检索结果-内蒙古大学图书馆

27th International Conference on Pattern Recognition, ICPR 2024

作者： Gurav, Aniket Krishnan, Narayanan C. Chanda, Sukalpa Department of Computer Science and Communication Østfold University College Halden1757 Norway Department of Data Science Indian Institute of Technology Palakkad Kerala India

ISBN: (纸本)9783031784941

Generating realistic handwritten word images that closely resemble a target style remains a challenging task in document image analysis. In recent years, deep learning techniques, such as Latent Diffusion Models (LDM), have shown promise in generating styled handwritten text. However, these models face significant challenges when creating images for ‘Out of Vocabulary’ (OOV) words, impacting their overall effectiveness. In this paper, we introduce an extended diffusion-based Handwritten generation method that incorporates a novel conditioning mechanism. It is based on the Pyramidal Histogram of Shapes (PHOS) representation, which takes into account the spatial and structural characteristics of the target handwriting style. By conditioning the diffusion model on input text, PHOS vector, and writer ID, our approach enables the generation of handwritten word images. Notably, our approach outperforms the original diffusion model, which only uses text and writer ID as conditions, in generating both in-sample and out-of-sample. Furthermore, we have developed a faster inference method that significantly reduces the number of steps required for generating the output. Through qualitative and quantitative evaluations, we demonstrate the effectiveness of our proposed method. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Variable-Length Feedback Codes Over Known and Unknown Channels With Non-Vanishing Error Probabilities

引用

IEEE Transactions on Information Theory 2025年第5期71卷 3271-3286页

作者： Yavas, Recep Can Tan, Vincent Y. F. Descartes Program CNRS@CREATE 138602 Singapore National University of Singapore Department of Computer Science Queenstown 117417 Singapore National University of Singapore Department of Mathematics Department of Electrical and Computer Engineering Queenstown 119077 Singapore

We study variable-length feedback (VLF) codes with noiseless feedback for discrete memoryless channels. We present a novel non-asymptotic bound, which analyzes the average error probability and average decoding time of our modified Yamamoto-Itoh scheme. We then optimize the parameters of our code in the asymptotic regime where the average error probability ∈ remains a constant as the average decoding time N approaches infinity. Our second-order achievability bound is an improvement of Polyanskiy et al.’s (2011) achievability bound. We also develop a universal VLF code that does not rely on the knowledge of the underlying channel parameters. Our universal VLF code employs the empirical mutual information as its decoding metric and universalizes the code by Polyanskiy et al. (2011). We derive a second-order achievability bound for universal VLF codes. Our results for both VLF and universal VLF codes are extended to the additive white Gaussian noise channel with an average power constraint. The former yields an improvement over Truong and Tan’s (2017) achievability bound. The proof of our results for universal VLF codes uses a refined version of the method of types and an asymptotic expansion from the nonlinear renewal theory literature. © 1963-2012 IEEE.

关键词： White noise

来源：评论

学校读者我要写书评

暂无评论

Drift Analysis with Fitness Levels for Elitist Evolutionary Algorithms

引用

Evolutionary computation 2025年第1期33卷 1-25页

作者： He, Jun Zhou, Yuren Department of Computer Science Nottingham Trent University Nottingham NG11 8NS United Kingdom School of Data and Computer Science Sun Yatsen University Guangzhou 510006 China

The fitness level method is a popular tool for analyzing the hitting time of elitist evolutionary algorithms. Its idea is to divide the search space into multiple fitness levels and estimate lower and upper bounds on the hitting time using transition probabilities between fitness levels. However, the lower bound generated by this method is often loose. An open question regarding the fitness level method is what are the tightest lower and upper time bounds that can be constructed based on transition probabilities between fitness levels. To answer this question, we combine drift analysis with fitness levels and define the tightest bound problem as a constrained multiobjective optimization problem subject to fitness levels. The tightest metric bounds by fitness levels are constructed and proven for the first time. Then linear bounds are derived from metric bounds and a framework is established that can be used to develop different fitness level methods for different types of linear bounds. The framework is generic and promising, as it can be used to draw tight time bounds on both fitness landscapes with and without shortcuts. This is demonstrated in the example of the (1+1) EA maximizing the TwoMax1 function. © 2024 Massachusetts Institute of Technology.

关键词： algorithm analysis drift analysis Evolutionary algorithm fitness levels hitting time Markov chain.

来源：评论

学校读者我要写书评

暂无评论

A Fine-Tuned DenseNet-Based Diagnosis Approach for Multi-Class Breast Cancer Classification 2

A Fine-Tuned DenseNet-Based Diagnosis Approach for Multi-Cla...

引用

2nd International Conference on Computational Intelligence, Communication Technology and Networking, CICTN 2025

作者： Kansal, Kanika Kansal, Kajal Department of Computer Science and Engineering Data Science ABES Engineering College Uttar Pradesh Ghaziabad India School of Computer Science Engineering and Technology Bennett University Uttar Pradesh Greater Noida India

ISBN: (数字)9798331530389

ISBN: (纸本)9798331530389

Breast cancer is a prevalent tumor across women and is associated with a high mortality rate. Prompt diagnosis is one of the biggest challenges that needs to be addressed globally, as it can considerably improve survival rates. An automatic diagnosis system based on deep learning models is critical for improving detection, prediction accuracy, and survivability. This study used various DenseNet-based architectures for multi-class classification using the BUSI dataset. The experiments indicate that the fine-tuned DenseNet201 model outperforms with an accuracy of 98.28%. The results demonstrate the promising capability of the fine-tuned DenseNet201 model to have a high potential for further implementation in practice for achieving early diagnosis and highly individualized approaches for better treatment. The further development of extensive and diverse data sets will be essential for developing new diagnostic methods and improving the existing ones. © 2025 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Optimizing Coverage in Wireless Sensor Networks Using the Tumbleweed Algorithm

Journal of Network Intelligence

引用

Journal of Network Intelligence 2025年第1期10卷 250-261页

作者： Zhang, Mengfei Chu, Shu-Chuan Liu, Nengxian Huang, Kuan-Chun Pan, Jeng-Shyang College of Computer Science and Engineering Shandong University of Science and Technology Qingdao266590 China College of Computer and Data Science Fuzhou University Fuzhou350108 China Department of Industrial and Systems Engineering Chung Yuan Christian University Taoyuan320314 Taiwan School of Artificial Intelligence Nanjing University of Information Science and Technology Nanjing210044 China Department of Information Management Chaoyang University of Technology Taichung41349 Taiwan

Wireless sensor networks (WSNs) have found extensive applications across various fields, significantly enhancing the convenience in our daily lives. Hence, an in-creasing number of researchers are directing their attention toward the performance of sensor nodes, with a particular emphasis on addressing the coverage challenges in WSNs. Node coverage plays a crucial role in determining the detection performance of WSNs, making it imperative to attain maximum coverage with a given number of sensor nodes. This paper applies the Tumbleweed Algorithm (TA) to the coverage problem in WSNs and validates its effectiveness through simulation experiments. The results demonstrate its unique advantages in global search and avoiding local optima, providing a new solution for the WSN coverage problem and offering valuable references for future research and practical applications. The TA algorithm simulates the lifecycle of tumbleweed from seedling to mature plant and includes the concept of growth cycles. This paper compares the TA algorithm with PSO, GWO, DE, BOA, SCA, and AOA, setting different numbers of wireless sensor nodes and varying sensing radii for the experiments. The experimental results show that the TA algorithm significantly improves coverage rates under various configurations and consistently outperforms other commonly used algorithms. © 2025, Taiwan Ubiquitous Information CO LTD. All rights reserved.

关键词： Sensor nodes

来源：评论

学校读者我要写书评

暂无评论

Seamless High Availability in MySQL database Systems: An Advanced Implementation of ProxySQL, Orchestrator, and Keepalived

Seamless High Availability in MySQL Database Systems: An Adv...

引用

2025 International Conference on Advancement in data science, E-learning and Information System, ICADEIS 2025

作者： Loa, Jeremy Soewito, Benfano Bina Nusantara University Binus Graduate Program Computer Science Department Jakarta Indonesia

ISBN: (纸本)9798331513320

High availability (HA) in MySQL databases remains a critical challenge, particularly due to risks such as single point of failure (SPOF) and limited scalability in existing setups. Previous studies have explored various approaches to address these issues. One study implemented ProxySQL and Orchestrator for query routing and failover but relied on a single server instance, creating a SPOF that could disrupt client access during failures. Another study implemented HAProxy to balance traffic and couple database servers with specific web applications. While effective for certain use cases, this approach reduced resource efficiency and scalability, because it relies on HTTP protocol and database server are coupled to each application, making it less suitable for dynamic, shared environments requiring high flexibility. These limitations highlight the need for a more robust and scalable HA solution. This paper proposes an improved HA architecture that eliminates SPOFs and enhances scalability by combining redundant ProxySQL instances synchronized with Keepalived managed Virtual IP (VIP) and automated failover using Orchestrator. The architecture allows shared database resources across multiple applications while decoupling them from specific application servers. Test results confirm the system's ability to maintain seamless failover, consistent query routing, and uninterrupted client access through dynamic Virtual IP reassignment to backup server. By addressing the issues of previous studies, this solution provides a practical and scalable framework to achieve high availability in the MySQL cluster by combing ProxySQL, Orchestrator, and Keepalived, making it suitable for modern enterprise environments. © 2025 IEEE.

关键词： HTTP

来源：评论

学校读者我要写书评

暂无评论

data Analysis with Model Explainability for Air Quality and Pollution Prediction of Urban Areas in Edge Networks 12th

Data Analysis with Model Explainability for Air Quality an...

引用

12th International Conference on Big data and Artificial Intelligence, BDA 2024

作者： Singh, Akansha Chakraborty, Soumendu Adhikari, Mainak Department of Computer Science Indian Institute of Information Technology Lucknow Lucknow India School of Data Science Indian Institute of Science Education and Research Thiruvananthapuram Thiruvananthapuram India

ISBN: (纸本)9783031818202

Air quality significantly impacts human health and economic conditions, making precise and timely assessment crucial in urban areas. Existing studies often fail to predict pollution accurately in smaller areas due to varying meteorological conditions. Most existing prototypes rely on standard ML models, trained with generic, publicly available datasets, which often lack local dynamics, adaptability, and synchronization. To address these challenges, in this paper, we propose a new Hybrid Edge-Cloud Air Quality Monitoring System. For initial model training a robust testbed is created by data Fusion of air quality data from diverse sources like Application programming Interfaces and public datasets. The system trains and refines ML models in the cloud, identifies key features to reduce feature dimensions, and leverages local decision-making using site-specific data collected by sensors on edge devices. Sensors monitor local environmental parameters for real-time analysis and decision-making, ensuring accurate predictions for specific urban locations while optimizing performance and minimizing resource usage on edge devices. Explainable AI techniques improve transparency and confidence in decisions. The model is validated by simulating various ML models on the testbed, with and without feature extraction. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Incremental SAT-Based Enumeration of Solutions to the Yang-Baxter Equation 31th

Incremental SAT-Based Enumeration of Solutions to the Yang-B...

引用

31st International Conference on Tools and Algorithms for the Construction and Analysis of Systems, TACAS 2025, which was held as part of the International Joint Conferences on Theory and Practice of Software, ETAPS 2025

作者： Van Caudenberg, Daimy Bogaerts, Bart Vendramin, Leandro Department of Computer Science KU Leuven Leuven. AI Leuven3000 Belgium Department of Computer Science Vrije Universiteit Brussel Brussels1050 Belgium Department of Mathematics and Data Science Vrije Universiteit Brussel Brussels1050 Belgium

ISBN: (纸本)9783031906527

We tackle the problem of enumerating set-theoretic solutions to the Yang-Baxter equation. This equation originates from statistical and quantum mechanics, but also has applications in knot theory, cryptography, quantum computation and group theory. Non-degenerate, involutive solutions have been enumerated for sets up to size 10 using constraint programming with partial static symmetry breaking [1];for general non-involutive solutions, a similar approach was used to enumerate solutions for sets up to size 8. In this paper, we use and extend the SAT Modulo Symmetries framework (SMS), to expand the boundaries for which solutions are known. The SMS framework relies on a minimality check;we present two solutions to this, one that stays close to the original one designed for enumerating graphs and a new incremental, SAT-based approach. With our new method, we can reproduce previously known results much faster and also report on results for sizes that have remained out of reach so far. © The Author(s) 2025.

关键词： Lie groups

来源：评论

学校读者我要写书评

暂无评论

HFANet: Hierarchical Feature-Enhanced Aggregation Network for Camouflaged Object Detection

引用

Journal of Shanghai Jiaotong University (science) 2025年 1-9页

作者： Zhang, Xinchao Zhu, Hengliang Mao, Guojun Department of Computer Science and Mathematics Fujian University of Technology Fuzhou350118 China Fujian Provincial Key Laboratory of Big Data Mining and Applications Fuzhou350118 China

Camouflaged object detection (COD) aims to identify target objects in complex scenes with extremely high similarity to their surroundings, and has significant applications in military, medical, and other fields. This paper proposes a hierarchical feature-enhanced aggregation network (HFANet) for COD, aiming to address the situations that the target object is highly similar to the background. First, we adopt the pyramid vision Transformer model as the backbone for feature extraction. On top of it, the object-region amplification module and deep interaction guidance module are stacked to enhance the perception of camouflaged objects in complex scenes. Second, an enhanced receptive field module is designed to improve edge perception of camouflaged objects. At last, a multi-scale interactive fusion module is designed by cross-scale connection through adjacent layers, effectively improving the accuracy of COD. The proposed method is evaluated on three challenging datasets: CAMO, CHAMELEON, and COD10K. Evaluation results demonstrate superior performance compared to the state-of-the-art methods. © Shanghai Jiao Tong University 2024.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Virtualizing Next-Generation programmable Networks: Techniques, Use Cases, and Promising Future Directions

引用

IEEE Network 2025年第3期39卷 148-155页

作者： Chen, Xiang Du, Hongyang Liu, Wenjing Liu, Hongyan Zhang, Jianshan Yang, Xu Zhang, Dong Wu, Chunming Liu, Xuan Niyato, Dusit Zhejiang University College of Computer Science and Technology Hangzhou310027 China The University of Hong Kong Department of Electrical and Electronic Engineering Pokfulam Hong Kong Zhejiang Media Group Hangzhou310005 China Minjiang University Fujian Provincial Key Laboratory of Information Processing and Intelligent Control College of Computer and Data Science Fuzhou350108 China Fuzhou University College of Computer and Data Science Fuzhou350108 China Yangzhou University College of Information Engineering College of Artificial Intelligence Yangzhou225009 China Nanyang Technological University College of Computing and Data Science Jurong West 639798 Singapore

For decades, network virtualization plays a crucial role in modern networks, e.g., 6G mobile networks: tenants construct arbitrary virtual networks on the same physical network. However, production networks are becoming programmable and need more ways of network configurations. So prior techniques like SDN hypervisors are deprecated since they cannot configure programmable networks. In response, a new category of network virtualization techniques has emerged recently to virtualize programmable networks, i.e., programmable network hypervisors (PNHs). This article first reviews this trend to comprehensively survey PNHs. To understand their benefits, we build a testbed with hardware switches and sophisticated topologies. Our testbed experiments stress-test hypervisors and demonstrate that they outperform prior works with higher acceptance ratios of virtual networks under large-scale scenarios and heavy loads. Finally, we highlight the open issues of these techniques to shed light on the future directions in this promising topic. © 1986-2012 IEEE.

关键词： Virtualization

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：