Search

Your search keyword '"Dong Kejun"' showing total 660 results
Start Over Author "Dong Kejun"
660 results on '"Dong Kejun"'

1. Phishing detection algorithm based on attention and feature fusion

Author

ZHANG Sirui, YAN Zhiwei, DONG Kejun, and YUCHI Xuebiao

Subjects
phishing detection, hierarchical feature fusion, attention mechanism, Electronic computers. Computer science, QA75.5-76.95
Abstract

Phishing has been the primary means utilized by attackers to conduct cyber fraud. As national anti-cyber fraud efforts continue to increase, the technical confrontation of various phishing activities has also escalated, bringing significant pressure to phishing detection work. For instance, current phishing attacks often employ images in place of text and apply small-scale shifts or rotations to high-weight website logo images to evade traditional detection algorithms that rely on text or image features. To address the problem of escalating adversarial phishing technologies, a phishing detection algorithm based on the attention mechanism and feature fusion was proposed, and a hierarchical classification model was established. This model included two stages of fusion involving domain names, web structure, web text, and web icons, capable of effectively countering various technical adversarial strategies employed by attackers. In the first stage, the algorithm leveraged the lightweight characteristics of the machine learning model to pre-recall a subset of suspicious domain names from a multitude of domain names. This was achieved by fusing the structural features of domain names, text, and web pages. In the second stage, based on the candidate subset, the attention mechanism was introduced to enhance the extraction of global text association features between the samples and the counterfeited objects. Additionally, the contrast features between the samples and the icons of the counterfeited objects were intensified, and a deep classification model fusing text and image features was established. The effectiveness of the algorithm was ultimately verified. This hierarchical detection method effectively avoids the extraction of image data from a large number of domain names to be detected, significantly improving detection efficiency while ensuring the accuracy of detection.

Published
2024
Full Text
View/download PDF

2. Early Risk Prediction of Pediatric Cardiac Arrest from Electronic Health Records via Multimodal Fused Transformer

Author

Lu, Jiaying, Brown, Stephanie R., Liu, Songyuan, Zhao, Shifan, Dong, Kejun, Bold, Del, Fundora, Michael, Aljiffry, Alaa, Fedorov, Alex, Grunwell, Jocelyn, and Hu, Xiao

Subjects
Computer Science - Machine Learning, Computer Science - Artificial Intelligence
Abstract

Early prediction of pediatric cardiac arrest (CA) is critical for timely intervention in high-risk intensive care settings. We introduce PedCA-FT, a novel transformer-based framework that fuses tabular view of EHR with the derived textual view of EHR to fully unleash the interactions of high-dimensional risk factors and their dynamics. By employing dedicated transformer modules for each modality view, PedCA-FT captures complex temporal and contextual patterns to produce robust CA risk estimates. Evaluated on a curated pediatric cohort from the CHOA-CICU database, our approach outperforms ten other artificial intelligence models across five key performance metrics and identifies clinically meaningful risk factors. These findings underscore the potential of multimodal fusion techniques to enhance early CA detection and improve patient care.

Published
2025

3. Role of Random Interaction Connection in the Order Transition of Active Matter Based on the Vicsek Model

Author

Jin, Ruizhi and Dong, Kejun

Subjects
Condensed Matter - Soft Condensed Matter, Condensed Matter - Disordered Systems and Neural Networks
Abstract

Randomness plays a key role in the order transition of active matter but has not yet been explicitly considered in pairwise interaction connection. In this letter, we introduce the perception rate P into the Vicsek model as the probability of the interaction connections and model the connections as superposition states. We show that with increasing P, the polar order number undergoes an order transition and then saturation. The order transition is a first-order phase transition with band formation, and the effect of P is different from density. The change of the order number is linked with the interaction structure. The order transition, order saturation, and phase separation correspond to different critical changes in the local interaction number. The global interaction structure is further analyzed as a network. The decrease of P is comparable to random edge removal, under which the network experiences modal transitions near the critical points of the order number, and the network exhibits surprising robustness. Our results suggest that random interaction can be a new important factor in active matter models, with potential applications in robotic swarms and social activities., Comment: 8 pages, 5 figures

Published
2025

9. A U-Sleep Model for Sleep Staging Using Electrocardiography and Respiration Signals

Author

Si, Kaiyue, Dong, Kejun, Lu, Jingyi, Zhao, Lina, Xiang, Wentao, Li, Jianqing, Liu, Chengyu, Magjarević, Ratko, Series Editor, Ładyżyński, Piotr, Associate Editor, Ibrahim, Fatimah, Associate Editor, Lackovic, Igor, Associate Editor, Rock, Emilio Sacristan, Associate Editor, Wang, Guangzhi, editor, Yao, Dezhong, editor, Gu, Zhongze, editor, Peng, Yi, editor, Tong, Shanbao, editor, and Liu, Chengyu, editor

Published
2024
Full Text
View/download PDF

18. Structure effect of ENPs on mechanical properties of amorphous CuCo alloys.

Author

Wang, Jie, Tian, Zean, Zheng, Quan, Liang, Chengshuang, Fu, Mingshao, and Dong, Kejun

Subjects
METALLIC glasses, AMORPHOUS alloys, COMPOSITE materials, DYNAMIC simulation, NANOPARTICLES
Abstract

Nanoparticles play an important role in the properties of metallic glasses (MGs) due to their diversified structures; however, their structure–property relationship is unclear. In this paper, three ex situ metallic glass matrix composites were assembled by three kinds of nanoparticles and Cu50Co50 MG obtained by rapid cooling, and their structural evolution under uniaxial compression is investigated by molecular dynamic simulation. It is found that the activated atoms always preferentially accumulate in the amorphous region near the embedded nanoparticles (ENPs). ENPs hinder the propagation of shear bands and lead to strain-hardening behavior. The fractal structures convert the HCP and tDh atoms into atoms of other structures to improve the anti-deformation ability, and the parallel-twin structure improves the anti-deformation ability through the mutual conversion of the FCC and HCP atoms. These findings provide a new idea for improving the mechanical properties of MGs. The change in the ENP structure provides theoretical support for the design of composite materials with specific requirements for structural evolution. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

32. Self-assembly near Ground State: Randomly Pack Granular Spheres and Cubes into Crystal

Author

Amirifar, Reza, Dong, Kejun, and Yu, Aibing

Subjects
Condensed Matter - Soft Condensed Matter, Nonlinear Sciences - Adaptation and Self-Organizing Systems
Abstract

Self-assembly of granular particles is of great interest in both applied and basic research. It is commonly observed that when randomly packed into a container, granular particles form disordered structures like glass. As the particles are athermal, the self-assembly of such packings can normally be directed with energy input via vibration or shear. However, here we show that in particular containers, mono-sized spheres and cubes can self-assemble into perfect crystals when randomly dropped in. This is because the favourable microstates for new particles are jammed in the ordered structure by the existing particles and the boundary synergistically. Such a self-assembly method has not been reported in the literature. It indicates that disordered packing structure may result from the conflict between the internal structure and the structure shaped by the boundary. Therefore, to bridge such inconsistency could be a general principle for directing self-assembly for different kinds of particles in emerging areas., Comment: Main text: 9 pages, 5 figures. Appendix: 6 pages, 5 figures

Published
2020
Full Text
View/download PDF

33. P2P Optimization Strategy for Integrated Energy Operators Based on Nash Negotiation

Author

Dong, Kejun, Wang, Yang, Angrisani, Leopoldo, Series Editor, Arteaga, Marco, Series Editor, Chakraborty, Samarjit, Series Editor, Chen, Jiming, Series Editor, Chen, Shanben, Series Editor, Chen, Tan Kay, Series Editor, Dillmann, Rüdiger, Series Editor, Duan, Haibin, Series Editor, Ferrari, Gianluigi, Series Editor, Ferre, Manuel, Series Editor, Jabbari, Faryar, Series Editor, Jia, Limin, Series Editor, Kacprzyk, Janusz, Series Editor, Khamis, Alaa, Series Editor, Kroeger, Torsten, Series Editor, Li, Yong, Series Editor, Liang, Qilian, Series Editor, Martín, Ferran, Series Editor, Ming, Tan Cher, Series Editor, Minker, Wolfgang, Series Editor, Misra, Pradeep, Series Editor, Mukhopadhyay, Subhas, Series Editor, Ning, Cun-Zheng, Series Editor, Nishida, Toyoaki, Series Editor, Oneto, Luca, Series Editor, Panigrahi, Bijaya Ketan, Series Editor, Pascucci, Federica, Series Editor, Qin, Yong, Series Editor, Seng, Gan Woon, Series Editor, Speidel, Joachim, Series Editor, Veiga, Germano, Series Editor, Wu, Haitao, Series Editor, Zamboni, Walter, Series Editor, Zhang, Junjie James, Series Editor, Tan, Kay Chen, Series Editor, Hu, Cungang, editor, and Cao, Wenping, editor

Published
2023
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results