检索结果-内蒙古大学图书馆

A Support Data-Based Core-Set Selection Method for Signal Recognition

China Communications 2024年第4期21卷 151-162页

作者： Yang Ying Zhu Lidong Cao Changjie National Key Laboratory of Wireless Communications(University of Electronic Science and Technology of China) Chengdu 611731China College of Computer Science and Cyber Security(Chengdu University of Technology) Chengdu 610059China College of Mathmatics and Physics(Chengdu University of Technology) Chengdu 610059China

In recent years,deep learning-based signal recognition technology has gained attention and emerged as an important approach for safeguarding the electromagnetic ***,training deep learning-based classifiers on large signal datasets with redundant samples requires significant memory and high *** paper proposes a support databased core-set selection method(SD)for signal recognition,aiming to screen a representative subset that approximates the large signal ***,this subset can be identified by employing the labeled information during the early stages of model training,as some training samples are labeled as supporting data *** support data is crucial for model training and can be found using a border sample *** results demonstrate that the SD method minimizes the impact on model recognition performance while reducing the dataset size,and outperforms five other state-of-the-art core-set selection methods when the fraction of training sample kept is less than or equal to 0.3 on the RML2016.04C dataset or 0.5 on the RML22 *** SD method is particularly helpful for signal recognition tasks with limited memory and computing resources.

关键词： core-set selection deep learning model training signal recognition support data

来源：评论

学校读者我要写书评

暂无评论

Behavioral Features of Users as a Security Solution in Cloud Computing 8

Behavioral Features of Users as a Security Solution in Cloud...

引用

8th International Conference on Contemporary Information Technology and Mathematics, ICCITM 2022

作者： Sheet, Mohammed Fawzi Saeed, Melad Jader College of Computer Science and Mathmatics Unversity of Mosul Computers Science Dept. Mosul Iraq

ISBN: (纸本)9798350334869

A large number of establishments and organizations implement clouds to store their databases. More active attacks are used on clouds to get unauthorized access or to do harmful actions that may affect on user's privacy. Therefore, many studies have proposed to increase the level of security in the clouds depended on several strategies. The behavior is one of the promising strategies that might prevent unauthorized or processes. In this paper, a set of features, are from several previous studies, and these features are based on the user activity and events in a special purpose cloud by which unauthorized process can be prevented and alert user about bad actions during his/her work in the cloud environment. The results of comparison show that the event-based features require less resources and time. Thus, they need to be enhanced by adding more informative features, or some available features form other strategies. © 2022 IEEE.

关键词： Malware

来源：评论

学校读者我要写书评

暂无评论

Research on Data Mining Algorithm Based on BP Neural Network

引用

International Journal of Circuits, Systems and Signal Processing 2022年 16卷 734-740页

作者： Zhang, Jingyou Zhong, Haiping School of Mathmatics and Statistics Chongqing Three Gorges University Wanzhou404100 China Mathematics and Computer Science College Yuzhang Normal University Nanchang330103 China

The current data mining algorithm has the problem of imperfect data mining function, which leads to the algorithm taking too long time. This paper designs a data mining algorithm based on BP neural network. Analyze the basic structure of the data mining algorithm, obtain the data characteristics of the multi-objective decision-making, adjust the convergence speed with the distributed computing technology to keep the inertia factor state unchanged, construct the local minimal discrete model, measure the interest of the model, calculate the optimal output value of the network using the BP (Back Propagation) neural network model, and complete the improved design of the data mining function. Experimental results: The average computational time consumption of the designed data mining algorithm is 559.827 seconds, which saves 145.975 seconds and 174.237 seconds respectively than other traditional algorithms. It is proved that the data mining algorithm based on BP neural network reduces the computational time consumption, improves the performance of data mining, and has high application value. © 2022, North Atlantic University Union NAUN. All rights reserved.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

The Number of Solutions of Certain Equations over Finite Fields

引用

Wuhan University Journal of Natural sciences 2022年第1期27卷 49-52页

作者： HU Shuangnian LIU Jianghan QIN Zhentao School of Mathematics and Statistics Nanyang Institute of TechnologyNanyang 473004HenanChina College of Computer and Information Science Southwest UniversityChongqing 400715China School of Mathmatics and Computer Panzhihua UniversityPanzhihua 617000SichuanChina

Let s be a positive integer,p be an odd prime,q=p^(s),and let F_(q)be a finite field of q *** N_(q)be the number of solutions of the following equations:(x_(1)^(m_(1))+x_(2)^(m_(2))+…+x_(n)^(m_(n)))^(k)=x_(1)x_(2)…x_(n)x^(k_(n+1))_(n+1)…x^(k_(t))_(t)over the finite field F_(q),with n≥2,t>n,k,and k_(j)(n+1≤j≤t),m_(i)(1≤i≤n)are positive *** this paper,we find formulas for N_(q)when there is a positive integer l such that dD|(p^(l)+1),where D=1 cm[d_(1),…,d_(n)],d=gcd(n∑i=1M/m_(i)-kM,(q-1)/D),M=1 cm[m_(1),…,m_(n)],d_(j)=gcd(m_(j),q-1),1≤j≤*** we determine N_(q)explicitly under certain *** extends Markoff-Hurwitz-type equations over finite field.

关键词： finite field rational point diagonal equation Markoff-Hurwitz-type equations

来源：评论

学校读者我要写书评

暂无评论

Method of Generating the Summary of Discussions in Comments to Web News for Understanding Opinion Trends and Discussion Points

Method of Generating the Summary of Discussions in Comments ...

引用

2023 IEEE International Conference on Computing, ICOCO 2023

作者： Nakayama, Hiroki Wakabayashi, Hiroki Onuma, Ryo Kaminaga, Hiroaki Miyadera, Youzou Nakamura, Shoichi Art and Science Yamagata University Faculty of Education Yamagata990-8560 Japan Fukushima University Dept. Computer Science and Mathmatics Fukushima960-1296 Japan College of Liberal Arts Tsuda University Dept. Computer Science Tokyo187-8577 Japan Tokyo Gakugei University Division of Natural Science Tokyo184-8501 Japan

ISBN: (纸本)9798350302684

In recent years, there have been increasing opportunities for discussion and exchange of opinions on the internet. In order to clearly understand such discussions, users should be able to fully understand the flow of discussion as well as the conclusions. It is especially important to understand the main points as well as the trends in people's opinions in order to have more than a superficial understanding of the discussion. However, it is often difficult to understand them as the number of comments increases over time and the discussions become complex. In this research, we aim to develop methods for visualizing discussions in comments on online news articles to understand opinion trends and discussion points. This paper describes the methods for generating summaries of discussions and presents an overview of the support system. We also discuss the features of the proposed methods through the results of experiments using a prototype system for visualizing discussions. © 2023 IEEE.

关键词： Visualization

来源：评论

学校读者我要写书评

暂无评论

Adaptive Collaboration with a Training Plan 25

Adaptive Collaboration with a Training Plan

引用

25th IEEE International Conference on computer Supported Cooperative Work in Design, CSCWD 2022

作者： Guo, Cong Wu, Shiyu Zhu, Haibin Sheng, Yin Zhang, Libo Southwest University College of Artificial Intelligence Chongqing400715 China Nipissing University Department of Computer Science and Mathmatics North BayON Canada Hohai University College of Internet of Things Engineering 210000 China

ISBN: (纸本)9781665405270

Training is an effective way to improve agents' performance. As an extension of group role assignment (GRA), GRA with a training plan (GRATP) aims to maximize the group performance or benefit by finding the optimal role assignment and training plan. However, GRATP has only been discussed in static scenarios. In dynamic environments, agents' performance changes over time and adaptive collaboration is designed to keep the group in a good state. Therefore, this paper investigates the GRATP problem in adaptive collaboration. The timing of training has a significant impact on the improvement of individual performance, which will in turn affect the team performance and total benefit. By utilizing Role-Based Collaboration and GRA, the optimal training timing and training plan are obtained, which maximize the total benefit of the group. After training, the roles are re-assigned to the agents based on their current performance. This paper's contributions include formalizing the GRATP problem in adaptive collaboration and presenting a solution to it. The effectiveness of the proposed method is verified by experiments. © 2022 IEEE.

关键词： Timing circuits

来源：评论

学校读者我要写书评

暂无评论

Analysis of Exploratory Traces in Programming for Identifying Students Struggling in Construction of Program Logic

Analysis of Exploratory Traces in Programming for Identifyin...

引用

2023 IEEE International Conference on Computing, ICOCO 2023

作者： Kawasaki, Mitsuhiro Onami, Sho Onuma, Ryo Nakayama, Hiroki Miyadera, Youzou Nakamura, Shoichi Fukushima University Dept. Computer Science and Mathmatics Fukushima960-1296 Japan College of Liberal Arts Tsuda University Dept. Computer Science Tokyo Kodaira187-8577 Japan Yamagata University Faculty of Education Art and Science Yamagata Yamagata-shi990-8560 Japan Tokyo Gakugei University Division of Natural Science Tokyo Koganei-shi184-8501 Japan

ISBN: (纸本)9798350302684

Opportunities for programming education have been increasing, and enrichment of guidance is needed. To provide precise guidance in programming exercises, instructors need to successfully grasp learners' impasses. However, this is difficult in exercises at universities since few instructors need to deal with many learners. In this research, we focus on the characteristic traces left by a learner repeatedly writing and erasing source code in a program (exploratory traces). Our goal is to develop methods for automatically estimating students stumbling in construction of program logic on the basis of the analysis of exploratory traces. This paper mainly describes the methods for analyzing exploratory traces along with examples. We also describe experiments applying our methods to actual programming and discuss their effectiveness on the basis of their results. © 2023 IEEE.

关键词： computer circuits

来源：评论

学校读者我要写书评

暂无评论

Behavioral Features of Users as a Security Solution in Cloud Computing

Behavioral Features of Users as a Security Solution in Cloud...

引用

Contemporary Information Technology and Mathematics (ICCITM), International Conference on

作者： Mohammed Fawzi Sheet Melad Jader Saeed Computers Science Dept. College of Computer Science and mathmatics/Unversity of Mosul Mosul Iraq

A large number of establishments and organizations implement clouds to store their databases. More active attacks are used on clouds to get unauthorized access or to do harmful actions that may affect on user’s privacy. Therefore, many studies have proposed to increase the level of security in the clouds depended on several strategies. The behavior is one of the promising strategies that might prevent unauthorized or processes. In this paper, a set of features, are from several previous studies, and these features are based on the user activity and events in a special purpose cloud by which unauthorized process can be prevented and alert user about bad actions during his/her work in the cloud environment. The results of comparison show that the event-based features require less resources and time. Thus, they need to be enhanced by adding more informative features, or some available features form other strategies.

关键词： Deep learning Cloud computing Privacy Organizations Feature extraction Mathematics Hardware

来源：评论

学校读者我要写书评

暂无评论

Method of Generating the Summary of Discussions in Comments to Web News for Understanding Opinion Trends and Discussion Points

Method of Generating the Summary of Discussions in Comments ...

引用

Computing (ICOCO), IEEE International Conference on

作者： Hiroki Nakayama Hiroki Wakabayashi Ryo Onuma Hiroaki Kaminaga Youzou Miyadera Shoichi Nakamura Faculty of Education Art and Science Yamagata University Yamagata Japan Dept. Computer Science and Mathmatics Fukushima University Fukushima Japan Dept. Computer Science College of Liberal Arts Tsuda University Tokyo Japan Division of Natural Science Tokyo Gakugei University Tokyo Japan

关键词：

来源：评论

学校读者我要写书评

暂无评论

Analysis of Exploratory Traces in Programming for Identifying Students Struggling in Construction of Program Logic

Analysis of Exploratory Traces in Programming for Identifyin...

引用

Computing (ICOCO), IEEE International Conference on

作者： Mitsuhiro Kawasaki Sho Onami Ryo Onuma Hiroki Nakayama Youzou Miyadera Shoichi Nakamura Dept. Computer Science and Mathmatics Fukushima University Fukushima Japan Dept. Computer Science College of Liberal Arts Tsuda University Kodaira Tokyo Japan Faculty of Education Art and Science Yamagata University Yamagata-shi Yamagata Japan Division of Natural Science Tokyo Gakugei University Koganei-shi Tokyo Japan

关键词：

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：