检索结果-内蒙古大学图书馆

13th International Conference on intelligent Control and information processing, ICICIP 2025

作者： Li, Sen Li, Fang Luo, Xiaonan School of Computer Science and Information Security Guilin University of Electronic Technology Guilin541004 China Guilin541004 China Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin541004 China

ISBN: (纸本)9798331516147

The k-means method is widely utilized for clustering. Its simplicity, efficacy, and swiftness make it a favored choice among clustering algorithms. It faces the challenge of sensitivity to the initial class center. The enhancement strategy for the k-means algorithm focuses on refining the initial selection of cluster centroids, no longer using its random selection of initial class center points, but starting from the entire dataset, choosing the most distant point to serve as the starting cluster centroid. This can also prevent the local optimization problem of the k-means algorithm. The improved algorithm proposed in this article is an effective method that can select the initial class center point from a global perspective and reduce computation time. The suggested approach has undergone rigorous testing and comparative analysis across multiple datasets, yielding commendable outcomes. © 2025 IEEE.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Frame Generation Algorithm for Differentiated Services in Tactical Communication Networks

引用

Journal of Communications and information Networks 2025年第1期10卷 15-25页

作者： Huaifeng Shi Chengsheng Pan Lishang Qin Yingzhi Wang Huangjie Lu Key Laboratory of Intelligent Support Technology for Complex Environments Ministry of EducationNanjing University of Information Science and TechnologyNanjing 210044China

In response to the complex and multidimensional nature of converged traffic on heterogeneous links in tactical communication networks,which leads to the difficulty in ensuring the quality of service(QoS)requirements for critical services,a frame generation algorithm for differentiated services(DS-FG)is ***-FG deploys an adaptive frame generation algorithm based on deep reinforcement learning(DRL-FG)for timesensitive service,while deploying a high efficient frame generation(HEFG)algorithm for non-time-sensitive ***-FG constructs a reward function by combining the queue status information of time-sensitive service and utilizes deep deterministic policy gradients(DDPG)to train a decision model for adaptive frame generation(AFG)algorithm ***,Gaussian noise sampling and prioritized experience replay strategies are employed to enhance model training efficiency and performance,achieving optimal matching between time-sensitive service QoS requirements and frame generation *** results demonstrate that DS-FG outperforms traditional algorithms,achieving up to 13%improvement in throughput and over 19.7%reduction in average queueing delay for time-sensitive service.

关键词： frame generation algorithm tactical communication network reinforcement learning differentiated services

来源：评论

学校读者我要写书评

暂无评论

A Holistic Evaluation of Piano Sound Quality 10th

A Holistic Evaluation of Piano Sound Quality

引用

10th Conference on Sound and Music technology, CSMT 2023

作者： Zhou, Monan Wu, Shangda Ji, Shaohua Li, Zijin Li, Wei Central Conservatory of Music Beijing China School of Computer Science and Technology Fudan University Shanghai200438 China Shanghai Key Laboratory of Intelligent Information Processing Fudan University Shanghai200433 China

ISBN: (纸本)9789819779611

This paper aims to develop a holistic evaluation method for piano sound quality to assist in purchasing decisions. Unlike previous studies that focused on the effect of piano performance techniques on sound quality, this study evaluates the inherent sound quality of different pianos. To derive quality evaluation systems, the study uses subjective questionnaires based on a piano sound quality dataset. The method selects the optimal piano classification models by comparing the fine-tuning results of different pre-training models of Convolutional Neural Networks (CNN). To improve the interpretability of the models, the study applies Equivalent Rectangular Bandwidth (ERB) analysis. The results reveal that musically trained individuals are better able to distinguish between the sound quality differences of different pianos. The best fine-tuned CNN pre-trained backbone achieves a high accuracy of 98.3% as the piano classifier. However, the dataset is limited, and the audio is sliced to increase its quantity, resulting in a lack of diversity and balance, so we use focal loss to reduce the impact of data imbalance. To optimize the method, the dataset will be expanded, or few-shot learning techniques will be employed in future research. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Hamiltonian boundary value methods applied to KdV-KdV systems

引用

Applied Numerical Mathematics 2025年 214卷 1-27页

作者： Luo, Qian Xiao, Aiguo Luo, Xuqiong Yan, Xiaoqiang School of Mathematics and Computational Science Hunan Key Laboratory for Computation and Simulation in Science and Engineering Xiangtan University Hunan 411105 China Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Hunan 411105 China School of Mathematics and Statistics Changsha University of Science and Technology Changsha410114 China National Center for Applied Mathematics in Hunan Xiangtan University Hunan 411105 China

In this paper, we propose a highly accurate scheme for two KdV systems of the Boussinesq type under periodic boundary conditions. The proposed scheme combines the Fourier-Galerkin method for spatial discretization with Hamiltonian boundary value methods for time integration, ensuring the conservation of discrete mass and energy. By expanding the system in Fourier series, the equations are firstly transformed into Hamiltonian form, preserving the original Hamiltonian structure. Applying the Fourier-Galerkin method for semi-discretization in space, we obtain a large-scale system of Hamiltonian ordinary differential equations, which is then solved using a class of energy-conserving Runge-Kutta methods, known as Hamiltonian boundary value methods. The efficiency of this approach is assessed, and several numerical examples are provided to demonstrate the effectiveness of the method. © 2025 IMACS

关键词： Ordinary differential equations

来源：评论

学校读者我要写书评

暂无评论

Fake Face Detection Based on Fusion of Spatial Texture and High-Frequency Noise

引用

Chinese Journal of Electronics 2025年第1期34卷 212-221页

作者： Dengyong Zhang Feifan Qi Jiahao Chen Jiaxin Chen Rongrong Gong Yuehong Tian Lebing Zhang Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation School of Computer and Communication Engineering Changsha University of Science and Technology School of Computer and Communication Engineering Changsha University of Science and Technology Changsha Social Work College Changkuangao Beijing Technology Co. Ltd. School of Computer and Artificial Intelligence Huaihua University

The rapid development of the Internet has led to the widespread dissemination of manipulated facial images, significantly impacting people's daily lives. With the continuous advancement of Deepfake technology, the generated counterfeit facial images have become increasingly challenging to distinguish. There is an urgent need for a more robust and convincing detection method. Current detection methods mainly operate in the spatial domain and transform the spatial domain into other domains for analysis. With the emergence of transformers, some researchers have also combined traditional convolutional networks with transformers for detection. This paper explores the artifacts left by Deepfakes in various domains and, based on this exploration, proposes a detection method that utilizes the steganalysis rich model to extract high-frequency noise to complement spatial features. We have designed two main modules to fully leverage the interaction between these two aspects based on traditional convolutional neural networks. The first is the multi-scale mixed feature attention module, which introduces artifacts from high-frequency noise into spatial textures, thereby enhancing the model's learning of spatial texture features. The second is the multi-scale channel attention module, which reduces the impact of background noise by weighting the features. Our proposed method was experimentally evaluated on mainstream datasets, and a significant amount of experimental results demonstrate the effectiveness of our approach in detecting Deepfake forged faces, outperforming the majority of existing methods.

关键词： Deepfakes Adaptation models Attention mechanisms Noise Transforms Transformers Feature extraction Internet Convolutional neural networks Faces

来源：评论

学校读者我要写书评

暂无评论

High-order consensus graph learning for incomplete multi-view clustering

引用

Applied Intelligence 2025年第6期55卷 1-25页

作者： Guo, Wei Che, Hangjun Leung, Man-Fai College of Electronic and Information Engineering Southwest University Chongqing400715 China Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing Chongqing400715 China Faculty of Science and Engineering Anglia Ruskin University CambridgeCB1 1PT United Kingdom

Incomplete Multi-View Clustering (IMVC) aims to partition data with missing samples into distinct groups. However, most IMVC methods rarely consider the high-order neighborhood information of samples, which represents complex underlying interactions, and often neglect the weights of different views. To address these issues, we propose a High-order Consensus Graph Learning (HoCGL) model. Specifically, we integrate a reconstruction term to recover the incomplete multi-view data. High-order proximity matrices are constructed, and the self-representation similarity matrices and multiple high-order proximity matrices are learned mutually, allowing the similarity matrices to incorporate complex high-order information. Finally, the consensus graph representation is derived from the similarity matrices through a self-weighted strategy. An efficient algorithm is designed to solve the proposed model. The excellent clustering performance of the proposed model is validated by comparing it with eight state-of-the-art models across nine datasets. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Consensus algorithm

来源：评论

学校读者我要写书评

暂无评论

Glare-SNet: Unsupervised Glare Suppression Balance Network 27th

Glare-SNet: Unsupervised Glare Suppression Balance Network

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Li, Pei Zuo, Chengyu Wei, Wangjuan Pan, Xiaoying Wang, Zhanhao School of Computer Science and Technology Xi’an University of Posts and Telecommunications Xi’an710121 China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi’an China Shaanxi Key Laboratory of Intelligent Media Computing and interaction Xi’an China Xi’an Key Laboratory of Big Data and Intelligent Computing Xi’an China

ISBN: (纸本)9783031781681

In light of the problems associated with glare and halo effects in low-light images, as well as the inadequacy of existing processing algorithms in handling details, a glare suppression balance network based on unsupervised learning has been designed and implemented in this study. A network that perceives brightness through light decomposition has been proposed, and an illumination learning network has been designed. The idea of integration has been employed to form an unsupervised glare suppression balance network, aiming to tackle the issues of glare and the accompanying halo effects. Through objective and subjective evaluations of real images, it has been proven that the method introduced in this paper surpasses other methods in suppressing glare and enhancing the overall quality of low-light images. Furthermore, it has been shown to exhibit good performance and effectiveness in target detection. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Tomato Leaf Disease Identification and Growth Dataset Augmentation Based on UAE-GAN 13

Tomato Leaf Disease Identification and Growth Dataset Augmen...

引用

13th International Conference on intelligent Control and information processing, ICICIP 2025

作者： Li, Xin Li, Fang Luo, Xiaonan School of Computer Science and Information Security Guilin University of Electronic Technology Guilin541004 China Guilin541004 China Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin541004 China

ISBN: (纸本)9798331516147

To delve into the characterization of growth disorders in different crops, it is important to support the model with a large amount of image data that includes a variety of disease types and disease levels to capture the typical and subtle differences of various diseases on plant leaves. However, the actual process of gathering data is challenging, sample coverage is challenging to accomplish, data capture is impeded, and the quality of the data is subpar. This work aims to address the issue of data shortages by employing technical methods. In particular, we creatively investigated the UAE-GAN approach, which naturally combines CycleGAN, U-Net, Variational Autoencoder VAE, and Autoencoder to increase the data. Among these, U-Net can precisely extract the small details of disease locations in crop photos and provide a strong basis for further processing thanks to its special codec architectural benefits. The Variational Autoencoder (VAE) significantly enhances the diversity of data by mapping the image to the latent space and sampling based on a certain probability distribution, so producing new image samples that are distinct from the original image yet inherently connected. Learning the coding and decoding of the original image is the foundation of autoencoders. If a mild disruption is introduced into the coding process, it can achieve data augmentation in another dimension and create a sequence of new images with just little modifications to the original image. The aforementioned models are closely linked with CycleGAN to efficiently map and convert in a variety of picture domains and to fully leverage CycleGAN's remarkable unsupervised image conversion capabilities. The perception ability, feature capture ability, and information conversion ability of the fusion model for crop image data are significantly improved, and the key elements of each link in the data enhancement process are comprehensively considered to ensure that the generated new image data can not o

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

Multi-objective Balanced Task Offloading in Vehicular Networks Based on Edge Computing 27th

Multi-objective Balanced Task Offloading in Vehicular Networ...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Wang, Lingjiao Meng, Lingwei Guo, Hua Xiangtan University Hunan Xiangtan411105 China Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Xiangtan University Hunan Xiangtan411105 China

ISBN: (纸本)9783031783821

The increasing number of vehicular networking devices and application demands has made the limited computing and communication resources a significant challenge. The heuristic task offloading strategy mechanism was proposed to improve the efficiency of task offloading in vehicular networks. This strategy mechanism utilized the Nondominated Sorting Genetic Fireworks Algorithm (NSGFA) based on the characteristics of the problem, integrated consideration of the multi-target balance between system offloading costs and load balancing. Experimental data results demonstrate that this method performs well in reducing latency, energy consumption, and load balancing, effectively enhancing the quality of service for vehicular network users. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Computation offloading

来源：评论

学校读者我要写书评

暂无评论

Rotational Cherenkov-Excited Luminescence Scanned Tomography Reconstruction with Symmetry Vision Mamba 17

Rotational Cherenkov-Excited Luminescence Scanned Tomography...

引用

17th International Conference on Photonics and Imaging in Biology and Medicine, PIBM 2024

作者： Zhang, Jingyue Zhang, Hu Hu, Ting Li, Zhe Sun, Zhonghua Jia, Kebin Feng, Jinchao Beijing Key Laboratory of Computational Intelligence and Intelligent System Faculty of Information Technology Beijing University of Technology Beijing100124 China Beijing Laboratory of Advanced Information Networks Beijing100124 China

ISBN: (数字)9781510688070

ISBN: (纸本)9781510688063

Rotational Cherenkov-Excited Luminescence Scanned Tomography (RCELST) is an emerging optical imaging technology that visualizes the distribution of luminescent quantum yield within a treated subject. This technology involves collecting luminescence signals resulting from the excitation of luminescence probes by Cherenkov emissions induced by the rotational scanning of MV X-rays. These signals are then mapped into a sinogram for reconstructing the distribution of luminescent quantum yield by neural networks. Vision Transformers (ViTs), an effective deep learning algorithm known for capturing long-distance dependencies, have been applied to medical image reconstruction tasks. However, the large scale of medical images, combined with the quadratic complexity of ViTs, leads to erratic and time-consuming reconstruction performance. Therefore, a more efficient algorithm is essential for reducing reconstruction time while maintaining accuracy. In this study, we propose the Symmetry Vision Mamba (S-VM) to address this challenge, reducing computational time while maintaining high reconstruction accuracy. The S-VM builds on the Vision Mamba, which leverages State Space Models (SSMs) to extract global information from 2D sinogram signals. With linear computational complexity, S-VM significantly accelerates the learning process compared to the Transformer algorithms. Additionally, S-VM utilizes a symmetrical encoder architecture, incorporating convolutional stems to extract local features and enable multi-scale feature fusion by sharing parameters between the two encoder branches. Training on 10,000 sinogram signals, the S-VM algorithm achieves a peak signal-to-noise ratio (PSNR) of up to 38.67 dB and a structural similarity index measure (SSIM) of 0.97. Remarkably, these results are achieved in a floating point operations (FLOPs) of 4.7G. © 2025 SPIE.

关键词： Photons

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：