Peng Zhang

Dr. Peng Zhang

orcid

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

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

Representative Publications

View All Publications
1 May 2020 in Annals of Nuclear Energy
Verified
Journal Article
Closed access
HLHyunsuk Lee
Hyunsuk Lee
WKWonkyeong Kim
Wonkyeong Kim
PZPeng Zhang
Peng Zhang
MLMatthieu Lemaire
Matthieu Lemaire
AKAzamat Khassenov
Azamat Khassenov
DLDeokjung Lee
Deokjung Lee

1 April 2019 in Nuclear Engineering and Technology
Verified
Journal Article
Open access
JCJiwon Choe
Jiwon Choe
SCSooyoung Choi
Sooyoung Choi
PZPeng Zhang
Peng Zhang
JPJinsu Park
Jinsu Park
WKWonkyeong Kim
Wonkyeong Kim
DLDeokjung Lee
Deokjung Lee

1 April 2018 in Annals of Nuclear Energy
Verified
Journal Article
Closed access
JJJaerim Jang
Jaerim Jang
WKWonkyeong Kim
Wonkyeong Kim
SJSanggeol Jeong
Sanggeol Jeong
EJEun Jeong
Eun Jeong
JPJinsu Park
Jinsu Park
Deokjung LeeDeokjung Lee
Deokjung Lee

1 May 2019 in Computer Physics Communications
Verified
Journal Article
Closed access
JIANKAI YUJIANKAI YU
JIANKAI YU
HLHyunsuk Lee
Hyunsuk Lee
MLMatthieu Lemaire
Matthieu Lemaire
HKHanjoo Kim
Hanjoo Kim
PZPeng Zhang
Peng Zhang
Deokjung LeeDeokjung Lee
Deokjung Lee

1 January 2018 in Annals of Nuclear Energy
Verified
Journal Article
Closed access
FKFarrokh Khoshahval
Farrokh Khoshahval
MPMinyong Park
Minyong Park
HSHo Cheol Shin
Ho Cheol Shin
PZPeng Zhang
Peng Zhang
Deokjung LeeDeokjung Lee
Deokjung Lee

21 July 2021 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Open access
QXQin Xie
Qin Xie
PZPeng Zhang
Peng Zhang
BYBoseon Yu
Boseon Yu
JCJaesik Choi
Jaesik Choi
Abnormal behaviors in industrial systems may be early warnings on critical events that may cause severe damages to facilities and security. Thus, it is important to detect abnormal behaviors accurately and timely. However, the anomaly detection problem is hard to solve in practice, mainly due to the rareness and the expensive cost to get the labels of the anomalies. Deep generative models parameterized by neural networks have achieved state-of-the-art performance in practice for many unsupervised and semisupervised learning tasks. We present a new deep generative model, Latent Enhanced regression/classification Deep Generative Model (LEDGM), for the anomaly detection problem with multidimensional data. Instead of using two-stage decoupled models, we adopt an end-to-end learning paradigm. Instead of conditioning the latent on the class label, LEDGM conditions the label prediction on the learned latent so that the optimization goal is more in favor of better anomaly detection than better reconstruction that the previously proposed deep generative models have been trained for. Experimental results on several synthetic and real-world small- and large-scale datasets demonstrate that LEDGM can achieve improved anomaly detection performance on multidimensional data with very sparse labels. The results also suggest that both labeled anomalies and labeled normal are valuable for semisupervised learning. Generally, our results show that better performance can be achieved with more labeled data. The ablation experiments show that both the original input and the learned latent provide meaningful information for LEDGM to achieve high performance.