为实现航空发动机气路性能诊断与预测,提出一种基于堆叠降噪自编码器(Stacked denoising auto encoder,SDAE)和支持向量回归(Support vector regression,SVR)相结合的航空发动机排气温度(Exhaust gas temperature,EGT)基线建模方法。以C...为实现航空发动机气路性能诊断与预测,提出一种基于堆叠降噪自编码器(Stacked denoising auto encoder,SDAE)和支持向量回归(Support vector regression,SVR)相结合的航空发动机排气温度(Exhaust gas temperature,EGT)基线建模方法。以CFM56-7B发动机实际采集的飞行数据作为原始数据样本,利用SDAE进行数据特征提取和降噪处理后,将提取到的非线性特征作为SVR网络的输入,建立排气温度基线模型。利用同型号的另一台发动机航后数据对所建立的排气温度基线模型进行验证,并与基于单一网络的基线模型进行对比。结果表明,基于SDAE-SVR融合模型的基线建模方法具有更强的鲁棒性和更高的预测精度。展开更多
For the task of content retrieval,analysis and generation of film and television scene images in the field of intelligent editing,fine-grained emotion recognition and prediction of images is of great significance.In t...For the task of content retrieval,analysis and generation of film and television scene images in the field of intelligent editing,fine-grained emotion recognition and prediction of images is of great significance.In this paper,the fusion of traditional perceptual features,art features and multi-channel deep learning features are used to reflect the emotion expression of different levels of the image.In addition,the integrated learning model with stacking architecture based on linear regression coefficient and sentiment correlations,which is called the LS-stacking model,is proposed according to the factor association between multi-dimensional emotions.The experimental results prove that the mixed feature and LS-stacking model can predict well on the 16 emotion categories of the self-built image dataset.This study improves the fine-grained recognition ability of image emotion by computers,which helps to increase the intelligence and automation degree of visual retrieval and post-production system.展开更多
文摘利用高光谱数据进行作物生长状况监测具有无损和高效的特点,是现代精准农业发展的必要手段。该研究以连续3 a(2018—2020年)不同水氮供应下夏玉米营养生长期采集的212份植物样品(地上部生物量和叶面积指数)和高光谱实测数据为数据源,分别采用偏最小二乘回归(Partial Least Squares Regression,PLS)、极限学习机(Extreme Learning Machine,ELM)、随机森林(Random Forest,RF)和基于PLS叠加策略的叠加极限学习机算法(Stacked Ensemble Extreme Learning Machine based on the PLS,SE_(PLS)_ELM)构建了夏玉米营养生长期地上部生物量和叶面积指数估算模型。结果表明:基于PLS和ELM构建的夏玉米地上部生物量和叶面积指数估算模型的精度均较低,前者验证集R^(2)低于0.85、均方根误差高于550 kg/hm^(2),后者R^(2)低于0.90、均方根误差高于0.40 cm^(2)/cm^(2)。相比之下,基于RF和SE_(PLS)_ELM构建的夏玉米营养生长期地上部生物量和叶面积指数估算模型均有着较高的估算精度,SE_(PLS)_ELM模型表现尤为突出,其地上部生物量和叶面积指数估算模型验证集的R^(2)分别为0.955和0.969,均方根误差分别为307.3 kg/hm^(2)和0.24 cm^(2)/cm^(2),表明叠加集成模型能够充分利用高光谱数据并提高作物地上部生物量和叶面积指数估算精度。
文摘为实现航空发动机气路性能诊断与预测,提出一种基于堆叠降噪自编码器(Stacked denoising auto encoder,SDAE)和支持向量回归(Support vector regression,SVR)相结合的航空发动机排气温度(Exhaust gas temperature,EGT)基线建模方法。以CFM56-7B发动机实际采集的飞行数据作为原始数据样本,利用SDAE进行数据特征提取和降噪处理后,将提取到的非线性特征作为SVR网络的输入,建立排气温度基线模型。利用同型号的另一台发动机航后数据对所建立的排气温度基线模型进行验证,并与基于单一网络的基线模型进行对比。结果表明,基于SDAE-SVR融合模型的基线建模方法具有更强的鲁棒性和更高的预测精度。
基金Supported by the Open Project of Key Laboratory of Audio and Video Restoration and Evaluation(2021KFKT005)。
文摘For the task of content retrieval,analysis and generation of film and television scene images in the field of intelligent editing,fine-grained emotion recognition and prediction of images is of great significance.In this paper,the fusion of traditional perceptual features,art features and multi-channel deep learning features are used to reflect the emotion expression of different levels of the image.In addition,the integrated learning model with stacking architecture based on linear regression coefficient and sentiment correlations,which is called the LS-stacking model,is proposed according to the factor association between multi-dimensional emotions.The experimental results prove that the mixed feature and LS-stacking model can predict well on the 16 emotion categories of the self-built image dataset.This study improves the fine-grained recognition ability of image emotion by computers,which helps to increase the intelligence and automation degree of visual retrieval and post-production system.
