|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | Multi-Modal Domain Adaptation Variational Autoencoder for EEG-Based Emotion Recognition显示文摘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. | Yixin Wang Shuang Qiu Dan Li Changde Du Bao-Liang Lu Huiguang He | 2022 | IEEE/CAA Journal of Automatica Sinica2022，9，9： | 1 |
| 2 | Tight-binding electrons on triangular and kagome lattices under staggered modulated magnetic fields:quantum Hall effects and Hofstadter butterflies显示文摘 | Li Juan Wang Yifei Gong Changde | | 0，，： | 1 |
| 3 | Analysis of Imaging Characteristics and Dynamic Changes of 3 Cases of Severe Novel Coronavirus Pneumonia in Qinghai Province显示文摘Objective:To analyze the characteristics,dynamic changes,and outcomes of the first imaging manifestations of 3 patients with severe COVID-19 in our hospital.Methods:Computed tomography(CT)findings of 3 patients with severe COVID-19 who tested positive by the nucleic acid test in our hospital were selected,mainly focusing on the morphology,distribution characteristics,and dynamic changes of the first CT findings.Results:3 patients with severe pneumonia were older,with one aged 80.The first chest CT examination for all 3 patients differed.Imaging showed a leafy distribution of consolidation,primarily affecting the lower lobes of both lungs and extending subpleurally.A grid-like pattern was observed,along with changes in the consolidation and air bronchogram.These changes had slower absorption,especially in patients with underlying diseases.Conclusion:CT manifestations of severe COVID-19 have specific characteristics and the analysis of their characteristics and dynamic changes provide valuable insights for clinical treatment. | Yingfang Yu Ruiyun Zhao Changde Li Fuqiang Ma Lingyun Guo Yang Li | 2024 | Journal of Clinical and Nursing Research2024，8，3： | 0 |
| 4 | CW Self-Frequency-Doubling Laser Operating on Nd:MgO:LiNbO_(3) High-Gain Polarization显示文摘The CW second-harmonic wave of high-gain polarization atλ=l.085μm was demonstrated with Nd:MgO:LiNbO_(3) self-frequency-doubling laser cavity inserted with a quarter wave-plate of the fundamental wavelength.The pump power threshold for the second-harmonic generation as low as 9.9mW was achieved.The maximum second-harmonic output was 11.4 m W,the conversion efficiency for the total second-harmonic output was 11.3%per Watt. | LI Ruining WANG Junmin LIANG Xiaoyan XIE Changde PENG Kunchi XU Guanfeng | 1993 | Chinese Physics Letters1993，10，4： | 0 |
| 5 | Brain Encoding and Decoding in fMRI with Bidirectional Deep Generative Models显示文摘Brain encoding and decoding via functional magnetic resonance imaging(fMRI)are two important aspects of visual perception neuroscience.Although previous researchers have made significant advances in brain encoding and decoding models,existing methods still require improvement using advanced machine learning techniques.For example,traditional methods usually build the encoding and decoding models separately,and are prone to overfitting on a small dataset.In fact,effectively unifying the encoding and decoding procedures may allow for more accurate predictions.In this paper,we first review the existing encoding and decoding methods and discuss the potential advantages of a“bidirectional”modeling strategy.Next,we show that there are correspondences between deep neural networks and human visual streams in terms of the architecture and computational rules.Furthermore,deep generative models(e.g.,variational autoencoders(VAEs)and generative adversarial networks(GANs))have produced promising results in studies on brain encoding and decoding.Finally,we propose that the dual learning method,which was originally designed for machine translation tasks,could help to improve the performance of encoding and decoding models by leveraging large-scale unpaired data. | Changde Du Jinpeng Li Lijie Huang Huiguang He | 2019 | Engineering2019，5，5： | 0 |
| 6 | An Aggregation Composition Compensation Method Based on Paired Net显示文摘With regard to the failure and cancellation of business logic of web services composition(WSC),this paper propose a novel web services transaction compensation mechanism based on paired net which can dynamically establish agile compensation-triggered process(CSCP-Nets),and satisfy prospective compensation requirements.The related execution semantics of five usual composition compensation patterns based on paired net are analyzed in the situations of successful execution,failure compensation and failure recovery.Paired net based application of trip reservation process(TRP) shows that it is feasible. | Xiao-Yong Mei 1,2 Yi-Yan Fan 2 Chang-Qin Huang 3 Ai-Jun Jiang 1 Shi-Xian Li 1 1 School of Information Science and Technology,Sun Yat-sen University,Guangzhou 510006,China 2 School of Computer Science and Technology,Hunan University of Arts and Science,Changde 415000,China 3 Department of Electrical Engineering and Computer Science,University of California,Irvine,CA,92697,USA | 2012 | International Journal of Automation and computing2012，9，5： | 0 |
您所在的机构暂未开通此部分的功能，请联系管理员