Jinjin Chai

Jinjin Chai

Auto-generated profile, based on publicly available information

Jinjin Chai

College of Air and Missile Defense, Air Force Engineering University, Xi’an 710051, China

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
16 May 2019 in Cryptography and Communications
Verified
Journal Article
Closed access
PDF file
ZWZilong Wang
Zilong Wang
JCJinjin Chai
Jinjin Chai
GGGuang Gong
Guang Gong

1 November 2020 in Discrete Mathematics
Verified
Journal Article
Closed access
JCJinjin Chai
Jinjin Chai
Sihem MesnagerSihem Mesnager
Sihem Mesnager
ZWZilong Wang
Zilong Wang

31 March 2021 in Journal of Clinical and Nursing Research
Verified
Journal Article
Open access
PDF file
HXHanmei Xue
Hanmei Xue
XRXiaofang Ren
Xiaofang Ren
JCJinjin Chai
Jinjin Chai
The theory of Xianghuo (lit. ‘ministerial fire’) was first recorded in the "Huangdi Neijing", and it was supplemented and perfected by later generations. During the Jin and Yuan Dynasties, Zhu Zhenheng refined it into "Xianghuo theory" to guide clinical treatment; modern scholars proposed the Xianghuo mechanism theory based on the corresponding characteristics of the Xianghuo theory to promote the clinical research in the Xianghuo theory. This paper discusses Danxi School's understanding of Xianghuo theory, and makes a rigorous research and summary in order to serve as a reference for Xianghuo theory.

24 February 2024 in Cryptography and Communications
Verified
Journal Article
Closed access
PDF file
EXErzhong Xue
Erzhong Xue
ZWZilong Wang
Zilong Wang
JCJinjin Chai
Jinjin Chai

29 November 2025 in Electronics
Verified
Journal Article
Open access
PDF file
XWXuan Wu
Xuan Wu
PWPeng Wang
Peng Wang
YSYafei Song
Yafei Song
XWXiaodan Wang
Xiaodan Wang
JCJinjin Chai
Jinjin Chai
Malicious traffic detection in IoT environments faces dual challenges: limited labeled data and heterogeneous, complex traffic patterns. To address these limitations, we propose a malicious traffic detection framework, GADF-SRGA, which integrates Gram-angle-difference-field (GADF) imaging with meta-learning. The framework first encodes raw IoT traffic into images via GADF, preserving the spatiotemporal characteristics of malicious traffic. It then employs meta-learning on these encoded images to enable feature-space learning under scarce data. In the inner loop, Sample-Relation Guided Attention (SRGA) leverages class-label-guided supervision graphs to learn sample similarity, improving intra-class compactness and inter-class separability in the feature space. Comprehensive evaluations on public IoT intrusion datasets Malicious_TLS and ToN_IoT demonstrate the framework’s superiority and robustness, particularly under class-imbalanced conditions, over baseline methods.