检索结果-内蒙古大学图书馆

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 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

Data-consistent Unsupervised Diffusion Model for Metal Artifact Reduction

Data-consistent Unsupervised Diffusion Model for Metal Artif...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Tong, Zhan Wu, Zhan Yang, Yang Mao, Weilong Wang, Shijie Li, Yinsheng Chen, Yang Southeast University Laboratory of Image Science and Technology Nanjing210096 China Southeast University Ministry of Education Key Laboratory of Computer Network and Information Integration Nanjing210096 China Chinese Academy of Sciences Research Center for Medical Artificial Intelligence Shenzhen Institutes of Advanced Technology Shenzhen518055 China School of Computer Science and Engineering Key Lab. of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing The Laboratory of Image Science and Technology Nanjing210096 China

ISBN: (纸本)9798350337488

Computed Tomography (CT) is an imaging technique widely used in clinical diagnosis. However, high-attenuation metallic implants result in the obstruction of low-energy Xrays and further lead to metal artifacts in the reconstructed CT images. Deep supervised model-based metal artifact reduction(MAR) approaches are limited in clinical applications due to the difficulty in obtaining paired artifact-affected and artifactfree data. Furthermore, these model-based methods lack the consideration of data consistency in the sinogram-domain to perform exact metal trace inpainting. To address these challenges, we propose a Data-consistent unsupErVised diffusiOn model for meTal artifact rEDuction, called DEVOTED-Net. First, DEVOTED-Net leverages prior knowledge to guide the conditional diffusion model for fine-grained metal trace inpainting. Second, an unsupervised MAR framework is designed in the reverse process for the unknown metal traces restoration in the sinogram domain. Third, to further enhance the sinogram-domain data consistency, physics-based consistency constraint loss including conjugateray consistency loss and accumulation-ray consistency loss is designed. Extensive experiments are carried out to verify the performance of our algorithm on the publicly available dataset and clinical experimental dataset. This efficient, accurate, and reliable MAR approach holds great potential in clinics. © 2023 IEEE.

关键词： computed tomography deep unsupervised learning denoising diffusion probabilistic model Metal artifact reduction physics-based consistency constraint

来源：评论

学校读者我要写书评

暂无评论

Design of AWG-based WDM-PON architecture with multicast capability

Design of AWG-based WDM-PON architecture with multicast capa...

引用

IEEE Conference on Computer Communications Workshops, INFOCOM Wksps

作者： Kyeong-Eun Han Won-Hyuk Yang Kyoung-Min Yoo Young-Chon Kim Research Center for Advanced Image and Information Technology Chonbuk National University Jeonju Korea Department of Computer Engineering Chonbuk National University Jeonju Korea

Recently, the triple play service (TPS) has been considered to be a promising business model or application. Thus, the capability for multicast transmission has become a very important requirement for access networks. However, unlike existing passive optical networks (PONs), the arrayed-waveguide grating (AWG) based wavelength-division multiplexing (WDM)-PON does not have multicast capability because it is a P2P network for the downstream direction, from optical line terminal (OLT) to optical network units (ONUs). In this paper, AWG- based WDM-PON architecture with multicast capability is proposed. It provides high scalability and single copy broadcast (SCB) capability by employing multi-stage AWGs at a remote node (RN) and a multi-wavelength converter (MWC) at OLT. The performance of the proposed architecture is evaluated in terms of cost, scalability, link capacity and bandwidth per user, in both upstream and downstream directions, by comparison with other multicasting architectures.

关键词： Passive optical networks Optical arrays Optical network units Scalability Arrayed waveguide gratings Wavelength division multiplexing Optical fiber networks Broadcasting Costs Bandwidth

来源：评论

学校读者我要写书评

暂无评论

Deep learninig of EEG signals for emotion recognition

Deep learninig of EEG signals for emotion recognition

引用

IEEE International Conference on Multimedia and Expo Workshops (ICMEW)

作者： Yongbin Gao Hyo Jong Lee Raja Majid Mehmood Division of Computer Science and Engineering Chonbuk National University Jeonju Korea Center for Advanced Image and Information Technology Chonbuk National University Jeonju Korea

Emotion recognition is an important task for computer to understand the human status in brain computer interface (BCI) systems. It is difficult to perceive the emotion of some disabled people through their facial expression, such as functional autism patient. EEG signal provides us a non-invasive way to recognize the emotion of these disable people through EEG headset electrodes placed on their scalp. In this paper, we propose a deep learning algorithm to simultaneously learn the features and classify the emotions of EEG signals. It differs from the conventional methods as we apply deep learning on the raw signal without explicit hand-crafted feature extraction. Because the EEG signal has subject dependency, it is better to train the emotion model subject-wise, while there is not much epochs available for each subject. Deep learning algorithm provides a solution with a pre-training way using three layers of restricted Boltzmann machines (RBMs). Thus, we can use epochs of all subjects to pre-training the deep network, and use back-propagation to fine tuning the network subject by subject. Experiment results show that our proposed framework achieves better recognition accuracy than conventional algorithms.

关键词： Electroencephalography Support vector machines Brain modeling Feature extraction Biomedical imaging image recognition Artificial neural networks

来源：评论

学校读者我要写书评

暂无评论

The luminance resolution characteristics of multi-primary color display

Shapu Giho/Sharp Technical Journal

引用

Shapu Giho/Sharp Technical Journal 2015年第108期 26-35页

作者： Yoshida, Yasuhiro Nakagawa, Shinji Yoshida, Akiko Yoshiyama, Kazuyoshi Furukawa, Hiroyuki A1288 Project Team China Advanced Display Systems Development Center Digital Information Appliance Division China Telecommunication and Image Technology Laboratories Corporate Research and Development Division China

In this paper, we analyze the resolution characteristics of multi-primary color (MPC) display systems. We demonstrate that four-primary (4 PC) displays can increase the effective resolution for achromatic images in the luminance domain by a factor of two as compared to conventional RGB-based displays with MPC-specialized sub-pixel rendering, which we propose in this paper. Five- and six-primary color (5PC and 6PC) display system can reproduce denser luminance data than conventional RGB-based display systems and solve a problem of MPC displays, viz. increase of production costs and decrease of the aperture ratio caused by increasing the number of sub-pixels in one pixel. This is an essential advantage of MPC display systems, which is related to the combination of our proposed color filter architecture and image processing: so, we propose a completely new advantage of MPC display systems in addition to their well-known capabilities of color reproduction and power-saving.

关键词： Luminance

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Logic Decision Making for an Intelligent Home Healthcare System

Fuzzy Logic Decision Making for an Intelligent Home Healthca...

引用

International Conference on Future information technology (FutureTech)

作者： Thomas M. Gatton Malrey Lee School of Engineering and Technology National University San Diego CA USA Research Center for Advanced Image and Information Technology School of Electronics & Information Engineering Chonbuk National University of Korea Jeonju Gyeongbuk South Korea

The increasing trends of an aging population and the occurrence of chronic diseases, such as diabetes and dementia, present serious near-term problems in providing suitable healthcare within the existing medical system infrastructure. With the increasing number of patients, the existing healthcare systems will be overloaded and unable to effectively process the rising demand and an effective solution must be developed for the real-time response requirements of critical health situations. This paper proposes a fuzzy logic based decision making system for home health care. The proposed system can provide an innovative resource and a supplement for the existing healthcare systems. The proposed home healthcare system is implemented for diabetes management and decision making. An analysis and evaluation of the system performance are presented along with the conclusions of the research.

关键词： Fuzzy logic Decision making Intelligent systems Medical services Diabetes Aging Diseases Dementia Real time systems Performance analysis

来源：评论

学校读者我要写书评

暂无评论

AN IKONOS image FUSION PROCESS USING SUPPORT VALUE TRANSFORM

AN IKONOS IMAGE FUSION PROCESS USING SUPPORT VALUE TRANSFORM

引用

2007 International Conference on Machine Learning and Cybernetics(IEEE第六届机器学习与控制论国际会议)

作者： SHENG ZHENG WENZHONG SHI JIAN LIU Institute of Intelligent Vision and Image Information Best College of Electrical Engineering and In Advanced Research Center for Spatial Information Technology Department of Land Surveying and Geo-In State Education Commission Key Lab for Image Processing and Intelligent Control HUST Wuhan 430074

Panchromatic (Pan)-sharpening of multispectral (MS) bands is an important technique in various applications of satellite remote *** this paper, we apply the support value transform (SVT) to Ikonos image *** fused saliency features are represented by support values and extracted by *** low-resolution MS bands are resampled to the fine scale of the Pan image and sharpened by injecting the detailed features extracted from the high-resolution Pan *** fusing results on Ikonos MS + Pan data demonstrate that the proposed image fusion method is effective and efficient.

关键词： Mapped least squares support vector machine (mapped LS-SVM) support value transform (SVT) Ikonos image fusion

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

Experiments in fuzzy multi-robot security system

Experiments in fuzzy multi-robot security system

引用

2016 International Conference on Artificial Intelligence, ICAI 2016 - WORLDCOMP 2016

作者： Tarokh, Mahmoud Lee, Malrey Chae, Hongseok An, Jeongran Jeong, Gisung Yun, Dukmo Department of Computer Science San Diego State University San DiegoCA92128-7720 United States 561-756 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 Korea Republic of Department of Fire Service Administration WonKwang University Korea Republic of

ISBN: (纸本)1601324383

This paper discusses a distributed fuzzy system for a set of robots engaged in securing inside or outside of a building and detecting any intruder. Each robot receives information from other robots but makes its own decision to engage in a particular activity such as patrol, inspection, intruder chasing. This decision is to best for overall objectives of the team and also to satisfy its own constraints such as its existing battery power. The performance of the system is investigated under various scenarios. CSREA Press ©.

关键词： Fuzzy logic

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：