检索结果-内蒙古大学图书馆

A Deep Learning Driven Feature Based Steganalysis Approach

Intelligent Automation & Soft Computing 2023年第8期37卷 2213-2225页

作者： Yuchen Li Baohong Ling Donghui Hu Shuli Zheng Guoan Zhang College of Computer Science and Information Engineering Hefei University of TechnologyHefei230009China College of Information Engineering Anhui Broadcasting Movie and Television CollegeHefei230011China Department of Informatics Faculty of Natural&Mathematical SciencesKing’s College LondonLondonWC2R2LSUK

The goal of steganalysis is to detect whether the cover carries the secret information which is embedded by steganographic *** traditional ste-ganalysis detector is trained on the stego images created by a certain type of ste-ganographic algorithm,whose detection performance drops rapidly when it is applied to detect another type of steganographic *** phenomenon is called as steganographic algorithm mismatch in *** resolve this pro-blem,we propose a deep learning driven feature-based *** advanced steganalysis neural network is used to extract steganographic features,different pairs of training images embedded with steganographic algorithms can obtain diverse features of each *** a multi-classiﬁer implemented as lightgbm is used to predict the matching *** results on four types of JPEG steganographic algorithms prove that the proposed method can improve the detection accuracy in the scenario of steganographic algorithm mismatch.

关键词： Image steganalysis algorithm mismatch convolutional neural network JPEG images

来源：评论

学校读者我要写书评

暂无评论

The influence of culture on creativity in ideation: a review

The influence of culture on creativity in ideation: a review

引用

2024 International Design Society Conference, Design 2024

作者： Gong, Zhengya Gonçalves, Milene Nanjappan, Vijayakumar Georgiev, Georgi V. Center for Ubiquitous Computing University of Oulu Finland Department of Design Organisation and Strategy Faculty of Industrial Design Engineering Delft University of Technology Netherlands School of Computer Science and Information Technology University College Cork Ireland

The relationship between culture and creativity has sparked the interest of researchers for decades. Although researchers have attempted to establish a connection between culture and creativity, the precise relationship between the two remains ambiguous. The current paper examined extant literature on the subject matter and synthesized the relations between culture and creativity in ideation over the past twenty years. The present study expounds upon the utilized samples, measures implemented to assess creativity and culture, and the study results. © 2024 Proceedings of the Design Society. All rights reserved.

关键词： Behavioral research

来源：评论

学校读者我要写书评

暂无评论

Complex Pythagorean Fuzzy Decision-Based Approach for Developing English Translation of the Scripture-Based Multiclustering Algorithms

引用

International Journal of information technology and Decision Making 2025年第2期24卷 473-533页

作者： Ahmed, Mohammed A. Zaidan, A.A. Qahtan, Sarah Alsattar, Hassan A. Zaidan, B.B. Mourad, Nahia Baharin, Hanif Kou, Gang Yatim, Khaironi Institute of IR 4.0 Universiti Kebangsaan Malaysia Bangi43600 Malaysia Network Engineering Department College of Engineering Al-Iraqia University Al Adhmia-Haiba Khaton Baghdad10053 Iraq SP Jain School of Global Management Lidcombe SydneyNSW2141 Australia Information Technology Unit College of Health and Medical Technology-Baghdad Middle Technical University Baghdad Iraq Research Center Mazaya University College Nasiriyah Iraq MEU Research Unit Middle East University Amman Jordan Faculty of Engineering and IT British University in Dubai Dubai United Arab Emirates School of Business Administration Faculty of Business Administration Southwestern University of Finance and Economics Chengdu611130 China Computer and Information Sciences Faculty of Sciences and Information Technology Universiti Teknologi PETRONAS Seri Iskandar32610 Malaysia

The English Translation of the Quran Tafsir (ETQT) is essential to understanding and interpreting Allah's words. Clustering is a common text mining technique for eliciting meaningful knowledge from a text collection. It is commonly used when the selected datasets lack typical ground truths. To the best of our knowledge, no study has evaluated and benchmarked ETQTs to select the most comprehensive and appropriate one. The process of evaluating and benchmarking ETQTs falls under the multicriteria decision-making (MCDM) problem because of different issues, namely, multiple internal clustering validation criteria, data variation, and trade-offs between different criteria. The fuzzy decision by opinion score method (FDOSM) is one of the most recommended MCDM ranking methods in the literature to address the said issues. FDOSM has been extended under different fuzzy set (FS) environments to address issues of uncertainty and vagueness caused by expert feedback subjectivity. Although prior versions of FDOSM improved the uncertainty and vagueness issues, they remain open issues. Therefore, this paper extended FDOSM into the complex Pythagorean fuzzy decision by opinion score method (CPFDOSM) to evaluate and benchmark ETQTs. The proposed method consists of two main phases. The first phase formulates decision-matrix-based cluster algorithms and internal cluster validation criteria. The second phase (CPFDOSM development) prioritizes ETQTs and selects the optimum one. Data generation is performed on five different cluster algorithms and six internal cluster validation criteria using 16 ETQTs based on three decision-makers (DMs). Results show the following: (1) 6.25% of the individual decision-making results are identical among the three DMs, whereas 93.75% (n = 15/16) are different when I = 0.5 and I = 2. When I = 0.5. In addition, T7 has consistent ranks (Rank=16) across all DMs, whereas T14 has consistent ranks (Rank=1) across all DMs when I = 1. (2) The results of the group de

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Recent Evolutionary Computing Algorithms and Industrial Applications: A Review 15th

Recent Evolutionary Computing Algorithms and Industrial Appl...

引用

15th International Conference on Genetic and Evolutionary Computing, ICGEC 2023

作者： Chu, Shu-Chuan Dao, Thi-Kien Ha, Thi-Minh-Phuong Ngo, Truong-Giang Nguyen, Trong-The College of Computer Science and Engineering Shandong University of Science and Technology Qingdao266590 China University of Information Technology Ho Chi Minh City700000 Viet Nam Vietnam National University Ho Chi Minh City700000 Viet Nam Information Technology Center Hanoi Law University Hanoi Viet Nam Faculty of Computer Science and Engineering Thuyloi University Hanoi Viet Nam

ISBN: (纸本)9789819700677

Evolutionary computing algorithms have gained significant attention in recent years due to their ability to solve complex optimization problems in various domains. This paper provides a comprehensive review of recent advancements in evolutionary computing algorithms and their industrial applications. The objective is to analyze the state-of-the-art evolutionary computing algorithms and assess their effectiveness in addressing real-world challenges in different industrial sectors. The paper also discusses the key challenges and future directions for the integration of evolutionary computing algorithms in industrial settings. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Leveraging Support Vector Machine for Sports Injury Classification 15

Leveraging Support Vector Machine for Sports Injury Classifi...

引用

15th International Conference on information technology and Electrical engineering, ICITEE 2023

作者： Surasak, Thattapon Praking, Phornnatee Kitchat, Kotcharat King Mongkut's University of Technology North Bangkok Faculty of Applied Science Dept. of Computer and Information Science Bangkok Thailand National Central University Dept. of Computer Science and Information Engineering Taoyuan Taiwan

ISBN: (纸本)9798350304466

This study explores the utility of Support Vector Machines (SVM) for the classification of injuries in Athletes including tennis, table tennis, and badminton. The primary objective of this research was to develop an automated method to detect between normal and injury pose, providing a poten-tially powerful tool for early detection. In other words, this research is the pioneer study to represent one another solution for sports injury classification using the image data apart from the current approaches that might be focused on the sensor-based. Therefore, we collect a dataset from various social media across the three sports, labeled into two categories: 'Normal' and 'Injury'. The SVM model was trained on this dataset, and tuned to optimize its performance in distinguishing the two classes. Achieving an accuracy of 96.63%, the result demonstrates that the SVM model can effectively identify injury patterns in the considered sports. The implications of this study are sig-nificant, presenting the initial steps towards applying computer vision tasks in sports topics. By demonstrating the feasibility of an SVM-based approach to injury detection in these racket sports. © 2023 IEEE.

关键词： Sports

来源：评论

学校读者我要写书评

暂无评论

The Possibility of Applying a Universal Testing Machine for Evaluating Food Textures 1

引用

International Conference of Experimental and Numerical Investigations and New Technologies, CNNTech 2023

作者： Jevtić, Ivana Trajković, Isaak Zlatanović, Ivan Mladenović, Goran Korolija, Nenad Milošević, Miloš Innovation Centre of the Faculty of Mechanical Engineering Kraljice Marije 16 Belgrade11120 Serbia Faculty of Mechanical Engineering University of Belgrade Kraljice Marije 16 Belgrade11120 Serbia The Department of Computer Science and Information Technology University of Belgrade - School of Electrical Engineering Belgrade11000 Serbia

ISBN: (数字)9783031464324

ISBN: (纸本)9783031464317

The evaluation of food texture is an essential aspect of food quality control, directly influencing consumer acceptance and preference. Various methods have been developed to assess food texture, including sensory evaluation, rheological measurements, and instrumental analysis. Among the versatile instruments used for measuring the mechanical properties of food, the universal testing machine (UTM) stands out. Traditionally used in the field of materials science and engineering, the possibility of applying UTM for evaluating food textures has gained significant attention in recent years. The UTM can perform compression, tension, bending, and shear tests on food samples, providing objective and quantifiable data on their mechanical properties. Compression testing involves measuring the force required to compress a food sample between two plates, shear testing measures the force required to cut through a food sample, while puncture testing measures the force required to puncture a food sample with a probe. This paper reviews the current state-of-the-art of UTM in the evaluation of food textures, including the types of tests that can be performed, the parameters that can be measured, and the challenges and limitations associated with the technique. The potential of utilizing UTMs in the food industry for quality control and product development, instead of traditional sensory evaluation methods, is discussed, along with its advantages and disadvantages. Overall, UTM represents a promising tool for the objective evaluation of food textures, and further research is needed to optimize its application in this field. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Compression testing

来源：评论

学校读者我要写书评

暂无评论

Offsets Reconstruction Method for Clock Skew Measurement Over High-Jitter Communication

引用

SN computer Science 2025年第5期6卷 1-14页

作者： Sastra, Nyoman Putra Saputra, Komang Oka Teng, Wei-Chung Study Program of Electrical Engineering Faculty of Engineering Udayana University Jalan Raya Kampus Bukit Jimbaran Bali Badung 80361 Indonesia Department of Computer Science and Information Engineering National Taiwan University of Science and Technology No. 43 Section 4 Keelung Rd Taipei 106 China

Measuring clock skew of devices over a network fully relies on the offsets, the differences between sending and receiving times. Offsets that shape a thick line are the most ideal one as their slope is directly the clock skew sought. When some outliers separate from the thick line due to higher delay jitter, current advanced approaches use the lower bound or the majority of offsets to derive accurate clock skew. However, outliers in offsets that shape parallel dotted lines, reduce the availability of offsets in the lower region, and scatter widely the offsets from their majority zone. These conditions drive the current skew estimation approaches to lose their accuracy. This paper then developed a new method, which reconstructs back the outliers into their origin positions, in order to provide ideal offsets for clock skew measurement. The experimental evaluations have demonstrated that the clock skew accuracy of dotted-lines offsets tampered by outliers was improved from 2.1 to 0.9 ppm by the proposed reconstruction method. For a broader purpose, the reconstruction method has been adjusted to be implemented also on non-dotted-lines offsets. The robustness of the proposed method for this case has also been exhibited by the very ideal reconstructed offsets that shape like a thick line. © The Author(s) 2025.

关键词： Clock skew Delay jitter Dotted lines Hough transform

来源：评论

学校读者我要写书评

暂无评论

Unsafe at any Bandwidth: Towards Understanding Risk Factors for Ransomware in Higher Education 15

Unsafe at any Bandwidth: Towards Understanding Risk Factors ...

引用

15th International Conference on Ambient Systems, Networks and Technologies Networks, ANT 2024 / The 7th International Conference on Emerging Data and Industry 4.0, EDI40 2024

作者： Suarez, Logan Alshubrumi, Dakhilallah O'Connor, Tj Sudhakaran, Sneha Department of Electrical Engineering and Computer Science Florida Institute of Technology MelbourneFL United States Faculty L3Harris Institute for Assured Information Florida Institute of Technology MelbourneFL United States

United States higher education institutions host an assortment of services that are accessible via public IP addresses. The wide variety of network services and the important personal and institutional data stored on such services make higher education institutions particularly desirable targets for attackers. This study analyses the vulnerabilities found through Shodan scans on these networks, in conjunction with institutional characteristics data taken from the National Center for Education Statistics (NCES), to examine correlations between an institution's characteristics and the vulnerabilities found on its networks. By exploring this data, the study aims to bring awareness to the current state of higher education institution network security and determine vulnerability trends between certain institutions. Our analysis reveals that most institutions have many medium impacts but highly exploitable vulnerabilities, with most being on Apache HTTP servers. We also present that the most significant indicators of an institution's vulnerability are its enrolment and yearly total expenses. We investigate how smaller institutions have lower numbers of vulnerabilities, but their vulnerabilities have the potential for higher impact. We conclude that there is a significant chance of ransomware risk in US higher educational institutions. © 2024 Elsevier B.V.. All rights reserved.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Image Encryption using Color Space Neural Network Transformation and Chaotic Pixel Perturbation

引用

Signal, Image and Video Processing 2025年第9期19卷 1-9页

作者： Al-Muhammed, Muhammed Ababneh, Ahmad Al-Daraiseh, Ahmad Department of Computer Science and Computer Engineering Morehead State University Morehead USA Faculty of Information Technology American University of Madaba Madaba Jordan

This paper presents a novel image encryption method combining neural networks, color space transformation, and chaotic systems. Unlike traditional methods, it enhances the dimensionality of complexity by introducing key- and input-dependent security. It integrates dual-stage pixel scrambling, memory-based bidirectional substitution, and color transformation neural networks. The proposed method yields low adjacent pixel correlation (0.0002) and near-ideal entropy (7.9990), with minimal computational load.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Developing a computer-Aided Diagnostic System for Breast Cancer Ultrasound Imaging

Developing a Computer-Aided Diagnostic System for Breast Can...

引用

2023 IEEE EMBS Special Topic Conference on Data Science and engineering in Healthcare, Medicine and Biology, IEEECONF 2023

作者： Taha, Radwa Afifi, Shereen Abd-Elghany, Mohamed A. Salem, Mohammed A.-M German University in Cairo The Faculty of Media Engineering and Technology New Cairo Egypt German University in Cairo Faculty of Media Engineering and Technology Computer Science Engineering New Cairo Egypt German University in Cairo Faculty of Information Engineering and Technology Electrical Engineering New Cairo Egypt Tu Darmstadt Integrated Electronics Systems Lab Germany German University in Cairo Faculty of Media Engineering and Technology Digital Media Engineering New Cairo Egypt

ISBN: (纸本)9798350383386

In this research we aim to develop a computer-aided diagnostic system (CAD) for breast ultrasound imaging to enhance the early detection of breast cancer. CAD tools aid physicians in the diagnostic process leading to early detection and treatment of breast cancer. The proposed CAD tool comprises three stages, the first is enhancement of breast ultrasound imaging by applying custom segmentation deep learning architectures [U-Net, SK-U-Net, RDA-U-Net] to enhance the isolation of masses in Ultrasound images, then generation of new ultrasound images by employing Generative Adversarial Networks [DAGAN, DCGAN] to overcome data limitation in available data-sets, and the last stage is the detection and classification of breast cancer masses by a CNN model. The enhancement stage shows promising results with accuracy of 98 % overall accuracy, 92 % overall precision, and 85 % overall *** Relevance: Breast cancer is one of the deadly diseases in the world. The earlier the detection the higher the chances of recovery. Thus a CAD tool that facilitates the screening process of ultrasound images will aid physicians in the early detection and diagnosis of the disease. © 2023 IEEE.

关键词： Diseases

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：