检索结果-内蒙古大学图书馆

Limits of Depth: Over-Smoothing and Over-Squashing in GNNs

Big Data Mining and Analytics 2024年第1期7卷 205-216页

作者： Aafaq Mohi ud din Shaima Qureshi Department of Computer Science and Engineering National Institute of Technology SrinagarSrinagar 190006India

Graph Neural Networks(GNNs)have become a widely used tool for learning and analyzing data on graph structures,largely due to their ability to preserve graph structure and properties via graph representation ***,the effect of depth on the performance of GNNs,particularly isotropic and anisotropic models,remains an active area of *** study presents a comprehensive exploration of the impact of depth on GNNs,with a focus on the phenomena of over-smoothing and the bottleneck effect in deep graph neural *** research investigates the tradeoff between depth and performance,revealing that increasing depth can lead to over-smoothing and a decrease in performance due to the bottleneck *** also examine the impact of node degrees on classification accuracy,finding that nodes with low degrees can pose challenges for accurate *** experiments use several benchmark datasets and a range of evaluation metrics to compare isotropic and anisotropic GNNs of varying depths,also explore the scalability of these *** findings provide valuable insights into the design of deep GNNs and offer potential avenues for future research to improve their performance.

关键词： Graph Neural Networks(GNNs) learning on graphs over-smoothing over-squashing isotropic-GNNs anisotropic-GNNs

来源：评论

学校读者我要写书评

暂无评论

Cryptography with optimal deep learning-based authentication scheme for preserving anonymity in telecare medical information system

引用

Multimedia Tools and Applications 2025年第10期84卷 8311-8330页

作者： Sheik, Syed Amma Durai, Saleem School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu India

The Telecare Medicine Information System (TMIS) revolutionizes healthcare delivery by integrating medical equipment and sensors, facilitating proactive and cost-effective services. Accessible online, TMIS empowers patients and practitioners to manage medical data efficiently, ensuring timely care provision and streamlined record maintenance. Recognizing security challenges inherent in this interconnected healthcare landscape, researchers have devised a two-factor authentication solution, increasingly leveraging password-based authentication via smart cards. This article presents the development of a tailored remote authentication system, the Deep Learning-Based Online Threat Detection with Key Agreement (DLOTDKA-MAP), designed specifically for TMIS. Comprising two critical phases, the DLOTDKA-MAP framework employs an Arithmetic Optimization Algorithm (AOA) and Deep Belief Network (DBN) model in real-time online threat detection, ensuring swift identification and mitigation of potential security threats. The subsequent phase employs Elliptic Curve Cryptography (ECC) with Schnorr's signature to establish secure data transmission among collaborating entities, preemptively addressing security breaches and ensuring mutual authentication. A comprehensive experimental study validates the presented DLOTDKA-MAP technique, showcasing its superiority over existing approaches and underscoring its role in advancing TMIS security infrastructure. Achieving remarkable performance values, includes an accuracy, precision, recall, and F1 score of 98.57%, this research significantly contributes to safeguarding the confidentiality and integrity of medical data within TMIS, particularly in a federated cloud environment. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Vision-Text Bidirectional Collaborative Image Captioning Algorithm

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer science 2025年第2期52卷 515-523页

作者： Li, Mei-Qi Zhou, Zi-Wei School of Computer Science and Software Engineering University of Science and Technology LiaoNing Anshan114051 China

Image captioning is an interdisciplinary research hotspot at the intersection of computer vision and natural language processing, representing a multimodal task that integrates core technologies from both fields. This task requires the use of computer vision techniques to analyze and extract key visual features from images, followed by the application of natural language processing techniques to generate descriptive text that is syntactically and semantically aligned with human cognition. This process poses a significant challenge for computers. Existing models mostly ignore the relative positional information of visual objects and struggle to efficiently capture the complex relationships between visual and textual data. To address these challenges, we propose a vision-to-text bidirectional collaborative image captioning method. This approach extracts both visual features and positional information of objects, allowing the model to better understand the spatial relationships between objects. The CEW word embedding approach encodes textual information more profoundly, enhancing semantic expression and contextual understanding. In the decoding phase, a bidirectional cross-attention mechanism strengthens the interaction between vision and text, leading to improved accuracy in image understanding. The model is trained and tested on the MSCOCO 2014 dataset and compared with several popular models. Experimental results demonstrate that the proposed method achieves significant improvements on the CIDEr and BLEU-1 evaluation metrics with an increase of 1.5 and 1.1, respectively. In addition, we conduct ablation experiments, quantitative analysis, and qualitative analysis to comprehensively validate the effectiveness and stability of the proposed algorithm. © (2025), (International Association of Engineers). All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Blockchain enabled MediVault for healthcare system

引用

Multimedia Tools and Applications 2025年第15期84卷 14805-14825页

作者： Chaurasia, Brijesh Kumar Department of Computer Science and Engineering Pranveer Singh Institute of Technology Kanpur India

The management of healthcare data has significantly benefited from the use of cloud-assisted MediVault for healthcare systems, which can offer patients efficient and convenient digital storage services for storing their medical records. Nevertheless, there are security risks associated with the current digital healthcare data, as malicious parties may work with cloud storage service providers to alter patient records or to directly disclose health record content to other adversaries for monetary advantage. In this paper, a blockchain-enabled MediVault for healthcare systems is proposed not only to provide safe storage of healthcare data in digital form but also secure access for authenticated entities such as patients, doctors, and pharmacists. In this MediVault, we introduced NFT generation and storage over the cloud using Interplanetary File System (IPFS) and FireBase as per user adaptability, Ehtereum Blockchain for immutability, and encryption and decryption using asymmetric keys for confidentiality. The empirical results and the performance evaluation demonstrate that the proposed MediVault is secure, simple, and efficient with a limited computation overhead. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

An improved soft voting-based machine learning technique to detect breast cancer utilizing effective feature selection and SMOTE-ENN class balancing

引用

Discover Artificial Intelligence 2025年第1期5卷 1-19页

作者： Chhillar, Indu Singh, Ajmer Computer Science & Engineering Deenbandhu Chhotu Ram University of Science and Technology Haryana Murthal India

Breast cancer is the primary cause of death among women globally, and it is becoming more prevalent. Early detection and precise diagnosis of breast cancer can reduce the disease’s mortality rate. Recent advances in machine learning have benefited in this regard. However, if the dataset contains duplicate or irrelevant features, machine learning-based algorithms are unable to give the intended results. To address this issue, a series of effective strategies such as the Robust Scaler is used for data scaling, Synthetic Minority Over-sampling Technique-Edited Nearest Neighbor (SMOTE-ENN) is utilized for class balancing, and Boruta and Coefficient-Based Feature Selection (CBFS) methods are employed for feature selection. For more accurate and reliable breast cancer classification, this study proposes a soft voting-based ensemble model that harnesses the capabilities of three diverse classifiers: Multilayer Perceptron (MLP), Support Vector Machine (SVM), and Extreme Gradient Boosting (XGBoost). To show the efficiency of the proposed ensemble model, it is compared with its base classifiers using the Wisconsin Diagnosis Breast Cancer Dataset (WDBC). The results of the experiment revealed that the soft voting classifier achieved high scores with an accuracy of 99.42%, precision of 100.0%, recall of 98.41%, F1 score of 99.20%, and AUC of 1.0 when it is trained on optimal features obtained from the CBFS method. However, with tenfold cross-validation (10-FCV), it shows a mean accuracy score of 99.34%. A comprehensive analysis of the results revealed that the suggested technique outperformed the existing state-of-the-art methods due to the efficient data preprocessing, feature selection, and ensemble methods. © The Author(s) 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Security experimental framework of trajectory planning for autonomous vehicles

引用

International Journal of Intelligent Networks 2024年第1期5卷 315-324页

作者： Al-sheyab, Sujoud Al-shara, Zakarea Al-khaleel, Osama Department of Computer Engineering Jordan University of Science and Technology Irbid Jordan Department of Software Engineering Jordan University of Science and Technology Irbid Jordan

In the contemporary landscape, autonomous vehicles (AVs) have emerged as a prominent technological advancement globally. Despite their widespread adoption, significant hurdles remain, with security standing out as a critical concern. The potential for attacks within AV networks, exemplified by the Trajectory Privacy Attack on Autonomous Driving (T-PAAD), underscores the urgency for robust security measures. Unfortunately, existing simulations for preemptively assessing the T-PAAD attack's impact are scarce. This paper introduces the Security Experimental Framework for Autonomous Vehicles (SEFAV), designed to address this gap by providing a versatile platform for simulating security scenarios in AV environments. SEFAV is cross-platform and compatible with different operating systems such as Windows and Linux, enhancing accessibility for researchers and practitioners. Our primary focus lies in showcasing the T-PAAD attack within our framework, highlighting its efficacy in evaluating and fortifying AV security. © 2024 The Authors

关键词： Vehicle routing

来源：评论

学校读者我要写书评

暂无评论

Comprehensive overview of Alzheimer's disease utilizing Machine Learning approaches

引用

Multimedia Tools and Applications 2024年第37期83卷 85277-85329页

作者： Kumar, Rahul Azad, Chandrashekhar Department of Computer Science and Engineering National Institute of Technology Jamshedpur India

Alzheimer's disease is a common and complex brain disorder that primarily affects the elderly. Because it is progressing and has few effective therapies, it requires a thorough understanding of the condition;our study offers a comprehensive analysis of AD with a dual approach that combines both bibliometric and experimental analyses. The bibliometric analysis applies statistical and mathematical techniques to figure out the states of AD research, including publishing trends, prestigious journals, and collaborative networks. Concurrently, the experimental examination explores current advancements, focusing on Machine Learning, Deep Learning, and Metaheuristic approaches, tackling complex issues resulting from varied datasets. The experimental work is fascinating because it uses twenty classifiers and two datasets, initially without feature selection and then with seven feature selection techniques. This thorough investigation focuses on developments in disease processes, therapeutic approaches, and diagnostic tool development. This research offers a multidimensional overview of Alzheimer's disease by combining bibliometric and experimental methods, addressing problems and highlighting the shortcomings of earlier studies. By helping academics, policymakers, and healthcare professionals navigate the complexities of AD, this novel methodology advances a more thorough understanding of the Alzheimer's disease domain. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Speech processing

来源：评论

学校读者我要写书评

暂无评论

Enhancing Cyber-Physical Systems Security: A Review of Deep Learning and Blockchain Integration 5

Enhancing Cyber-Physical Systems Security: A Review of Deep ...

引用

5th International Conference on Image Processing and Capsule Networks, ICIPCN 2024

作者： Selvi, K. Dilip, Golda SRM Institute of Science and Technology Faculty of Engineering and Technology Department of Computer Science and Engineering Vadapalani Campus Chennai India

ISBN: (纸本)9798350367171

Cyber-Physical Systems (CPS) combine physical and computational elements to produce intelligent systems communicating with their surroundings. By integrating digital and physical processes, CPS provides increased functionality in various industries, including industry, transportation, and healthcare. However, there are security, data integrity, and privacy issues brought on by the extensive integration of CPS across several domains. Therefore, addressing these issues is significant for an effective and reliable CPS model. This study presents a comprehensive review exploring the synergistic relationship between two cutting-edge technologies, Deep Learning (DL) and Blockchain, deployed to resolve these issues in CPS. This study explores the efficiency of leveraging DL and blockchain to enhance the reliability and effectiveness of the CPS models. Also, this study examines the challenges and limitations faced by those DL and blockchain approaches during their implementation across different CPS domains. This comprehensive review provides promising directions for future research in this dynamic and interdisciplinary field for mitigating the challenges in CPS models. It also aids researchers, practitioners, and policymakers by providing a deeper understanding of the possible effects, difficulties, and opportunities related to utilizing DL and Blockchain technologies to improve the security and functionality of CPS. © 2024 IEEE.

关键词： Blockchain technologies Cyber-Physical Systems Deep Learning Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Ancient Character Recognition: A Comprehensive Review

引用

IEEE Access 2025年 13卷 88847-88857页

作者： Krithiga, R. Varsini, S.R. Joshua, R. Gabriel Om Kumar, C.U. Vellore Institute of Technology School of Computer Science and Engineering Chennai600127 India

Deep learning-based character recognition of Tamil inscriptions plays a significant role in preserving the ancient Tamil language. The complexity of the task lies in the precise classification of the age-old Tamil letters (Vattezhuthu) into modern-day Tamil letter structures. Various methodologies and pre-processing techniques have been used for denoising the ancient Tamil manuscript to retrieve the Tamil text. Researchers have used various synthesized and scanned images of stone wall inscriptions, palm leaves manuscripts, and offline handwritten characters for their analysis. Over the years, Ancient Tamil scripts have deteriorated with time due to various natural calamities. Strong denoising and feature extraction methods are required to separate the letters accurately to tackle this issue. Techniques such as CNN(OCR), ResNet, SVM, KNN, HorVer method, etc., are utilized to digitize Tamil characters. This technique has successfully converted handwritten characters into digitalized text for multiple languages, including Tamil, Arabic, English, Latin, Chinese, German, etc. Different models have been evaluated based on their segmentation and recognition rates, accuracy, detection rate, precision, and confusion matrix. This paper will concentrate on Ancient Tamil character segmentation and recognition models. Besides, we will give an overview of the different models and datasets available. Lastly, we summarise the key challenges and the future scope related to the topic. © 2013 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

ECG Signal Classification of Cardiovascular Disorder using CWT and DCNN

引用

Journal of Biomedical Physics and engineering 2025年第1期15卷 77-92页

作者： Rahman, Tawfikur Ahommed, Rasel Deb, Nibedita Das, Utpal Kanti Moniruzzaman, Md. Bhuiyan, Md. Alamgir Sultana, Farzana Kausar, Md. Kamruzzaman Department of Electrical and Electronic Engineering Faculty of Engineering International University of Business Agriculture and Technology Uttara Dhaka 1230 Bangladesh Department of Agriculture International University of Business Agriculture and Technology Uttara Dhaka 1230 Bangladesh Department of Computer Science and Engineering Faculty of Engineering International University of Business Agriculture and Technology Uttara Dhaka 1230 Bangladesh

Background: Cardiovascular Diseases (CVD) requires precise and efficient diagnostic tools. The manual analysis of Electrocardiograms (ECGs) is labor-intensive, necessitating the development of automated methods to enhance diagnostic accuracy and efficiency. Objective: This research aimed to develop an automated ECG classification using Continuous Wavelet Transform (CWT) and Deep Convolutional Neural Network (DCNN), and transform 1D ECG signals into 2D spectrograms using CWT and train a DCNN to accurately detect abnormalities associated with CVD. The DCNN is trained on datasets from PhysioNet and the MIT-BIH arrhythmia dataset. The integrated CWT and DCNN enable simultaneous classification of multiple ECG abnormalities along-side normal signals. Material and Methods: This analytical observational research employed CWT to generate spectrograms from 1D ECG signals, as input to a DCNN trained on di-verse datasets. The model is evaluated using performance metrics, such as precision, specificity, recall, overall accuracy, and F1-score. Results: The proposed algorithm demonstrates remarkable performance metrics with a precision of 100% for normal signals, an average specificity of 100%, an average recall of 97.65%, an average overall accuracy of 98.67%, and an average F1-score of 98.81%. This model achieves an approximate average overall accuracy of 98.67%, highlighting its effectiveness in detecting ***: The integration of CWT and DCNN in ECG classification improves accuracy and classification capabilities, addressing the challenges with manual analy-sis. This algorithm can reduce misdiagnoses in primary care and enhance efficiency in larger medical institutions. By contributing to automated diagnostic tools for cardiovascular disorders, it can significantly improve healthcare practices in the field of CVD detection. © Journal of Biomedical Physics and engineering.

关键词： Wavelet transforms

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：