检索结果-南通市图书馆

Deep Learning-Based Action Classification Using One-Shot Object Detection

Computers, Materials & Continua 2023年第8期76卷 1343-1359页

作者： hyun yoo Seo-El Lee Kyungyong Chung Contents Convergence Software Research Institute Kyonggi UniversitySuwon-si16227Korea Department of Public Safety Bigdata Kyonggi UniversitySuwon-si16227Korea Division of Computer Science and Engineering Kyonggi UniversitySuwon-si16227Korea

Deep learning-based action classification technology has been applied to various fields,such as social safety,medical services,and *** an action on a practical level requires tracking multiple human bodies in an image in real-time and simultaneously classifying their *** are various related studies on the real-time classification of actions in an ***,existing deep learning-based action classification models have prolonged response speeds,so there is a limit to real-time *** addition,it has low accuracy of action of each object ifmultiple objects appear in the ***,it needs to be improved since it has a memory overhead in processing image *** learning-based action classification using one-shot object detection is proposed to overcome the limitations of multiframe-based analysis *** proposed method uses a one-shot object detection model and a multi-object tracking algorithm to detect and track multiple objects in the ***,a deep learning-based pattern classification model is used to classify the body action of the object in the image by reducing the data for each object to an action *** to the existing studies,the constructed model shows higher accuracy of 74.95%,and in terms of speed,it offered better performance than the current studies at 0.234 s per *** proposed model makes it possible to classify some actions only through action vector learning without additional image learning because of the vector learning feature of the posterior neural ***,it is expected to contribute significantly to commercializing realistic streaming data analysis technologies,such as CCTV.

关键词： Human action classification artificial intelligence deep neural network pattern analysis video analysis

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Pharmacokinetics and tissue distribution of a novel PDE5 inhibitor,SK-3530,in rats

引用

Acta Pharmacologica Sinica 2007年第8期28卷 1247-1253页

作者： Hye-hyun yoo Nam-sun KIM Guang-jin Im Dong-hyun KIM Bioanalysis and Biotransformation Research Center Korea Institute of Science & Technology Seoul 136-791Korea Life Science RD Center SK ChemicalsGyeonggi-do 440-300Korea

Aim:To investigate the pharmacokinetic profile and tissue distribution of a novelphosphodiesterase type 5 inhibitor,5-ethyl-2-{5-[4-（2-hydroxy-ethyl）-piperazine-1-sulfonyl]-2-propoxy-phenyl}-7-propyl-3,5-dihydro-pyrrolo（3,2-d）pyrimidin-4-one（SK-3530）,in rats after administration of the14C-labeled ***:The pharmacokinetic parameters of SK-3530 were measured based on the totalradioactivity and parent SK-3530 concentration in rat plasma after intravenousand oral *** tissue distribution of total radioactivity after a singleoral administration of[14C]SK-3530 at a dose of 40 mg/kg was *** protein binding rates of SK-3530 were assessed by in vitro and ex ***:The total radioactivity profiles showed linear *** maximum plasma concentration and area under the curve of the parent SK3530were 10%-20% compared to those of the total *** the oral admin-istration of[14C]SK-3530,the radioactivity was widely distributed in all tissues,and the tissue/plasma ratio of the radioactivity 1 h after administration was calcu-lated as 0.5-2.6 with the exception of excretory organs.A relatively high penetra-tion was shown in the adrenal glands,liver,and *** vitro and ex vivo plasmaprotein binding assay by ultrafiltration showed a considerably high binding rateof more than 97%.Conclusion:SK-3530 was relatively well absorbed in the gas-trointestinal tract and showed linear pharmacokinetics over the investigated ***-3530 had low oral bioavailability due to a high,first-pass metabolism.

关键词： SK-3530 PDE5 inhibitor pharmacokinetics tissue distribution rats

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Multiple-Object Tracking Using Histogram Stamp Extraction in CCTV Environments

引用

Computers, Materials & Continua 2023年第12期77卷 3619-3635页

作者： Ye-Yeon Kang Geon Park hyun yoo Kyungyong Chung Division of AI Computer Science and Engineering Kyonggi UniversitySuwon16227Korea Contents Convergence Software Research Institute Kyonggi UniversitySuwon16227Korea

Object tracking,an important technology in the field of image processing and computer vision,is used to continuously track a specific object or person in an *** technology may be effective in identifying the same person within one image,but it has limitations in handling multiple images owing to the difficulty in identifying whether the object appearing in other images is the *** tracking the same object using two or more images,there must be a way to determine that objects existing in different images are the same ***,this paper attempts to determine the same object present in different images using color information among the unique information of the ***,this study proposes a multiple-object-tracking method using histogram stamp extraction in closed-circuit television *** proposed method determines the presence or absence of a target object in an image by comparing the similarity between the image containing the target object and other *** this end,a unique color value of the target object is extracted based on its color distribution in the image using three methods:mean,mode,and interquartile *** Top-N accuracy method is used to analyze the accuracy of each method,and the results show that the mean method had an accuracy of 93.5%(Top-2).Furthermore,the positive prediction value experimental results show that the accuracy of the mean method was 65.7%.As a result of the analysis,it is possible to detect and track the same object present in different images using the unique color of the *** the results,it is possible to track the same object that can minimize manpower without using personal information when detecting objects in different *** the last response speed experiment,it was shown that when the mean was used,the color extraction of the object was possible in real time with 0.016954 *** this,it is possible to detect and track the same object in real time when using the proposed

关键词： Data mining deep learning object detection object tracking real-time object detection multiple object image processing

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Defect Detection Model Using Time Series Data Augmentation and Transformation

引用

Computers, Materials & Continua 2024年第2期78卷 1713-1730页

作者： Gyu-Il Kim hyun yoo Han-Jin Cho Kyungyong Chung Department of Computer Science Kyonggi UniversitySuwon-si16227Korea Contents Convergence Software Research Institue Kyonggi UniversitySuwon-si16227Korea Department of Energy IT Engineering Far East UniversityEumsung-gun27601Korea Division of AI Computer Science and Engineering Kyonggi UniversitySuwon-si16227Korea

Time-series data provide important information in many fields,and their processing and analysis have been the focus of much ***,detecting anomalies is very difficult due to data imbalance,temporal dependence,and ***,methodologies for data augmentation and conversion of time series data into images for analysis have been *** paper proposes a fault detection model that uses time series data augmentation and transformation to address the problems of data imbalance,temporal dependence,and robustness to *** method of data augmentation is set as the addition of *** involves adding Gaussian noise,with the noise level set to 0.002,to maximize the generalization performance of the *** addition,we use the Markov Transition Field(MTF)method to effectively visualize the dynamic transitions of the data while converting the time series data into *** enables the identification of patterns in time series data and assists in capturing the sequential dependencies of the *** anomaly detection,the PatchCore model is applied to show excellent performance,and the detected anomaly areas are represented as heat *** allows for the detection of anomalies,and by applying an anomaly map to the original image,it is possible to capture the areas where anomalies *** performance evaluation shows that both F1-score and Accuracy are high when time series data is converted to ***,when processed as images rather than as time series data,there was a significant reduction in both the size of the data and the training *** proposed method can provide an important springboard for research in the field of anomaly detection using time series ***,it helps solve problems such as analyzing complex patterns in data lightweight.

关键词： Defect detection time series deep learning data augmentation data transformation

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Time-Frequency Characteristics of the Relationships Between Tropical Indo-Pacific SSTs

引用

Advances in Atmospheric Sciences 2007年第3期24卷 343-359页

作者： Song YANG 丁晓利郑大伟 Soo-hyun yoo NOAA ＇s Climate Prediction Center 5200 Auth Road Camp Springs MD 20746 USA Department of Land Surveying and Geo-Informatics Hong Kong Polytechnic University Center for Astrogeodynamics Research Shanghai Astronomical Observatory Chinese Academy of Sciences Shanghai 200030 RSIS/Climate Prediction Center 5200 Auth Road Camp Springs MD 20746 USA

In this study, several advanced analysis methods are applied to understand the relationships between the Nino-3.4 sea surface temperatures （SST） and the SSTs related to the tropical Indian Ocean Dipole （IOD）. By analyzing a long data record, the authors focus on the time-frequency characteristics of these relationships, and of the structure of IOD. They also focus on the seasonal dependence of those characteristics in both time and frequency domains. Among the Nino-3.4 SST, IOD, and SSTs over the tropical western Indian Ocean （WIO） and eastern Indian Ocean （EIO）, the WIO SST has the strongest annual and semiannual oscillations. While the Nino-3.4 SST has large inter-annual variability that is only second to its annual variability, the IOD is characterized by the largest semiannual oscillation, which is even stronger than its annual oscillation. The IOD is strongly and stably related to the EIO SST in a wide range of frequency bands and in all seasons. However, it is less significantly related to the WIO SST in the boreal winter and spring. There exists a generally weak and unstable relationship between the WIO and EIO SSTs, especially in the biennial and higher frequency bands. The relationship is especially weak in summer and fall, when IOD is apparent, but appears highly positive in winter and spring, when the IOD is unimportantly weak and even disappears. This feature reflects a caution in the definition and application of IOD. The Nino-3.4 SST has a strong positive relationship with the WIO SST in all seasons, mainly in the biennial and longer frequency bands. However, it shows no significant relationship with the EIO SST in summer and fall, and with IOD in winter and spring.

关键词： Indian Ocean dipole ENSO time-frequency relationship coherence analysis

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Abnormal Behavior Detection Using Deep-Learning-Based Video Data Structuring

引用

Intelligent Automation & Soft Computing 2023年第8期37卷 2371-2386页

作者： Min-Jeong Kim Byeong-Uk Jeon hyun yoo Kyungyong Chung Department of Computer Science Kyonggi UniversitySuwon-si16227Gyeonggi-doKorea Contents Convergence Software Research Institute Kyonggi UniversitySuwon-si16227Gyeonggi-doKorea Division of AI Computer Science and Engineering Kyonggi UniversitySuwon-si16227Gyeonggi-doKorea

With the increasing number of digital devices generating a vast amount of video data,the recognition of abnormal image patterns has become more ***,it is necessary to develop a method that achieves this task using object and behavior information within video *** methods for detecting abnormal behaviors only focus on simple motions,therefore they cannot determine the overall behavior occurring throughout a *** this study,an abnormal behavior detection method that uses deep learning(DL)-based video-data structuring is *** and motions are first extracted from continuous images by combining existing DL-based image analysis *** weight of the continuous data pattern is then analyzed through data structuring to classify the overall *** performance of the proposed method was evaluated using varying parameter settings,such as the size of the action clip and interval between action *** model achieved an accuracy of 0.9817,indicating excellent ***,we conclude that the proposed data structuring method is useful in detecting and classifying abnormal behaviors.

关键词： Deep learning object detection abnormal behavior recognition classification data structuring

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

SlowFast Based Real-Time Human Motion Recognition with Action Localization

引用

Computer Systems Science & Engineering 2023年第11期47卷 2135-2152页

作者： Gyu-Il Kim hyun yoo Kyungyong Chung Department of Computer Science Kyonggi UniversitySuwon16227Korea Contents Convergence Software Research Institute Kyonggi UniversitySuwon16227Korea Division of AI Computer Science and Engineering Kyonggi UniversitySuwon16227Korea

Artificial intelligence is increasingly being applied in the field of video analysis,particularly in the area of public safety where video surveillance equipment such as closed-circuit television(CCTV)is used and automated analysis of video information is ***,various issues such as data size limitations and low processing speeds make real-time extraction of video data *** analysis technology applies object classification,detection,and relationship analysis to continuous 2D frame data,and the various meanings within the video are thus analyzed based on the extracted basic *** recognition is key in this *** recognition is a challenging field that analyzes human body movements,requiring the interpretation of complex movements of human joints and the relationships between various *** deep learning-based human skeleton detection algorithm is a representative motion recognition ***,motion analysis models such as the SlowFast network algorithm,have also been developed with excellent ***,these models do not operate properly in most wide-angle video environments outdoors,displaying low response speed,as expected from motion classification extraction in environments associated with high-resolution *** proposed method achieves high level of extraction and accuracy by improving SlowFast’s input data preprocessing and data structure *** input data are preprocessed through object tracking and background removal using YOLO and DeepSORT.A higher performance than that of a single model is achieved by improving the existing SlowFast’s data structure into a frame unit *** on the confusion matrix,accuracies of 70.16%and 70.74%were obtained for the existing SlowFast and proposed model,respectively,indicating a 0.58%increase in *** detection,based on behavioral classification,the existing SlowFast detected 2,341,164 cases,whereas the proposed model detected 3,11

关键词： Artificial intelligence convolutional neural network video analysis human action recognition skeleton extraction

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Finite-size correction for slab supercell calculations of materials with spontaneous polarization

引用

npj Computational Materials 2021年第1期7卷 520-528页

作者： Su-hyun yoo Mira Todorova Darshana Wickramaratne Leigh Weston Chris GVan de Walle Jörg Neugebauer Department of Computational Materials Design Max-Planck-Institut für Eisenforschung GmbHDüsseldorfGermany Materials Department University of California Santa BarbaraSanta BarbaraCAUSA Center for Computational Materials Science US Naval Research LaboratoryWashingtonDCUSA

The repeated slab approach has become a de facto standard to accurately describe surface properties of materials by density functional theory calculations with periodic boundary *** materials exhibiting spontaneous polarization,we show that the conventional scheme of passivation with pseudo hydrogen is unable to realize a charge-neutral *** presence of a net surface charge induces via Gauss’s law a macroscopic electric field through the slab and results in poor size convergence with respect to the thickness of the *** propose a modified passivation method that accounts for the effect of spontaneous polarization,describes the correct bulk limits and boosts convergence with respect to slab *** robustness,reliability,and superior convergence of energetics and electronic structure achieved by the proposed method are demonstrated using the example of polar ZnO surfaces.

关键词： surface convergence size

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Dietary fat-associated osteoarthritic chondrocytes gain resistance to lipotoxicity through PKCK2/STAMP2/FSP27

引用

Bone Research 2018年第3期6卷 238-251页

作者： Sung Won Lee Jee hyun Rho Sang Yeob Lee Won Tae Chung yoo Jin Oh Jung Ha Kim Seung Hee yoo Woo Young Kwon Ju Yong Bae Su Young Seo Hokeun Sun Hye Young Kim Young hyun yoo Department of Rheumatology Dong-A University College of Medicine Department of Anatomy and Cell Biology Dong-A University College of Medicine and Mitochondria Hub Regulation Center Department of Microbiology Dong-A University College of Medicine Department of Statistics Pusan National University

Free fatty acids(FFAs), which are elevated with metabolic syndrome, are considered the principal offender exerting lipotoxicity. Few previous studies have reported a causal relationship between FFAs and osteoarthritis pathogenesis. However, the molecular mechanism by which FFAs exert lipotoxicity and induce osteoarthritis remains largely unknown. We here observed that oleate at the usual clinical range does not exert lipotoxicity while oleate at high pathological ranges exerted lipotoxicity through apoptosis in articular chondrocytes. By investigating the differential effect of oleate at toxic and nontoxic concentrations, we revealed that lipid droplet(LD) accumulation confers articular chondrocytes, the resistance to lipotoxicity. Using high fat diet-induced osteoarthritis models and articular chondrocytes treated with oleate alone or oleate plus palmitate, we demonstrated that articular chondrocytes gain resistance to lipotoxicity through protein kinase casein kinase 2(PKCK2)—six-transmembrane protein of prostate 2(STAMP2)—and fat-specific protein 27(FSP27)-mediated LD accumulation. We further observed that the exertion of FFAs-induced lipotoxicity was correlated with the increased concentration of cellular FFAs freed from LDs, whether FFAs are saturated or not. In conclusion, PKCK2/STAMP2/FSP27-mediated sequestration of FFAs in LD rescues osteoarthritic chondrocytes. PKCK2/STAMP2/FSP27 should be considered for interventions against metabolic OA.

关键词： osteoarthritis remains articular chondrocytes

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Epithelioid sarcoma of the spine: a case report and review

引用

Open Journal of Clinical Diagnostics 2011年第1期1卷 1-4页

作者： Jeong hyun yoo 不详

Epithelioid sarcoma is a rare malignant soft tissue neoplasm commonly involving extremities of young adults and rarely occurring in the trunk area. It re-sembles a chronic inflammatory process and mimics benign reactive granuloma or other benign diseases. Despite its indolence and slow growth, the prognosis is poor with high recurrence and early lymph node spreading and hematogeneous distant metastasis. Involvement of the spine is extremely rare and diffi-cult to diagnose correctly in clinical presentation and pathology. We describe our experience a case of epi-thelioid sarcoma involving lumbar spine. A pre-ope- rative spine MRI showed a large solid and necrotic paraspinal mass which extended into the spinal canal with cord compression, and bone destruction. Final correct diagnosis was confirmed by immunohisto-chemical studies. When young adults present with a spinal lesion that has unusual large necrotic soft tissue mass, immunohistochemical studies are recommended for promptly determining the possibility of spinal epithelioid sarcoma.

关键词： Sarcoma Epithelioid: Spine Neoplasm: MR Image

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

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：