检索结果-内蒙古大学图书馆

Attack Detection and Optimal Deployment for Underwater Constrained Wireless Sensor Networks via Hybrid Trust Evidence

引用

IEEE Transactions on Network Science and Engineering 2025年第3期12卷 1791-1803页

作者： Jiang, Bin Zhou, Ronghao Luo, Fei Cui, Xuerong Wang, Huihui Helen Song, Houbing Herbert College of Oceanography and Space Informatics Qingdao266580 China Great Bay University School of Computing and Information Technology Dongguan523000 China Northeastern University Computing Programs ArlingtonVA22209 United States University of Maryland Baltimore County Department of Information Systems BaltimoreMD21250 United States

Underwater wireless sensor networks have been widely used in the acquisition and processing of oceanic information. The marine environment is complex and changeable, and the existence of obstacles is the main manifestation of the complex underwater environment, which affect the communication between underwater nodes. In addition, wireless sensor networks with obstacles are often more vulnerable to various attacks, making it more fragile. In order to address the aforementioned issues, we firstly propose a underwater wireless sensor deployment strategy with obstacle avoidance as the target (GEHO). After that, we use Tabtransformer algorithm to build trust model and detect attacks according to trust data set, which can enhance the robustness of the entire wireless sensor network. In the final stage, we collect the patterns of malicious attacks on nodes according to the detection results, which is convenient for us to make timely responses and reduce the losses of underwater wireless sensor networks due to malicious attacks. The simulation results show that the trust model can effectively detect malicious nodes and attack types in the network, and has higher detection accuracy than the existing trust model. © 2013 IEEE.

关键词： Hybrid sensors

来源：评论

学校读者我要写书评

暂无评论

Decentralized Federated Learning in Metacomputing Based on Directed Acyclic Graph With Optimized Tip Selector

引用

IEEE Internet of Things Journal 2025年第10期12卷 13723-13733页

作者： Jiang, Bin Zhao, Bo Luo, Fei Wang, Huihui Helen Song, Houbing Herbert College of Oceanography and Space Informatics Qingdao266580 China Great Bay University School of Computing and Information Technology Dongguan523000 China Computing Programs Northeastern University Arlington ArlingtonVA22209 United States University of Maryland at Baltimore County Department of Information Systems BaltimoreMD21250 United States

Metacomputing optimizes distributed computing resources to enhance federated learning (FL) systems by enabling efficient resource allocation, improved scheduling, and greater scalability, thereby addressing challenges in large-scale and dynamic environments. This article proposes an innovative framework integrating directed acyclic graph (DAG) technology with FL within a metacomputing environment. The key contributions include a three-layer decentralized FL model integrating DAG and metacomputing to enhance resilience and scalability, two advanced tip selection models LazyEval tip selector and precision tip selector to optimize node selection and improve data flow, and a benchmark improvement protocol (BIP) for efficient node publishing and role adaptation. The BIP ensures that only high-performing models are published by comparing new models against established benchmarks, which enhances node collaboration and optimizes resource allocation. LazyEval Tip Selector minimizes redundant computations by leveraging a global cache and employing a lazy evaluation strategy, thereby improving computational efficiency. On the other hand, Precision Tip Selector uses a precise scoring mechanism to ensure accurate tip selection, thereby enhancing the robustness and reliability of the entire system. Collectively, these innovations enhance model training efficiency, support real-time updates, and improve the scalability of FL systems, making them well-suited for managing complex, dynamic environments. © 2014 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Heart Sound Classification Using Weka for Machine Learning

Heart Sound Classification Using Weka for Machine Learning

引用

2025 IEEE SoutheastCon, SoutheastCon 2025

作者： Mergist, Tanner Yenumula, T. Maheswara Reddy Muhammad, Rafeeq James, Tytiana Harimi, Ali Khalil, Kasem Kumar, Ashok School of Computing and Informatics University of Louisiana at Lafayette Lafayette United States University of Mississippi MS United States

ISBN: (纸本)9798331504847

The accurate and efficient classification of heart sounds represents a crucial challenge in cardiac care, with significant implications for early diagnosis and timely intervention. This study investigates the application of machine learning techniques, utilizing the Weka framework, to address this problem and used PhysioNet dataset, which comprises 3,240 heart sound recordings, and extracted 238 features to capture the essential spectral and temporal characteristics of heartbeats. Considering the high dimensionality of the dataset, various feature selection methods were evaluated, including information gain ranking, Principal Component Analysis (PCA), and Recursive Feature Elimination (RFE). Ultimately, the InfoGain algorithm was applied, selecting the 50 most significant features from the initial set of 238. The performance of five machine learning models - Multilayer Perceptron, Random Forest, Decision Tree, k-Nearest Neighbor (k-NN), and Support Vector Machine (SVM) - on both the full and reduced feature sets, using 80-20 split and 10-fold cross-validation was evaluated. The results demonstrate that the Random Forest model achieved the highest accuracy of 92.1% on the full feature set, while the k-NN model exhibited superior computational efficiency on the reduced set, with an accuracy of 89.4% and significantly faster training times. These findings highlight the trade-offs between model complexity and efficiency, providing valuable insights for clinicians and researchers in selecting appropriate algorithms for real-world heart sound classification applications. © 2025 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Exploring Design Recommendations for Promoting Brain Health, ADRD Health Literacy, and Participation in clinical ADRD trials in Older African American/Black Adults

引用

Proceedings of the ACM on Human-Computer Interaction 2025年第2期9卷 1-26页

作者： Theisz, Alec Andrew Bosco, Cristina Torres, John Osorio Shojaei, Fereshtehossadat Lin, Jenny Cureton, Bianca Himes, Anna K. Jessup, Nenette M. Barnes, Priscilla A. Lu, Yvonne Hendrie, Hugh C. Hill, Carl V. Shih, Patrick C. Luddy School of Informatics Computing and Engineering Indiana University United States School of Nursing Indiana University United States Alzheimer’s Association United States

Alzheimer’s Disease and related dementia (ADRD) is prevalent in one in nine individuals age 65 or above, and it has a 65% higher risk of incidence for African American/Black adults. With an aging population in the United States and persisting healthcare inequities for African American/Black adults, our research aims to explore design requirements of a digital health platform for delivering culturally relevant content that informs African Americans/Black adults (45 years and older) about brain health and participation in clinical ADRD studies. We conducted seven focus groups (n = 44) to collect information on facilitators and barriers to brain health literacy and participation in clinical ADRD research, followed by seven participatory design workshops (n = 44) to collaboratively develop solutions for improving brain health literacy and participation in clinical ADRD research. Our findings provide insights into incorporating community into accessible, technological design for reducing brain health disparities for African American/Black adults. © 2025 Copyright held by the owner/author(s).

关键词： mHealth

来源：评论

学校读者我要写书评

暂无评论

Mix-YOLONet: Deep Image Dehazing for Improving Object Detection 31st

Mix-YOLONet: Deep Image Dehazing for Improving Object Detec...

引用

31st International Conference on Multimedia Modeling, MMM 2025

作者： Lim, Xin Wong, Lai-Kuan Loh, Yuen Peng Gu, Ke Lin, Weisi Faculty of Computing and Informatics Multimedia University Cyberjaya Malaysia Beijing University of Technology Beijing China Nanyang Technological University Singapore Singapore

ISBN: (纸本)9789819620609

Atmospheric haze significantly impairs the performance of computer vision tasks such as image dehazing and object detection. Existing methods often address these tasks independently, failing to provide an integrated solution that can effectively handle hazy conditions while maintaining accurate object detection. This paper presents Mix-YOLONet, a novel joint network architecture designed to tackle both image dehazing and object detection simultaneously. Mix-YOLONet leverages the powerful image restoration capabilities of U-Net-like architecture and integrates it with the detection precision of a YOLO head. Additionally, we integrated Mix Structure Blocks (MSB) to our joint network and experimented various configurations at strategic locations to enhance feature extraction and context aggregation. Through extensive experiments, we demonstrate that Mix-YOLONet achieves superior performance in both dehazing and object detection tasks under challenging visibility conditions, outperforming state-of-the-art methods on three benchmark datasets both quantitatively and qualitatively. The proposed joint network not only improves the clarity of hazy images but also ensures accurate object localization, paving the way for more robust object detection in adverse environmental conditions. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Restoration

来源：评论

学校读者我要写书评

暂无评论

Cross Feature Fusion of Fundus Image and Generated Lesion Map for Referable Diabetic Retinopathy Classification 17th

Cross Feature Fusion of Fundus Image and Generated Lesion ...

引用

17th Asian Conference on Computer Vision, ACCV 2024

作者： Mok, Dahyun Bum, Junghyun Tai, Le Duc Choo, Hyunseung Department of Electrical and Computer Engineering Sungkyunkwan University Suwon Korea Republic of College of Computing and Informatics Sungkyunkwan University Suwon Korea Republic of

ISBN: (纸本)9789819609000

Diabetic Retinopathy (DR) is a primary cause of blindness, necessitating early detection and diagnosis. This paper focuses on referable DR classification to enhance the applicability of the proposed method in clinical practice. We develop an advanced cross-learning DR classification method leveraging transfer learning and cross-attention mechanisms. The proposed method employs the Swin U-Net architecture to segment lesion maps from DR fundus images. The Swin U-Net segmentation model, enriched with DR lesion insights, is transferred to generate a lesion map. Both the fundus image and its segmented lesion map are used as complementary inputs for the classification model. A cross-attention mechanism is deployed to improve the model’s ability to capture fine-grained details from the input pairs. Our experiments, utilizing two public datasets, FGADR and EyePACS, demonstrate a superior accuracy of 94.6%, surpassing current state-of-the-art methods by 4.4%. To this end, we aim for the proposed method to be seamlessly integrated into clinical workflows, enhancing accuracy and efficiency in identifying referable DR. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

NDAS: Noise-Decomposed Abnormal Segmentation for Robust Medical Image Retrieval 19

NDAS: Noise-Decomposed Abnormal Segmentation for Robust Medi...

引用

19th International Conference on Ubiquitous Information Management and Communication, IMCOM 2025

作者： Kim, Ju-Chan Van Nguyen, Pham Le, Duc-Tai Choo, Hyunseung College of Computing and Informatics Sungkyunkwan University Suwon Korea Republic of Department of Electrical and Computer Engineering Sungkyunkwan University Suwon Korea Republic of

ISBN: (纸本)9798331507817

This paper presents NDAS (Noise-Decomposed Abnormal Segmentation), an innovative framework for robust medical image retrieval and segmentation. By explicitly decomposing noise and abnormal features, NDAS enhances retrieval accuracy and segmentation precision. Experimental results on the BraTS 2019 dataset validate NDAS’s superiority over CBMIR and SBMIR methods, achieving the highest Top-5 accuracy and Dice coefficient. This demonstrates its effectiveness in handling noise, isolating pathological regions, and retrieving diagnostically relevant medical images. NDAS offers a significant advancement in medical imaging analysis, emphasizing its potential for clinical applications requiring precision and reliability. © 2025 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

ERBM: A Machine Learning-Driven Rule-Based Model for Intrusion Detection in IoT Environments

引用

Computers, Materials and Continua 2025年第3期83.0卷 5155-5179页

作者： Mehmmod, Arshad Batool, Komal Sajid, Ahthsham Alam, Muhammad Mansoor Khan, Inam Ullah Department of Information Security and Data Science Riphah Institute of Systems Engineering Riphah International University Islamabad 46000 Pakistan Faculty of Computing Riphah International University Islamabad 46000 Pakistan Faculty of Computing and Informatics Multimedia University Cyberjaya 63100 Malaysia

Traditional rule-based Intrusion Detection Systems (IDS) are commonly employed owing to their simple design and ability to detect known threats. Nevertheless, as dynamic network traffic and a new degree of threats exist in IoT environments, these systems do not perform well and have elevated false positive rates—consequently decreasing detection accuracy. In this study, we try to overcome these restrictions by employing fuzzy logic and machine learning to develop an Enhanced Rule-Based Model (ERBM) to classify the packets better and identify intrusions. The ERBM developed for this approach improves data preprocessing and feature selections by utilizing fuzzy logic, where three membership functions are created to classify all the network traffic features as low, medium, or high to remain situationally aware of the environment. Such fuzzy logic sets produce adaptive detection rules by reducing data uncertainty. Also, for further classification, machine learning classifiers such as Decision Tree (DT), Random Forest (RF), and Neural Networks (NN) learn complex ways of attacks and make the detection process more precise. A thorough performance evaluation using different metrics, including accuracy, precision, recall, F1 Score, detection rate, and false-positive rate, verifies the supremacy of ERBM over classical IDS. Under extensive experiments, the ERBM enables a remarkable detection rate of 99% with considerably fewer false positives than the conventional models. Integrating the ability for uncertain reasoning with fuzzy logic and an adaptable component via machine learning solutions, the ERBM system provides a unique, scalable, data-driven approach to IoT intrusion detection. This research presents a major enhancement initiative in the context of rule-based IDS, introducing improvements in accuracy to evolving IoT threats. Copyright © 2025 The Authors.

关键词： fuzzy prediction intrusions IoT Rule based

来源：评论

学校读者我要写书评

暂无评论

Usability, Efficacy, and Acceptability of the U.S. Cyber Trust Mark 25

Usability, Efficacy, and Acceptability of the U.S. Cyber Tru...

引用

Proceedings of the 2025 CHI Conference on Human Factors in computing Systems

作者： Peter Caven Ambarish Gurjar Zitao Zhang Xinyao Ma LJean Camp School of Informatics Computing and Engineering Indiana Unviersity Bloomington Indiana USA School of Informatics Computing and Engineering Bloomington Indiana USA School of Informatics Computing and Engineering Indiana University Bloomington Bloomington Indiana USA School of Informatics Computing and Engineering Indiana University Bloomington Indiana USA School of Informatics Computing and Engineering Indiana University Bloomington Indiana USA

来源：评论

学校读者我要写书评

暂无评论

A Review of Human Vulnerabilities in Cyber Security: Challenges and Solutions for Microfinance Institutions

引用

Journal of Information Security 2025年第1期16卷 114-130页

作者： Evaline Waweru Simon Maina Karume Alex Kibet Department of Computing and Informatics The Cooperative University Nairobi Kenya Department of Computer Science and Information Technology Kabarak University Nakuru Kenya Department of Computing and Informatics Laikipia University Laikipia Kenya

This review examines human vulnerabilities in cybersecurity within Microfinance Institutions, analyzing their impact on organizational resilience. Focusing on social engineering, inadequate security training, and weak internal protocols, the study identifies key vulnerabilities exacerbating cyber threats to MFIs. A literature review using databases like IEEE Xplore and Google Scholar focused on studies from 2019 to 2023 addressing human factors in cybersecurity specific to MFIs. Analysis of 57 studies reveals that phishing and insider threats are predominant, with a 20% annual increase in phishing attempts. Employee susceptibility to these attacks is heightened by insufficient training, with entry-level employees showing the highest vulnerability rates. Further, only 35% of MFIs offer regular cybersecurity training, significantly impacting incident reduction. This paper recommends enhanced training frequency, robust internal controls, and a cybersecurity-aware culture to mitigate human-induced cyber risks in MFIs.

关键词： Human Vulnerabilities Cybersecurity Microfinance Institutions Cyber Threats Cybersecurity Awareness Risk Mitigation

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：