检索结果-南通市图书馆

A Deep Learning Hierarchical Ensemble for Remote Sensing Image Classification

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2022年第8期72卷 2649-2663页

作者： Seung-Yeon Hwang jeong-Joon kim Department of Computer Engineering Anyang UniversityAnyang-si14028Korea Department of ICT Convergence Engineering Anyang UniversityAnyang-si14028Korea

Artificial intelligence,which has recently emerged with the rapid development of information technology,is drawing attention as a tool for solving various problems demanded by society and *** particular,convolutional neural networks(CNNs),a type of deep learning technology,are highlighted in computer vision fields,such as image classification and recognition and object *** these CNN models requires a large amount of data,and a lack of data can lead to performance degradation problems due to *** CNN architecture development and optimization studies become active,ensemble techniques have emerged to perform image classification by combining features extracted from multiple CNN *** this study,data augmentation and contour image extraction were performed to overcome the data shortage *** addition,we propose a hierarchical ensemble technique to achieve high image classification accuracy,even if trained from a small amount of ***,we trained the UCMerced land use dataset and the contour images for each image on pretrained VGGNet,GoogLeNet,ResNet,DenseNet,and *** then apply a hierarchical ensemble technique to the number of cases in which each model can be *** experiments were performed in cases where the proportion of training datasets was 30%,50%,and 70%,resulting in a performance improvement of up to 4.68%compared to the average accuracy of the entire model.

关键词： Image classification deep learning CNNs hierarchical ensemble UC-Merced land use dataset contour image

ON TRANSmiSSION PROBLEM FOR VISCOELASTIC WAVE EQUATION WITH A LOCALIZED A NONLINEAR DISSIPATION

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Acta Mathematica Scientia 2013年第2期33卷 362-374页

作者： jeong Ja BAE Seong Sik kim Department of Mathematics Dongeui UniversityPusan 614-714Korea

In this article, we consider the global existence and decay rates of solutions for the transmission problem of Kirchhoff type wave equations consisting of two physically different types of materials, one component being a Kirchhoff type wave equation with time dependent localized dissipation which is effective only on a neighborhood of certain part of boundary, while the other being a Kirchhoff type viscoelastic wave equation with nonlinear memory

关键词： Existence of solution uniform decay transmission problem boundary valueproblem localized dissipation

A Delayed Stochastic Volatility Correction to the Constant Elasticity of Variance Model

在线全文

学校读者我要写书评

暂无评论

Acta Mathematicae Applicatae Sinica 2016年第3期32卷 611-622页

作者： min-Ku LEE jeong-Hoon kim Department of Mathematics Kunsan National University Department of Mathematics Yonsei University

The Black-Scholes model does not account non-Markovian property and volatility smile or skew although asset price might depend on the past movement of the asset price and real market data can find a non-flat structure of the implied volatility surface. So, in this paper, we formulate an underlying asset model by adding a delayed structure to the constant elasticity of variance （CEV） model that is one of renowned alternative models resolving the geometric issue. However, it is still one factor volatility model which usually does not capture full dynamics of the volatility showing discrepancy between its predicted price and market price for certain range of options. Based on this observation we combine a stochastic volatility factor with the delayed CEV structure and develop a delayed hybrid model of stochastic and local volatilities. Using both a martingale approach and a singular perturbation method, we demonstrate the delayed CEV correction effects on the European vanilla option price under this hybrid volatility model as a direct extension of our previous work [12].

关键词： constant elasticity variance , delay stochastic volatility martingale option pricing

Multi-View Multi-Modal Head-Gaze Estimation for Advanced Indoor User Interaction

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2022年第3期70卷 5107-5132页

作者： Jung-Hwa kim Jin-Woo jeong Department of Computer Engineering Kumoh National Institute of TechnologyGumi39177Korea Department of Data Science Seoul National University of Science and TechnologySeoul01811Kore

Gaze estimation is one of the most promising technologies for supporting indoor monitoring and interaction ***,previous gaze estimation techniques generally work only in a controlled laboratory environment because they require a number of high-resolution eye *** makes them unsuitable for welfare and healthcare facilities with the following challenging characteristics:1)users’continuous movements,2)various lighting conditions,and 3)a limited amount of available *** address these issues,we introduce a multi-view multi-modal head-gaze estimation system that translates the user’s head orientation into the gaze *** proposed system captures the user using multiple cameras with depth and infrared modalities to train more robust gaze estimators under the aforementioned *** this end,we implemented a deep learning pipeline that can handle different types and combinations of *** proposed system was evaluated using the data collected from 10 volunteer participants to analyze how the use of single/multiple cameras and modalities affect the performance of head-gaze *** various experiments,we found that 1)an infrared-modality provides more useful features than a depth-modality,2)multi-view multi-modal approaches provide better accuracy than singleview single-modal approaches,and 3)the proposed estimators achieve a high inference efficiency that can be used in real-time applications.

关键词： Human-computer interaction deep learning head-gaze estimation indoor monitoring

Data Augmentation Using Contour Image for Convolutional Neural Network

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2023年第6期75卷 4669-4680页

作者： Seung-Yeon Hwang jeong-Joon kim Department of Computer Engineering Anyang UniversityAnyang-si14058Korea Department of ICT Convergence Engineering Anyang UniversityAnyang-si14058Korea

With the development of artificial intelligence-related technologies such as deep learning,various organizations,including the government,are making various efforts to generate and manage big data for use in artificial ***,it is difficult to acquire big data due to various social problems and restrictions such as personal information *** are many problems in introducing technology in fields that do not have enough training data necessary to apply deep learning ***,this study proposes a mixed contour data augmentation technique,which is a data augmentation technique using contour images,to solve a problem caused by a lack of ***,a famous convolutional neural network(CNN)architecture,and CIFAR-10,a benchmark data set,are used for experimental performance evaluation to prove the superiority of the proposed *** to prove that high performance improvement can be achieved even with a small training dataset,the ratio of the training dataset was divided into 70%,50%,and 30%for comparative *** a result of applying the mixed contour data augmentation technique,it was possible to achieve a classification accuracy improvement of up to 4.64%and high accuracy even with a small amount of data *** addition,it is expected that the mixed contour data augmentation technique can be applied in various fields by proving the excellence of the proposed data augmentation technique using benchmark datasets.

关键词： Data augmentation image classification deep learning convolutional neural network mixed contour image benchmark dataset

Antioxidant and anticancer activity of Artemisia princeps *** extract in HepG2 and Hep3B hepatocellular carcinoma cells

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Cancer Research 2013年第5期25卷 536-543页

作者： Eun-jeong Choi Gun-Hee kim Plant Resources Research Institute Duksung Women's University

Objective：The aim of the present study was to investigate antioxidant and the anticancerigen activity of a methanol extract from Artemisia princeps *** （APME）,a well-known traditional herbal medicine in Asia,in hepatocellular cancer ***：To evaluate the antioxidant activity of APME,reactive oxygen species （ROS） and the antioxidant enzymes,superoxide dismutase （SOD） and catalase were investigated in HepG2 cells exposed to APME （5,100,and 200 μg/mL） for 72 ***,to evaluate the anticancer activity of APME,we investigated the proliferation and apoptosis induction of HepG2 and Hep3B cells exposed to APME （1-200 μg/mL） for 24,48,and 72 ***：APME dose-dependently reduced the generation of ROS in the presence of H2O2 compared with control ***,it increased catalase and SOD ***,APME inhibited cell proliferation in a dose-and time-dependcnt manner,but at concentrations lower than 100 μg/mL,the inhibition was less dose-dependent than ***2 and Hep3B cells exposed to 5,100,and 200 μg/mL APME for 72 h underwent cell cycle arrest and *** to APME resulted in a significant increase in the number of cells in G1 phase and a decrease in the G2/M phase cell *** addition,APME induced P53 expression of HepG2 cells in a dose-dependent manner,and played a role in the downregulation of Bcl-2 and upregulation of Bax in both HepG2 and Hep3B ***：These results indicate the potential role of APME as an antioxidant and anticancerigen agent in hepatocarcinoma cell lines.

关键词： Artemisia princeps var.orientalis antioxidant anticancer hepatocellular carcinoma

Brain-derived neurotrophic factor mediates macrophage migration inhibitory factor to protect neurons against oxygen-glucose deprivation

在线全文

学校读者我要写书评

暂无评论

Neural Regeneration Research 2020年第8期15卷 1483-1489页

作者： Su Hwan Bae mi Ran Yoo Ye Yeong kim In Kyung Hong mi Hee kim Seung Hak Lee Dae Yul kim Department of Rehabilitation Medicine Asan Medical CenterUniversity of Ulsan College of MedicineSeoulRepublic of Korea Asan Institute for Life Sciences Asan Medical CenterUniversity of Ulsan College of MedicineSeoulRepublic of Korea

Macrophage migration inhibitory factor(miF)is a chemokine that plays an essential role in immune system *** studies suggested that miF protects neurons in ischemic ***,few studies are reported on the role of miF in neurological recovery after ischemic *** purpose of this study is to identify the molecular mechanism of neuroprotection mediated by *** neuroblastoma cells were incubated in Dulbecco’s modified Eagle’s medium under oxygen-glucose deprivation(OGD)for 4 hours and then returned to normal aerobic environment for reperfusion(OGD/R).30 ng/mL miF recombinant(30 ng/mL)or ISO-1(miF antagonist;50μM)was administered to human neuroblastoma *** cell cultures were assigned to one of four groups:control,OGD/R,OGD/R with miF,OGD/R with *** viability was analyzed using WST-1 *** levels of brain-derived neurotrophic factor(BDNF),microtubule-associated protein 2(MAP2),Caspase-3,Bcl2,and Bax were detected by western blot assay and immunocytochemistry in each group to measure apoptotic ***-1 assay results revealed that compared to the OGD/R group,cell survival rate was significantly higher in the OGD/R with miF group and lower in the OGD/R with ISO-1 *** blot assay and immunocytochemistry results revealed that expression levels of BDNF,Bcl2,and MAP2 were significantly higher,and expression levels of Caspase-3 and Bax were significantly lower in the miF group than in the OGD/R *** levels of BDNF,Bcl2,and MAP2 were significantly lower,and expression levels of Caspase-3 and Bax were significantly higher in the ISO-1 group than in the OGD/R *** administration promoted neuronal cell survival and induced high expression levels of BDNF,MAP2,and Bcl2(anti-apoptosis)and low expression levels of Caspase-3 and Bax(pro-apoptosis)in an OGD/R *** results suggest that miF administration is effective for inducing expression of BDNF and leads to neuroprotection of neuronal cells

关键词： apoptosis brain-derived neurotrophic factor hypoxia in vitro ischemic stroke macrophage migration inhibitory factor nerve regeneration neuroprotective effect reperfusion

A Universal Activation Function for Deep Learning

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2023年第5期75卷 3553-3569页

作者： Seung-Yeon Hwang jeong-Joon kim Department of Computer Engineering Anyang UniversityAnyang-si14028Korea Department of ICT Convergence Engineering Anyang UniversityAnyang-si14028Korea

Recently,deep learning has achieved remarkable results in fields that require human cognitive ability,learning ability,and reasoning *** functions are very important because they provide the ability of artificial neural networks to learn complex patterns through *** activation functions are being studied to solve problems such as vanishing gradients and dying nodes that may occur in the deep learning ***,it takes a lot of time and effort for researchers to use the existing activation function in their ***,in this paper,we propose a universal activation function(UA)so that researchers can easily create and apply various activation functions and improve the performance of neural *** can generate new types of activation functions as well as functions like traditional activation functions by properly adjusting three *** famous Convolutional Neural Network(CNN)and benchmark datasetwere used to evaluate the experimental performance of the UA proposed in this *** compared the performance of the artificial neural network to which the traditional activation function is applied and the artificial neural network to which theUA is *** addition,we evaluated the performance of the new activation function generated by adjusting the hyperparameters of *** experimental performance evaluation results showed that the classification performance of CNNs improved by up to 5%through the UA,although most of them showed similar performance to the traditional activation function.

关键词： Deep learning activation function convolutional neural network benchmark datasets universal activation function

Three-Tesla magnetic resonance elastography for hepatic fibrosis:Comparison with diffusion-weighted imaging and gadoxetic acid-enhanced magnetic resonance imaging

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

World Journal of Gastroenterology 2014年第46期20卷 17558-17567页

作者： Hee Sun Park Young Jun kim mi Hye Yu Won Hyeok Choe Sung Il Jung Hae jeong Jeon Department of Radiology Konkuk University School of MedicineSeoul 143-729South Korea Digestive Disease Center Konkuk University School of MedicineSeoul 143-729South Korea

AIM: To evaluate the feasibility of 3-Tesla magnetic resonance elastography (MRE) for hepatic fibrosis and to compare that with diffusion-weighted imaging (DWI) and gadoxetic acid-enhanced magnetic resonance (MR) imag... 详细信息

关键词： Magnetic resonance elastography Hepatic fibrosis Diffusion weighted imaging Gadoxetic acid enhanced magnetic resonance imaging Serum markers