachine learning to reveal the latent relationships within data,this paper proposes a novel machinelearning method,Implicit Geometry Neural Network(IGNN),for automatic prediction of appro-priate MSFs based on the existing mesh data,enabling the generation of unstructured meshes thatalign precisely with geometric features.IGNN employs the generative adversarial theory to learnthe mapping between the implicit representation of the geometry(Signed Distance Function,SDF)and the corresponding MSF.Experimental results show that the proposed method is capableof automatically generating appropriate meshes and achieving comparable meshing results com-pared to traditional methods.This paper demonstrates the possibility of significantly decreasingthe workload of mesh generation using machine learning techniques,and it is expected to increasethe automation level of mesh generation.
文摘Objective:To explore and analyze the clinical efficacy of flat mesh tension-free hernioplasty in the treatment of patients with inguinal hernia.Methods:A total of 60 patients with inguinal hernia were included and equally divided into an observation group(30 cases,flat mesh tension-free hernioplasty)and a control group(30 cases,mesh plug tension-free hernioplasty)based on differences in surgical plans.The visual analog scale(VAS)for postoperative pain,inflammatory markers(C-reactive protein,white blood cell count),and complication rates were compared between the two groups.Results:At 24 and 48 hours postoperatively,the VAS scores in the observation group were significantly lower than those in the control group(P<0.05).At 24 hours postoperatively,the levels of CRP and WBC were also lower in the observation group(P<0.05).The complication rate was slightly lower in the observation group(P>0.05).Conclusion:Flat mesh tension-free hernioplasty for inguinal hernia can alleviate postoperative pain and suppress inflammatory responses,with fewer complications,making it suitable for promotion at primary healthcare facilities.
文摘从三维Mesh数据中分割建筑物立面以识别对象,是三维场景理解的关键,但现有方法多依赖高成本的精细标注数据。针对该问题,提出了一种半监督学习方法,引入一种基于对比学习和一致性正则化的半监督语义分割(semi-supervised semantic segmentation based on contrastive learning and consistency regularization,SS_CC)方法,用于分割三维Mesh数据的建筑物立面。在SS_CC方法中,改进后的对比学习模块利用正负样本之间的类可分性,能够更有效地利用类特征信息;提出的基于特征空间的一致性正则化损失函数,从挖掘全局特征的角度增强了对所提取建筑物立面特征的鉴别力。实验结果表明,所提出的SS_CC方法在F1分数、mIoU指标上优于当前一些主流方法,且在建筑物的墙面和窗户上的分割效果相对更好。
基金Funded by the National Natural Science Foundation of China(No.22165019)。
文摘Separating oil/water mixtures via superhydrophobic stainless steel mesh(SSM)is a kind of efficient methods of treating oily wastewater,and the superhydrophobic SSM with a low cost,simple fabrication process and robust usability remains a challenge.Herein,urushiol-based benzoxazine(U-D)with a strong substrate adhesion and low surface free energy was used to anchor SiO_(2) particles on the SSM surface to obtain a durable superhydrophobic SSM(PU-D/SiO_(2)/SSM)through a simple dip-coating process,meanwhile,epoxy resin was also introduced to further improve the adhesion between coating and SSM.PU-D/SiO_(2)/SSM could successfully separate various immiscible oil-water mixtures with a separation efficiency of over 96%and a flux up to 27100 L/m^(2) h only by gravity,respectively.Especially,the modified SSM could effectively remove water from water-in-oil emulsion with a separation efficiency of 99.7%.Moreover,PU-D/SiO_(2)/SSM had an outstanding reusability,whose water contact angle and separation efficiency only slightly decreased after 20 cycles of separating oil/water mixture.In addition,the modified SSM also displayed a satisfactory abrasion resistance,chemical stability and self-cleaning property.Thereby,the robust PU-D/SiO_(2)/SSM prepared by cheap raw materials and facile dip-coating method exhibits a high potential for separating oil/water mixtures.
