检索结果-内蒙古大学图书馆

37th Annual Conference on Learning Theory, COLT 2024

作者： Chase, Zachary Chornomaz, Bogdan Hanneke, Steve Moran, Shay Yehudayoff, Amir Department of Mathematics Technion Israel Department of Computer Science Purdue University United States Departments of Mathematics Computer Science and Data and Decision Sciences Technion Google Research Israel Department of Computer Science Copenhagen University Denmark

This work studies embedding of arbitrary VC classes in well-behaved VC classes, focusing particularly on extremal classes. Our main result expresses an impossibility: such embeddings necessarily require a significant increase in dimension. In particular, we prove that for every d there is a class with VC dimension d that cannot be embedded in any extremal class of VC dimension smaller than exponential in d. In addition to its independent interest, this result has an important implication in learning theory, as it reveals a fundamental limitation of one of the most extensively studied approaches to tackling the long-standing sample compression conjecture (Warmuth, 2003). Concretely, the approach proposed by Floyd and Warmuth (1995) entails embedding any given VC class into an extremal class of a comparable dimension, and then applying an optimal sample compression scheme for extremal classes. However, our results imply that this strategy would in some cases result in a sample compression scheme at least exponentially larger than what is predicted by the sample compression conjecture. The above implications follow from a general result we prove: any extremal class with VC dimension d has dual VC dimension at most 2d + 1. This bound is exponentially smaller than the classical bound 2d+1-1 of Assouad (1983), which applies to general concept classes (and is known to be unimprovable for some classes). We in fact prove a stronger result, establishing that 2d + 1 upper bounds the dual Radon number of extremal classes. This theorem represents an abstraction of the classical Radon theorem for convex sets, extending its applicability to a wider combinatorial framework, without relying on the specifics of Euclidean convexity. The proof utilizes the topological method and is primarily based on variants of the Topological Radon Theorem (Bajmóczy and Bárány, 1979). © 2024 Z. Chase, B. Chornomaz, S. Hanneke, S. Moran & A. Yehudayoff.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

TezNet: An Efficient Convolutional Neural Network for Optical Coherence Tomography Classification 6

TezNet: An Efficient Convolutional Neural Network for Optica...

引用

6th International Conference on Robotics and Automation in Industry, ICRAI 2024

作者： Qaiser, Muhid Abbas, Muhammad Sohail Muhammad, Asif Haider, Khadija Khan, Haroon National University of Computer and Emerging Sciences Department of Artificial Intelligence and Data Science Islamabad Pakistan National University of Computer and Emerging Sciences Department of Software Engineering Islamabad Pakistan

ISBN: (纸本)9798350355703

Retinal diseases such as Choroidal Neovascularization (CNV), Drusen, and Diabetic Macular Edema (DME) can severely impair vision and are challenging to reverse if detected late. Optical Coherence Tomography (OCT) serves as a non-invasive imaging modality to diagnose these conditions through cross-sectional retinal images. Current advancements in retinal disease detection predominantly focus on fine-tuning larger models to achieve high accuracy, often at the expense of substantial training time and data requirements. We introduce an innovative Convolutional Neural Network (CNN) named TezNet that is deeper and wider than existing custom CNNs for the dataset used in this research yet maintains a lightweight architecture with only 3.6 million parameters. This high efficiency is accomplished by leveraging depthwise and spatial separable convolutional techniques without employing preprocessing techniques or noise reduction filters. The data augmentation techniques generate diverse image qualities, ensuring robust predictions across various scenarios. By training exclusively on a single dataset, our model achieves rapid training times and optimal resource utilization, minimizing the risk of overfitting. This blend of advanced parameter optimization, minimal preprocessing, and strategic data augmentation underscores the potential of our CNN model for swift, precise, and resource-efficient retinal disease detection. TezNet model achieves a remarkable 96% accuracy, competing closely with state-of-the-art networks like ResNet50 (over 23M parameters), InceptionV3 (over 25M parameters), and ResNeXt (89M parameters). © 2024 IEEE.

关键词： Optical coherence tomography

来源：评论

学校读者我要写书评

暂无评论

List Sample Compression and Uniform Convergence 37

List Sample Compression and Uniform Convergence

引用

37th Annual Conference on Learning Theory, COLT 2024

作者： Hanneke, Steve Moran, Shay Waknine, Tom Department of Computer Science Purdue University United States Departments of Mathematics Computer Science and Data and Decision Sciences Technion Google Research Israel Department of Mathematics Technion Israel

List learning is a variant of supervised classification where the learner outputs multiple plausible labels for each instance rather than just one. We investigate classical principles related to generalization within the context of list learning. Our primary goal is to determine whether classical principles in the PAC setting retain their applicability in the domain of list PAC learning. We focus on uniform convergence (which is the basis of Empirical Risk Minimization) and on sample compression (which is a powerful manifestation of Occam's Razor). In classical PAC learning, both uniform convergence and sample compression satisfy a form of 'completeness': whenever a class is learnable, it can also be learned by a learning rule that adheres to these principles. We ask whether the same completeness holds true in the list learning setting. We show that uniform convergence remains equivalent to learnability in the list PAC learning setting. In contrast, our findings reveal surprising results regarding sample compression: we prove that when the label space is Y = {0, 1, 2}, then there are 2-list-learnable classes that cannot be compressed. This refutes the list version of the sample compression conjecture by Littlestone and Warmuth (1986). We prove an even stronger impossibility result, showing that there are 2-list-learnable classes that cannot be compressed even when the reconstructed function can work with lists of arbitrarily large size. We prove a similar result for (1-list) PAC learnable classes when the label space is unbounded. This generalizes a recent result by Pabbaraju (2023). In our impossibility results on sample compression, we employ direct-sum arguments which might be of independent interest. In fact, these arguments raise natural open questions that we leave for future research. Our findings regarding uniform convergence rely on a coding theoretic perspective. © 2024 S. Hanneke, S. Moran & T. Waknine.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based ECG Classification for Arterial Fibrillation Detection

引用

computers, Materials & Continua 2024年第6期79卷 4805-4824页

作者： Muhammad Sohail Irshad Tehreem Masood Arfan Jaffar Muhammad Rashid Sheeraz Akram Abeer Aljohani Faculty of Computer Science&Information Technology The Superior UniversityLahore54000Pakistan Intelligent Data Visual Computing Research(IDVCR) Lahore54000Pakistan Department of Computer Science National University of TechnologyIslamabad45000Pakistan Information Systems Department College of Computer and Information SciencesImam Mohammad Ibn Saud Islamic University(IMSIU)Riyadh11432Saudi Arabia Department of Computer Science Applied CollegeTaibah UniversityMedina42353Saudi Arabia

The application of deep learning techniques in the medical field,specifically for Atrial Fibrillation(AFib)detection through Electrocardiogram(ECG)signals,has witnessed significant *** and timely diagnosis increases the patient’s chances of ***,issues like overfitting and inconsistent accuracy across datasets remain *** a quest to address these challenges,a study presents two prominent deep learning architectures,ResNet-50 and DenseNet-121,to evaluate their effectiveness in AFib *** aim was to create a robust detection mechanism that consistently performs *** such as loss,accuracy,precision,sensitivity,and Area Under the Curve(AUC)were utilized for *** findings revealed that ResNet-50 surpassed DenseNet-121 in all evaluated *** demonstrated lower loss rate 0.0315 and 0.0305 superior accuracy of 98.77%and 98.88%,precision of 98.78%and 98.89%and sensitivity of 98.76%and 98.86%for training and validation,hinting at its advanced capability for AFib *** insights offer a substantial contribution to the existing literature on deep learning applications for AFib detection from ECG *** comparative performance data assists future researchers in selecting suitable deep-learning architectures for AFib ***,the outcomes of this study are anticipated to stimulate the development of more advanced and efficient ECG-based AFib detection methodologies,for more accurate and early detection of AFib,thereby fostering improved patient care and outcomes.

关键词： Convolution neural network atrial fibrillation area under curve ECG false positive rate deep learning classification

来源：评论

学校读者我要写书评

暂无评论

Open problem: Direct Sums in Learning Theory 37

Open problem: Direct Sums in Learning Theory

引用

37th Annual Conference on Learning Theory, COLT 2024

来源：评论

学校读者我要写书评

暂无评论

Community Clustering on Fraud Transactions Applied the Louvain-Coloring Algorithm

引用

International Journal of Electronics and Telecommunications 2023年第3期69卷 593-598页

作者： Mardiansyah, Heru Suwilo, Saib Nababan, Erna Budiarti Efendi, Syahril Department Computer Science Faculty of Computer Science and Information Technology Universitas Sumatera Utara Medan Indonesia Department Mathematics Faculty of Mathematics and Natural Sciences Universitas Sumatera Utara Medan Indonesia Department Data Science and Artificial Intelligence Faculty of Computer Science and Information Technology Universitas Sumatera Utara Medan Indonesia

The contribution main from this research is modularity and better processing time in detecting community by using K-1 coloring. Testing performed on transaction datasets remittance on P2P platforms where the Louvain Coloring algorithm is better in comparison to Louvain Algorithm data used is data transfer transactions made by customers on the P2P Online platform. The data is the User data that has information transfer transactions, Card data that has information card, IP data that has IP information, and Device data that has information device. Every user owns unique 128-bit identification, and other nodes representing card, device, and IP are assigned a random UUID. The Device node has the guide, and device properties. IP nodes only have property guide and node User has property fraud Money Transfer, guide, money Transfer Error Cancel Amount, first Charge back Date. Each node has a unique 128-bit guide, with the amount whole of as many as 789,856 nodes. Application technique K-1 staining on Louvain algorithm shows enhancement value modularity and better processing time for detecting community on the network large scale. Through a series of exercises and tests carried out in various scenarios, it shows that the experiments carried out in this paper, namely the Louvain Coloring algorithm, are more effective and efficient than the Louvain algorithm in scenario 1,3, and 5 meanwhile For Scenarios 2 and 4 Louvain Algorithm is better. © 2023 Polish Academy of sciences. All rights reserved.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

MatrikalinDiabetes: User-Centered Design of a mHealth App for Gestational Diabetes Mellitus Management and Education Among Bangladeshi Women 26th

MatrikalinDiabetes: User-Centered Design of a mHealth App ...

引用

26th International Conference on Human-computer Interaction, HCII 2024

作者： Ratul, Mohammad Arshad Hossain Yanoor Bristy, Tunisha Sayeed, Noorjahan Islam, Ashraful Chaudhry, Beenish Moalla Center for Computational and Data Sciences Independent University Bangladesh Dhaka Bangladesh Department of Computer Science and Engineering Independent University Bangladesh Dhaka Bangladesh School of Computing and Informatics University of Louisiana at Lafayette Louisiana United States

ISBN: (纸本)9783031768088

This study employs the User-Centered Design (UCD) methodology to develop a mobile health (mHealth) application (app) specifically tailored for Bangladeshi women with Gestational Diabetes Mellitus (GDM). GDM affects approximately 10% of pregnant women globally and around 35% within Bangladesh, as reported by the World Health Organization (WHO). Despite its high prevalence, there is a significant lack of awareness and education about GDM in Bangladesh, compounded by language barriers that make existing digital solutions less accessible. The MatrikalinDiabetes mHealth app aims to overcome these barriers by providing comprehensive management and educational resources for GDM in the Bangla language, addressing both pre-pregnancy and post-pregnancy needs. To ensure the app meets the actual needs of potential users, personas were created based on a literature review, and a survey was conducted. This process informed the development of both a low-fidelity, paper-based prototype and a high-fidelity digital prototype. Key features of the MatrikalinDiabetes app include tracking of food and water intake, physical activity monitoring, reminders, GDM education, chat forums for community support, blood glucose level (BGL) monitoring, an SOS button for emergency contacts, and quizzes for user engagement. Preliminary feedback indicated that 53.8% of participants favored the integrated features and expressed willingness to use and recommend the app. The survey of the high-fidelity prototype yielded positive responses, with 57.9% of participants strongly agreeing and 42.1% agreeing that the features were beneficial. The user-friendly design of the high-fidelity prototype ensures intuitive interaction, aiding in health management, enhancing GDM understanding, and promoting a healthier lifestyle among pregnant women in Bangladesh. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Obstetrics

来源：评论

学校读者我要写书评

暂无评论

Age-of-Information-Aware Federated Learning

引用

Journal of computer science & Technology 2024年第3期39卷 637-653页

作者：徐殷肖明军吴晨吴杰周津锐孙贺 Student Member CCF 1.School of Computer Science and TechnologyUniversity of Science and Technology of ChinaHefei 230026China Suzhou Institute for Advanced Research University of Science and Technology of ChinaSuzhou 215123China School of Data Science University of Science and Technology of ChinaHefei 230026China Department of Computer and Information Sciences Temple UniversityPhiladelphiaPA 19122U.S.A. CCF IEEE

Federated learning(FL)is an emerging privacy-preserving distributed computing paradigm,enabling numerous clients to collaboratively train machine learning models without the necessity of transmitting clients’private datasets to the central *** most existing research where the local datasets of clients are assumed to be unchanged over time throughout the whole FL process,our study addresses such scenarios in this paper where clients’datasets need to be updated periodically,and the server can incentivize clients to employ as fresh as possible datasets for local model *** primary objective is to design a client selection strategy to minimize the loss of the global model for FL loss within a constrained *** this end,we introduce the concept of“Age of Information”(AoI)to quantitatively assess the freshness of local datasets and conduct a theoretical analysis of the convergence bound in our AoI-aware FL *** on the convergence bound,we further formulate our problem as a restless multi-armed bandit(RMAB)***,we relax the RMAB problem and apply the Lagrangian Dual approach to decouple it into multiple ***,we propose a Whittle’s Index Based Client Selection(WICS)algorithm to determine the set of selected *** addition,comprehensive simulations substantiate that the proposed algorithm can effectively reduce training loss and enhance the learning accuracy compared with some state-of-the-art methods.

关键词： federated learning Age of Information restless multi-armed bandit Whittle’s index

来源：评论

学校读者我要写书评

暂无评论

Forensic handwriting analysis: a hybrid classification framework for writer identification in Devanagari script

引用

Multimedia Tools and Applications 2025年 1-12页

作者： Sethi, Monika Kumar, Munish Jindal, M.K. Department of Computer Science and Application Panjab University Chandigarh India P.G. Department of Information Technology Goswami Ganesh Dutta Sanatan Dharma College Chandigarh India Department of Computational Sciences Maharaja Ranjit Singh Punjab Technical University Punjab Bathinda India Department of Computer Science and Applications Panjab University Regional Centre Muktsar India

In a period marked by swift technological progress, the task of identifying writers through handwriting holds significant importance across various domains, including forensic investigation, plagiarism detection, and historical research. The importance of this endeavor has been further magnified by the widespread influence of digitalization. This study employs a hybrid approach that integrates cutting-edge deep learning techniques, specifically Convolutional Neural Networks (CNNs), with traditional machine learning methodologies, such as Support Vector Machines (SVM) and Random Forest (RF). Deep learning techniques are particularly valuable for analyzing extensive handwriting samples because they can automatically discern complex features and patterns from large datasets. In this research, we synthesize predictions from deep learning models and employ machine learning classification for writer identification based on handwriting analysis. Central to our study is a comprehensive dataset of Devanagari characters, collected from 220 unique writers. This dataset has been thoughtfully curated to validate the methodology we have employed. Our hybrid classification approach, combining CNN with SVM and CNN with RF, achieves remarkable accuracy rates of 91.49% and 88.78%, respectively—significantly surpassing the performance of standalone SVM and RF models, which achieved accuracies of 59.52% and 59%, respectively. Through a series of comprehensive experiments, we demonstrate the enhanced effectiveness and precision of our proposed methodology in the domain of Devanagari script writer identification. The findings of this study not only underscore the potential of our methodology but also represent a substantial advancement in the fields of pattern recognition and machine learning technology. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Traffic Management in Internet of Vehicles Using Improved Ant Colony Optimization

引用

computers, Materials & Continua 2023年第6期75卷 5379-5393页

作者： Abida Sharif Imran Sharif Muhammad Asim Saleem Muhammad Attique Khan Majed Alhaisoni Marriam Nawaz Abdullah Alqahtani Ye Jin Kim Byoungchol Chang Department of Computer Science COMSATS University IslamabadPakistan Faculty of Computing Riphah International UniversityFaisalabadPakistan Department of Computer Science HITEC UniversityTaxilaPakistan Computer Sciences Department College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh11671Saudi Arabia Department of Computer Science UET TaxilaTaxilaPakistan Department of Software Engineering UET TaxilaTaxilaPakistan Software Engineering Department College of Computer Engineering and SciencesPrince Sattam bin Abdulaziz UniversityP.O.Box 151Al-Kharj11942KSA Department of Computer Science Hanyang UniversitySeoul04763Korea Center for Computational Social Science Hanyang UniversitySeoul04763Korea

The Internet of Vehicles(IoV)is a networking paradigm related to the intercommunication of vehicles using a *** a dynamic network,one of the key challenges in IoV is traffic management under increasing vehicles to avoid ***,optimal path selection to route traffic between the origin and destination is *** research proposed a realistic strategy to reduce traffic management service response time by enabling real-time content distribution in IoV systems using heterogeneous network ***,this work proposed a novel use of the Ant Colony Optimization(ACO)algorithm and formulated the path planning optimization problem as an Integer Linear Program(ILP).This integrates the future estimation metric to predict the future arrivals of the vehicles,searching the optimal *** the mobile nature of IOV,fuzzy logic is used for congestion level estimation along with the ACO to determine the optimal *** model results indicate that the suggested scheme outperforms the existing state-of-the-art methods by identifying the shortest and most cost-effective ***,this work strongly supports its use in applications having stringent Quality of Service(QoS)requirements for the vehicles.

关键词： Internet of vehicles internet of things fuzzy logic optimization path planning

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：