针对滚动轴承故障诊断中样本分布不均衡引起的模型泛化能力差、诊断精度低的问题,从两个方面展开研究:(1)故障样本增广,提出结合变分自编码器(VAE)和生成对抗网络(GAN)的VAE-GAN样本增广模型;(2)改进分类算法,提出基于焦点损失(FL)和卷...针对滚动轴承故障诊断中样本分布不均衡引起的模型泛化能力差、诊断精度低的问题,从两个方面展开研究:(1)故障样本增广,提出结合变分自编码器(VAE)和生成对抗网络(GAN)的VAE-GAN样本增广模型;(2)改进分类算法,提出基于焦点损失(FL)和卷积神经网络(CNN)的FLCNN(focal loss and convolutional neural network)样本分类模型。在此基础上,将VAE-GAN和FLCNN融合,构建VAE-GAN+FLCNN轴承故障诊断模型。首先,将样本量少的故障类输入VAE-GAN模型,通过交替训练编码网络、生成网络和判别网络,学习出真实故障样本的数据分布,从而实现故障样本的增广;然后用增广后的数据样本训练FLCNN分类模型,完成轴承故障识别。试验对比结果表明,所提方法能够有效提升样本不均衡条件下的轴承故障诊断效果,拥有更高的Recall值和F1-score值。展开更多
With the increasing application of surveillance cameras,vehicle re-identication(Re-ID)has attracted more attention in the eld of public security.Vehicle Re-ID meets challenge attributable to the large intra-class diff...With the increasing application of surveillance cameras,vehicle re-identication(Re-ID)has attracted more attention in the eld of public security.Vehicle Re-ID meets challenge attributable to the large intra-class differences caused by different views of vehicles in the traveling process and obvious inter-class similarities caused by similar appearances.Plentiful existing methods focus on local attributes by marking local locations.However,these methods require additional annotations,resulting in complex algorithms and insufferable computation time.To cope with these challenges,this paper proposes a vehicle Re-ID model based on optimized DenseNet121 with joint loss.This model applies the SE block to automatically obtain the importance of each channel feature and assign the corresponding weight to it,then features are transferred to the deep layer by adjusting the corresponding weights,which reduces the transmission of redundant information in the process of feature reuse in DenseNet121.At the same time,the proposed model leverages the complementary expression advantages of middle features of the CNN to enhance the feature expression ability.Additionally,a joint loss with focal loss and triplet loss is proposed in vehicle Re-ID to enhance the model’s ability to discriminate difcult-to-separate samples by enlarging the weight of the difcult-to-separate samples during the training process.Experimental results on the VeRi-776 dataset show that mAP and Rank-1 reach 75.5%and 94.8%,respectively.Besides,Rank-1 on small,medium and large sub-datasets of Vehicle ID dataset reach 81.3%,78.9%,and 76.5%,respectively,which surpasses most existing vehicle Re-ID methods.展开更多
AIM： To identify clonality and genetic alterations in focal nodular hyperplasia （FNH） and the nodules derived from it. METHODS： Twelve FNH lesions were examined. Twelve hepatocellular adenomas （HCAs） and 22 hepa...AIM： To identify clonality and genetic alterations in focal nodular hyperplasia （FNH） and the nodules derived from it. METHODS： Twelve FNH lesions were examined. Twelve hepatocellular adenomas （HCAs） and 22 hepatocellular carcinomas （HCCs） were used as references. Nodules of different types were identified and isolated from FNH by microdissection. An X-chromosome inactivation assay was employed to describe their clonality status. Loss of heterozygosity （LOH） was detected, using 57 markers, for genetic alterations.RESULTS： Nodules of altered hepatocytes （NAH）, the putative precursors of HCA and HCC, were found in all the FNH lesions. Polyclonality was revealed in 10 FNH lesions from female patients, and LOH was not detected in any of the six FNH lesions examined, the results apparently showing their polyclonal nature. In contrast, monoclonality was demonstrated in all the eight HCAs and in four of the HCCs from females, and allelic imbalances were found in the HCAs （9/9） and HCCs （15/18）, with chromosomal arms 11p, 13q and 17p affected in the former, and 6q, 8p, 11p, 16q and 17p affected in the latter lesions in high frequencies （≥ 30%）. Monodonality was revealed in 21 （40%） of the 52 microdissected NAH, but was not found in any of the five ordinary nodules. LOH was found in all of the 13 NAH tested, being highly frequent at six loci on 8p, 11p, 13q and 17p. CONCLUSION： FNH, as a whole, is polyclonal, but some of the NAH lesions derived from it are already neoplastic and harbor similar allelic imbalances as HCAs.展开更多
文摘针对滚动轴承故障诊断中样本分布不均衡引起的模型泛化能力差、诊断精度低的问题,从两个方面展开研究:(1)故障样本增广,提出结合变分自编码器(VAE)和生成对抗网络(GAN)的VAE-GAN样本增广模型;(2)改进分类算法,提出基于焦点损失(FL)和卷积神经网络(CNN)的FLCNN(focal loss and convolutional neural network)样本分类模型。在此基础上,将VAE-GAN和FLCNN融合,构建VAE-GAN+FLCNN轴承故障诊断模型。首先,将样本量少的故障类输入VAE-GAN模型,通过交替训练编码网络、生成网络和判别网络,学习出真实故障样本的数据分布,从而实现故障样本的增广;然后用增广后的数据样本训练FLCNN分类模型,完成轴承故障识别。试验对比结果表明,所提方法能够有效提升样本不均衡条件下的轴承故障诊断效果,拥有更高的Recall值和F1-score值。
基金supported,in part,by the National Nature Science Foundation of China under Grant Numbers 61502240,61502096,61304205,61773219in part,by the Natural Science Foundation of Jiangsu Province under Grant Numbers BK20201136,BK20191401in part,by the Priority Academic Program Development of Jiangsu Higher Education Institutions(PAPD)fund.
文摘With the increasing application of surveillance cameras,vehicle re-identication(Re-ID)has attracted more attention in the eld of public security.Vehicle Re-ID meets challenge attributable to the large intra-class differences caused by different views of vehicles in the traveling process and obvious inter-class similarities caused by similar appearances.Plentiful existing methods focus on local attributes by marking local locations.However,these methods require additional annotations,resulting in complex algorithms and insufferable computation time.To cope with these challenges,this paper proposes a vehicle Re-ID model based on optimized DenseNet121 with joint loss.This model applies the SE block to automatically obtain the importance of each channel feature and assign the corresponding weight to it,then features are transferred to the deep layer by adjusting the corresponding weights,which reduces the transmission of redundant information in the process of feature reuse in DenseNet121.At the same time,the proposed model leverages the complementary expression advantages of middle features of the CNN to enhance the feature expression ability.Additionally,a joint loss with focal loss and triplet loss is proposed in vehicle Re-ID to enhance the model’s ability to discriminate difcult-to-separate samples by enlarging the weight of the difcult-to-separate samples during the training process.Experimental results on the VeRi-776 dataset show that mAP and Rank-1 reach 75.5%and 94.8%,respectively.Besides,Rank-1 on small,medium and large sub-datasets of Vehicle ID dataset reach 81.3%,78.9%,and 76.5%,respectively,which surpasses most existing vehicle Re-ID methods.
基金Supported by The National Natural Science Foundation of China (NSFC), Grants 30171052, 30572125 and 30772508the CAMS Cancer Hospital Clinical Research Project LC2007A21
文摘AIM： To identify clonality and genetic alterations in focal nodular hyperplasia （FNH） and the nodules derived from it. METHODS： Twelve FNH lesions were examined. Twelve hepatocellular adenomas （HCAs） and 22 hepatocellular carcinomas （HCCs） were used as references. Nodules of different types were identified and isolated from FNH by microdissection. An X-chromosome inactivation assay was employed to describe their clonality status. Loss of heterozygosity （LOH） was detected, using 57 markers, for genetic alterations.RESULTS： Nodules of altered hepatocytes （NAH）, the putative precursors of HCA and HCC, were found in all the FNH lesions. Polyclonality was revealed in 10 FNH lesions from female patients, and LOH was not detected in any of the six FNH lesions examined, the results apparently showing their polyclonal nature. In contrast, monoclonality was demonstrated in all the eight HCAs and in four of the HCCs from females, and allelic imbalances were found in the HCAs （9/9） and HCCs （15/18）, with chromosomal arms 11p, 13q and 17p affected in the former, and 6q, 8p, 11p, 16q and 17p affected in the latter lesions in high frequencies （≥ 30%）. Monodonality was revealed in 21 （40%） of the 52 microdissected NAH, but was not found in any of the five ordinary nodules. LOH was found in all of the 13 NAH tested, being highly frequent at six loci on 8p, 11p, 13q and 17p. CONCLUSION： FNH, as a whole, is polyclonal, but some of the NAH lesions derived from it are already neoplastic and harbor similar allelic imbalances as HCAs.
