检索结果-内蒙古大学图书馆

Exploring information hiding in images – problems and measures: a survey

Multimedia Tools and Applications 2025年 1-63页

作者： Khan, Ahmed Sarfaraz, Aaliya School of Computer Science Taylor’s University Subang Jaya Malaysia School of Computing and Artificial Intelligence Faculty of Engineering and Technology Sunway University No. 5 Jalan Universiti Selangor Darul Ehsan Bandar Sunway47500 Malaysia

The widespread adoption of digital communication technologies across various domains has led to a significant shift towards digitalization. However, this evolution has also introduced vulnerabilities, including unauthorized access, data manipulation, and fabrication by malicious entities, which severely impact the confidentiality and integrity of information. The proliferation of digital images on the internet has facilitated the use of these media for embedding confidential data in a way that prevents detection or extraction by unauthorized third parties. Despite numerous efforts, existing image steganography and watermarking techniques often lack robustness. This paper proposes several novel strategies to enhance the dynamism and imperceptibility of these techniques, integrating cryptographic methods by manipulating the entropy of encrypted images using minimal pixel value differences and applying unique image transformations. Additionally, the study highlights that implementing multi-layered security mechanisms can protect confidential information from modern statistical steganalysis attacks, thereby preserving both the integrity of hidden data and image quality. A comprehensive review of information hiding, specifically focusing on image watermarking and steganography, is provided. Furthermore, this survey outlines key problem statements and offers quantitative metrics for future research in this area. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Steganography

来源：评论

学校读者我要写书评

暂无评论

Local Texture Patterns Fusion For Content Based Image Retrieval 9th

Local Texture Patterns Fusion For Content Based Image Retrie...

引用

9th International Conference on Smart City Applications, SCA 2024

作者： Zekkouri, Hassan Zarouit, Yousra Aksasse, Brahim Ouanan, Mohammed Ouhda, Mohamed Department of Computer Science Faculty of Science and Techniques Errachidia Moulay Ismail University Errachidia Morocco Department of Computer Science Faculty of Sciences and Technics Moulay Ismail University Errachidia Morocco Department of Computer Science Faculty of Science Meknes Moulay Ismail University Errachidia Morocco Department of Computer and Mathematics TIAD Laboratory Higher School of Technology Sultan Moulay Slimane University Khenifra Morocco

ISBN: (纸本)9783031886522

Content-based image retrieval (CBIR) is a method of developing image search engines. It involves searching for images that are similar to a given query image from a large collection of images. This is done by analyzing the content of each image pixel. CBIR is considered a substitute for traditional text-based image retrieval (TBIR), which depends on text annotation for conducting image retrieval. Although TBIR is capable of conducting image retrieval, it is limited by its use of a restricted vocabulary for annotating images, which may not encompass all aspects of the image’s content. This limitation can lead to ambiguity and various interpretations. This results in the imprecise retrieval of images via TBIR. To address these limitations and overcome additional obstacles, instead of using a textual description, CBIR (Content-Based Image Retrieval) utilizes the content of each image to generate a vector description by analyzing the digital image properties such as color, texture, and shape. This work explores the utilization of specific local texture patterns for image vector description. In addition, we employ various similarity/dissimilarity metrics to evaluate the performance of each technique in comparison to the Corel-1k dataset. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Content based retrieval

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning-Based Framework for Enhancing Cybersecurity

International Journal of Interactive Mobile Technologies

引用

International Journal of Interactive Mobile Technologies 2025年第3期19卷 170-190页

作者： Al-Nawashi, Malek M. Al-Hazaimeh, Obaida M. Tahat, Nedal M. Gharaibeh, Nasr Abu-Ain, Waleed A. Abu-Ain, Tarik Al-Huson University College Al-Balqa Applied University Irbid Jordan Faculty of Information Technology Department of Information Security and Cybersecurity Philadelphia University Amman Jordan Faculty of Science The Hashemite University Zarqa Jordan College of Science and Computer Engineering Taibah University Yanbu Saudi Arabia College of Computing and Informatics Saudi Electronic University Riyadh Saudi Arabia

The detection of cyberattacks has been increasingly emphasized in recent years, focusing on both infrastructure and people. Conventional security measures such as intrusion detection, firewalls, and encryption are insufficient in protecting cyber systems against growing and changing threats. In order to address this problem, scholars have explored reinforcement learning (i.e., RL) as a potential solution for intricate cybersecurity decision-making difficulties. Nevertheless, the use of RL faces several obstacles, including dynamic attack scenarios, insufficient training data, and the challenge of replicating real-world complexities. This study presents a novel framework that uses deep reinforcement learning (i.e., DRL) to simulate harmful cyberattacks and improve cybersecurity. This study presents an agent-based framework that is capable of ongoing learning and adaptation in a dynamic network security environment. The agent determines the optimal course of action by considering the current state of the network and the rewards it receives for its decisions. The CIC-IDS-2018 database, constructed using Python 3.7 programming, was used. The conducted studies yielded outstanding results, with a detection accuracy of 98.82% achieved for the CIC-IDS-2018 database in cyber-attack classification. © 2025 by the authors of this article. Published under CC-BY.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

A Wideband 4X4 Patch Array Antenna With Low Sidelobes for Radar-Based Obstacle Detection in Railway Transportation

IEEE Open Journal of Antennas and Propagation

引用

IEEE Open Journal of Antennas and Propagation 2025年第3期6卷 774-788页

作者： Phakaew, Thipamas Pongthavornkamol, Tiwat Torrungrueng, Danai Dallmann, Thomas Chalermwisutkul, Suramate National Science and Technology Development Agency National Electronics and Computer Technology Center Pathum Thani12120 Thailand King Mongkut's University of Technology North Bangkok Faculty of Technical Education Bangkok10800 Thailand Ilmenau University of Technology Faculty of Electrical Engineering and Information Technology Ilmenau98693 Germany King Mongkut's University of Technology North Bangkok Sirindhorn International Thai-German Graduate School of Engineering Bangkok10800 Thailand Rwth Aachen University Institute of High Frequency Technology Aachen52074 Germany

This paper presents the design, fabrication, and measurement of a 4W4 patch array antenna for radar-based obstacle detection systems in railway transportation. Sidelobe suppression is achieved through amplitude tapering of sub-array elements in the E-plane and asymmetric power dividers in the feed network for the H-plane. The array antenna is framed by a coplanar ground conductor to further reduce sidelobes and fed by a coplanar waveguide port for enhanced impedance bandwidth. The proposed antenna offers an impedance bandwidth from 9.13 GHz to 9.76 GHz (6.3%) and a broadside gain of 18.15 dBi at the center frequency of 9.55 GHz. Sidelobe suppression exceeds 12.22 dB and 19.06 dB in the E-and H-plane, respectively. The 3-dB beamwidth is 17° in the E-plane and 16° in the H-plane with simulated radiation efficiency of 85%. A prototype was fabricated and measured, with sensitivity analysis conducted to assess performance variations due to fabrication tolerances and measurement fixture effects. To validate system performance, antenna prototypes were integrated into a frequency-modulated continuous wave radar system and tested in a realistic railway environment. The system successfully detected a truck crossing a railway track at approximately 1,260 meters, confirming the antenna's suitability for radar-based obstacle detection in railway transportation. © 2020 IEEE.

关键词： Obstacle detectors

来源：评论

学校读者我要写书评

暂无评论

A Multi-Scale Deep Learning Framework Combining MobileViT-ECA and LSTM for Accurate ECG Analysis

引用

IEEE Access 2025年 13卷 85473-85492页

作者： Ba Mahel, Abduljabbar S. Al-Gaashani, Mehdhar S. A. M. Alkanhel, Reem Ibrahim Hassan, Dina S. M. Muthanna, Mohammed Saleh Ali Muthanna, Ammar Aziz, Ahmed University of Electronic Science and Technology of China School of Life Science and Technology Chengdu610054 China University of Electronic Science and Technology of China School of Resources and Environment Chengdu610056 China Princess Nourah bint Abdulrahman University College of Computer and Information Sciences Department of Information Technology P.O. Box 84428 Riyadh11671 Saudi Arabia Tashkent State University of Economics Department of International Business Management Tashkent Uzbekistan RUDN University Department of Applied Probability and Informatics Peoples’Friendship University of Russia 6 Miklukho-Maklaya St Moscow117198 Russia Faculty of Computer and Artificial Intelligence Benha University Department of Computer Science Egypt Central Asian University Engineering school Tashkent Uzbekistan

Electrocardiogram (ECG) analysis is crucial for diagnosing cardiovascular diseases (CVD), especially atrial fibrillation (AF), a prevalent cardiac rhythm abnormality. However, the variability and complexity of ECG signals make AF classification challenging, highlighting the need for more accurate and reliable methods. This paper introduces a novel deep learning (DL) architecture designed to enhance the processing, feature extraction, and analysis of ECG signals. The proposed model utilizes a hybrid framework that combines standard and dilated convolutional networks, advanced attention mechanisms, and temporal sequence learning to address the complexities of ECG data. A parallel architecture integrates a MobileViT block for efficient spatial feature extraction and an Efficient Channel Attention (ECA) module to refine feature representations. Simultaneously, a Long Short-Term Memory (LSTM) network captures temporal dependencies in the data. The concatenation of the outputs from both the MobileViT-ECA block and the LSTM network allows for the extraction of both local and global features. Fully connected layers, along with dropout regularization, ensure robust performance and effective classification. We analyzed ECG signals of three different lengths (1, 2, and 3 seconds) to investigate how segment length affects model performance. Additionally, we conducted various classification scenarios and an ablation study to simulate real-world conditions and identify key components of the architecture. Our experimental findings show that the model attains high accuracy in ECG classification and AF identification, with average metrics including accuracy of 87.80%, recall of 87.80%, F1-score of 87.45%, and specificity of 95.66%. The proposed model outperforms existing methods on the same AF dataset, demonstrating its superior performance. This method accurately classifies ECG signals and detects AF, highlighting its potential for clinical application. The results help move forwar

关键词： Electrocardiography

来源：评论

学校读者我要写书评

暂无评论

IoT Based Monitoring System for Health During Menstruation 4

IoT Based Monitoring System for Health During Menstruation

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Khadse, Chinmaya Hajare, Shital Sheikh, Nishad Dahule, Roshni Kate, Priya Datta Meghe Institute of Higher Education and Research Faculty of Engineering and Technology Department of Computer Science and Engineering Sawangi Maharashtra Wardha442001 India Datta Meghe Institute of Higher Education and Research Faculty of Engineering and Technology Department of Artificial Intelligence and Machine Learning Sawangi Maharashtra Wardha442001 India Datta Meghe Institute of Higher Education and Research Faculty of Engineering and Technology Department of Computer Science and Engineering Sawani Maharashtra Wardha442001 India

ISBN: (纸本)9798331523923

The integration of IoT and ML brought forth new prospective solutions in menstrual health management, pertaining to continuous monitoring of physiological signals and personalization of insights for women. This article discusses the usage of IoT, smartphones, and cloud-based systems for tracking vital signs, temperature, pulse rate, and flow of menstruation that will enable pro-active management of the cycle. The use of ML algorithms, including supervised models-like Random Forest and Logistic Regression-and complex techniques like RNNs and LSTM networks-offers added advantages for predicting menstrual cycles and ovulation. These technologies offer personalized health recommendations, early diagnosis of menstrual disorders, and help in communicating with healthcare providers in a very short span of time. While offering huge potential to improve women's health, concerns around data privacy, ethical considerations, and equitable access to these digital health solutions are highlighted. The existing systems showed improvements yet they encountered problems because of insufficient data diversity and health system integration as well as insufficient personalization and imprecise cycle predictions. Data privacy issues and security threats that stem from ML models along with constant bias concerns prevent broad acceptance of ML systems in general use. This research study analyzes IoT and ML applications in menstrual health today and introduces their advantages as well as the barriers that require resolution before mass acceptance can occur. The proposal introduces an approach to create menstrual tracking software through a combination of rule-based systems with ML algorithms that generates precise forecasts alongside tailored information for women who have PCOS or PCOD. © 2025 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Privacy Protection in Learning Management Systems’ Mobile technology-Based Learning Analytics

International Journal of Interactive Mobile Technologies

引用

International Journal of Interactive Mobile Technologies 2025年第6期19卷 197-208页

作者： Rawat, Manoj Kumar Jha, Suresh Kumar Sree Lakshmi, A. Venkata Ramana, J. Gonge, Sudhanshu S. De, Arunava Department of Computer Science and Engineering Medi-Caps University Madhya Pradesh Indore India Manipal University Rajasthan Jaipur India Geetanjali College of Engineering and Technology Telangana Hyderabad India Department of MBA KL Business School Koneru Lakshmaiah Education Foundation Vaddeswaram Campus Guntur District Andhra Pradesh India Department of Computer Science & Information Technology Symbiosis Institute of Technology Lavale A Constituent of Symbiosis International University Maharashtra Pune India Faculty of Information Technology Gopal Narayan Singh University Bihar Jamuhar India

Mobile technology use in education is changing, much like in the business and health sectors. Research is now conducted on designing user-centric platforms that allow people to engage in teaching and learning activities. Although the learning management systems (LMS) field supports students and academic endeavors, the application’s high requirements prevent it from having the desired effect. More significantly, although mobile applications are conve-nient, there is a chance that user data could be maliciously exploited and eavesdropped. Due to the communication overhead of sending raw data to the central learning processor, wire-less application structures cannot adapt to the original structure of mobile learning, which calls for data and processing heads to have a centralized entity. The goal is to offer fresh viewpoints and approaches that bring educational assessment up to date. This project aims to give educators scientifically based assessment tools and tactics by thoroughly examining the use of mobile technology in academic assessment. This will allow for more accurate teaching management and individualized instruction. © 2025 by the authors of this article. Published under CC-BY.

关键词： Mobile computing

来源：评论

学校读者我要写书评

暂无评论

Boundary Extraction for Unseen Entities Prediction Using Bidirectional Long Short-Term Memory 17th

Boundary Extraction for Unseen Entities Prediction Using Bid...

引用

17th International Conference on Multi-disciplinary Trends in Artificial Intelligence, MIWAI 2024

作者： Kuntichod, Watcharet Lee, Wilaiporn Prayote, Akara Department of Computer and Information Science King Mongkut’s University of Technology North Bangkok Bangkok10800 Thailand Department of Electrical and Computer Engineering Faculty of Engineering King Mongkut’s University of Technology North Bangkok Bangkok10800 Thailand

ISBN: (纸本)9789819606917

Named Entities Recognition (NER), which is a task to identify and classify named entities within text, has gained significant popularity in recent years. This task often requires pre-labeled data and large datasets to achieve high accuracy. A key challenge in NER is extracting unseen entities that have not been previously labeled or are new terms, posing difficulties in adapting to rapidly changing data and the emergence of new vocabularies. In this article, we propose a model utilizing Bidirectional Long Short-Term Memory (Bi-LSTM) for boundary extraction. The model aims to enhance the detection and labeling of unseen entities by leveraging Bi-LSTM's strengths in capturing contextual information and accurately identifying entities boundaries. The model demonstrates high potential in identifying unseen names without pre-labeling. Our study demonstrates the model's showcasing its effectiveness in discovering unlabeled words and unseen entities in Thai language datasets. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Labeled data

来源：评论

学校读者我要写书评

暂无评论

Leveraging Pruning, Quantization and Multi-objective Optimization for an Efficient Deployment of Multi-modal Models 31st

Leveraging Pruning, Quantization and Multi-objective Optimi...

引用

31st International Conference on Multimedia Modeling, MMM 2025

作者： Vu, Dang Dang, Tien Nguyen, Quoc-Trung Pham, Tan Faculty of Information Technology University of Science Ho Chi Minh City Viet Nam FPT Software AI Center Ho Chi Minh City Viet Nam AISIA Lab Faculty of Mathematics and Computer Science Ho Chi Minh City Viet Nam Faculty of Computer Science University of Information Technology Ho Chi Minh City Viet Nam Vietnam National University Ho Chi Minh City Viet Nam

ISBN: (纸本)9789819620739

The rise of large-scale machine learning models, such as GPT, LLaMa, and DALL-E, has revolutionized the development of AI systems but poses challenges for real-world deployment, particularly in edge computing environments with limited resources. This paper presents a comprehensive benchmark for simulating edge computing with multi-modal AI models, focusing on optimizing these complex architectures for the Artificial Intelligence of Things (AIoT). We address key challenges such as model size reduction, computational resource constraints, and federated learning environments. Specifically, we propose methods including model pruning, quantization, and reinforcement learning-based optimization for adaptive offloading to enhance performance while maintaining accuracy. By leveraging techniques such as Vision Transformer pruning and quantization, we demonstrate how to scale down large multimodal networks for efficient deployment on edge devices. Our experiments show significant improvements in computational efficiency and reduced training times, making these models more feasible for real-world AIoT applications. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Multi Meta Information Fusion Graph Neural Networks for Session-based Recommendation

Journal of Network Intelligence

引用

Journal of Network Intelligence 2025年第1期10卷 366-382页

作者： Wen, Yan Sun, Hui-Zheng Liu, Liang Zhou, Ya-Kun Bian, Wei Yan, Ming-Hai College of Computer Science and Engineering Shandong University of Science and Technology Qingdao266590 China Shandong Port Group Co. Ltd Qingdao266000 China Geography and Environment Management Faculty of Environment Universoty of Waterloo WaterlooN2L3G1 Canada

Session-based recommendation aims to predict the anonymous user’s next click action based on his/her latest click sequence. Most state-of-the-art approaches use graph neural networks to model sessions as graphs to capture dynamic transitions between items within a session. Inspired by recent progress on hypergraph-based neural networks, we think it is a good candidate to model the commonly related items within a session, and it can provide a sound complement to the normal graph models. In addition, cross session information may also be helpful. But the excessive noise introduced by other sessions is a big challenge and is still not be well resolved by existing works. To this end, we propose a new approach, called Multi Meta Information Fusion Graph Neural Networks (MM-GNN) to infer user preferences for the current session in a more comprehensive way for the anonymous *** fuse information from normal graph and hypergraph to fully exploit their capabilities of capturing sequential behavior and group intention within a session. In order to better use cross session information, we propose a globallevel subsequent item injection module, which injects information of the most possible subsequent item of the last item in the current session in the global scope. Besides, to learn richer information on the hypergraph structure, we model the whole session as a hyperedge to complement sliding windows-based hyperedges when creating the hypergraph. We have evaluated the method on several benchmark datasets and the results show that our method outperforms state-of-the-art methods. © 2025, Taiwan Ubiquitous Information CO LTD. All rights reserved.

关键词： Graph neural networks

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：