噪声环境下语音检测准确率偏低是短波通话面临的公开挑战。当前已有方法应用有限,其根源在于难以可靠地在噪音环境下提取准确且高效的语音特征。针对上述问题,提出了一个面向短波通信的低秩方向梯度直方图(Low-rank Histogram of Orient...噪声环境下语音检测准确率偏低是短波通话面临的公开挑战。当前已有方法应用有限,其根源在于难以可靠地在噪音环境下提取准确且高效的语音特征。针对上述问题,提出了一个面向短波通信的低秩方向梯度直方图(Low-rank Histogram of Oriented Gradient,LHOG)话音检测方法。首先,对目标音频源数据进行预处理,实现噪声环境下语音信息的可视化表征;然后,在HOG特征提取器中嵌入低秩化结构,缓解特征中的冗余信息,并降低噪声干扰,从而获得准确且高效的特征;最后,通过常用的SVM分类模型便可在噪声环境中准确快速地区分话音和噪声。测试结果表明,该方法的准确率达到了95.12%,误报率仅为0.96%,漏报率为13.14%。与现有主流方法的对比实验证明,该方法话音检测准确率高,资源占用少,能够有效提高短波通信侦控效率。展开更多
Mountains are paramount for exploring biodiversity patterns due to the mosaic of topographies and climates encompassed over short distances.Biodiversity research has traditionally focused on taxonomic diversity when i...Mountains are paramount for exploring biodiversity patterns due to the mosaic of topographies and climates encompassed over short distances.Biodiversity research has traditionally focused on taxonomic diversity when investigating changes along elevational gradients,but other facets should be considered.For first time,we simultaneously assessed elevational trends in taxonomic,functional,and phylogenetic diversity of woody plants in Andean tropical montane forests and explored their underlying ecological and evolutionary causes.This investigation covered four transects(traversing ca.2200 m a.s.l.) encompassing 114 plots of 0.1 ha across a broad latitudinal range(ca.10°).Using Hill numbers to quantify abundance-based diversity among 37,869 individuals we observed a consistent decrease in taxonomic,functional,and phylogenetic diversity as elevation increased,although the decrease was less pronounced for higher Hill orders.The exception was a slight increase in phylogenetic diversity when dominant species were over-weighted.The decrease in taxonomic and functional diversity might be attributed to an environmental filtering process towards highlands,where the increasingly harsher conditions exclude species and functional strategies.Besides,the differences in steepness decrease between Hill orders suggest that rare species disproportionately contribute to functional diversity.For phylogenetic diversity the shifting elevational trend between Hill orders indicates a greater than previously considered influence in central Andean highlands of tropical lowlands originated species with strong niche conservatism relative to distantly related temperate lineages.This could be explained by a decreasing presence and abundance of temperate,extratropical taxa towards the central Andes relative to northern or southern Andes,where they are more prevalent.展开更多
In areas with large temperature differences,the uneven distribution of temperatures in the CRTS III ballastless track slab due to daytime sunlight can cause warpage deformation,leading to periodic rail irregularities ...In areas with large temperature differences,the uneven distribution of temperatures in the CRTS III ballastless track slab due to daytime sunlight can cause warpage deformation,leading to periodic rail irregularities that increase the wheel-rail impact of high-speed vehicles and accelerate track structure damage.Therefore,it is necessary to study the dynamic contact relationship between the composite slab and the base plate during vehicle running.The results of the study show that:1)Under the influence of temperature gradients,the composite slab tends to deform elliptically.With a positive temperature gradient,the middle part of the track slab bulges upward,causing the slab to be supported by its four corners.Conversely,with a negative temperature gradient,the four corners of the track slab bulge upward,resulting in the slab being supported by its center.2)Temperature gradients can lead to separation between the composite slab and the base plate,reducing the contact area between layers.During vehicle running,the contact area between layers gradually increases,but the separation cannot be completely closed.3)The temperature gradient significantly affects the vertical displacement of the track.The vertical displacement in the middle of the slab increases with a positive temperature gradient.In contrast,the vertical displacement at the ends of the slab increases with a negative temperature gradient.4)The stress of self-compacting concrete at the side position significantly increases under a positive temperature gradient,with the vertical stress increasing by 2.7 times when the temperature gradient increases from 0 to 90℃·m^(-1).展开更多
This article proposes a VGG network with histogram of oriented gradient(HOG) feature fusion(HOG-VGG) for polarization synthetic aperture radar(PolSAR) image terrain classification.VGG-Net has a strong ability of deep ...This article proposes a VGG network with histogram of oriented gradient(HOG) feature fusion(HOG-VGG) for polarization synthetic aperture radar(PolSAR) image terrain classification.VGG-Net has a strong ability of deep feature extraction,which can fully extract the global deep features of different terrains in PolSAR images,so it is widely used in PolSAR terrain classification.However,VGG-Net ignores the local edge & shape features,resulting in incomplete feature representation of the PolSAR terrains,as a consequence,the terrain classification accuracy is not promising.In fact,edge and shape features play an important role in PolSAR terrain classification.To solve this problem,a new VGG network with HOG feature fusion was specifically proposed for high-precision PolSAR terrain classification.HOG-VGG extracts both the global deep semantic features and the local edge & shape features of the PolSAR terrains,so the terrain feature representation completeness is greatly elevated.Moreover,HOG-VGG optimally fuses the global deep features and the local edge & shape features to achieve the best classification results.The superiority of HOG-VGG is verified on the Flevoland,San Francisco and Oberpfaffenhofen datasets.Experiments show that the proposed HOG-VGG achieves much better PolSAR terrain classification performance,with overall accuracies of 97.54%,94.63%,and 96.07%,respectively.展开更多
为了实现对焊缝表面缺陷的自动检测与分类,研究一种有效识别焊缝表面缺陷的激光视觉检测方法.通过激光视觉传感器采集焊缝图像并进行预处理,包括图像分割,灰度化,平滑去噪以及焊缝轮廓提取.采用方向梯度直方图(Histogram of Oriented Gr...为了实现对焊缝表面缺陷的自动检测与分类,研究一种有效识别焊缝表面缺陷的激光视觉检测方法.通过激光视觉传感器采集焊缝图像并进行预处理,包括图像分割,灰度化,平滑去噪以及焊缝轮廓提取.采用方向梯度直方图(Histogram of Oriented Gradient,HOG)提取焊缝激光条纹轮廓图像的特征向量.其次,基于5折-交叉验证网格搜索方法进行模型参数寻优,最终建立了支持向量机(Support Vector Machine,SVM)智能模型识别与分类焊缝表面缺陷.通过调整焊缝轮廓提取算法、HOG特征维度得到不同特征数据并进行对比、分析焊缝缺陷的识别效果.在相同试验条件下,发现支持向量机比随机森林分类器、K最近邻分类器以及朴素贝叶斯分类器的识别率更高,达到97.86%.基于HOG-SVM的焊缝表面缺陷智能识别方法可有效提高焊缝缺陷(气孔、凹陷、咬边)及无缺陷的分类精度.展开更多
Resin transfer molding(RTM)is among the most used manufacturing processes for composite parts.Initially,the resin cure is initiated by heat supply to the mold.The supplementary heat generated during the reaction can c...Resin transfer molding(RTM)is among the most used manufacturing processes for composite parts.Initially,the resin cure is initiated by heat supply to the mold.The supplementary heat generated during the reaction can cause thermal gradients in the composite,potentially leading to undesired residual stresses which can cause shrinkage and warpage.In the present numerical study of these processes,a one-dimensional finite difference method is used to predict the temperature evolution and the degree of cure in the course of the resin polymerization;the effect of some parameters on the thermal gradient is then analyzed,namely:the fiber nature,the use of multiple layers of reinforcement with different thermal properties and also the temperature cycle variation.The validity of this numerical model is tested by comparison with experimental and numerical results in the existing literature.展开更多
文摘噪声环境下语音检测准确率偏低是短波通话面临的公开挑战。当前已有方法应用有限,其根源在于难以可靠地在噪音环境下提取准确且高效的语音特征。针对上述问题,提出了一个面向短波通信的低秩方向梯度直方图(Low-rank Histogram of Oriented Gradient,LHOG)话音检测方法。首先,对目标音频源数据进行预处理,实现噪声环境下语音信息的可视化表征;然后,在HOG特征提取器中嵌入低秩化结构,缓解特征中的冗余信息,并降低噪声干扰,从而获得准确且高效的特征;最后,通过常用的SVM分类模型便可在噪声环境中准确快速地区分话音和噪声。测试结果表明,该方法的准确率达到了95.12%,误报率仅为0.96%,漏报率为13.14%。与现有主流方法的对比实验证明,该方法话音检测准确率高,资源占用少,能够有效提高短波通信侦控效率。
基金Guillermo Bañares was funded through grants from the Spanish Ministry of Education (FPU14/05303),Escuela Internacional de Doctorado-Universidad Rey Juan Carlos (Doctor Internacional 2017)and the Education and Research Department of Madrid Autonomous Region Government (REMEDINAL TE,S2018/EMT-4338)supported through three grants from the Spanish Ministries of Economy and Competitiveness and Science and Technology (CGL2013-45634-P,CGL2016-75414-P,and PID2019-105064 GB-I00)a grant from Centro de Estudios de América Latina (CEAL)at Universidad Autónoma de Madrid and Banco Santander.
文摘Mountains are paramount for exploring biodiversity patterns due to the mosaic of topographies and climates encompassed over short distances.Biodiversity research has traditionally focused on taxonomic diversity when investigating changes along elevational gradients,but other facets should be considered.For first time,we simultaneously assessed elevational trends in taxonomic,functional,and phylogenetic diversity of woody plants in Andean tropical montane forests and explored their underlying ecological and evolutionary causes.This investigation covered four transects(traversing ca.2200 m a.s.l.) encompassing 114 plots of 0.1 ha across a broad latitudinal range(ca.10°).Using Hill numbers to quantify abundance-based diversity among 37,869 individuals we observed a consistent decrease in taxonomic,functional,and phylogenetic diversity as elevation increased,although the decrease was less pronounced for higher Hill orders.The exception was a slight increase in phylogenetic diversity when dominant species were over-weighted.The decrease in taxonomic and functional diversity might be attributed to an environmental filtering process towards highlands,where the increasingly harsher conditions exclude species and functional strategies.Besides,the differences in steepness decrease between Hill orders suggest that rare species disproportionately contribute to functional diversity.For phylogenetic diversity the shifting elevational trend between Hill orders indicates a greater than previously considered influence in central Andean highlands of tropical lowlands originated species with strong niche conservatism relative to distantly related temperate lineages.This could be explained by a decreasing presence and abundance of temperate,extratropical taxa towards the central Andes relative to northern or southern Andes,where they are more prevalent.
基金supported by the National Natural Science Foundation of China(Grant No.52278466)the Project of China Academy of Railway Sciences Co.,Ltd(Grant No.2023YJ194).The useful contribution and discussions from project partners are also acknowledged.
文摘In areas with large temperature differences,the uneven distribution of temperatures in the CRTS III ballastless track slab due to daytime sunlight can cause warpage deformation,leading to periodic rail irregularities that increase the wheel-rail impact of high-speed vehicles and accelerate track structure damage.Therefore,it is necessary to study the dynamic contact relationship between the composite slab and the base plate during vehicle running.The results of the study show that:1)Under the influence of temperature gradients,the composite slab tends to deform elliptically.With a positive temperature gradient,the middle part of the track slab bulges upward,causing the slab to be supported by its four corners.Conversely,with a negative temperature gradient,the four corners of the track slab bulge upward,resulting in the slab being supported by its center.2)Temperature gradients can lead to separation between the composite slab and the base plate,reducing the contact area between layers.During vehicle running,the contact area between layers gradually increases,but the separation cannot be completely closed.3)The temperature gradient significantly affects the vertical displacement of the track.The vertical displacement in the middle of the slab increases with a positive temperature gradient.In contrast,the vertical displacement at the ends of the slab increases with a negative temperature gradient.4)The stress of self-compacting concrete at the side position significantly increases under a positive temperature gradient,with the vertical stress increasing by 2.7 times when the temperature gradient increases from 0 to 90℃·m^(-1).
基金Sponsored by the Fundamental Research Funds for the Central Universities of China(Grant No.PA2023IISL0098)the Hefei Municipal Natural Science Foundation(Grant No.202201)+1 种基金the National Natural Science Foundation of China(Grant No.62071164)the Open Fund of Information Materials and Intelligent Sensing Laboratory of Anhui Province(Anhui University)(Grant No.IMIS202214 and IMIS202102)。
文摘This article proposes a VGG network with histogram of oriented gradient(HOG) feature fusion(HOG-VGG) for polarization synthetic aperture radar(PolSAR) image terrain classification.VGG-Net has a strong ability of deep feature extraction,which can fully extract the global deep features of different terrains in PolSAR images,so it is widely used in PolSAR terrain classification.However,VGG-Net ignores the local edge & shape features,resulting in incomplete feature representation of the PolSAR terrains,as a consequence,the terrain classification accuracy is not promising.In fact,edge and shape features play an important role in PolSAR terrain classification.To solve this problem,a new VGG network with HOG feature fusion was specifically proposed for high-precision PolSAR terrain classification.HOG-VGG extracts both the global deep semantic features and the local edge & shape features of the PolSAR terrains,so the terrain feature representation completeness is greatly elevated.Moreover,HOG-VGG optimally fuses the global deep features and the local edge & shape features to achieve the best classification results.The superiority of HOG-VGG is verified on the Flevoland,San Francisco and Oberpfaffenhofen datasets.Experiments show that the proposed HOG-VGG achieves much better PolSAR terrain classification performance,with overall accuracies of 97.54%,94.63%,and 96.07%,respectively.
文摘Resin transfer molding(RTM)is among the most used manufacturing processes for composite parts.Initially,the resin cure is initiated by heat supply to the mold.The supplementary heat generated during the reaction can cause thermal gradients in the composite,potentially leading to undesired residual stresses which can cause shrinkage and warpage.In the present numerical study of these processes,a one-dimensional finite difference method is used to predict the temperature evolution and the degree of cure in the course of the resin polymerization;the effect of some parameters on the thermal gradient is then analyzed,namely:the fiber nature,the use of multiple layers of reinforcement with different thermal properties and also the temperature cycle variation.The validity of this numerical model is tested by comparison with experimental and numerical results in the existing literature.