检索结果-内蒙古大学图书馆

Optimal Cyber Attack Strategy Using Reinforcement Learning Based onCommon Vulnerability Scoring System

Computer Modeling in engineering & Sciences 2024年第11期141卷 1551-1574页

作者： Bum-Sok Kim Hye-Won Suk Yong-Hoon Choi Dae-Sung Moon Min-Suk Kim Department of Electronic Information System Engineering Sangmyung UniversityCheonan31066Republic of Korea Department of Human Intelligence&Robot Engineering Sangmyung UniversityCheonan31066Republic of Korea Intelligent Convergence Research Laboratory Electronics and Telecommunications Research InstituteDaejeon34129Republic of Korea

Currently,cybersecurity threats such as data breaches and phishing have been on the rise due to the many differentattack strategies of cyber attackers,significantly increasing risks to individuals and *** technologies such as intrusion detection have been developed to respond to these cyber ***,advanced integrated cybersecurity that incorporates Artificial intelligence has been the *** this paper,wepropose a response strategy using a reinforcement-learning-based cyber-attack-defense simulation tool to addresscontinuously evolving cyber ***,we have implemented an effective reinforcement-learning-basedcyber-attack scenario using Cyber Battle Simulation,which is a cyber-attack-defense *** scenarioinvolves important security components such as node value,cost,firewalls,and ***,we applieda new vulnerability assessment method based on the Common Vulnerability Scoring *** approach candesign an optimal attack strategy by considering the importance of attack goals,which helps in developing moreeffective response *** attack strategies are evaluated by comparing their performance using a variety ofReinforcement Learning *** experimental results show that RL models demonstrate improved learningperformance with the proposed attack strategy compared to the original *** particular,the success rateof the Advantage Actor-Critic-based attack strategy improved by 5.04 percentage points,reaching 10.17%,whichrepresents an impressive 98.24%increase over the original ***,the proposed method canenhance security and risk management capabilities in cyber environments,improving the efficiency of securitymanagement and significantly contributing to the development of security systems.

关键词： Reinforcement learning common vulnerability scoring system cyber attack cyber battle simulation

来源：评论

学校读者我要写书评

暂无评论

Fusion-attention network using dense scale-invariant feature transform flow image and point cloud for 3D pedestrian detection

引用

Multimedia Tools and Applications 2025年第14期84卷 12813-12833页

作者： Park, Sang Kyoo Chung, Jun Ho Pae, Dong Sung Kang, Tae Koo Lim, Myo Taeg School of Electrical Engineering Korea University Seoul Korea Republic of Department of Software Sangmyung University Cheonan Korea Republic of Department of Human Intelligence and Robot Engineering Sangmyung University Cheonan Korea Republic of

In this paper, we introduce a fusion-attention network for three-dimensional (3D) pedestrian detection using the fusion of dense scale-invariant feature transform (SIFT) flow image and point cloud data. Because a pedestrian has a small size and shape, the point cloud data of the pedestrian are insufficient. The absence of point data needs supplementation with an RGB image. However, fusing the RGB image with the point cloud is difficult because of dimensional difference. To fuse the RGB image and point cloud data, point-wise fusion is employed by extracting features from points on the RGB image corresponding to the point cloud. To extract more meaningful features from images, the RGB image is replaced by dense SIFT flow, which represents the movement of the RGB image. To evaluate the proposed method, experimental results were compared with other state-of-the-art methods on the KITTI 3D detection validation set. Then, three ablation studies were conducted. First, to verify the effect of dense SIFT flow, the results were compared with optical flow and RGB image. Second, various fusion methods for dense SIFT flow image and point cloud features were analyzed. Eventually, a final ablation study was set up to ascertain the applicability of the proposed algorithm in a real outdoor driving environment by using a two-dimensional (2D) detection and tracking algorithm instead of a 2D ground-truth boundary box. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

AI-based Algorithm for GNSS Spoofing Detection 14

AI-based Algorithm for GNSS Spoofing Detection

引用

14th International Conference on Information and Communication Technology Convergence, ICTC 2023

作者： Bong, Jae Hwan Kim, Doyoung Jeong, Seongkyun Sangmyung University Department of Human Intelligence Robot Engineering Cheonan Korea Republic of

ISBN: (纸本)9798350313277

GNSS is extensively employed for applications requiring high reliability. However, GNSS inherently encompasses varying error factors and is susceptible to malicious attacks such as spoofing. To ensure stable GNSS utilization, it is imperative to incorporate GNSS spoofing signal detection mechanisms into GNSS signal processing. In this paper, artificial intelligence (AI) to detect the spoofing in GNSS signal is proposed. The developed AI model effectively detects the spoofing within GNSS signals while the satellite navigation solutions changing over time. The AI was trained using simulated GNSS data, confirming the feasibility of employing AI techniques for GNSS signal processing. © 2023 IEEE.

关键词： Anomaly Detection Artificial intelligence GNSS

来源：评论

学校读者我要写书评

暂无评论

Demand Forecasting in Transportation: A Graph Attention Networks for Predicting Bus Ridership 27

Demand Forecasting in Transportation: A Graph Attention Netw...

引用

27th International Conference on Advanced Communications Technology, ICACT 2025

作者： Munkhbayar, Tsetsentsengel Dashdorj, Zolzaya Jargalsaikhan, Zoljargal Tae-Koo, Kang Altangerel, Erdenebaatar Department of Computer Science Mongolian University of Science and Technology Ulaanbaatar Mongolia Department of Human Intelligence and Robot Engineering Sangmyung University Seoul Korea Republic of

ISBN: (纸本)9791188428137

Demand prediction in transportation systems plays a critical role in optimizing resources and improving service efficiency. This study explores demand prediction for Ulaanbaatar's public transportation network using Graph Attention Networks (GATs), Convolutional Neural Networks (CNNs), and Generative Adversarial Networks (GANs). GATs effectively capture spatial relationships, achieving the best performance while GANs struggle with stability and convergence issues. The findings emphasize the potential of using graph-based methods that incorporate key stations in the analysis of public transportation networks for predicting transit demand. Copyright 2025 Global IT Research Institute (GIRI). All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

AI-based Algorithm for GNSS Spoofing Detection

AI-based Algorithm for GNSS Spoofing Detection

引用

International Conference on Information and Communication Technology Convergence (ICTC)

作者： Jae Hwan Bong Doyoung Kim Seongkyun Jeong Department of Human Intelligence Robot Engineering Sangmyung University Cheonan South Korea

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learning Medical Subject Headings in PubMed Articles to Enhance Deep Predictions 11

Learning Medical Subject Headings in PubMed Articles to Enha...

引用

11th IEEE International Conference on Computational Cybernetics and Cyber-Medical Systems, ICCC 2024

作者： Dashdorj, Zolzaya Jargalsaikhan, Zoljargal Grigorev, Stanislav Trufanov, Andrey Kang, Tae-Koo Altangerel, Erdenebaatar Mongolian University of Science and Technology Computer Science Ulaanbaatar Mongolia School of Information Technology and Data Science Irkutsk National Research Technical University Irkutsk Russia Sangmyung University Department of Human Intelligence and Robot Engineering Seoul Korea Republic of

ISBN: (纸本)9798350350142

MeSH is a vocabulary of terms used in the life sciences and biomedical fields. A large amount of Medical Subject Headings (MeSH) occur in PubMed articles with different weights. In this research, we analyze a disease-symptom network exploiting MeSH metadata co-occurring in 7 million PubMed articles and configure a deep model in the context of biomedical and health care data. Optimized and efficient data networks are important to compile machine learning models. We optimize the deep model by reducing important features. Our result highlights that the degree of the severity of symptoms associated with a disease improves the accuracy of disease prediction models. The network was well optimized by reducing the number of symptoms. This finding may have important implications in healthcare: healthcare chatbots, clinical significance, practical implications. © 2024 IEEE.

关键词： Data Analytics

来源：评论

学校读者我要写书评

暂无评论

Demand Forecasting in Transportation: A Graph Attention Networks for Predicting Bus Ridership

Demand Forecasting in Transportation: A Graph Attention Netw...

引用

International Conference on Advanced Communication Technology (ICACT)

作者： Tsetsentsengel Munkhbayar Zolzaya Dashdorj Zoljargal Jargalsaikhan Kang Tae-Koo Erdenebaatar Altangerel Department of Computer Science Mongolian University of Science and Technology Ulaanbaatar Mongolia Department of Human Intelligence and Robot Engineering Sangmyung University Seoul Republic of Korea

ISBN: (数字)9791188428137

ISBN: (纸本)9798331507602

关键词： Deep learning Neural networks Demand forecasting Predictive models Generative adversarial networks Stability analysis Convolutional neural networks Resource management Public transportation Convergence

来源：评论

学校读者我要写书评

暂无评论

The Performance Of A Novel P300 Brain-Computer Interface Paradigm With Electrical And Vibration Modes 12

The Performance Of A Novel P300 Brain-Computer Interface Par...

引用

12th International Conference on CYBER Technology in Automation, Control, and Intelligent Systems, CYBER 2022

作者： Chu, Chenxi Luo, Jingjing Du, Qiang Han, Xiangke Guo, Shijie and Robotics Academy for Engineering and Technology Fudan University Shanghai China Hebei University of Technology The Hebei Key Laboratory of Robot Perception and Human-Robot Interaction Department of the State Key Laboratory of Reliability and Intelligence of Electrical Equipment Tianjin China

ISBN: (数字)9781665472678

ISBN: (纸本)9781665472678

A novel tactile P300 paradigm was proposed for Brain-Computer Interface(BCI), in which only two types of stimuli was used to distinguish different targets. We also adapted an algorithm for intention recognition, which used spatial information to distinguish different stimulation sites, and frequency information to identify attended-target stimuli and disturbances. Our novel paradigm was verified on both vibration and electrical stimuli modes, and achieved an average classification accuracy of 95.21% for vibration stimuli mode and 94.88% for electrical stimuli mode, respectively. Furthermore, we evaluated performances of brain's functional connectivity by the correlation coefficient, and preliminarily explored the similarities and differences between vibration stimuli mode and electrical stimuli mode. © 2022 IEEE.

关键词： Brain computer interface

来源：评论

学校读者我要写书评

暂无评论

Cognitive Systems engineering at 40, Part I: Deriving Theory from Practice 67th

Cognitive Systems Engineering at 40, Part I: Deriving Theory...

引用

67th International Annual Meeting of the human Factors and Ergonomics Society, HFES 2023

作者： Rayo, Michael F. Cooke, Nancy J. Flach, John M. Hoffman, Robert R. Smith, Philip J. Woods, David D. Department of Integrated Systems Engineering The Ohio State University ColumbusOH United States Center for Human Artificial Intelligence and Robot Teaming Arizona State University TempeAZ United States Mile Two DaytonOH United States Institute for Human Machine Cognition PensacolaFL United States

This expert panel is the first of a two-panel series marking the 40th anniversary of "Cognitive Systems engineering: New Wine in New Bottles" by Hollnagel and Woods (1983) and, arguably, the beginning of Cognitive Systems engineering (CSE). These experts were there at (or near) the beginning, devising new methods, expanding and creating new theories, and revealing a new perspective on how complex systems sustain performance and fail. They also wrestled and struggled with these new ideas to propose and implement solutions to improve performance in a number of high-consequence industries. Whether in graduate school or as early-career professionals, they saw the surprises that served as signals that the thinking that brought us to that point would not, alone, be the thinking and doing that would take us further. They will each answer the question, "What ideas and perspectives are important about Cognitive Systems engineering, and why?" © 2023 human Factors and Ergonomics Society.

关键词： cognitive systems engineering practice theory

来源：评论

学校读者我要写书评

暂无评论

Leaf-Inspired FSR Array and Insole-Type Sensor Module for Mobile Three-Dimensional Ground Reaction Force Estimation

Leaf-Inspired FSR Array and Insole-Type Sensor Module for Mo...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Taeyeon Kim Eunseok Song Seongbin An Hyunjin Choi Kyoungchul Kong Exoskeleton Laboratory the Department of Mechanical Engineering Korea Advanced Institute of Science and Technology (KAIST) Daejeon Republic of Korea Department of Human Intelligence and Robot Engineering Sangmyung University Chungcheongnam-do Republic of Korea

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

This paper presents an insole-type sensor module with a novel leaf-inspired force-sensitive resistor (FSR) array for accurate three-dimensional ground reaction force (GRF) estimation during human’s various motions. Joint torque analysis, essential for numerous applications in biomechanics and wearable robotics, necessitates the measurement of three-dimensional GRF vector information, traditionally achieved in indoor environments using costly force plates. To overcome these limitations, this study proposes an alternative method by incorporating FSRs on three inclined planes within the insole. A vector scaling process transforms the force values from the FSRs into the three-dimensional force vector, enabling continuous and user-independent estimation of GRF. The sensor module is integrated with machine learning, demonstrating its accuracy and usability in various motion scenarios. The results confirm the effectiveness of the leaf-inspired FSR array, giving the possibilities for portable and cost-effective motion analysis systems.

关键词： Training Force measurement Accuracy Protocols Force Estimation robot sensing systems

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：