检索结果-内蒙古大学图书馆

5th International Conference on Intelligent Communication Technologies and Virtual Mobile Networks, ICICV 2024

作者： Rajput, Shweta Singh Manimaran, S. Satapathy, Sandeep Kumar Mishra, Shruti Mohanty, Sachi Nandan School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Chennai600127 India VIT-AP University Andhra Pradesh Amaravati522503 India Yonsei University Department of Computer Science Seoul03722 Korea Republic of Centre for Advanced Data Sciences Vellore Institute of Technology Tamil Nadu Chennai600127 India

ISBN: (纸本)9798350385649

The biometric identification method of fingerprint recognition is quite popular because of its uniqueness and durability. The KNN-S 1FT algorithm is used in this research work to present a novel method for extracting and recognizing fingerprint features. The extraction of fingerprint feature information and fingerprint matching are the two main topics of the article. For the purpose of handling image differences brought on by scale, rotation, and affine transformations, a number of fingerprint feature extraction techniques are explored, with a focus on the SIFT algorithm. The KNN-S 1FT technique boosts the precision and dependability of fingerprint matching by combining the power of machine learning with pattern recognition. Experimental tests on a benchmark fingerprint database show that the proposed algorithm outperforms other cutting-edge methods in terms of accuracy and reliability. The findings of this study have broad ramifications for fields requiring safe identification procedures, including forensic investigations, access control systems, and law enforcement. The KNN-S 1FT technique that has been suggested helps to create sophisticated, effective fingerprint identification systems. © 2024 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Characterization of Highly Robust Solutions in Multi-Objective Programming in Banach Spaces

arXiv

引用

arXiv 2025年

作者： Rahimi, Morteza Soleimani-Damaneh, Majid Department of Mathematics University of Antwerp Antwerp Belgium School of Mathematics Statistics and Computer Science College of Science University of Tehran Tehran Iran

This paper delves into the challenging issues in uncertain multi-objective optimization, where uncertainty permeates nonsmooth nonconvex objective and constraint functions. In this context, we investigate highly robust (weakly efficient) solutions, a solution concept defined by efficiency across all scenarios. Our exploration reveals important relationships between highly robust solutions and other robustness notions, including set-based and worst-case notions, as well as connections with proper and isolated efficiency. Leveraging modern techniques from variational analysis, we establish necessary and sufficient optimality conditions for these solutions. Moreover, we explore the robustness of multi-objective optimization problems in the face of various uncertain sets, such as ball, ellipsoidal, and polyhedral *** Codes 90C29, 90C17, 90C46 Copyright © 2025, The Authors. All rights reserved.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Pairwise alignment improves graph domain adaptation 24

Pairwise alignment improves graph domain adaptation

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Shikun Liu Deyu Zou Han Zhao Pan Li Department of Electrical and Computer Engineering Georgia Institute of Technology Georgia School of Data Science University of Science and Technology of China Hefei China Department of Computer Science University of Illinois Urbana- Champaign Champaign

Graph-based methods, pivotal for label inference over interconnected objects in many real-world applications, often encounter generalization challenges, if the graph used for model training differs significantly from the graph used for testing. This work delves into Graph Domain Adaptation (GDA) to address the unique complexities of distribution shifts over graph data, where interconnected data points experience shifts in features, labels, and in particular, connecting patterns. We propose a novel, theoretically principled method, Pairwise Alignment (Pair-Align) to counter graph structure shift by mitigating conditional structure shift (CSS) and label shift (LS). Pair-Align uses edge weights to recalibrate the influence among neighboring nodes to handle CSS and adjusts the classification loss with label weights to handle LS. Our method demonstrates superior performance in real-world applications, including node classification with region shift in social networks, and the pileup mitigation task in particle colliding experiments. For the first application, we also curate the largest dataset by far for GDA studies. Our method shows strong performance in synthetic and other existing benchmark datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Boosting Performance and QoS for Concurrent GPU B+trees by Combining-Based Synchronization 23

Boosting Performance and QoS for Concurrent GPU B+trees by C...

引用

28th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming, PPoPP 2023

作者： Zhang, Weihua Zhao, Chuanlei Peng, Lu Lin, Yuzhe Zhang, Fengzhe Lu, Yunping School of Computer Science Fudan University China Institute of Big Data Fudan University China State Key Laboratory of Mathematical Engineering and Advanced Computing China Parallel Processing Institute Fudan University China Department of Computer Science Tulane University United States

ISBN: (纸本)9798400700156

Concurrent B+trees have been widely used in many systems. With the scale of data requests increasing exponentially, the systems are facing tremendous performance pressure. GPU has shown its potential to accelerate concurrent B+trees performance. When many concurrent requests are processed, the conflicts should be detected and resolved. Prior methods guarantee the correctness of concurrent GPU B+trees through lock-based or software transactional memory (STM)-based approaches. However, these methods complicate the request processing logic, increase the number of memory accesses and bring execution path divergence. They lead to performance degradation and variance in response time increasing. Moreover, previous methods do not guarantee linearizability among concurrent requests. In this paper, we design a combined-based concurrency control framework, called Eirene, for GPU B+tree to reduce the overhead of conflict detection and resolution. First, a combining-based synchronization method is designed to combine and issue requests. It combines the requests with the same key, constructs their dependence, decides the issued request, and determines their return values. Since only one request for each key is issued, key conflicts are eliminated. Then, an optimistic STM method is used to reduce structure conflicts. The query and the update requests are partitioned into different kernels. For the update kernels, STM is involved only when the number of the retry reaches a threshold. Finally, a locality-aware warp reorganization optimization is proposed to improve memory behavior and reduce conflicts by exploiting the locality among requests. Evaluations on an NVIDIA A100 GPU show that Eirene is efficient (a throughput of 2.4 billion per second) and can guarantee linearizability. Compared to the state-of-the-art GPU B+tree, it can achieve a speedup of 7.43X and reduce the response time variance from 36% to 5%. © 2023 ACM.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Slow-Fast Adaptation for Source-Free Object Detection

Slow-Fast Adaptation for Source-Free Object Detection

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Luojun Lin Qipeng Liu Xiangwei Zheng Zheng Lin College of Computer and Data Science Fuzhou University Fuzhou China Department of Computer Science and Technology Tsinghua University Beijing China College of Computer Science Nankai University Tianjin China

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

Unsupervised Domain Adaptive Object Detection (DAOD) task can relax the domain shift problem between source and target domains, which requires to train models on labeled source and unlabeled target domains jointly. However, due to limitations of data privacy protection, the source domain data is usually inaccessible, which poses significant challenges for the DAOD task. Hence, Source-Free Object Detection (SFOD) task has been developed that aims to fine-tune a pre-trained source model with only unlabeled target domain data. Most of the existing SFOD methods are based on pseudo labeling using the student-teacher framework, where the teacher model is the Exponential Moving Average (EMA) of the student models in different time steps. However, these methods always exist a knowledge bias problem due to class imbalance, and therefore, a fixed EMA update rate is no longer suitable for different classes. For high-quality classes, a fast EMA rate can accelerate knowledge updating and promote model convergence, while for low-quality classes, a fast EMA rate can accelerate the accumulation of knowledge bias and lead to the collapse of such categories. To solve this problem, we propose a novel SFOD method called Slow-Fast Adaptation which develops two different teacher models, a slow teacher, and a fast teacher model, to jointly guide the student training. The slow and fast teacher models can provide richer supervision information and complement each other. The experiments on four benchmark datasets show that our method achieves state-of-the-art results and even outperforms DAOD methods in some cases, which demonstrate the effectiveness of our method on the SFOD task.

关键词： Training Adaptation models data privacy Object detection Benchmark testing Predictive models data models

来源：评论

学校读者我要写书评

暂无评论

Maximizing Crop Yields and Water Efficiency through Tailored Irrigation System Design and Crop Selection

Maximizing Crop Yields and Water Efficiency through Tailored...

引用

2023 IEEE Global Conference on Information Technologies and Communications, GCITC 2023

作者： Musale, Prajakta Jadhav, Balasaheb Bahir, Suvarna A Thopate, Kaushalya Anarase, Dipali Jaiswal, Krishna Vishwakarma Institute of Technology Department of Engineering Sciences and Humanities Pune India Vishwakarma Institute of Technology Department of Artificial Intelligence and Data Science Pune India Trinity Academy of Engineering Department of Computer Engineering India Vishwakarma Institute of Technology Department of Computer Engineering Pune India Wipro Technology India

ISBN: (纸本)9798350308167

Today various water-pump operating systems are available in the market, which allows the user/farmer to operate his water-pump from a distant location using mobile app or on a phone call to the system which is integrated with the water-pump. While studying the existing system we came across a problem that, existing systems does not provide any solution for optimizing the usage of water and power. Optimizing the use of power and water in farming has become a real-time problem these days. To overcome this problem, we have proposed an IOT based system "Advanced Irrigation System". This system provides automation for operating the water pump in the farm by automatically turning ON and OFF the water-pump depending on the type of the crop and its moisture requirements. Also, proposed system provides farmer interface via a mobile application in his regional language, where he can check the moisture, humidity and temperature of his farm. Along with this proposed system has a Google Assistant integrated, using which famer can operate the water-pump remotely over a voice command. © 2023 IEEE.

关键词： Advanced Irrigation System Crop Selection Maximizing Crop Yields power Optimization Water Efficiency water-pump operating systems

来源：评论

学校读者我要写书评

暂无评论

FuseMoE: Mixture-of-Experts Transformers for Fleximodal Fusion

arXiv

引用

arXiv 2024年

作者： Han, Xing Nguyen, Huy Harris, Carl Ho, Nhat Saria, Suchi Department of Computer Science Johns Hopkins University United States Department of Statistics and Data Sciences The University of Texas Austin United States Department of Biomedical Engineering Johns Hopkins University United States

As machine learning models in critical fields increasingly grapple with multimodal data, they face the dual challenges of handling a wide array of modalities, often incomplete due to missing elements, and the temporal irregularity and sparsity of collected samples. Successfully leveraging this complex data, while overcoming the scarcity of high-quality training samples, is key to improving these models’ predictive performance. We introduce "FuseMoE", a mixture-of-experts framework incorporated with an innovative gating function. Designed to integrate a diverse number of modalities, FuseMoE is effective in managing scenarios with missing modalities and irregularly sampled data trajectories. Theoretically, our unique gating function contributes to enhanced convergence rates, leading to better performance in multiple downstream tasks. The practical utility of FuseMoE in the real world is validated by a diverse set of challenging prediction tasks. Copyright © 2024, The Authors. All rights reserved.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

Existence and Nonexistence of Solutions for a Class of Nonlinear Fractional Boundary Value Problems 23

Existence and Nonexistence of Solutions for a Class of Nonli...

引用

23rd IEEE/ACIS International Conference on computer and Information science, ICIS 2023

作者： Kang, Shugui Han, Yonghui Guo, Caixia Feng, Wenying Gao, Ying School of Mathematics and Statistics Shanxi Datong University Shanxi Datong037009 China School of Mathematics and Computer Science Shanxi Normal University Shanxi Linfen041004 China Trent University Department of Mathematics and Computer Science PeterboroughONK9LOG2 Canada

In this paper, the existence and nonexistence of solutions for a class of fractional differential equations are studied by using an interesting fixed point theorem on order intervals and the well-known Schauder's ... 详细信息

ISBN: (纸本)9798350345841

关键词： Boundary value problems

来源：评论

学校读者我要写书评

暂无评论

Parameter-Efficient Image Classification with Convolutional Spiking Neural Network via Fast Sigmoid Surrogate Gradient Descent

Parameter-Efficient Image Classification with Convolutional ...

引用

International Conference on Electrical, computer and Communication Engineering (ECCE)

作者： Joy Datta Fabliha Afaf Sarwar Rawhatur Rabbi Puja Saha Md. Golam Rabiul Alam Jia Uddin Aniqua Nusrat Zereen Department of Computer Science & Engineering School of Data & Sciences Brac University Dhaka Bangladesh Department of Computer Science & Engineering Rajshahi University of Engineering & Technology Rajshahi Bangladesh AI and Big Data Department Endicott College Woosong University Daejeon South Korea

ISBN: (数字)9798350357509

ISBN: (纸本)9798350357516

Spiking Neural Networks (SNNs) offer several advantages over traditional Artificial Neural Networks (ANNs), especially in terms of biologically inspired event-driven mechanisms and energy efficiency. This paper aims to demonstrate parameter efficiency of Convolutional Spiking Neural Networks (CSNNs) by training extremely small CSNNs and comparing those with conventional Convolutional Neural Networks (CNNs) of same parameter count and depth, as well as against state-of-the-art SNN implementations. Through experiments conducted on multiple small-scale CSNN models, we observed that CSNNs are able to achieve exceptional parameter efficiency and performance with the help of a fast sigmoid surrogate gradient descent, proving an astonishing balance between accuracy and compactness. The findings fulfill the promise that CSNNs hold as a feasible solution for resource-constrained and low-power applications at the same time, as it demonstrates the biological plausibility of learning in such complex machine learning tasks.

关键词： Training Image recognition Biological system modeling Neurons Spiking neural networks Machine learning computer architecture Energy efficiency Convolutional neural networks Image classification

来源：评论

学校读者我要写书评

暂无评论

Improved Image Classification with Manifold Neural Networks

Improved Image Classification with Manifold Neural Networks

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Caio F. Deberaldini Netto Zhiyang Wang Luana Ruiz Department of Applied Mathematics and Statistics Mathematical Institute for Data Science (MINDS) Data Science and Artificial Intelligence Institute (DSAI) Johns Hopkins University Baltimore USA Department of Electrical and Systems Engineering University of Pennsylvania Philadelphia USA

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Graph Neural Networks (GNNs) have gained popularity in various learning tasks, with successful applications in fields like molecular biology, transportation systems, and electrical grids. These fields naturally use graph data, benefiting from GNNs’ message-passing framework. However, the potential of GNNs in more general data representations, especially in the image domain, remains underexplored. Leveraging the manifold hypothesis, which posits that high-dimensional data lies in a low-dimensional manifold, we explore GNNs’ potential in this context. We construct an image manifold using variational autoencoders, then sample the manifold to generate graphs where each node is an image. This approach reduces data dimensionality while preserving geometric information. We then train a GNN to predict node labels corresponding to the image labels in the classification task, and leverage convergence of GNNs to manifold neural networks to analyze GNN generalization. Experiments on MNIST and CIFAR10 datasets demonstrate that GNNs generalize effectively to unseen graphs, achieving competitive accuracy in classification tasks.

关键词： Manifolds Electric potential High dimensional data Autoencoders Transportation Signal processing Graph neural networks Molecular biology Speech processing Image classification

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：