检索结果-南通市图书馆

Utility of a deep learning model and a clinical model for predicting bleeding after endoscopic submucosal dissection in patients with early gastric cancer

引用

World Journal of Gastroenterology 2022年第24期28卷 2721-2732页

作者： Ji Eun Na Yeong Chan Lee Tae Jun Kim Hyuk Lee Hong-Hee Won Yang Won Min Byung-Hoon Min Jun Haeng Lee Poong-Lyul Rhee Jae J Kim Department of Internal Medicine Inje University Haeundae Paik HospitalBusan 48108South Korea Department of Medicine Samsung Medical CenterSungkyunkwan University School of MedicineSeoul 06351South Korea Department of Digital Health Samsung Advanced Institute for Health Science and TechnologySungkyunkwan UniversitySeoul 06351South Korea

BACKGROUND Bleeding is one of the major complications after endoscopic submucosal dissection(ESD)in early gastric cancer(EGC)*** are limited studies on estimating the bleeding risk after ESD using an artificial intelligence *** To derivate and verify the performance of the deep learning model and the clinical model for predicting bleeding risk after ESD in EGC *** Patients with EGC who underwent ESD between January 2010 and June 2020 at the Samsung Medical Center were enrolled,and post-ESD bleeding(PEB)was investigated *** split the entire cohort into a development set(80%)and a validation set(20%).The deep learning and clinical model were built on the development set and tested in the validation *** performance of the deep learning model and the clinical model were compared using the area under the curve and the stratification of bleeding risk after *** A total of 5629 patients were included,and PEB occurred in 325 *** area under the curve for predicting PEB was 0.71(95%confidence interval:0.63-0.78)in the deep learning model and 0.70(95%confidence interval:0.62-0.77)in the clinical model,without significant difference(P=0.730).The patients expected to the low-(deep learning model;4.0%,8.8%,and 18.2%,respectively,in the clinical *** A deep learning model can predict and stratify the bleeding risk after ESD in patients with EGC.

关键词： Clinical model deep learning model Post-endoscopic submucosal dissection bleeding Stratification of bleeding risk

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

Automatic Image Annotation Using Adaptive Convolutional deep learning model

引用

Intelligent Automation & Soft Computing 2023年第4期36卷 481-497页

作者： R.Jayaraj S.Lokesh Department of Computer Science and Engineering Hindusthan College of Engineering and TechnologyCoimbatore641032TamilnaduIndia Department of Computer Science and Engineering Hindusthan Institute of TechnologyCoimbatore641032TamilnaduIndia

Every day,websites and personal archives create more and more *** size of these archives is *** comfort of use of these huge digital image gatherings donates to their ***,not all of these folders deliver relevant indexing *** the outcomes,it is dif-ﬁcult to discover data that the user can be absorbed ***,in order to determine the signiﬁcance of the data,it is important to identify the contents in an informative *** annotation can be one of the greatest problematic domains in multimedia research and computer ***,in this paper,Adap-tive Convolutional deep learning model(ACDLM)is developed for automatic image ***,the databases are collected from the open-source system which consists of some labelled images(for training phase)and some unlabeled images{Corel 5 K,MSRC v2}.After that,the images are sent to the pre-processing step such as colour space quantization and texture color class *** pre-processed images are sent to the segmentation approach for efﬁcient labelling technique using J-image segmentation(JSEG).Theﬁnal step is an auto-matic annotation using ACDLM which is a combination of Convolutional Neural Network(CNN)and Honey Badger Algorithm(HBA).Based on the proposed classiﬁer,the unlabeled images are *** proposed methodology is imple-mented in MATLAB and performance is evaluated by performance metrics such as accuracy,precision,recall and F1_*** the assistance of the pro-posed methodology,the unlabeled images are labelled.

关键词： deep learning model J-image segmentation honey badger algorithm convolutional neural network image annotation

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

Surface Defect Detection and Evaluation Method of Large Wind Turbine Blades Based on an Improved deeplabv3+deep learning model

引用

Structural Durability & Health Monitoring 2024年第5期18卷 553-575页

作者： Wanrun Li Wenhai Zhao Tongtong Wang Yongfeng Du Institution of Earthquake Protection and Disaster Mitigation Lanzhou University of TechnologyLanzhou730050China International Research Base on Seismic Mitigation and Isolation of GANSU Province Lanzhou University of TechnologyLanzhou730050China Disaster Prevention and Mitigation Engineering Research Center of Western Civil Engineering Lanzhou University of TechnologyLanzhou730050China

The accumulation of defects on wind turbine blade surfaces can lead to irreversible damage,impacting the aero-dynamic performance of the *** address the challenge of detecting and quantifying surface defects on wind turbine blades,a blade surface defect detection and quantiﬁcation method based on an improved deeplabv3+deep learning model is ***,an improved method for wind turbine blade surface defect detection,utilizing Mobilenetv2 as the backbone feature extraction network,is proposed based on an original deeplabv3+deep learning model to address the issue of limited ***,through integrating the concept of pre-trained weights from transfer learning and implementing a freeze training strategy,signiﬁcant improvements have been made to enhance both the training speed and model training accuracy of this deep learning ***,based on segmented blade surface defect images,a method for quantifying blade defects is *** method combines image stitching algorithms to achieve overall quantiﬁcation and risk assessment of the entire *** results show that the improved deeplabv3+deep learning model reduces training time by approximately 43.03%compared to the original model,while achieving mAP and MIoU values of 96.87%and 96.93%,***,it demonstrates robustness in detecting different surface defects on blades across different *** application of a blade surface defect quantiﬁcation method enables the precise quantiﬁcation of dif-ferent defects and facilitates the assessment of risk levels associated with defect measurements across the entire *** method enables non-contact,long-distance,high-precision detection and quantiﬁcation of surface defects on the blades,providing a reference for assessing surface defects on wind turbine blades.

关键词： Structural health monitoring computer vision blade surface defects detection deeplabv3+ deep learning model

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

Advancing automated pupillometry:a practical deep learning model utilizing infrared pupil images

引用

国际眼科杂志 2024年第10期24卷 1522-1528页

作者： Dai Guangzheng Yu Sile Liu Ziming Yan Hairu He Xingru School of Public Health He UniversityShenyang 110000Liaoning ProvinceChina School of Artificial Intelligence and Big Data He UniversityShenyang 110000Liaoning ProvinceChina Clinical Research Center He Eye Specialist HospitalShenyang 110000Liaoning ProvinceChina The Graduate School Liaoning University of Traditional Chinese MedicineShenyang 110000Liaoning ProvinceChina

AIM:To establish pupil diameter measurement algorithms based on infrared images that can be used in real-world clinical ***:A total of 188 patients from outpatient clinic at He Eye Specialist Shenyang Hospital from Spetember to December 2022 were included,and 13470 infrared pupil images were collected for the *** infrared images for pupil segmentation were labeled using the Labelme *** computation of pupil diameter is divided into four steps:image pre-processing,pupil identification and localization,pupil segmentation,and diameter *** major models are used in the computation process:the modified YoloV3 and deeplabv 3+models,which must be trained ***:The test dataset included 1348 infrared pupil *** the test dataset,the modified YoloV3 model had a detection rate of 99.98% and an average precision(AP)of 0.80 for *** deeplabV3+model achieved a background intersection over union(IOU)of 99.23%,a pupil IOU of 93.81%,and a mean IOU of 96.52%.The pupil diameters in the test dataset ranged from 20 to 56 pixels,with a mean of 36.06±6.85 *** absolute error in pupil diameters between predicted and actual values ranged from 0 to 7 pixels,with a mean absolute error(MAE)of 1.06±0.96 ***:This study successfully demonstrates a robust infrared image-based pupil diameter measurement algorithm,proven to be highly accurate and reliable for clinical application.

关键词： pupil infrared image algorithm deep learning model

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

Comparative analysis of empirical and deep learning models for ionospheric sporadic E layer prediction

引用

Earth and Planetary Physics 2025年第1期9卷 10-19页

作者： BingKun Yu PengHao Tian XiangHui Xue Christopher JScott HaiLun Ye JianFei Wu Wen Yi TingDi Chen XianKang Dou Institute of deep Space Sciences Deep Space Exploration LaboratoryHefei 230088China CAS Key Laboratory of Geospace Environment School of Earth and Space SciencesUniversity of Science and Technology of ChinaHefei 230026China Hefei National Laboratory University of Science and Technology of ChinaHefei 230088China Department of Meteorology University of ReadingReading RG66BBUK

Sporadic E(Es)layers in the ionosphere are characterized by intense plasma irregularities in the E region at altitudes of 90-130 *** they can significantly influence radio communications and navigation systems,accurate forecasting of Es layers is crucial for ensuring the precision and dependability of navigation satellite *** this study,we present Es predictions made by an empirical model and by a deep learning model,and analyze their differences comprehensively by comparing the model predictions to satellite RO measurements and ground-based ionosonde *** deep learning model exhibited significantly better performance,as indicated by its high coefficient of correlation(r=0.87)with RO observations and predictions,than did the empirical model(r=0.53).This study highlights the importance of integrating artificial intelligence technology into ionosphere modelling generally,and into predicting Es layer occurrences and characteristics,in particular.

关键词： ionospheric sporadic E layer radio occultation ionosondes numerical model deep learning model artificial intelligence

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

Impacts of spatially inconsistent permafrost degradation on streamflow in the Lena River Basin

引用

Science China(Technological Sciences) 2024年第11期67卷 3559-3570页

作者： XUE ZeHuan WANG YiChu ZHAO Yi LI DongDeng BORTHWICK Alistair George Liam The Key Laboratory of Water and Sediment Sciences Ministry of EducationCollege of Environmental Sciences and EngineeringPeking UniversityBeijing 100871China College of Water Sciences Beijing Normal UniversityBeijing 100875China State Key Laboratory of Hydraulics and Mountain River Engineering Sichuan UniversityChengdu 610065China State Environmental Protection Key Laboratory of All Materials Fluxes in River Ecosystems Peking UniversityBeijing 100871China School of Engineering The University of EdinburghEdinburgh EH93JLUnited Kingdom School of Engineering Computing and MathematicsUniversity of PlymouthPlymouth PL48AAUnited Kingdom

Although permafrost degradation contributes significantly to hydrological change in cold regions, gaps remain in our understanding of streamflow variation induced by degrading permafrost in different river basins. We therefore used a deep learning model to simulate the long-term(≥ 30 years) monthly streamflow at 60 hydrological stations along the Lena River, the third longest circum-Arctic river. Analyzing the effects of precipitation, temperature, and thaw depth on streamflow variation throughout the Lena River Basin, we identified two feedback patterns relating streamflow to warming permafrost, observed in areas of continuous and discontinuous permafrost. In northern plain regions with continuous permafrost, 94% of stations presented an increasing trend in annual streamflow from the 1900s to the 2010s due to permafrost degradation. The enhanced streamflow was mainly due to increased meltwater in the flood season. In southern regions covered by both continuous and discontinuous permafrost, approximately 38% of stations exhibited a declining trend in annual streamflow in response to permafrost degradation, with a high proportion(61%) located in mountain regions(elevation ≥ 500 m). The decline is attributed to the enhanced infiltration capacity of thawing frozen layers within discontinuous permafrost regions. Our study provides new insights into the mechanisms behind permafrost degradation-induced streamflow variation and highlights the importance of formulating tailored strategies for sustainable river management in cold regions experiencing climate change.

关键词： permafrost degradation streamflow variation deep learning model climate change large cold basin

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

Enhancing landslide susceptibility mapping incorporating landslide typology via stacking ensemble machine learning in Three Gorges Reservoir,China

引用

Geoscience Frontiers 2024年第4期15卷 78-96页

作者： Lanbing Yu Yang Wang Biswajeet Pradhan Faculty of Engineering China University of GeosciencesWuhan 430074China Research Center of Geohazard Monitoring and Warning in the Three Gorges Reservoir Chongqing 404199China Centre for Advanced modelling and Geospatial Information Systems(CAMGIS) School of Civil and Environmental EngineeringFaculty of Engineering and ITUniversity of Technology SydneyUltimoNSW 2007Australia Earth Observation Centre Institute of Climate ChangeUniversiti Kebangsaan Malaysia43600 UKMBangiSelangorMalaysia

Different types of landslides exhibit distinct relationships with environmental conditioning ***,in regions where multiple types of landslides coexist,it is required to separate landslide types for landslide susceptibility mapping(LSM).In this paper,a landslideprone area located in Chongqing Province within the middle and upper reaches of the Three Gorges Reservoir area(TGRA),China,was selected as the study area.733 landslides were classified into three types:reservoir-affected landslides,non-reservoir-affected landslides,and *** landslide inventory datasets and 15 landslide conditional factors were trained by three Machine learning models(logistic regression,random forest,support vector machine),and a deep learning(DL)*** comparing the models using receiver operating characteristics(ROC),the landslide susceptibility indexes of three types landslides were acquired by the best performing *** indexes were then used as input to generate the final map based on the Stacking *** results revealed that DL model showed the best performance in LSM without considering landslide types,achieving an area under the curve(AUC)of 0.854 for testing and 0.922 for ***,when we separated the landslide types for LSM,the AUC improved by 0.026 for testing and 0.044 for ***,this paper demonstrates that considering different landslide types in LSM can significantly improve the quality of landslide susceptibility *** maps in turn,can be valuable tools for evaluating and mitigating landslide hazards.

关键词： Landslide susceptibility mapping deep learning model Landslide types Stacking method

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

Diagnosis of Various Skin Cancer Lesions Based on Fine-Tuned ResNet50 deep Network

引用

Computers, Materials & Continua 2021年第7期68卷 117-135页

作者： Sameh Abd ElGhany Mai Ramadan Ibraheem Madallah Alruwaili Mohammed Elmogy Department of Information Systems College of Computers and Information SciencesJouf UniversitySakakaSaudi Arabia Department of Information Systems Faculty of Computers and InformationMansoura UniversityEgypt Department of Information Technology Faculty of Computers and InformationKafrelsheikh UniversityEgypt Department of Computer Engineering and Networks College of Computers and Information SciencesJouf UniversitySaudi Arabia Department of Information Technology Faculty of Computers and InformationMansoura UniversityMansoura35516Egypt

With the massive success of deep networks,there have been signi-cant efforts to analyze cancer diseases,especially skin *** this purpose,this work investigates the capability of deep networks in diagnosing a variety of dermoscopic lesion *** paper aims to develop and ne-tune a deep learning architecture to diagnose different skin cancer grades based on dermatoscopic ***-tuning is a powerful method to obtain enhanced classication results by the customized pre-trained ***,batch normalization,and hyperparameter optimization are performed for ne-tuning the proposed deep *** proposed ne-tuned ResNet50 model successfully classied 7-respective classes of dermoscopic lesions using the publicly available HAM10000 *** developed deep model was compared against two powerful models,i.e.,InceptionV3 and VGG16,using the Dice similarity coefcient(DSC)and the area under the curve(AUC).The evaluation results show that the proposed model achieved higher results than some recent and robust models.

关键词： deep learning model multiclass diagnosis dermatoscopic images analysis ResNet50 network

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

Artificial Intelligence Providing a More Optimized Assessment Tool for Comprehensive Geriatric Assessment

引用

Journal of Beijing Institute of Technology 2023年第2期32卷 131-141页

作者： Na Guo Jian Guo Xinxin Yan Department of Geri-atrics Aerospace Central HospitalBeijing 100049China Xi’an University of Finance and Eco-nomics Xi’an 710100China

With the continuous development of science and technology,artificial intelligence(AI)is coming into our lives and changing our *** China entered the aging society in 2000,the degree of population aging has *** geriatric assessment(CGA)is now the accepted gold standard for the care of older people in ***,some problems limit the clinical application,such as complexity and time ***,by analyzing previous studies,we summarize some existing AI tools in order to find a more optimized assessment tool to complete the entire CGA process.

关键词： artificial intelligence(AI) comprehensive geriatric assessment(CGA) wearable devices deep learning model image acquisition

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

deep Transfer learning Approach for Robust Hand Detection

引用

Intelligent Automation & Soft Computing 2023年第4期36卷 967-979页

作者： Stevica Cvetkovic Nemanja Savic Ivan Ciric Faculty of Electronic Engineering University of NisNis18000Serbia Faculty of Mechanical Engineering University of NisNis18000Serbia

Human hand detection in uncontrolled environments is a challenging visual recognition task due to numerous variations of hand poses and background image *** achieve highly accurate results as well as provide real-time execution,we proposed a deep transfer learning approach over the state-of-the-art deep learning object *** method,denoted as YOLOHANDS,is built on top of the You Only Look Once(YOLO)deep learning architecture,which is modiﬁed to adapt to the single class hand detection *** model transfer is performed by modifying the higher convolutional layers including the last fully connected layer,while initializing lower non-modiﬁed layers with the generic pre-trained *** address robustness issues,we introduced a comprehensive augmentation procedure over the training image dataset,speciﬁcally adapted for the hand detection *** evaluation of the proposed method,which is performed on a challenging public dataset,has demonstrated highly accurate results,comparable to the state-of-the-art methods.

关键词： deep learning model object detection hand detection transfer learning data augmentation

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：