Yushan Zhu

Yushan Zhu

Auto-generated profile, based on publicly available information

Yushan Zhu

Central University of Finance and Economics

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 September 2021 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
XWXiao Wang
Xiao Wang
YZYushan Zhu
Yushan Zhu
SHShuangshuang Han
Shuangshuang Han
LYLinyao Yang
Linyao Yang
HGHaixia Gu
Haixia Gu
FWFei-Yue Wang
Fei-Yue Wang
In recent years, deep learning (DL) has been widely used in vehicle misbehavior detection and has attracted great attention due to its powerful nonlinear mapping ability. However, because of the large number of network parameters, the training processes of these methods are time consuming. Besides, the existing detection methods lack scalability; thus, they are not suitable for Internet of Vehicles (IoV) where new data are constantly generated. In this article, the concept of the broad learning system (BLS) is innovatively introduced into vehicle misbehavior detection. In order to make better use of vehicle information, key features are first extracted from the collected raw data. Then, a BLS is established, which is able to calculate the connection weight of the network efficiently and effectively by ridge regression approximation. Finally, the system can be updated and refined by an incremental learning algorithm based on the newly generated data in IoV. The experimental results show that the proposed method performs much better than DL or traditional classifiers, and could update and optimize the old model fastly and progressively while improving the system’s misbehavior detection accuracy.

30 April 2023
Verified
Conference Paper
Open access
WZWen Zhang
Wen Zhang
YZYushan Zhu
Yushan Zhu
MCMingyang Chen
Mingyang Chen
YGYuxia Geng
Yuxia Geng
YHYufeng Huang
Yufeng Huang
HCHuajun Chen
Huajun Chen
Knowledge graphs (KG) are essential background knowledge providers in many tasks. When designing models for KG-related tasks, one of the key tasks is to devise the Knowledge Representation and Fusion (KRF) module that learns the representation of elements from KGs and fuses them with task representations. While due to the difference of KGs and perspectives to be considered during fusion across tasks, duplicate and ad hoc KRF modules design are conducted among tasks. In this paper, we propose a novel knowledge graph pretraining model KGTransformer that could serve as a uniform KRF module in diverse KG-related tasks. We pretrain KGTransformer with three self-supervised tasks with sampled sub-graphs as input. For utilization, we propose a general prompt-tuning mechanism regarding task data as a triple prompt to allow flexible interactions between task KGs and task data. We evaluate pretrained KGTransformer on three tasks, triple classification, zero-shot image classification, and question answering. KGTransformer consistently achieves better results than specifically designed task models. Through experiments, we justify that the pretrained KGTransformer could be used off the shelf as a general and effective KRF module across KG-related tasks. The code and datasets are available at https://github.com/zjukg/KGTransformer.



2 December 2019
Verified
Book Chapter
Closed access
PDF file
YZYushan Zhu
Yushan Zhu
XTXing Tong
Xing Tong
DFDan Fan
Dan Fan
XWXi Wang
Xi Wang

1 January 2020
Verified
Conference Paper
Open access
PDF file
XWXi Wang
Xi Wang
XTXing Tong
Xing Tong
YZYushan Zhu
Yushan Zhu
TTTianyi Tan
Tianyi Tan
BZBowen Zheng
Bowen Zheng
Online Health Communities (OHCs), frequently adopted as online discussion forums for online users to communicate on health issues, have been used worldwide. By analyzing a representative breastcancer-related OHC from mainland China-Baidu Discussion Forum, this study attempts to investigate social support exchange and communication patterns through user-generated content by data mining approaches. According to the outcomes, emotional support seeking and providing presents itself to be a more critical theme among Chinese users than other types of social support. In addition, almost half of the users on Baidu Discussion Forum have simple patterns of involvement, and a fairly small proportion of highly active Chinese users are quite influential in shaping the connections of the social support network. Meanwhile, the off-topic discussions which are not directly on health concerns are not frequently touched by Chinese people. This may impact the longevity of both users and threads, and undermine the foundation of OHCs in the long term. The findings have practical implications for researchers and health practitioners targeting on the Chinese population.