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 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

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

Extended PCA and SGM based algorithm for foreground segmentation

Extended PCA and SGM based algorithm for foreground segmenta...

引用

4th International Congress on image and Signal Processing, CISP 2011

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

ISBN: (纸本)9781424493067

A real-time background segmentation system has already proposed based on two methods Principle Components Analysis (PCA) and Single Gaussian Model (SGM). But PCA based method is required to calculate of decomposition and for this reasons time consumption is vast. On the other hand SGM based foreground segmentation model which is reliably deals with lighting changes, detects repetitive motion from clutter and long-term scene changes. This paper presents a method consists with two methods extended PCA (EPCA) and SGM. An adaptive strategy is used to integrate two methods. We adopt the adaptively incremental eigenspace model to build the intensity information for each pixel. Weng designed Candidate Covariance-Free Incremental PCA (CCIPCA) method, which does not need decomposition. Moreover, it is also simpler and faster than other proposed incremental PCA (IPCA) methods. Shadow removal using adaptive filter and post-processing techniques are used in a proposed method. Therefore, as the proposed algorithm does not require decomposition so this method is faster with PCA and SGM based foreground extraction method. Experimental results represent that this proposed model is robust to noise and illumination change due to inheriting eigenbackground and Gaussian's model advantages to improve the segmentation results. © 2011 IEEE.

关键词： Adaptive filters

来源：评论

学校读者我要写书评

暂无评论

Construction robot prototype design and development for a modular push-up tower crane gantry system

Construction robot prototype design and development for a mo...

引用

2010 International Conference on Artificial Intelligence, ICAI 2010

作者： Gatton, Thomas M. Lee, Malrey Department School of Engineering and Technology National University San Diego CA United States Center for Advanced Image and Information Technology Chonbuk National University JeonJu Korea Republic of

ISBN: (纸本)9781601321480

Push-up tower crane gantry systems have been widely applied in automated construction system, and variations of this approach have been successfully implemented in Japan. While demonstrating technical feasibility, this approach does not provide flexibility and adaptability to a wide variety of building footprints. Consequently, each system has to be developed for a specific building project, resulting in excessive costs. This paper proposes a modular push-up gantry tower crane system for automated construction and presents the design development of the system's core module as a construction robot prototype, using a physical modeling approach. The proposed system is comprised of core modules and connectors, and can be configured for adaptation to a wide variety of building footprints. The overall research project plan for the proposed system is presented and the scope of this project phase is defined. The design and development of the prototype core module are described. The conclusions and recommendations of the study are presented to show the validity of a prototype model-based approach for research and development in construction automation, and its usefulness as a teaching and learning tool.

关键词： Modular construction

来源：评论

学校读者我要写书评

暂无评论

Dynamic health level 7 packetizer for on-the-fly integrated healthcare enterprises (IHE) in disaster zones

Dynamic health level 7 packetizer for on-the-fly integrated ...

引用

19th International Conference on Neural information Processing, ICONIP 2012

作者： Chaudhry, Junaid Ahsenali Qidwai, Uvais A. Malrey, Lee Department of Computer Science and Engineering Qatar University Doha Qatar Center for Advanced Image and Information Technology School of Electronics and Information Engineering ChonBuk National University ChonBuk Korea Republic of

ISBN: (纸本)9783642344749

The advent of standards i.e. IEEE 11073 for device connectivity, Health Level 7 (HL7) etc. provide an assimilating platform for medical devices and seamless data flow among modern Health information Systems (HIS). However, to date, these standards are either not widely accepted or lack the support of 'on-the-fly' formation of HIS in a disaster zone. In a situation where hybrid medical (standard compliant and the otherwise) devices are in operation, incomplete and ambiguous data can lead to fatal misconduct on the part of technology. In order to eliminate this problem, we propose an HL7 compliant policy engine in support of HL7 Reference information Model (RIM). The policy engine is used for rich policy expression, vivid XML policies for HL7 compliant devices, and performance enhancement. Due to dynamic nature of on-the-fly HIS in a disaster zone, it is very costly to manage the change and keep track of authentic HIS devices. We use Java language to extend the HL7 Reference information Model (RIM) in order to create/modify policies instead of scripting languages to overcome the complexity and interoperability. © 2012 Springer-Verlag.

关键词： information theory

来源：评论

学校读者我要写书评

暂无评论

Runge-kutta(5,5) methods for robot arm & initial value problem

International Journal of Control and Automation

引用

International Journal of Control and Automation 2013年第3期6卷 329-336页

作者： Senthilkumar, Sukumar Lee, Malrey Kwon, Tae-Kyu Center for Advanced Image and Information Technology School of Electronics and Information Engineering Chon Buk National University 664-14 1Ga Deokjin-Dong Jeonju Chon Buk 561-756 Korea Republic of Division of Biomedical Engineering College of Engineering Chonbuk National University Korea Republic of

An ultimate aim of this present paper is to solve application problem such as robot arm and initial value problems by applying Runge-Kutta fifth order five stage numerical techniques. The calculated output for robot a... 详细信息

关键词： Numerical methods

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：