In recent years,the heterogeneous SAR image classification task of"training on simulated data and testing on measured data"has garnered increasing attention in the field of Synthetic Aperture Radar Automatic...In recent years,the heterogeneous SAR image classification task of"training on simulated data and testing on measured data"has garnered increasing attention in the field of Synthetic Aperture Radar Automatic Target Recognition(SAR-ATR).Although current mainstream domain adaptation methods have made significant breakthroughs in addressing domain shift problems,the escalating model complexity and task complexity have constrained their deployment in real-world applications.To tackle this challenge,this paper proposes a domain adaptation framework based on linear-kernel Maximum Mean Discrepancy(MMD),integrated with a near-zero-cost pseudo-label denoising technique leveraging deep feature clustering.Our method completely eliminates the need for data augmentation and handcrafted feature design,achieving endto-end pseudo-label self-training.Competitive performance is demonstrated across three typical scenarios in the SAMPLE dataset,with the highest accuracy of 98.65%achieved in ScenarioⅢ.The relevant code is available at:https://github.com/TheGreatTreatsby/SAMPLE_MMD.展开更多
In the field of supercritical wing design, various principles and rules have been summarized through theoretical and experimental analyses. Compared with black-box relationships between geometry parameters and perform...In the field of supercritical wing design, various principles and rules have been summarized through theoretical and experimental analyses. Compared with black-box relationships between geometry parameters and performances, quantitative physical laws about pressure distributions and performances are clearer and more beneficial to designers. With the advancement of computational fluid dynamics and computational intelligence, discovering new rules through statistical analysis on computers has become increasingly attractive and affordable. This paper proposes a novel sampling method for the statistical study on pressure distribution features and performances, so that new physical laws can be revealed. It utilizes an adaptive sampling algorithm, of which the criteria are developed based on Kullback–Leibler divergence and Euclidean distance.In this paper, the proposed method is employed to generate airfoil samples to study the relationships between the supercritical pressure distribution features and the drag divergence Mach number as well as the drag creep characteristic. Compared with conventional sampling methods, the proposed method can efficiently distribute samples in the pressure distribution feature space rather than directly sampling airfoil geometry parameters. The corresponding geometry parameters are searched and found under constraints, so that supercritical airfoil samples that are well distributed in the pressure distribution space are obtained. These samples allow statistical studies to obtain more reliable and universal aerodynamic rules that can be applied to supercritical airfoil designs.展开更多
域适应学习因其有效减少域差异实现标签传播被广泛应用。目前,大多数域适应学习仅通过线性判别分析增强线性数据的判别性而忽略了现实世界存在非线性数据;同时,这些方法未考虑目标域的低置信样本对训练过程的负影响。因此,本文提出一种...域适应学习因其有效减少域差异实现标签传播被广泛应用。目前,大多数域适应学习仅通过线性判别分析增强线性数据的判别性而忽略了现实世界存在非线性数据;同时,这些方法未考虑目标域的低置信样本对训练过程的负影响。因此,本文提出一种新颖的置信样本选择与差异性特征增强的域适应框架(Confidence Sample Selection and Specific Feature Enhancement, CSS-SFE)。首先,该框架通过最小最大原则选择高置信的目标样本来辅助训练,减少不正确伪标签影响;其次,权衡类散点矩阵和邻居散点矩阵的贡献来增强线性和非线性数据集的特征,提高数据集的判别性;接着,分别为源域和目标域的样本学习不同投影矩阵来保持各自的差异性特征,防止源域和目标域的样本区分性降低;再次,进一步应用边缘分布对齐和条件分布对齐减少域分布差异;最后,在多个基准数据集上进行的广泛实验证明该方法优于目前的方法。展开更多
In this study,eight different varieties of maize seeds were used as the research objects.Conduct 81 types of combined preprocessing on the original spectra.Through comparison,Savitzky-Golay(SG)-multivariate scattering...In this study,eight different varieties of maize seeds were used as the research objects.Conduct 81 types of combined preprocessing on the original spectra.Through comparison,Savitzky-Golay(SG)-multivariate scattering correction(MSC)-maximum-minimum normalization(MN)was identified as the optimal preprocessing technique.The competitive adaptive reweighted sampling(CARS),successive projections algorithm(SPA),and their combined methods were employed to extract feature wavelengths.Classification models based on back propagation(BP),support vector machine(SVM),random forest(RF),and partial least squares(PLS)were established using full-band data and feature wavelengths.Among all models,the(CARS-SPA)-BP model achieved the highest accuracy rate of 98.44%.This study offers novel insights and methodologies for the rapid and accurate identification of corn seeds as well as other crop seeds.展开更多
In power systems,environmental fluctuations and electricity price volatility introduce uncertainties in user energy consumption behaviors,posing significant challenges to reliable energy planning.Existing studies ofte...In power systems,environmental fluctuations and electricity price volatility introduce uncertainties in user energy consumption behaviors,posing significant challenges to reliable energy planning.Existing studies often overlook the coupled relationships between the importance and correlations of multiple complex variables,lack consideration of the weighting and distribution of multi-dimensional features across multi-scale spaces,and fall short in multi-scale extraction and fusion of complex spatiotemporal characteristics.To address these issues,this paper proposes a multi-factor collaborative load forecasting method based on feature importance and multi-scale feature extraction.First,a novel evaluation model integrating feature importance and correlation is developed,and a comprehensive feature importance assessment method is proposed.Then,a multi-dimensional weighting extraction framework is designed,from which a multi-dimensional weight matrix and its multi-layer input structure are constructed.Finally,a multi-scale fusion model driven by a multi-channel convolutional neural network is developed.The backbone network is a multi-channel convolutional structure,consisting of a multilevel feature extraction module in the front,a multi-scale sampling mechanism in the middle,and a multiscale feature fusion architecture in the rear.Based on the proposed comprehensive feature importance assessment method,a multi-factor collaborative load forecasting model is established,achieving accurate load prediction.Experimental results demonstrate that,compared with various state-of-the-art forecasting models,the proposed method reduces Mean Absolute Error(MAE),Root Mean Square Error(RMSE),and Mean Absolute Percentage Error(MAPE)by up to 28.30%,24.14%,and 30.35%,respectively.展开更多
探明海洋生物资源的分布情况,对渔业捕捞和海洋牧场管理具有重要意义。该研究针对水下环境复杂、水下目标存在多尺度、多类别及小目标较多等复杂情况,提出水下目标两阶段网络检测方法。首先通过改进多尺度特征提取和融合,获取水下目标...探明海洋生物资源的分布情况,对渔业捕捞和海洋牧场管理具有重要意义。该研究针对水下环境复杂、水下目标存在多尺度、多类别及小目标较多等复杂情况,提出水下目标两阶段网络检测方法。首先通过改进多尺度特征提取和融合,获取水下目标多尺度信息和增强目标特征,得到更加丰富的目标特征信息,然后构建多重注意力,利用空间和通道维度中的全局特征依赖关系,进一步挖掘深层特征信息和隐藏信息,突出背景和目标的差异性,最后在模型训练中采用样本均衡方法,自适应均衡正负样本比例,减少无效样本,实现模型快速收敛。在国际水下机器人大赛公开数据集UPRC2019、WildFish及自建数据集上对所提方法进行试验,其mAP(mean Average Precision)分别达到85.3%、96.9%和97.8%,召回率分别达到90.6%、98.7%和98.9%,相较于Libra RCNN(CVPR2019)、Double head RCNN(ECCV2020)和STransFuse(2021)等检测方法,该文方法mAP要比上述方法分别高9.58、12.2和4.1个百分点。研究结果可为海洋渔业生物监测、水下机器人精准捕捞作业提供技术支撑。展开更多
文摘In recent years,the heterogeneous SAR image classification task of"training on simulated data and testing on measured data"has garnered increasing attention in the field of Synthetic Aperture Radar Automatic Target Recognition(SAR-ATR).Although current mainstream domain adaptation methods have made significant breakthroughs in addressing domain shift problems,the escalating model complexity and task complexity have constrained their deployment in real-world applications.To tackle this challenge,this paper proposes a domain adaptation framework based on linear-kernel Maximum Mean Discrepancy(MMD),integrated with a near-zero-cost pseudo-label denoising technique leveraging deep feature clustering.Our method completely eliminates the need for data augmentation and handcrafted feature design,achieving endto-end pseudo-label self-training.Competitive performance is demonstrated across three typical scenarios in the SAMPLE dataset,with the highest accuracy of 98.65%achieved in ScenarioⅢ.The relevant code is available at:https://github.com/TheGreatTreatsby/SAMPLE_MMD.
基金supported by the National Natural Science Foundation of China(Nos.91852108 and 11872230)。
文摘In the field of supercritical wing design, various principles and rules have been summarized through theoretical and experimental analyses. Compared with black-box relationships between geometry parameters and performances, quantitative physical laws about pressure distributions and performances are clearer and more beneficial to designers. With the advancement of computational fluid dynamics and computational intelligence, discovering new rules through statistical analysis on computers has become increasingly attractive and affordable. This paper proposes a novel sampling method for the statistical study on pressure distribution features and performances, so that new physical laws can be revealed. It utilizes an adaptive sampling algorithm, of which the criteria are developed based on Kullback–Leibler divergence and Euclidean distance.In this paper, the proposed method is employed to generate airfoil samples to study the relationships between the supercritical pressure distribution features and the drag divergence Mach number as well as the drag creep characteristic. Compared with conventional sampling methods, the proposed method can efficiently distribute samples in the pressure distribution feature space rather than directly sampling airfoil geometry parameters. The corresponding geometry parameters are searched and found under constraints, so that supercritical airfoil samples that are well distributed in the pressure distribution space are obtained. These samples allow statistical studies to obtain more reliable and universal aerodynamic rules that can be applied to supercritical airfoil designs.
文摘域适应学习因其有效减少域差异实现标签传播被广泛应用。目前,大多数域适应学习仅通过线性判别分析增强线性数据的判别性而忽略了现实世界存在非线性数据;同时,这些方法未考虑目标域的低置信样本对训练过程的负影响。因此,本文提出一种新颖的置信样本选择与差异性特征增强的域适应框架(Confidence Sample Selection and Specific Feature Enhancement, CSS-SFE)。首先,该框架通过最小最大原则选择高置信的目标样本来辅助训练,减少不正确伪标签影响;其次,权衡类散点矩阵和邻居散点矩阵的贡献来增强线性和非线性数据集的特征,提高数据集的判别性;接着,分别为源域和目标域的样本学习不同投影矩阵来保持各自的差异性特征,防止源域和目标域的样本区分性降低;再次,进一步应用边缘分布对齐和条件分布对齐减少域分布差异;最后,在多个基准数据集上进行的广泛实验证明该方法优于目前的方法。
基金supported by the Science and Technology Development Plan Project of Jilin Provincial Department of Science and Technology (No.20220203112S)the Jilin Provincial Department of Education Science and Technology Research Project (No.JJKH20210039KJ)。
文摘In this study,eight different varieties of maize seeds were used as the research objects.Conduct 81 types of combined preprocessing on the original spectra.Through comparison,Savitzky-Golay(SG)-multivariate scattering correction(MSC)-maximum-minimum normalization(MN)was identified as the optimal preprocessing technique.The competitive adaptive reweighted sampling(CARS),successive projections algorithm(SPA),and their combined methods were employed to extract feature wavelengths.Classification models based on back propagation(BP),support vector machine(SVM),random forest(RF),and partial least squares(PLS)were established using full-band data and feature wavelengths.Among all models,the(CARS-SPA)-BP model achieved the highest accuracy rate of 98.44%.This study offers novel insights and methodologies for the rapid and accurate identification of corn seeds as well as other crop seeds.
基金supported by the Key Program of the National Natural Science Foundation of China(Grant No.62133008)the Key Research and Development Program of Shandong Province(No.2025CXPT076).
文摘In power systems,environmental fluctuations and electricity price volatility introduce uncertainties in user energy consumption behaviors,posing significant challenges to reliable energy planning.Existing studies often overlook the coupled relationships between the importance and correlations of multiple complex variables,lack consideration of the weighting and distribution of multi-dimensional features across multi-scale spaces,and fall short in multi-scale extraction and fusion of complex spatiotemporal characteristics.To address these issues,this paper proposes a multi-factor collaborative load forecasting method based on feature importance and multi-scale feature extraction.First,a novel evaluation model integrating feature importance and correlation is developed,and a comprehensive feature importance assessment method is proposed.Then,a multi-dimensional weighting extraction framework is designed,from which a multi-dimensional weight matrix and its multi-layer input structure are constructed.Finally,a multi-scale fusion model driven by a multi-channel convolutional neural network is developed.The backbone network is a multi-channel convolutional structure,consisting of a multilevel feature extraction module in the front,a multi-scale sampling mechanism in the middle,and a multiscale feature fusion architecture in the rear.Based on the proposed comprehensive feature importance assessment method,a multi-factor collaborative load forecasting model is established,achieving accurate load prediction.Experimental results demonstrate that,compared with various state-of-the-art forecasting models,the proposed method reduces Mean Absolute Error(MAE),Root Mean Square Error(RMSE),and Mean Absolute Percentage Error(MAPE)by up to 28.30%,24.14%,and 30.35%,respectively.
文摘探明海洋生物资源的分布情况,对渔业捕捞和海洋牧场管理具有重要意义。该研究针对水下环境复杂、水下目标存在多尺度、多类别及小目标较多等复杂情况,提出水下目标两阶段网络检测方法。首先通过改进多尺度特征提取和融合,获取水下目标多尺度信息和增强目标特征,得到更加丰富的目标特征信息,然后构建多重注意力,利用空间和通道维度中的全局特征依赖关系,进一步挖掘深层特征信息和隐藏信息,突出背景和目标的差异性,最后在模型训练中采用样本均衡方法,自适应均衡正负样本比例,减少无效样本,实现模型快速收敛。在国际水下机器人大赛公开数据集UPRC2019、WildFish及自建数据集上对所提方法进行试验,其mAP(mean Average Precision)分别达到85.3%、96.9%和97.8%,召回率分别达到90.6%、98.7%和98.9%,相较于Libra RCNN(CVPR2019)、Double head RCNN(ECCV2020)和STransFuse(2021)等检测方法,该文方法mAP要比上述方法分别高9.58、12.2和4.1个百分点。研究结果可为海洋渔业生物监测、水下机器人精准捕捞作业提供技术支撑。
