Search

Your search keyword '"Lu, Zhengyu"' showing total 474 results
Start Over Author "Lu, Zhengyu"
474 results on '"Lu, Zhengyu"'

1. Noisy Node Classification by Bi-level Optimization based Multi-teacher Distillation

Author

Liu, Yujing, Wu, Zongqian, Lu, Zhengyu, Nie, Ci, Wen, Guoqiu, Hu, Ping, and Zhu, Xiaofeng

Subjects
Computer Science - Machine Learning
Abstract

Previous graph neural networks (GNNs) usually assume that the graph data is with clean labels for representation learning, but it is not true in real applications. In this paper, we propose a new multi-teacher distillation method based on bi-level optimization (namely BO-NNC), to conduct noisy node classification on the graph data. Specifically, we first employ multiple self-supervised learning methods to train diverse teacher models, and then aggregate their predictions through a teacher weight matrix. Furthermore, we design a new bi-level optimization strategy to dynamically adjust the teacher weight matrix based on the training progress of the student model. Finally, we design a label improvement module to improve the label quality. Extensive experimental results on real datasets show that our method achieves the best results compared to state-of-the-art methods.

Published
2024

4. Research on facial expression recognition based on Multimodal data fusion and neural network

Author

Han, Yi, Wang, Xubin, and Lu, Zhengyu

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence
Abstract

Facial expression recognition is a challenging task when neural network is applied to pattern recognition. Most of the current recognition research is based on single source facial data, which generally has the disadvantages of low accuracy and low robustness. In this paper, a neural network algorithm of facial expression recognition based on multimodal data fusion is proposed. The algorithm is based on the multimodal data, and it takes the facial image, the histogram of oriented gradient of the image and the facial landmarks as the input, and establishes CNN, LNN and HNN three sub neural networks to extract data features, using multimodal data feature fusion mechanism to improve the accuracy of facial expression recognition. Experimental results show that, benefiting by the complementarity of multimodal data, the algorithm has a great improvement in accuracy, robustness and detection speed compared with the traditional facial expression recognition algorithm. Especially in the case of partial occlusion, illumination and head posture transformation, the algorithm also shows a high confidence.

Published
2021

27. Construction of a Metallacyclopentadiene Ring through the Attack of Carbanions to M≡C Bond Followed by C—H Activation†.

Author

Tang, Chun, Zhang, Shengjie, Lu, Zhengyu, Li, Qian, Luo, Ming, Chen, Dafa, and Xia, Haiping

Subjects
NUCLEOPHILIC reactions, CARBANIONS, METALLACYCLES
Abstract

Comprehensive Summary: Metallacyclopentadienes are important metallacycles and regarded as intermediates in many reactions, therefore, new methods to achieve them are anticipated. In this study, a formal [3+2] method, through the reactions of an osmapentalyne with benzyl carbanions, was developed. The reactions underwent a nucleophilic attack of carbanions to the Os≡C bond, followed by C—H activation to form the five‐membered osmacyclopentadiene ring. Most of the reactions were carried out at room temperature, the substituents on the aromatic rings of benzyl carbanions are diverse, and the resulting products contain an Os—H bond, representing a novel type of 10C‐carbolong complexes. This work provides a new convenient route to construct metallacyclopentadienes, which is expected to further promote the development of such a type of substances. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

34. Research on facial expression recognition based on multimodal data fusion and neural network

Author

Han, Yi, Wang, Xubin, and Lu, Zhengyu

Abstract

Facial expression recognition is a challenging task when neural network is applied to pattern recognition. Most of the current recognition research is based on single source facial data, which generally has the disadvantages of low accuracy and low robustness. In this paper, a neural network algorithm of facial expression recognition based on multimodal data fusion is proposed. The algorithm is based on the multimodal data, and it takes the facial image, the histogram of oriented gradient of the image and the facial landmarks as the input, and establishes Convolutional Neural Network (CNN) designed to extract features from facial image, neural network designed to extract features from facial Landmarks and Neural Network (LNN) designed to extract features from Histogram of gradient (HNN), three sub-neural networks to extract data features, using multimodal data feature fusion mechanism to improve the accuracy of facial expression recognition. Experimental results show that, the algorithm has a great improvement in accuracy, robustness and detection speed.

Published
2024
Full Text
View/download PDF

42. Microbiota Research: From History to Advances

Author

Lu Zhengyu

Subjects
Environmental sciences, GE1-350
Abstract

Microbiota are communities of diverse microorganisms found in multicellular creatures. The study of microbiota in human bodies initiated since the late of the 19th century, and has been flourishing with the proceeding of the Human Microbiome Project (HMP), an international project aimed to identify the types and roles of the microorganisms in human. So far, human microbiota, especially the microbiota residing in human intestines, have been shown to affect various aspects of human life, including metabolism, immunity, neural activities, aging process, and so on. Some of them are pathogenic, while some of them are beneficial, or even essential to human. In this review, we summarized the up-to-date studies characterizing the influence of different microorganism to human.

Published
2020
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results