Traditional electroencephalograph(EEG)-based emotion recognition requires a large number of calibration samples to build a model for a specific subject,which restricts the application of the affective brain computer i...Traditional electroencephalograph(EEG)-based emotion recognition requires a large number of calibration samples to build a model for a specific subject,which restricts the application of the affective brain computer interface(BCI)in practice.We attempt to use the multi-modal data from the past session to realize emotion recognition in the case of a small amount of calibration samples.To solve this problem,we propose a multimodal domain adaptive variational autoencoder(MMDA-VAE)method,which learns shared cross-domain latent representations of the multi-modal data.Our method builds a multi-modal variational autoencoder(MVAE)to project the data of multiple modalities into a common space.Through adversarial learning and cycle-consistency regularization,our method can reduce the distribution difference of each domain on the shared latent representation layer and realize the transfer of knowledge.Extensive experiments are conducted on two public datasets,SEED and SEED-IV,and the results show the superiority of our proposed method.Our work can effectively improve the performance of emotion recognition with a small amount of labelled multi-modal data.展开更多
Zero-shot learning enables the recognition of new class samples by migrating models learned from semanticfeatures and existing sample features to things that have never been seen before. The problems of consistencyof ...Zero-shot learning enables the recognition of new class samples by migrating models learned from semanticfeatures and existing sample features to things that have never been seen before. The problems of consistencyof different types of features and domain shift problems are two of the critical issues in zero-shot learning. Toaddress both of these issues, this paper proposes a new modeling structure. The traditional approach mappedsemantic features and visual features into the same feature space;based on this, a dual discriminator approachis used in the proposed model. This dual discriminator approach can further enhance the consistency betweensemantic and visual features. At the same time, this approach can also align unseen class semantic features andtraining set samples, providing a portion of information about the unseen classes. In addition, a new feature fusionmethod is proposed in the model. This method is equivalent to adding perturbation to the seen class features,which can reduce the degree to which the classification results in the model are biased towards the seen classes.At the same time, this feature fusion method can provide part of the information of the unseen classes, improvingits classification accuracy in generalized zero-shot learning and reducing domain bias. The proposed method isvalidated and compared with othermethods on four datasets, and fromthe experimental results, it can be seen thatthe method proposed in this paper achieves promising results.展开更多
For the Hardy space H_E^2(R) over a ?at unitary vector bundle E on a ?nitely connected domain R, let TE be the bundle shift as [3]. If B is a reductive algebra containing every operator ψ(TE) for any rational functi...For the Hardy space H_E^2(R) over a ?at unitary vector bundle E on a ?nitely connected domain R, let TE be the bundle shift as [3]. If B is a reductive algebra containing every operator ψ(TE) for any rational function ψ with poles outside of R, then B is self adjoint.展开更多
The transmission coefficients of electromagnetic （EM） waves due to a superconductor-dielectric superlattice are numerically calculated. Shift operator finite difference time domain （SO-FDTD） method is used in the ...The transmission coefficients of electromagnetic （EM） waves due to a superconductor-dielectric superlattice are numerically calculated. Shift operator finite difference time domain （SO-FDTD） method is used in the analysis. By using the SO-FDTD method, the transmission spectrum is obtained and its characteristics are investigated for different thicknesses of superconductor layers and dielectric layers, from which a stop band starting from zero frequency can be apparently observed. The relation between this low-frequency stop band and relative temperature, and also the London penetration depth at a superconductor temperature of zero degree are discussed, separately. The low-frequency stop band properties of superconductor-dielectric superlattice thus are well disclosed.展开更多
<div style="text-align:justify;"> Most existing image dehazing methods based learning are less able to perform well to real hazy images. An important reason is that they are trained on synthetic hazy i...<div style="text-align:justify;"> Most existing image dehazing methods based learning are less able to perform well to real hazy images. An important reason is that they are trained on synthetic hazy images whose distribution is different from real hazy images. To relieve this issue, this paper proposes a new hazy scene generation model based on domain adaptation, which uses a variational autoencoder to encode the synthetic hazy image pairs and the real hazy images into the latent space to adapt. The synthetic hazy image pairs guide the model to learn the mapping of clear images to hazy images, the real hazy images are used to adapt the synthetic hazy images’ latent space to real hazy images through generative adversarial loss, so as to make the generative hazy images’ distribution as close to the real hazy images’ distribution as possible. By comparing the results of the model with traditional physical scattering models and Adobe Lightroom CC software, the hazy images generated in this paper is more realistic. Our end-to-end domain adaptation model is also very convenient to synthesize hazy images without depth map. Using traditional method to dehaze the synthetic hazy images generated by this paper, both SSIM and PSNR have been improved, proved that the effectiveness of our method. The non-reference haze density evaluation algorithm and other quantitative evaluation also illustrate the advantages of our method in synthetic hazy images. </div>展开更多
A closed form expression for the bit error rate (BER) performance of frequency domaindifferential demodulation(FDDD) for orthogonal frequency division multiplexing system in flat fadingchannel is derived.The performan...A closed form expression for the bit error rate (BER) performance of frequency domaindifferential demodulation(FDDD) for orthogonal frequency division multiplexing system in flat fadingchannel is derived.The performance is evaluated by computer simulation and compared with the timedomain differential demodulation(TDDD).The results indicate that the performance of FDDD is betterthan that of TDDD,and the lower band of BER in the former is lower than that of the latter.展开更多
针对轴承故障诊断中特征提取困难、数据中含有大量噪声以及在单一工况数据下训练的模型无法在复杂工况下实现有效故障诊断的问题,提出了一种基于改进卷积稀疏自编码器(improved convolutional sparse auto encoder,ICSAE)的变工况轴承...针对轴承故障诊断中特征提取困难、数据中含有大量噪声以及在单一工况数据下训练的模型无法在复杂工况下实现有效故障诊断的问题,提出了一种基于改进卷积稀疏自编码器(improved convolutional sparse auto encoder,ICSAE)的变工况轴承故障诊断方法。首先,在卷积自编码中增加稀疏性约束条件,提高模型有效特征提取能力,并对于输入信号和重构信号的重构误差通过最大均值差异(MMD)结合均方误差(MSE)进行构建,提高模型的泛化能力和抗噪能力。然后,结合领域自适应方法,利用MMD损失减小两域特征分布差异,有效提高跨域诊断性能。使用CWRU数据集和JNU数据集验证所提方法在变工况下对于滚动轴承的故障诊断效果,结果表明在变工况迁移下,测试模型在CWRU数据集和JNU数据集的诊断准确率分别能达到99.81%和98.32%,提出的模型能够有效应对复杂工况下的滚动轴承故障诊断。展开更多
基金National Natural Science Foundation of China(61976209,62020106015,U21A20388)in part by the CAS International Collaboration Key Project(173211KYSB20190024)in part by the Strategic Priority Research Program of CAS(XDB32040000)。
文摘Traditional electroencephalograph(EEG)-based emotion recognition requires a large number of calibration samples to build a model for a specific subject,which restricts the application of the affective brain computer interface(BCI)in practice.We attempt to use the multi-modal data from the past session to realize emotion recognition in the case of a small amount of calibration samples.To solve this problem,we propose a multimodal domain adaptive variational autoencoder(MMDA-VAE)method,which learns shared cross-domain latent representations of the multi-modal data.Our method builds a multi-modal variational autoencoder(MVAE)to project the data of multiple modalities into a common space.Through adversarial learning and cycle-consistency regularization,our method can reduce the distribution difference of each domain on the shared latent representation layer and realize the transfer of knowledge.Extensive experiments are conducted on two public datasets,SEED and SEED-IV,and the results show the superiority of our proposed method.Our work can effectively improve the performance of emotion recognition with a small amount of labelled multi-modal data.
文摘Zero-shot learning enables the recognition of new class samples by migrating models learned from semanticfeatures and existing sample features to things that have never been seen before. The problems of consistencyof different types of features and domain shift problems are two of the critical issues in zero-shot learning. Toaddress both of these issues, this paper proposes a new modeling structure. The traditional approach mappedsemantic features and visual features into the same feature space;based on this, a dual discriminator approachis used in the proposed model. This dual discriminator approach can further enhance the consistency betweensemantic and visual features. At the same time, this approach can also align unseen class semantic features andtraining set samples, providing a portion of information about the unseen classes. In addition, a new feature fusionmethod is proposed in the model. This method is equivalent to adding perturbation to the seen class features,which can reduce the degree to which the classification results in the model are biased towards the seen classes.At the same time, this feature fusion method can provide part of the information of the unseen classes, improvingits classification accuracy in generalized zero-shot learning and reducing domain bias. The proposed method isvalidated and compared with othermethods on four datasets, and fromthe experimental results, it can be seen thatthe method proposed in this paper achieves promising results.
基金Project Supported by Scientific and Technological Research Program of Chongqing Municipal Education Commission(KJQN201801110)Chongqing Science and Technology Commission(CSTC2015jcyjA00045,cstc2018jcyjA2248)and NSFC(11871127)
文摘For the Hardy space H_E^2(R) over a ?at unitary vector bundle E on a ?nitely connected domain R, let TE be the bundle shift as [3]. If B is a reductive algebra containing every operator ψ(TE) for any rational function ψ with poles outside of R, then B is self adjoint.
基金Project supported partly by the Open Research Program in State Key Laboratory of Millimeter Waves of China(Grant No.K200802)partly by the National Natural Science Foundation of China(Grant No.60971122)
文摘The transmission coefficients of electromagnetic （EM） waves due to a superconductor-dielectric superlattice are numerically calculated. Shift operator finite difference time domain （SO-FDTD） method is used in the analysis. By using the SO-FDTD method, the transmission spectrum is obtained and its characteristics are investigated for different thicknesses of superconductor layers and dielectric layers, from which a stop band starting from zero frequency can be apparently observed. The relation between this low-frequency stop band and relative temperature, and also the London penetration depth at a superconductor temperature of zero degree are discussed, separately. The low-frequency stop band properties of superconductor-dielectric superlattice thus are well disclosed.
文摘<div style="text-align:justify;"> Most existing image dehazing methods based learning are less able to perform well to real hazy images. An important reason is that they are trained on synthetic hazy images whose distribution is different from real hazy images. To relieve this issue, this paper proposes a new hazy scene generation model based on domain adaptation, which uses a variational autoencoder to encode the synthetic hazy image pairs and the real hazy images into the latent space to adapt. The synthetic hazy image pairs guide the model to learn the mapping of clear images to hazy images, the real hazy images are used to adapt the synthetic hazy images’ latent space to real hazy images through generative adversarial loss, so as to make the generative hazy images’ distribution as close to the real hazy images’ distribution as possible. By comparing the results of the model with traditional physical scattering models and Adobe Lightroom CC software, the hazy images generated in this paper is more realistic. Our end-to-end domain adaptation model is also very convenient to synthesize hazy images without depth map. Using traditional method to dehaze the synthetic hazy images generated by this paper, both SSIM and PSNR have been improved, proved that the effectiveness of our method. The non-reference haze density evaluation algorithm and other quantitative evaluation also illustrate the advantages of our method in synthetic hazy images. </div>
基金Supported by National Natural Science Foundation of China(No.60272009)and National 863 Plan Project(NO.2001AA1230131)
文摘A closed form expression for the bit error rate (BER) performance of frequency domaindifferential demodulation(FDDD) for orthogonal frequency division multiplexing system in flat fadingchannel is derived.The performance is evaluated by computer simulation and compared with the timedomain differential demodulation(TDDD).The results indicate that the performance of FDDD is betterthan that of TDDD,and the lower band of BER in the former is lower than that of the latter.
文摘针对轴承故障诊断中特征提取困难、数据中含有大量噪声以及在单一工况数据下训练的模型无法在复杂工况下实现有效故障诊断的问题,提出了一种基于改进卷积稀疏自编码器(improved convolutional sparse auto encoder,ICSAE)的变工况轴承故障诊断方法。首先,在卷积自编码中增加稀疏性约束条件,提高模型有效特征提取能力,并对于输入信号和重构信号的重构误差通过最大均值差异(MMD)结合均方误差(MSE)进行构建,提高模型的泛化能力和抗噪能力。然后,结合领域自适应方法,利用MMD损失减小两域特征分布差异,有效提高跨域诊断性能。使用CWRU数据集和JNU数据集验证所提方法在变工况下对于滚动轴承的故障诊断效果,结果表明在变工况迁移下,测试模型在CWRU数据集和JNU数据集的诊断准确率分别能达到99.81%和98.32%,提出的模型能够有效应对复杂工况下的滚动轴承故障诊断。
