This paper is devoted to the two-dimensional nonlinear modeling of the fluid-solid interaction (FSI) between fabric and air flow, which is based on the Automatic Incremental Dynamic Nonlinear Analysis (AIDNA)-FSI prog...This paper is devoted to the two-dimensional nonlinear modeling of the fluid-solid interaction (FSI) between fabric and air flow, which is based on the Automatic Incremental Dynamic Nonlinear Analysis (AIDNA)-FSI program in order to study the dynamic bending features of fabrics in a specific air flow filed. The computational fluid dynamics (CFD) model for flow and the finite element model (FEM) for fabric was set up to constitute an FSI model in which the geometric nonlinear behavior and the dynamic stress-strain variation of the relatively soft fabric material were taken into account. Several FSI cases with different time-dependent wind load and the model frequency analysis for fabric were carried out. The dynamic response of fabric and the distribution of fluid variables were investigated. The results of numerical simulation and experiments fit quite well. Hence, this work contributes to the research of modeling the dynamic bending behavior of fabrics in air field.展开更多
Fetal health care is vital in ensuring the health of pregnant women and the fetus.Regular check-ups need to be taken by the mother to determine the status of the fetus’growth and identify any potential problems.To kn...Fetal health care is vital in ensuring the health of pregnant women and the fetus.Regular check-ups need to be taken by the mother to determine the status of the fetus’growth and identify any potential problems.To know the status of the fetus,doctors monitor blood reports,Ultrasounds,cardiotocography(CTG)data,etc.Still,in this research,we have considered CTG data,which provides information on heart rate and uterine contractions during pregnancy.Several researchers have proposed various methods for classifying the status of fetus growth.Manual processing of CTG data is time-consuming and unreliable.So,automated tools should be used to classify fetal health.This study proposes a novel neural network-based architecture,the Dynamic Multi-Layer Perceptron model,evaluated from a single layer to several layers to classify fetal health.Various strategies were applied,including pre-processing data using techniques like Balancing,Scaling,Normalization hyperparameter tuning,batch normalization,early stopping,etc.,to enhance the model’s performance.A comparative analysis of the proposed method is done against the traditional machine learning models to showcase its accuracy(97%).An ablation study without any pre-processing techniques is also illustrated.This study easily provides valuable interpretations for healthcare professionals in the decision-making process.展开更多
Urban transportation systems are facing severe challenges due to the rapid growth of the urban population,especially in China.Suspended monorail system(SMS),as a sky rail transportation form,can effectively alleviate ...Urban transportation systems are facing severe challenges due to the rapid growth of the urban population,especially in China.Suspended monorail system(SMS),as a sky rail transportation form,can effectively alleviate urban traffic congestion due to its independent right-of-way and minimal ground footprint.However,the SMS possesses a special traveling system with unique vehicle structure and bridge configuration,which results in significant differences in both the mechanisms and dynamics problems associated with train–bridge interaction(TBI)when contrasted with those of traditional railway systems.Therefore,a thorough understanding of the SMS dynamics is essential for ensuring the operational safety of the system.This article presents a state-of-the-art review of the TBI modeling methodologies,critical dynamic features,field tests,and practice of the SMS in China.Firstly,the development history,technical features,and potential dynamics problems of the SMS are briefly described,followed by the mechanical characteristics and mechanisms of the train–bridge interactive systems.Then,the modeling methodology of the fundamental elements in the suspended monorail TBI is systematically reviewed,including the suspended train subsystem,bridge subsystem,train–bridge interaction relationships,system excitations,and solution method.Further,the typical dynamic features of the TBI under various operational scenarios are elaborated,including different train speeds,a variety of line sections,and a natural wind environment.Finally,the first new energy-based SMS test line in the world is systematically introduced,including the composition and functionality of the system,the details of the conducted field tests,and the measured results of the typical dynamic responses.At the end of the paper,both the guidance on further improvement of the SMS and future research topics are proposed.展开更多
目前,主流的基于点击的交互式分割方法对所有用户点击进行无差异的编码.这样的编码方法意味着用户的交互只能给神经网络提供目标的位置信息,且每次点击的影响力是相同的.然而,不同阶段的点击的影响力是不同的.早期的交互用于目标轮廓的...目前,主流的基于点击的交互式分割方法对所有用户点击进行无差异的编码.这样的编码方法意味着用户的交互只能给神经网络提供目标的位置信息,且每次点击的影响力是相同的.然而,不同阶段的点击的影响力是不同的.早期的交互用于目标轮廓的选择,中后期的交互则偏向于对分割结果的局部细节进行微调.因此,应该适当扩大早期点击的影响力,以便更快地获得目标轮廓,同时削弱中后期点击的影响力,以防止因为超调或歧义而影响交互式分割的收敛性.1)本文提出了一种动态盘码(Dynamic Disk Coding,DDC)算法,该算法将用户的每个点击都编码成一个特定半径的圆盘,以此添加关于点击影响力的先验信息;2)本文提出了一个交互式分割网络DDC-Net,通过交互信息预处理模块加强交互信息,并在分割网络的浅层和深层将交互式信息与语义信息进行混合,缓解交互信息随着网络加深而逐渐衰减的问题;3)本文提出了一种改进的模拟训练策略,使得网络在训练时能够充分学习不同编码半径的点击所具备的不同影响力,从而使得提出的方法兼顾收敛速度和收敛性.通过实验表明,本文提出的使用动态盘码的深度交互式分割方法具有科学性和有效性,相较于基线方法,和分别平均取得3.63%和2.44%的提升.展开更多
针对红外小目标图像的低分辨率、特征信息少、识别准确率低等问题,提出嵌入空间位置信息和多视角特征提取(Embedded Spatial Location Information and Multi-view Feature Extraction,ESLIMFE)的红外小目标检测模型。首先,随着网络深...针对红外小目标图像的低分辨率、特征信息少、识别准确率低等问题,提出嵌入空间位置信息和多视角特征提取(Embedded Spatial Location Information and Multi-view Feature Extraction,ESLIMFE)的红外小目标检测模型。首先,随着网络深度的增加导致特征图分辨率逐渐减小从而丢失细节信息,因此在骨干网络中嵌入空间位置信息融合注意力机制(Spatial Location Information Fusion,SLIF)弥补小目标特征信息。其次,结合C3模块和动态蛇形卷积提出多视角特征提取(Multi-view Feature Extraction,MVFE)模块,通过在不同视角下提取同一特征来增强小目标的特征表达能力。采用大选择核(Large Selection Kernel,LSK)模块,通过使用不同大小的卷积核提取小目标多尺度信息,以提高对红外小目标定位能力。最后,引入基于注意力的尺度内特征交互(Attention-based Intrascale Feature Interaction,AIFI)模块增强特征之间的交互性。在对空红外小目标数据集上进行实验,实验结果表明,mAP75的检测精度为90.5%,mAP50~95检测精度为74.5%,文中模型能够较好地实现对红外小目标精确检测。展开更多
基金National Natural Science Foundations of China(No.50803010,No.60904056)
文摘This paper is devoted to the two-dimensional nonlinear modeling of the fluid-solid interaction (FSI) between fabric and air flow, which is based on the Automatic Incremental Dynamic Nonlinear Analysis (AIDNA)-FSI program in order to study the dynamic bending features of fabrics in a specific air flow filed. The computational fluid dynamics (CFD) model for flow and the finite element model (FEM) for fabric was set up to constitute an FSI model in which the geometric nonlinear behavior and the dynamic stress-strain variation of the relatively soft fabric material were taken into account. Several FSI cases with different time-dependent wind load and the model frequency analysis for fabric were carried out. The dynamic response of fabric and the distribution of fluid variables were investigated. The results of numerical simulation and experiments fit quite well. Hence, this work contributes to the research of modeling the dynamic bending behavior of fabrics in air field.
基金This work was supported by the National Research Foundation of Korea(NRF)grant funded by the Korea government(MSIT)(NRF-2023R1A2C1005950)Jana Shafi is supported via funding from Prince Sattam bin Abdulaziz University Project Number(PSAU/2024/R/1445).
文摘Fetal health care is vital in ensuring the health of pregnant women and the fetus.Regular check-ups need to be taken by the mother to determine the status of the fetus’growth and identify any potential problems.To know the status of the fetus,doctors monitor blood reports,Ultrasounds,cardiotocography(CTG)data,etc.Still,in this research,we have considered CTG data,which provides information on heart rate and uterine contractions during pregnancy.Several researchers have proposed various methods for classifying the status of fetus growth.Manual processing of CTG data is time-consuming and unreliable.So,automated tools should be used to classify fetal health.This study proposes a novel neural network-based architecture,the Dynamic Multi-Layer Perceptron model,evaluated from a single layer to several layers to classify fetal health.Various strategies were applied,including pre-processing data using techniques like Balancing,Scaling,Normalization hyperparameter tuning,batch normalization,early stopping,etc.,to enhance the model’s performance.A comparative analysis of the proposed method is done against the traditional machine learning models to showcase its accuracy(97%).An ablation study without any pre-processing techniques is also illustrated.This study easily provides valuable interpretations for healthcare professionals in the decision-making process.
基金supported by the National Natural Science Foundation of China(Grant Nos.52202483,52108476,and 52388102)。
文摘Urban transportation systems are facing severe challenges due to the rapid growth of the urban population,especially in China.Suspended monorail system(SMS),as a sky rail transportation form,can effectively alleviate urban traffic congestion due to its independent right-of-way and minimal ground footprint.However,the SMS possesses a special traveling system with unique vehicle structure and bridge configuration,which results in significant differences in both the mechanisms and dynamics problems associated with train–bridge interaction(TBI)when contrasted with those of traditional railway systems.Therefore,a thorough understanding of the SMS dynamics is essential for ensuring the operational safety of the system.This article presents a state-of-the-art review of the TBI modeling methodologies,critical dynamic features,field tests,and practice of the SMS in China.Firstly,the development history,technical features,and potential dynamics problems of the SMS are briefly described,followed by the mechanical characteristics and mechanisms of the train–bridge interactive systems.Then,the modeling methodology of the fundamental elements in the suspended monorail TBI is systematically reviewed,including the suspended train subsystem,bridge subsystem,train–bridge interaction relationships,system excitations,and solution method.Further,the typical dynamic features of the TBI under various operational scenarios are elaborated,including different train speeds,a variety of line sections,and a natural wind environment.Finally,the first new energy-based SMS test line in the world is systematically introduced,including the composition and functionality of the system,the details of the conducted field tests,and the measured results of the typical dynamic responses.At the end of the paper,both the guidance on further improvement of the SMS and future research topics are proposed.
文摘目前,主流的基于点击的交互式分割方法对所有用户点击进行无差异的编码.这样的编码方法意味着用户的交互只能给神经网络提供目标的位置信息,且每次点击的影响力是相同的.然而,不同阶段的点击的影响力是不同的.早期的交互用于目标轮廓的选择,中后期的交互则偏向于对分割结果的局部细节进行微调.因此,应该适当扩大早期点击的影响力,以便更快地获得目标轮廓,同时削弱中后期点击的影响力,以防止因为超调或歧义而影响交互式分割的收敛性.1)本文提出了一种动态盘码(Dynamic Disk Coding,DDC)算法,该算法将用户的每个点击都编码成一个特定半径的圆盘,以此添加关于点击影响力的先验信息;2)本文提出了一个交互式分割网络DDC-Net,通过交互信息预处理模块加强交互信息,并在分割网络的浅层和深层将交互式信息与语义信息进行混合,缓解交互信息随着网络加深而逐渐衰减的问题;3)本文提出了一种改进的模拟训练策略,使得网络在训练时能够充分学习不同编码半径的点击所具备的不同影响力,从而使得提出的方法兼顾收敛速度和收敛性.通过实验表明,本文提出的使用动态盘码的深度交互式分割方法具有科学性和有效性,相较于基线方法,和分别平均取得3.63%和2.44%的提升.
