检索结果-内蒙古大学图书馆

Asymptotics-Aware Multi-View Subspace Clustering

IEEE Transactions on Multimedia 2025年

作者： Xu, Yesong Chen, Shuo Li, Jun Yang, Jian Anhui Polytechnic University School of Computer and Information Wuhu241000 China RIKEN Center for Advanced Intelligence Project Tokyo103-0027 Japan Nanjing University of Science and Technology PCA Laboratory Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Nanjing210094 China Nanjing University of Science and Technology Jiangsu Key Laboratory of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing210094 China

Recently, multi-view subspace clustering has attracted extensive attention due to the rapid increase of multi-view data in many real-world applications. The main goal of this task is to learn a common representation of multiple subspaces from the given multi-view data, and most existing methods usually directly merge multiple groups of features by the single-step integration. However, there may exist large disparities among different views of the data, and thus the conventional single-step practice can hardly obtain a generally consistent feature representation for the multi-view data. To overcome this challenge, we present a novel approach dubbed "Asymptotics-Aware Multi-view Subspace Clustering (A2 MSC)"to pursue a consistent feature representation in a multi-step way, which iteratively conducts the data recovery to gradually reduce the differences between pairwise views. Specifically, we construct an asymptotic learning rule to update the feature representation, and the iteration result converges to a consistent feature vector for characterizing each instance of the original multi-view data. After that, we utilize such a new feature representation to learn a clustering-oriented similarity matrix via minimizing a self-expressive objective, and we also design the corresponding optimization algorithm to solve it with convergence guarantees. Theoretically, we prove that the learned asymptotic representation effectively integrates multiple views, thereby ensuring the effective handling of multi-view data. Empirically, extensive experimental results demonstrate the superiority of our proposed A2 MSC over the state-of-the-art multi-view subspace clustering approaches. © 2025 IEEE.

关键词： Data assimilation

来源：评论

学校读者我要写书评

暂无评论

An efficient and energy-saving data dissemination mechanism for low-power and lossy networks

引用

IEIE Transactions on Smart Processing and Computing 2018年第4期7卷 271-278页

作者： Zhang, Kaibin Kim, Jinsoo Cho, Gihwan Division of Computer Science and Engineering [Center for Advanced Image and Information Technology Chonbuk National University Jeonju Korea Republic of Department of Information Security Engineering Chonbuk National University Jeonju Korea Republic of

A low-power and lossy network (LLN) connects a huge amount of resource-constrained devices. These devices are limited in processing ability, memory, and power supply. With a view to performance, the Trickle timer algorithm was proposed to reduce control overhead of the routing protocol for LLNs, which aims to emphasize a high data transfer rate while consuming low power. In this paper, we propose an efficient and energy-saving data dissemination mechanism for LLNs to overcome the choke-point problem left over by the Trickle timer mechanism. A new parameter is introduced to indicate the neighbor density, and two modes are utilized to distinguish a node's actions in silence or burst situations. If a node is detected inside a circle of updated nodes, it will enter silence mode to reduce broadcasting frequency. When a node is recognized on the border, it will enter burst mode to increase broadcasting frequency. Simulation results validate that our method outperforms the Trickle timer mechanism in terms of convergence time and energy consumption to disseminate data, especially in a dense LLN. Copyrights © 2018 The Institute of Electronics and information Engineers.

关键词： Data transfer

来源：评论

学校读者我要写书评

暂无评论

Consistency of optimized facial features through the ages

International Journal of Multimedia and Ubiquitous Engineeri...

引用

International Journal of Multimedia and Ubiquitous Engineering 2013年第5期8卷 61-69页

作者： Du, Ruoyu Lee, Hyo Jong Division of Computer Science and Engineering Chonbuk National University Jeonju Korea Republic of Center for Advanced Image and Information Technology Chonbuk National University Jeonju Korea Republic of

The evaluation and measurement of human body dimensions are achieved by physical anthropometry. The main goal of this research is to optimization of facial feature point by establishing a mathematical relationship among facial features and used optimize feature points for age classification. According to this proposes method, sixteen Euclidean distances are calculated from the eighteen selected facial feature points vertically as well as horizontally. The distances between the specified features points increase with respect the age progression of a human from his or her childhood but the ratio of the distances does not change (δ=1.618). Feature distances are used for classification of age using Support Vector Machine (SVM) - Sequential Minimal Optimization (SMO) algorithm and shown around 96% accuracy. © 2013 SERSC.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

An adaptive genetic algorithm for improving dynamic performance of PD control systems

International Journal of Control and Automation

引用

International Journal of Control and Automation 2015年第7期8卷 335-346页

作者： Shuli, Xing Lee, Hyang Ran Lee, Malrey Center for Advanced Image and Information Technology School of Electronics and Information Engineering Chon Buk National University 664-14 1Ga Deokjin-DongJeonju Chon Buk Korea Republic of

The appropriate choice of crossover and mutation rates is critical to the success of genetic algorithms. Earlier researches focused on finding optimal non-dynamic crossover or mutation rates, which vary for different problems, and different stages of the genetic process in a problem. This paper proposed an ameliorate adaptive genetic algorithm where the mutation and crossover rates are adapted dynamically based on the evaluation results of the respective offspring in the next generation. Simultaneously, we combined this new algorithm with PD controllers to improve the stability of control systems. The experimental results are compared with other researchers' approaches in this field. The PD-GA method can also significantly accelerate the system response and induce lower overshoot as well. © 2015 SERSC.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

COMEM: In-Context Retrieval-Augmented Mass-Editing Memory in Large Language Models

COMEM: In-Context Retrieval-Augmented Mass-Editing Memory in...

引用

2024 Findings of the Association for Computational Linguistics: NAACL 2024

作者： Qiao, Shanbao Liu, Xuebing Na, Seung-Hoon Center for Advanced Image and Information Technology Department of Computer Science and Artificial Intelligence Jeonbuk National University Korea Republic of

ISBN: (纸本)9798891761193

Noting that world knowledge continuously evolves over time, large language models (LLMs) need to be properly adjusted by performing the "knowledge editing", which involves updating outdated information or correcting false information. To achieve reliable and "massive" editing capabilities in terms of generalization and specificity, this paper proposes a unified knowledge editing method called in-COntext retrieval-augmented Mass-Editing Memory (COMEM), which combines two types of editing approaches: parameter updating and in-context knowledge editing (IKE). In particular, COMEM incorporates retrieval-augmented IKE, a novel extension of IKE designed for massive editing tasks, based on an updating-aware demonstration construction. Experimental results on the zsRE and CounterFact datasets demonstrate that COMEM outperforms all existing methods, achieving state-of-the-art performance. Our code is available at https://***/JoveReCode/***. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

High-resolution subsurface articular cartilage imaging based on Fourier-domain common-path optical coherence tomography

引用

Chinese Optics Letters 2010年第2期8卷 167-169页

作者： Jae-Ho Han Xuan Liu Jin U. Kang Chul Gyu Song Department of Electrical and Computer Engineering Johns Hopkins University 3400 N. Charles St. Baltimore MD 21218 USA Division of Electronics and Information Engineering Center for Advanced Image and Information Technology Chonbuk National University Deokjin-Dong Jeonju 561-756 Korea

We demonstrate the subsurface imaging of an articular cartilage using Fourier-domain common-path optical coherence tomography. The bare fiber probe integrated with a hypodermic needle provides the rigidness required to perform lateral scanning with less microscale bending. By submerging both the probe and the specimen into saline solution, we not only reduce the beam divergence, but also increase the signal-to-noise ratio compared with the measurement in free space. Our system can differentiate the characteristic cartilage zones and identity various micro-structured defects in an ex vivo chicken knee cartilage, thus demonstrating that it could be used to conduct early arthritis diagnosis and intraoperative endo-microscopy.

关键词： High-resolution subsurface articular cartilage imaging based on Fourier-domain common-path optical coherence tomography

来源：评论

学校读者我要写书评

暂无评论

Use of artificial neural network for the prediction of ammonia emission concentration of granulated blast furnace slag mortar

引用

International Journal of Smart Home 2014年第2期8卷 123-136页

作者： Jang, Hongseok Lee, Malrey So, Seungyoung Dept. of Architectural Engineering Chonbuk National University Korea Republic of The research Center for Advanced Image and Information Technology School of Electronics and information Engineering Chonbuk National University Korea Republic of Research Center of Industrial Technology Dept. of Architectural Engineering Chonbuk National University Korea Republic of

In this study, an artificial neural networks study was carried out to predict the quantity of ammonia gas (NH3) of Granulated Blast Furnace Slag (GBFS) cement mortar. A data set of a laboratory work, in which a total of 4 mortars were produced, was utilized in the Artificial Neural Networks (ANNs) study. The mortar mixture parameters were four different GBFS ratios (0%, 20%, 40% and 60%). Measurement ammonia of moist cured specimens were measured at 1, 3, 10, 30, 100, 365 days. ANN model is constructed, trained and tested using these data. The data used in the ANN model are arranged in a format of two input parameters that cover the cement, GBFS and age of samples and, an output parameter which is concentrations of ammonia emission of mortar. The results showed that ANN can be an alternative approach for the predicting the ammonia concentration of GBFS mortar using mortar ingredients as input parameters. © 2014 SERSC.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Face sketch synthesis: A neural style approach

引用

2017 International Conference on image Processing, Computer Vision, and Pattern Recognition, IPCV 2017

作者： Philip, Chikontwe Lee, Hyo Jong Division of Computer Science and Engineering Chonbuk National University Jeonju561-756 Korea Republic of Center for Advanced Image and Information Technology

ISBN: (纸本)1601324642

Face sketch synthesis plays a significant role in the domain of face recognition and retrieval applications. Great interest of its applications in law enforcement and entertainment have continued to be noted in the research community. Over the years, great advances have been noted in face sketch synthesis as most recent methods are gradually moving towards deep representation based approaches. In this paper, we propose a style transfer approach for synthesis of sketches by leveraging recent algorithms applied to artistic style transfer. In addition, the approach shows the application style transfer produces visually appealing synthetic sketches results as well as facial reconstructions. Lastly, we show poorly reconstructed images can be improved with a denoising autoencoder to create better synthetic images. The effectiveness of the approach is presented through experiments on the CUHK face sketch database. CSREA Press ©

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Scalability in privacy-preserving data aggregation for wireless sensor networks

Scalability in privacy-preserving data aggregation for wirel...

引用

IEEE International Symposium on Parallel and Distributed Processing With Applications

作者： Bista, Rabindra Shin, Young-Sung Chang, Jae-Woo Dept. of Computer Engineering Center for Advanced Image and Information Technology Chonbuk National University Chonju Chonbuk 561-756 Korea Republic of

ISBN: (纸本)9780769541907

In this paper, we propose a new privacy preserving data aggregation scheme for WSNs. Our scheme applies additive property of complex numbers in order to combine sensor data and preserve data privacy during transmission to the sink node. In addition, for supporting scalability, we propose a novel mechanism in which a special set of real numbers are assigned to sensor nodes as their IDs so that a single bit is sufficient to hold ID of a sensor node during transmission of aggregated data to the sink node. For this, we, first, generate fixed size signatures for the IDs of all sensor nodes and then superimpose the signatures during data aggregation phase. By analytical evaluations, we show that our scheme is more scalable and energy efficient than the existing methods to achieve data privacy and transmit IDs of sensor nodes along with the aggregated data to the sink node. © 2010 IEEE.

关键词： Sensor nodes

来源：评论

学校读者我要写书评

暂无评论

Endothelial cell image enhancement using non-subsampled image pyramid

引用

information technology Journal 2007年第7期6卷 1057-1062页

作者： Khan, Mohammad A. U. Khan, M. Khalid Khan, M. Aurangzeb Ibrahim, M. Talal Department of Electrical Engineering COMSATS Institute of Information Technology Abbottabad Pakistan Centre for Image Analysis Uppsala University Uppsala Sweden Department of Electrical Engineering COMSATS Institute of Information Technology Islamabad Pakistan Department of Computer Engineering Center for Advanced Studies in Engineering Islamabad Pakistan Department of Electrical Engineering COMSATS Institute of Information Technology University Road Abbottabad Pakistan

A corneal endothelial cell image provides vast amount of information about a human eye. The cell density and cell shape parameters of a given endothelial cell image help ophthalmologists in making many vital clinical decisions. The acquired endothelial image is poor in contrast where cell boundaries are masked in the background. Previously, most of the work was based on morphological operations in spatial domain. However, if we think of cell structure as texture hidden in noisy background, we can get help from wavelet-texture segmentation, a well studied area. In this study, we propose a non-subsampled Wavelet pyramid decomposition of lowpass region. At certain level of the pyramid, we start observing cleaner cell boundary structure which greatly facilitates its segmentation. Once segmented automatic cell counting can be used and simulation results have shown improvement in cell density count. © 2007 Asian Network for Scientific information.

关键词： image enhancement

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：