Search

Your search keyword '"Shen, WenFeng"' showing total 330 results
Start Over Author "Shen, WenFeng"
330 results on '"Shen, WenFeng"'

4. Improving Generalization and Personalization in Long-Tailed Federated Learning via Classifier Retraining

Author

Li, Yuhang, Liu, Tong, Shen, Wenfeng, Cui, Yangguang, Lu, Weijia, Goos, Gerhard, Series Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Carretero, Jesus, editor, Shende, Sameer, editor, Garcia-Blas, Javier, editor, Brandic, Ivona, editor, Olcoz, Katzalin, editor, and Schreiber, Martin, editor

Published
2024
Full Text
View/download PDF

5. Gradient-Based Meta-Learning Using Uncertainty to Weigh Loss for Few-Shot Learning

Author

Ding, Lin, Liu, Peng, Shen, Wenfeng, Lu, Weijia, and Chen, Shengbo

Subjects
Computer Science - Machine Learning
Abstract

Model-Agnostic Meta-Learning (MAML) is one of the most successful meta-learning techniques for few-shot learning. It uses gradient descent to learn commonalities between various tasks, enabling the model to learn the meta-initialization of its own parameters to quickly adapt to new tasks using a small amount of labeled training data. A key challenge to few-shot learning is task uncertainty. Although a strong prior can be obtained from meta-learning with a large number of tasks, a precision model of the new task cannot be guaranteed because the volume of the training dataset is normally too small. In this study, first,in the process of choosing initialization parameters, the new method is proposed for task-specific learner adaptively learn to select initialization parameters that minimize the loss of new tasks. Then, we propose two improved methods for the meta-loss part: Method 1 generates weights by comparing meta-loss differences to improve the accuracy when there are few classes, and Method 2 introduces the homoscedastic uncertainty of each task to weigh multiple losses based on the original gradient descent,as a way to enhance the generalization ability to novel classes while ensuring accuracy improvement. Compared with previous gradient-based meta-learning methods, our model achieves better performance in regression tasks and few-shot classification and improves the robustness of the model to the learning rate and query sets in the meta-test set.

Published
2022

6. Using EBGAN for Anomaly Intrusion Detection

Author

Cui, Yi, Shen, Wenfeng, Zhang, Jian, Lu, Weijia, Liu, Chuang, Sun, Lin, and Chen, Si

Subjects
Computer Science - Cryptography and Security, Computer Science - Artificial Intelligence
Abstract

As an active network security protection scheme, intrusion detection system (IDS) undertakes the important responsibility of detecting network attacks in the form of malicious network traffic. Intrusion detection technology is an important part of IDS. At present, many scholars have carried out extensive research on intrusion detection technology. However, developing an efficient intrusion detection method for massive network traffic data is still difficult. Since Generative Adversarial Networks (GANs) have powerful modeling capabilities for complex high-dimensional data, they provide new ideas for addressing this problem. In this paper, we put forward an EBGAN-based intrusion detection method, IDS-EBGAN, that classifies network records as normal traffic or malicious traffic. The generator in IDS-EBGAN is responsible for converting the original malicious network traffic in the training set into adversarial malicious examples. This is because we want to use adversarial learning to improve the ability of discriminator to detect malicious traffic. At the same time, the discriminator adopts Autoencoder model. During testing, IDS-EBGAN uses reconstruction error of discriminator to classify traffic records.

Published
2022

11. Formation of SO3 in Flue Gas Under SNCR Conditions

Author

Wang, Kang, Shen, Wenfeng, Zhang, Yang, Peng, Yu, Zhang, Hai, Yang, Hairui, Lyu, Junfu, Förstner, Ulrich, Series Editor, Rulkens, Wim H., Series Editor, Salomons, Wim, Series Editor, Lyu, Junfu, editor, and Li, Shuiqing, editor

Published
2022
Full Text
View/download PDF

21. Humidity Sensing Using Polymers: A Critical Review of Current Technologies and Emerging Trends.

Author

Qian, Jintian, Tan, Ruiqin, Feng, Mingxia, Shen, Wenfeng, Lv, Dawu, and Song, Weijie

Subjects
POROUS polymers, ELECTRONIC equipment, POROUS materials, NANOSTRUCTURED materials, CRITICAL currents
Abstract

In the post-pandemic era, human demand for a healthy lifestyle and a smart society has surged, leading to vibrant growth in the field of flexible electronic sensor technology for health monitoring. Flexible polymer humidity sensors are not only capable of the real-time monitoring of human respiration and skin moisture information but also serve as a non-contact human–machine interaction method. In addition, the development of moist-electric generation technology is expected to break free from the traditional reliance of flexible electronic devices on power equipment, which is of significant importance for the miniaturization, reliability, and environmentally friendly development of flexible devices. Currently, flexible polymer humidity sensors are playing a significant role in the field of wearable electronic devices and thus have attracted considerable attention. This review begins by introducing the structural types and working principles of various humidity sensors, including the types of capacitive, impedance/resistive, frequency-based, fiber optic, and voltage-based sensors. It mainly focuses on the latest research advancements in flexible polymer humidity sensors, particularly in the modification of humidity-sensitive materials, sensor fabrication, and hygrosensitivity mechanisms. Studies on material composites including different types of polymers, polymers combined with porous nanostructured materials, polymers combined with metal oxides, and two-dimensional materials are reviewed, along with a comparative summary of the fabrication and performance mechanisms of related devices. This paper concludes with a discussion on the current challenges and opportunities faced by flexible polymer humidity sensors, providing new research perspectives for their future development. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

31. Efficient Graph Mining on Heterogeneous Platforms in the Cloud

Author

Zhang, Tao, Tong, Weiqin, Shen, Wenfeng, Peng, Junjie, Niu, Zhihua, Akan, Ozgur, Series editor, Bellavista, Paolo, Series editor, Cao, Jiannong, Series editor, Coulson, Geoffrey, Series editor, Dressler, Falko, Series editor, Ferrari, Domenico, Series editor, Gerla, Mario, Series editor, Kobayashi, Hisashi, Series editor, Palazzo, Sergio, Series editor, Sahni, Sartaj, Series editor, Shen, Xuemin Sherman, Series editor, Stan, Mircea, Series editor, Xiaohua, Jia, Series editor, Zomaya, Albert Y., Series editor, Wan, Jiafu, editor, Lin, Kai, editor, Zeng, Delu, editor, Li, Jin, editor, Xiang, Yang, editor, Liao, Xiaofeng, editor, Huang, Jiwu, editor, and Liu, Zheli, editor

Published
2018
Full Text
View/download PDF

35. An Improved Algorithm for Video Abstract

Author

Zhang, Jianlei, Li, Qin, Shen, Wenfeng, Chen, Shengbo, Diniz Junqueira Barbosa, Simone, Series editor, Chen, Phoebe, Series editor, Du, Xiaoyong, Series editor, Filipe, Joaquim, Series editor, Kara, Orhun, Series editor, Kotenko, Igor, Series editor, Liu, Ting, Series editor, Sivalingam, Krishna M., Series editor, Washio, Takashi, Series editor, Yuan, Hanning, editor, Geng, Jing, editor, and Bian, Fuling, editor

Published
2017
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results