检索结果-内蒙古大学图书馆

An Image Matching Method Using Heat Kernels on Graphs

AUTOMATION AND REMOTE CONTROL 2022年第10期83卷 1538-1543页

作者： Zakharov, A. A. Vladimir State Univ Murom Inst Stoletovs Murom 602264 Vladimir Oblast Russia

The paper presents an image matching method based on heat kernels. The method permits one to single out the most stable features of images at the initial stage using heat kernels on graphs for subsequent comparison. Popular descriptors can be used for this. When using the method, the number of false matches is considerably reduced compared with traditional approaches.

关键词： computer vision image comparison heat kernels on graphs

来源：评论

学校读者我要写书评

暂无评论

A Tensor-Array Approach to Direction-of-Arrival and Cyclic Frequency Detection for Cyclostationary Signals 17

A Tensor-Array Approach to Direction-of-Arrival and Cyclic F...

引用

17th International conference on Signal Processing and Communication Systems, ICSPCS 2024

作者： Sirianunpiboon, Songsri Howard, Stephen D. Cochran, Douglas Defence Science and Technology Group PO Box 1500 Edinburgh5111 Australia Arizona State University School of Mathematical and Statistical Sciences TempeAZ85287-5706 United States

ISBN: (纸本)9798350389630

Inspired by an effective and computationally efficient approach for detecting and estimating the parameters of a linear frequency modulated waveform incident on an array of receivers, this paper introduces a method for joint detection/estimation of the directions of arrival and cyclic frequencies of a collection of cyclostationary signals impinging on a receiver array. This approach is underpinned by a tensor-array representation of the signal and steering vector parameters that enables mitigation of cross-terms, thereby providing improved performance relative to established methods - particularly at low SNR. The approach is shown to perform well in experiments involving one and more digitally modulated signals at low SNR. © 2024 IEEE.

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

Risk Minimization Approach for Image Restoration Using L2Penalty in EM Framework 6

Risk Minimization Approach for Image Restoration Using L2Pen...

引用

6th International conference on Information Systems and computer Networks, ISCON 2023

作者： Singh, Ravi Pratap Singh, Manoj Kumar Banaras Hindu University DST-Center for Interdisciplinary Mathematical Sciences Institute of Science Varanasi India Banaras Hindu University Department of Computer Science Institute of Science Varanasi India

ISBN: (纸本)9798350346961

This paper presents a modified expectation maximization (EM) technique for the restoring the image from its degraded model. The proposed methodology comprises the concept of minimization of the risk associated with the L2 penalty in the maximization step (M-step) of the algorithm. This method optimizes the worst case error, and at the same time also ensures the uniform shrinkage of the wavelet coefficients by using proper regularization parameter. The proposed methodology achieves 8.77 dB which is larger than the ISNR achieved by the state-of-the art methods.. © 2023 IEEE.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Influence of the Sequence of Drilling Fields on the Maximum Total Gas Production 16

Influence of the Sequence of Drilling Fields on the Maximum ...

引用

16th International conference Management of Large-Scale System Development, MLSD 2023

作者： Skiba, Alexander Federal Research Center 'Computer Science and Control' of Ras Department of Mathematical Methods of Regional Programming Moscow Russia

We analyze an aggregated dynamic model for the development of gas fields. The same company consistently drills all fields. We pose and solve the problem of maximizing accumulated gas production over a predetermined pe... 详细信息

ISBN: (纸本)9798350337907

关键词： Gas industry

来源：评论

学校读者我要写书评

暂无评论

Self-Converged Ensemble Deep RNN Classifier for Student Performance Prediction in Academics

Self-Converged Ensemble Deep RNN Classifier for Student Perf...

引用

2024 International conference on Advances in Computing Research on science Engineering and Technology, ACROSET 2024

作者： Sharma, Vaibhav Pandey, Vivek Patil, Manoj Jeswani, Ravi Shinde, Pratiksha Agrawal, Shital Mumbai University Computer Engineering Mumbai India Mumbai University Master of Management Studies Mumbai India

ISBN: (纸本)9798350388800

Education institutes have been gaining major improvisation due to the establishment of virtual learning techniques which provide the pupils and staff with enormous information and knowledge that accessed from anywhere at any time virtually, which eventually. The virtual learning environment provides datasets for examining the learning methods of pupils and their evolution as well as their performance in academics. This paper proposed a Self-converged Ensemble Deep RNN Classifier that included an activation ensemble for the prediction and analysis of student performance and explores the moment to establish the relevant methods for student performance prediction by utilizing deep learning techniques. The proposed model self-converged ensemble deep learning RNN classifier, that enhances the MAE is 2.82, MSE is 12.07 and RMSE is 3.47 based on the mathematical dataset. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Multi-vehicle cooperative handling formation optimization method based on improved genetic algorithm 3

Multi-vehicle cooperative handling formation optimization me...

引用

3rd International conference on Intelligent Mechanical and Human-computer Interaction Technology, IHCIT 2024

作者： Ge, Jiachen Xue, Shanliang Liu, Guohui Zhang, Chen Xu, Xinyi College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Jiangsu Nanjing211106 China Jiangsu Jinling Institute of Intelligent Manufacturing Co. Ltd. Jiangsu Nanjing210006 China

ISBN: (纸本)9781510683105

In order to improve the safety of the multi-vehicle collaborative handling process and the flexibility of mobile robot scheduling, this paper optimizes the design of target formations for different types of mobile robots to carry heavy objects well. Rolling moment, combined with the handling strategy, a multi-vehicle intact heavy object handling model was established. At the same time, the energy-based static stability description method ESM (Energy Stability Margin) and the spacing between each short-circuit mobile robot are introduced to evaluate the team's search for the optimal form through an improved genetic algorithm, and the initial population generation method and selection methods, crossover and mutation methods;finally, the advantages and disadvantages of the form proposed in this article are proved through example verification and comparison with traditional genetic algorithms. The algorithm for solving multi-vehicle collaborative handling teams optimizes suction and perception problems. © 2024 SPIE.

关键词： Mobile robots Genetic algorithms Design mathematical optimization Transportation Safety Electronic support measures Manufacturing Data modeling Roads

来源：评论

学校读者我要写书评

暂无评论

Research on student achievement prediction based on machine learning 4

Research on student achievement prediction based on machine ...

引用

4th International conference on Artificial Intelligence and computer Engineering, ICAICE 2023

作者： Liang, Hong Yang, Shuwen Tao, Junyu Faculty of Information Engineering Guangxi Polytechnic of Construction Nanning530007 China School of Science Hubei University of Technology Wuhan430068 China School of Mathematical Sciences Suzhou University of Science and Technology Suzhou215000 China

ISBN: (纸本)9798400708831

Aiming at the problem of how high school teachers can effectively improve examinees' test-taking education ability and put forward relevant test-taking strategies, a mathematical achievement prediction model based on support vector machine and artificial neural network was proposed. A single support vector machine is prone to overfitting on a small sample data set, while artificial neural network can effectively learn the inherent law. Therefore, combining the predicted values of the two and modifying them with residual neural network can effectively improve the prediction accuracy. In addition, in order to explore the influence of individual differences and overall differences on the predicted scores in the previous model exams, two prediction methods were designed. The experimental results show that the proposed model is superior to other methods and the overall difference is much greater than the individual difference. © 2023 ACM.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Proposed Security Enhancement Conceptual Models Using Quantum Key Distribution for Future Cryptography

Proposed Security Enhancement Conceptual Models Using Quantu...

引用

2023 IEEE conference on computer Applications, ICCA 2023

作者： Naing, Phone Oo, Kyaw Zin Su Thwin, Mie Mie Higher Education Centre Departmernt of Computer Science Pyin Oo Lwin Myanmar University of Computer Studies Cyber Security Research Lab Yangon Myanmar

ISBN: (纸本)9781665435994

Today's Cryptographic methods are based on mathematical ideas and its complexity. Quantum computers are getting increasing attention because of the tremendous power by harnessing the unique properties of Quantum Physics. When they will be able to run circles around today's computers, solving problems are infinitely faster than the world's most powerful Super computers. So, for future Cryptographic Infrastructures, Quantum Cryptography is proposed by using Quantum Key Distribution (QKD). In this paper, it is constructed Enhancement Security Conceptual Models, QSC, Quantum Symmetric Conceptual Model and QAC, Quantum Asymmetric Conceptual Model so as to present an improvement of future cryptography by modeling being against to break Encryption Schemes from Quantum Algorithms combined with the Concepts of mathematical and Physical Laws based on Classical Cryptography and Quantum Cryptography. Furthermore, the Security Analysis of the Performance Evaluation of the Proposed Approach is evaluated with Avalanche Effect in our Research. © 2023 IEEE.

关键词： Quantum cryptography

来源：评论

学校读者我要写书评

暂无评论

TomoSelfDEQ: Self-supervised Deep Equilibrium Learning for Sparse-Angle CT Reconstruction 10th

TomoSelfDEQ: Self-supervised Deep Equilibrium Learning for ...

引用

10th International conference on Scale Space and Variational methods in computer Vision, SSVM 2025

作者： Bubba, Tatiana A. Santacesaria, Matteo Sebastiani, Andrea Department of Mathematics and Computer Science University of Ferrara Ferrara Italy MaLGa Center Department of Mathematics University of Genoa Genoa Italy Department of Physics Computer Science and Mathematics University of Modena and Reggio Emilia Modena Italy

ISBN: (纸本)9783031923654

Deep learning has emerged as a powerful tool for solving inverse problems in imaging, including computed tomography (CT). However, most approaches require paired training data with ground truth images, which can be difficult to obtain, e.g., in medical applications. We present TomoSelfDEQ, a self-supervised Deep Equilibrium (DEQ) framework for sparse-angle CT reconstruction that trains directly on undersampled measurements. We establish theoretical guarantees showing that, under suitable assumptions, our self-supervised updates match those of fully-supervised training with a loss including the (possibly non-unitary) forward operator like the CT forward map. Numerical experiments on sparse-angle CT data confirm this finding, also demonstrating that TomoSelfDEQ outperforms existing self-supervised methods, achieving state-of-the-art results with as few as 16 projection angles. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

HEAP-BASED POLITICAL OPTIMIZER

HEAP-BASED POLITICAL OPTIMIZER

引用

2025 International conference on Energy, Power, Environment, Control and Computing, ICEPECC 2025

作者： Islam, Zunaina Rafique, Faheem Faheem, Muhammad Askari, Qamar Department of Computer Science GIFT University Gujranwala Pakistan

ISBN: (纸本)9781837243235

A new hybrid metaheuristic algorithm called Heap-Based Political Optimizer (HBPO) has been developed by integrating the ideas from Heap-Based Optimizer (HBO) and Political Optimizer (PO). To tackle the challenging optimization problems, the HBPO mimics corporate hierarchies and political systems observed in the actual world. In contrast to the original PO, HBPO uses a heap-based structure to improve position update methods and population representation, which leads to better exploration and exploitation capabilities. The elimination of party leaders, the incorporation of heap-based relationships, and flexible populations represent some of the primary modifications. 23 benchmark functions used to compare HBPO against PO and HBO. The results demonstrate that HBPO performed better on multimodal and composite functions while maintaining similar performance on unimodal functions. These results showed the robustness and reliability of HBPO in handling high-dimensional optimization problems. © The Institution of Engineering & Technology 2025.

关键词： mathematical programming

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：