检索结果-内蒙古大学图书馆

Recent Advances in computer science and Communications 2021年第9期14卷 2969-2975页

作者： Zhang, Sheng Luo, Qi Feng, Yukun Ding, Ke Gifu, Daniela Zhang, Silan Ma, Xiaohang Xia, Jingbo College of Science Huazhong Agricultural University Hubei Wuhan430070 China Faculty of Computer Science "Alexandru Ioan Cuza" University of Iasi Gen. Berthelot street N0. 16 RO-700483 Romania Institute of Computer Science Romanian Academy-Iasi branch Codreanu 2 RO-700481 Romania Hubei Key Lab of Agricultural Bioinformatics College of Informatics Huazhong Agricultural University Hubei Wuhan430070 China

Background: As a known keyphrase extraction algorithm, TextRank is an analog of the PageRank algorithm, which relies heavily on the statistics of term frequency in the manner of cooccurrence analysis. Objective: The frequency-based characteristic made it a bottleneck for performance enhancement, and various improved TextRank algorithms were proposed in recent years. Most of the improvements incorporated semantic information into the keyphrase extraction algorithm and achieved improvement. Method: In this research, taking both syntactic and semantic information into consideration, we integrated syntactic tree algorithm and word embedding and put forward an algorithm of Word Embedding and Syntactic Information Algorithm (WESIA), which improved the accuracy of the TextRank algorithm. Results: By applying our method on a self-made test set and a public test set, the result implied that the proposed unsupervised keyphrase extraction algorithm outperformed the other algorithms to some extent. © 2021 Bentham science Publishers.

关键词： Syntactics

来源：评论

学校读者我要写书评

暂无评论

Intraclass Correlation Coefficient as a Reliability Measure for Biomedical Text Annotation

SSRN

引用

SSRN 2023年

作者： Sulaman, Ismat Mohd Bulgiba, Awang Kareem, Sameem Abdul Health Informatics Centre Planning Division Ministry of Health Malaysia Malaysia Academy of Sciences Malaysia Department of Artificial Intelligence Faculty of Computer Science and Information Technology University of Malaya Kuala Lumpur Malaysia

Introduction: This paper compares the reliability of intraclass correlation coefficient (ICC) against 'Krippendorff's alpha in biomedical text annotation for Named Entity Recognition task. The task was to identify abbreviations in discharge ***: A total of 44 randomly sampled discharge notes were annotated independently by two or three medical graduates using the Brat Rapid Annotation Tool. The reliability of the annotated corpus was assessed with intraclass correlation coefficient two-way random effects and absolute agreement with multiple annotations (ICC(2,k)) and Krippendorff's alpha. Results: A total of 15,547 word-tokens were annotated either as an abbreviation or not. The mean difference between the two reliability measures was not statistically significant, with Krippendorff's alpha (M=0.866, SD=0.384) and ICC (M=0.858, SD=0.079), t (10) = -0.610, p = 0.556, 95% CI [-0.071, 0.040].Conclusion: ICC can be an alternative reliability measure for biomedical entity recognition tasks that do not require evaluation of semantic agreement. © 2023, The Authors. All rights reserved.

关键词： Reliability

来源：评论

学校读者我要写书评

暂无评论

A New Approach for Spread Spectrum Steganography in Audio Containers

A New Approach for Spread Spectrum Steganography in Audio Co...

引用

International Conference on Control Systems, Mathematical Modelling, Automation and Energy Efficiency (SUMMA)

作者： Stanimir Zhelezov Krasimir Kordov Atanas Nachev Daniela Pavlova Panayot Gindev Nikolay Litchkov Konstantin Nesterov dept. Computer Science and Technologies Konstantin Preslavsky University of Shumen Shumen Bulgaria dept. Computer Informatics Konstantin Preslavsky University of Shumen Shumen Bulgaria University of Library Studies and Information Technologies Sofia Bulgaria Institute of Robotics at Bulgarian Academy of Sciences Sofia Bulgaria Institute of Metal Science Equipment and Technologies with Center for Hydro- and Aerodynamics Acad. A. Balevski Bulgarian Academy of Sciences Sofia Bulgaria

ISBN: (数字)9798331532178

ISBN: (纸本)9798331532185

The most common approach among researchers is to implement cryptographic techniques and methods to provide a secure and reliable way to transmit sensitive information. This paper proposes a steganographic embedding algorithm based on Circle Map and Modified Rotation Equations. Audio files randomly selected from the Internet are used for the purpose of the study. Messages of different sizes were embedded in them using the proposed steganographic embedding algorithm. The accumulated database of more than 200 containers and stegofiles was analyzed using the most common steganalysis methods. From the analyses, it can be clearly seen that the proposed method of steganographic embedding in audio containers provides a very high level of security in the transmission of hidden information.

关键词： Steganography Automation Databases Containers Control systems Mathematical models Generators Energy efficiency Internet Reliability

来源：评论

学校读者我要写书评

暂无评论

Pathological Semantics-Preserving Learning for H&E-to-IHC Virtual Staining

arXiv

引用

arXiv 2024年

作者： Chen, Fuqiang Zhang, Ranran Zheng, Boyun Sun, Yiwen He, Jiahui Qin, Wenjian Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China Shenzhen College of Advanced Technology University of Chinese Academy of Sciences Shenzhen China Department of Health Technology and Informatics The Hong Kong Polytechnic University Hong Kong School of Computer Science University of Nottingham Ningbo China Ningbo China

Conventional hematoxylin-eosin (H&E) staining is limited to revealing cell morphology and distribution, whereas immunohistochemical (IHC) staining provides precise and specific visualization of protein activation at the molecular level. Virtual staining technology has emerged as a solution for highly efficient IHC examination, which directly transforms H&E-stained images to IHC-stained images. However, virtual staining is challenged by the insufficient mining of pathological semantics and the spatial misalignment of pathological semantics. To address these issues, we propose the Pathological Semantics-Preserving Learning method for Virtual Staining (PSPStain), which directly incorporates the molecular-level semantic information and enhances semantics interaction despite any spatial inconsistency. Specifically, PSPStain comprises two novel learning strategies: 1) Protein-Aware Learning Strategy (PALS) with Focal Optical Density (FOD) map maintains the coherence of protein expression level, which represents molecular-level semantic information;2) Prototype-Consistent Learning Strategy (PCLS), which enhances cross-image semantic interaction by prototypical consistency learning. We evaluate PSPStain on two public datasets using five metrics: three clinically relevant metrics and two for image quality. Extensive experiments indicate that PSPStain outperforms current state-of-the-art H&E-to-IHC virtual staining methods and demonstrates a high pathological correlation between the staging of real and virtual stains. © 2024, CC BY-NC-SA.

关键词： Proteins

来源：评论

学校读者我要写书评

暂无评论

Privacy Preservation in eLearning: Exploration and Analysis

Privacy Preservation in eLearning: Exploration and Analysis

引用

International Conference on Information Technology Based Higher Education and Training, ITHET

作者： Malinka Ivanova Iskra Trifonova Galina Bogdanova Department of Informatics Technical Faculty of Applied Mathematics and Informatics University of Sofia Sofia Bulgaria Vocational High School for Construction Architecture and Computer Science Montana Bulgaria Academy of Sciences Institute of Mathematics and Informatics Bulgarian Sofia Bulgaria

ISBN: (纸本)9781665489096

Nowadays, a big amount of data is collected in eLearning environments, tracking students’ behavior and their performance of learning activities. Also, a part of educational data is used by third parties for statistical or research purposes. In many cases, the datasets are transferred and processed without any techniques for students’ identity protection and there are possibilities after attacks private and sensitive data to be revealed. The aim of the paper is to present the results from conducted explorations and analysis about applying privacy preserving algorithms k-anonymity and ($\varepsilon,\delta$)-differential privacy on data, collected in eLearning environment. The balance between students’ privacy protection and usefulness of output information is discussed considering several privacy parameters. Machine learning is used to predict the most suitable privacy models and in this way to support the decision making of data holder/owner.

关键词： Data privacy Privacy Electronic learning Machine learning algorithms Machine learning Predictive models Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

Software-Defined Networking Model for Unmanned Systems Projects

Software-Defined Networking Model for Unmanned Systems Proje...

引用

Wave Electronics and its Application in Information and Telecommunication Systems (WECONF)

作者： S. V. Kozlov A. N. Kubankov A. P. Shabanov Federal Research Center "Computer Science and Control" Russian Academy of Sciences Moscow Russia Moscow Technical University of Communications and Informatics Moscow Russia

The research is carried out on the issues of building a software-adaptable network based on intentions and intended for intellectual support of promising instrument-engineering projects in the field of creating unmanned systems. Intentions are understood as the ordering of a certain level of quality of research experience (QoE metrics) with the goal of providing access to it, regardless of whether the network’s clients belong to various sectors of the economy and management spheres, but depending on their needs for research results. The network’s customers are organizational systems - sources of research results and their potential consumers, who use the research results in projects for the design of digital models and the development of microelectronic components and devices for unmanned vehicles for ground, air and other applications. The analysis of known models of a software-adaptable network is carried out and a new model is developed. The novelty of the model is determined by its architecture, which provides automatic identification of addresses of potential consumers of research results based on their needs recorded in the network and research metrics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Comparing the Effectiveness of Generative Adversarial Networks for Clustering Tasks 19

Comparing the Effectiveness of Generative Adversarial Networ...

引用

19th IEEE International Conference on computer science and Information Technologies, CSIT 2024

作者： Lytvynenko, Volodymyr Olszewski, Serge Osypenko, Volodymyr Lurie, Iryna Demchenko, Violeta Dontsova, Dariia Kherson National Technical University Department of Informatics and Computer Science Kherson Ukraine Taras Shevchenko National University Department of Radio Engineering and Electronic Systems Kyiv Ukraine Kyiv National University of Technology and Design Department of Computer Science Kyiv Ukraine State Institution 'Kundiiev Institute of Occupational Health of the National Academy of Medical Sciences of Ukraine' Kyiv Ukraine

ISBN: (纸本)9798331542627

This study compares the effectiveness of various Generative Adversarial Network architectures, including WGAN and WGAN-GP, in data clustering using the Iris dataset. Performance was evaluated with metrics such as Silhouette Score, Davies-Bouldin Index, Adjusted Rand Index, and Mutual Information. WGANs demonstrated the best clustering performance, while GANs showed promising results but were outperformed by WGAN. Contrary to expectations, WGAN-GP performed the worst. The research underscores the potential of GANs in clustering and highlights the need for further optimization based on specific datasets. © 2024 IEEE.

关键词： adjusted mutual information Davies-Bouldin index generative adversarial networks adjusted rand index mutual information silhouette index

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of the Use of Variational Autoencoders and Generative Adversarial Networks for Anomalous Image Detection Tasks

Comparative Analysis of the Use of Variational Autoencoders ...

引用

IEEE International Conference on Actual Problems of Unmanned Air Vehicles Developments Proceedings (APUAVD)

作者： Volodtmyr Lytvynenko Serge Olszewski Volodymyr Osypenko Iryna Lurie Violeta Demchenko Dariia Dontsova Department of Informatics and Computer Science Kherson National Technical University Kherson Ukraine Department of Radio Engineering and Electronic Systems Taras Shevchenko National University Kyiv Ukraine Department of Computer Science Kyiv National University of Technology and Design Kyiv Ukraine State Institution «Kundiiev Institute of Occupational Health of the National Academy of Medical Sciences of Ukraine» Kyiv Ukraine

ISBN: (数字)9798331534141

ISBN: (纸本)9798331534158

This paper presents a comparative analysis of the application of Variational Autoencoders (VAE) and Wasserstein Generative Adversarial Networks (WGAN) for detecting anomalous images. The performance evaluation of the models is conducted using metrics such as AUC, Precision, Recall, and F1-Score. The results indicate that VAEs provide high Recall in anomaly detection but with low Precision, whereas WGANs demonstrate more balanced results with fewer false positives. Recommendations are proposed for selecting an appropriate model depending on the specific task requirements and the need to minimize false alarms or achieve high detection completeness.

关键词： Performance evaluation Analytical models Sensitivity Costs Accuracy Generative adversarial networks Autonomous aerial vehicles Anomaly detection Tuning

来源：评论

学校读者我要写书评

暂无评论

Comparing the Effectiveness of Generative Adversarial Networks for Clustering Tasks

Comparing the Effectiveness of Generative Adversarial Networ...

引用

International computer sciences and Information Technologies (CSIT)

作者： Volodymyr Lytvynenko Serge Olszewski Volodymyr Osypenko Iryna Lurie Violeta Demchenko Dariia Dontsova Department of Informatics and Computer Science Kherson National Technical University Kherson Ukraine Department of Radio Engineering and Electronic Systems Taras Shevchenko National University Kyiv Ukraine Department of Computer Science Kyiv National University of Technology and Design Kyiv Ukraine State Institution «Kundiiev Institute of Occupational Health of the National Academy of Medical Sciences of Ukraine» Kyiv Ukraine

ISBN: (数字)9798331542634

ISBN: (纸本)9798331542641

关键词： Training Measurement Iris Stability criteria computer architecture Generative adversarial networks Indexes Information technology Mutual information Optimization

来源：评论

学校读者我要写书评

暂无评论

Active Disturbance Rejection Control for 3D Crane Systems 11

Active Disturbance Rejection Control for 3D Crane Systems

引用

11th International Conference on Information Technology and Quantitative Management, ITQM 2024

作者： Roman, Raul-Cristian Precup, Radu-Emil Petriu, Emil M. Politehnica University of Timisoara Dept. Automation and Applied Informatics Bd. V. Parvan 2 Timisoara300223 Romania Center for Fundamental and Advanced Tech. Res. Romanian Academy - Timisoara Br. Bd. Mihai Viteazu 24 Timisoara300223 Romania University of Ottawa School of Electrical Engineering and Computer Science 800 King Eduard OttawaONK1N 6N5 Canada

Active Disturbance Rejection Control (ADRC) is a data-driven algorithm that offers a promising approach for robust control design. This paper investigates the effectiveness of first-order and second-order ADRC for 3D cranes. To compare the results fairly and reduce the heuristics in parameter tuning, the ADRC parameters were optimally computed via the African Vultures Optimization Algorithm. Both controllers based on ADRC are validated using experiments on a 3D crane laboratory system and their design and performance evaluation are done by minimizing the sum of squared errors. The results demonstrate the robustness of the ADRCs. This comparative analysis highlights the advantages and limitations of both control strategies, providing valuable insights for selecting the appropriate ADRC order for specific applications. © 2024 The Authors.

关键词： Disturbance rejection

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：