检索结果-内蒙古大学图书馆

Non-invasive biopsy diagnosis of diabetic kidney disease via deep learning applied to retinal images: a population-based study

引用

The Lancet Digital Health 2025年第5期7卷 100868页

作者： Meng, Ziyao Guan, Zhouyu Yu, Shujie Wu, Yilan Zhao, Yaoning Shen, Jie Lim, Cynthia Ciwei Chen, Tingli Yang, Dawei Ran, An Ran He, Feng Hamzah, Haslina Singh, Sarkaaj Abd Raof, Anis Syazwani Lee-Boey, Jian Wen Samuel Lim, Soo-Kun Sun, Xufang Ge, Shuwang Xu, Gang Su, Hua Cheng, Yang Lu, Feng Liao, Xiaofei Jin, Hai Deng, Chenxin Ruan, Lei Zhang, Cuntai Wu, Chan Dai, Rongping Jin, Yixiao Wang, Wenxiao Li, Tingyao Liu, Ruhan Li, Jiajia Shu, Jia Lu, Yuwei Wang, Xiangning Wu, Qiang Qin, Yiming Tang, Jin Sheng, Xiaohua Jiao, Qiong Yang, Xiaokang Guo, Minyi McKay, Gareth J Hogg, Ruth E Liew, Gerald Chee, Evelyn Yi Lyn Hsu, Wynne Lee, Mong Li Szeto, Simon Luk, Andrea O Y Chan, Juliana C N Cheung, Carol Y Tan, Gavin Siew Wei Tham, Yih-Chung Cheng, Ching-Yu Sabanayagam, Charumathi Lim, Lee-Ling Jia, Weiping Li, Huating Sheng, Bin Wong, Tien Yin Shanghai Belt and Road International Joint Laboratory of Intelligent Prevention and Treatment for Metabolic Diseases Department of Computer Science and Engineering School of Electronic Information and Electrical Engineering Institute for Proactive Healthcare Shanghai Jiao Tong University Department of Endocrinology and Metabolism Shanghai Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine Shanghai Diabetes Institute Shanghai Clinical Centre for Diabetes Shanghai Key Laboratory of Diabetes Mellitus Shanghai China MOE Key Laboratory of AI School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China Beijing Tsinghua Changgung Hospital Eye Center School of Clinical Medicine Tsinghua Medicine Tsinghua University Beijing China Medical Records and Statistics Office Shanghai Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine Shanghai China Department of Renal Medicine Singapore General Hospital SingHealth-Duke Academic Medical Centre Singapore Singapore Department of Ophthalmology Shanghai Health and Medical Center Wuxi China Department of Ophthalmology and Visual Sciences The Chinese University of Hong Kong Hong Kong Special Administrative Region China Singapore Eye Research Institute Singapore National Eye Centre Singapore Department of Medicine Faculty of Medicine Universiti Malaya Kuala Lumpur Malaysia Department of Ophthalmology Tongji Hospital Tongji Medical College Huazhong University of Science and Technology Hubei Wuhan China Department of Nephrology Tongji Hospital Tongji Medical College Huazhong University of Science and Technology Wuhan China Department of Nephrology Union Hospital Tongji Medical College Huazhong University of Science and Technology Wuhan China Department of Ophthalmology Union Hospital Tongji Medical College Huazhong University of Science and Technology Wuhan China National Engineering Research Centre for Big Dat

Background: Improving the accessibility of screening diabetic kidney disease (DKD) and differentiating isolated diabetic nephropathy from non-diabetic kidney disease (NDKD) are two major challenges in the field of diabetes care. We aimed to develop and validate an artificial intelligence (AI) deep learning system to detect DKD and isolated diabetic nephropathy from retinal fundus images. Methods: In this population-based study, we developed a retinal image-based AI-deep learning system, DeepDKD, pretrained using 734 084 retinal fundus images. First, for DKD detection, we used 486 312 retinal images from 121 578 participants in the Shanghai Integrated Diabetes Prevention and Care System for development and internal validation, and ten multi-ethnic datasets from China, Singapore, Malaysia, Australia, and the UK (65 406 participants) for external validation. Second, to differentiate isolated diabetic nephropathy from NDKD, we used 1068 retinal images from 267 participants for development and internal validation, and three multi-ethnic datasets from China, Malaysia, and the UK (244 participants) for external validation. Finally, we conducted two proof-of-concept studies: a prospective real-world study with 3 months' follow-up to evaluate the effectiveness of DeepDKD in screening DKD;and a longitudinal analysis of the effectiveness of DeepDKD in differentiating isolated diabetic nephropathy from NDKD on renal function changes with 4·6 years' follow-up. Findings: For detecting DKD, DeepDKD achieved an area under the receiver operating characteristic curve (AUC) of 0·842 (95% CI 0·838–0·846) on the internal validation dataset and AUCs of 0·791–0·826 across external validation datasets. For differentiating isolated diabetic nephropathy from NDKD, DeepDKD achieved an AUC of 0·906 (0·825–0·966) on the internal validation dataset and AUCs of 0·733–0·844 across external validation datasets. In the prospective study, compared with the metadata model, DeepDKD could detect DKD wit

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Recommending more suitable music based on users’ real context 14th

Recommending more suitable music based on users’ real conte...

引用

14th EAI International Conference on Collaborative computing: Networking, Applications and Worksharing, CollaborateCom 2018

作者： Yang, Qing Zhan, Le Han, Li Zhang, Jingwei Bi, Zhongqin School of Electronic Engineering and Automation Guilin University of Electronic Technology Guilin541004 China Guangxi Cooperative Innovation Center of Cloud Computing and Big Data Guilin University of Electronic Technology Guilin541004 China Guangxi Key Laboratory of Trusted Software Guilin University of Electronic Technology Guilin541004 China College of Computer Science and Technology Shanghai University of Electronic Power Shanghai200090 China

ISBN: (纸本)9783030129804

Music recommendation is an popular function for personalized services and smart applications since it focuses on discovering users’ leisure preference. The traditional music recommendation strategy captured users’ music preference by analyzing their historical behaviors to conduct personalized recommendation. However, users’ current states, such as in busy working or in a leisure travel, etc., have an important influence on their music enjoyment. Usually, those existing methods only focus on pushing their favorite music to users, which may be not the most suitable for current scenarios. Users’ current states should be taken into account to make more perfect music recommendation. Considering the above problem, this paper proposes a music recommendation method by considering both users’ current states and their historical behaviors. First, a feature selection process based on ReliefF method is applied to discover the optimal features for the following recommendation. Second, we construct different feature groups according to the feature weights and introduce Naive Bayes model and Adaboost algorithm to train these feature groups, which will output a base classifier for each feature group. Finally, a majority voting strategy decides the optimal music type and each user will be recommended more suitable music based on their current context. The experiments on the real datasets show the effectiveness of the proposed method. © 2019, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

关键词： Adaptive boosting

来源：评论

学校读者我要写书评

暂无评论

Three-Dimensional Reconstruction Method with Parameter Optimization for Point Cloud Based on Kinect v2

Three-Dimensional Reconstruction Method with Parameter Optim...

引用

作者： Kai-zhang WANG Tong-kai LU Qi-hang YANG Xi-hao FU Ze-hong LU Bo-lun WANG Xin JIANG Key Laboratory of Mathematics Informatics and Behavioral Semantics and School of Mathematics and Systems Science Beihang University Peng Cheng Laboratory Beijing Advanced Innovation Center for Big Data and Brain Computing (BDBC) School of Mathematical Science Peking University

Three-Dimensional(3D) reconstruction is a significant part in the field of computer vision. In this paper, we use Kinect v2 to obtain the 3D point cloud. As a consumer used 3D sensor, Kinect has numerous advantages such as low price, relative high dot per inch(DPI) and frames per second(FPS) and strong robustness. During the experiment, the object was placed on a turntable spinning and stop for every 12°, collecting 30 images of point cloud in total. Then we used Iterated Closest Points(ICP) algorithm to calculate the optimal rotation matrix and translation matrix to match all point cloud into the same coordinate. After that, three algorithms including Statistical Outlier Removal, Movement Least Squares(MLS) and Voxelgrid were used to reduce the noise. At last, we applied greedy projection algorithm to generate the triangulate mesh. During the procession, we observed the relationship between parameters and outcome and drew pictures to have the data more visible, which gave out the optimal parameters in return.

关键词： 3D Reconstruction Parameter optimization Kinect v2

来源：评论

学校读者我要写书评

暂无评论

FW-GAN: Flow-Navigated Warping GAN for Video Virtual Try-On

FW-GAN: Flow-Navigated Warping GAN for Video Virtual Try-On

引用

International Conference on Computer Vision (ICCV)

作者： Haoye Dong Xiaodan Liang Xiaohui Shen Bowen Wu Bing-Cheng Chen Jian Yin School of Data and Computer Science Sun Yat-sen University Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou P.R.China School of Intelligent Systems Engineering Sun Yat-sen University ByteDance AI Lab

ISBN: (数字)9781728148038

ISBN: (纸本)9781728148045

Beyond current image-based virtual try-on systems that have attracted increasing attention, we move a step forward to developing a video virtual try-on system that precisely transfers clothes onto the person and generates visually realistic videos conditioned on arbitrary poses. Besides the challenges in image-based virtual try-on (e.g., clothes fidelity, image synthesis), video virtual try-on further requires spatiotemporal consistency. Directly adopting existing image-based approaches often fails to generate coherent video with natural and realistic textures. In this work, we propose Flow-navigated Warping Generative Adversarial Network (FW-GAN), a novel framework that learns to synthesize the video of virtual try-on based on a person image, the desired clothes image, and a series of target poses. FW-GAN aims to synthesize the coherent and natural video while manipulating the pose and clothes. It consists of: (i) a flow-guided fusion module that warps the past frames to assist synthesis, which is also adopted in the discriminator to help enhance the coherence and quality of the synthesized video; (ii) a warping net that is designed to warp clothes image for the refinement of clothes textures; (iii) a parsing constraint loss that alleviates the problem caused by the misalignment of segmentation maps from images with different poses and various clothes. Experiments on our newly collected dataset show that FW-GAN can synthesize high-quality video of virtual try-on and significantly outperforms other methods both qualitatively and quantitatively.

关键词： Integrated circuits Generators Gallium nitride Three-dimensional displays Image generation Computational modeling Visualization

来源：评论

学校读者我要写书评

暂无评论

A new runoff calculation model based on multi-source radar remote sensing technology 6

A new runoff calculation model based on multi-source radar r...

引用

6th Asia-Pacific Conference on Synthetic Aperture Radar, APSAR 2019

作者： Zhao, Jianhui Wang, Ning Wu, Lin Min, Lin College of Computer and Information Engineering Henan University Kaifeng475004 China College of Environment and Planning Henan University Kaifeng475004 China Network Information Center Office Henan University Kaifeng475004 China Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng475004 China Henan Engineering Research Center of Intelligent Technology and Application Kaifeng475004 China

ISBN: (纸本)9781728129129

River runoff changing will directly affect the safety of the surrounding areas. In theory, river runoff can be calculated from water depth, river width and flow velocity. But in the actual monitoring, the observation of water depth, river width and flow velocity is complex. Radar remote sensing can observe target all-time and all-weather, and has the ability to penetrate clouds, rain and fog. The common Radar remote sensing runoff calculation model is depth-runoff relationship model, which is constructed by fitting water depth and in-situ runoff. The river depth is derived from Radar Altimetry (RA) data. But this model has only one input parameter, the accuracy of this model inverted runoff is not high. In view of the above problems, this paper proposed the Multi-source Radar Remote Sensing Runoff Calculation Model (MRRS-RCM). Firstly, river width and relative water depth were derived from Synthetic Aperture Radar (SAR) images and RA data. Secondly, based on the Manning's equation, the flow velocity were described from river width and relative water depth. Thirdly, river width relative water depth, and in-situ runoff were fitted to construct MRRS-RCM. Experiments show the accuracy of MRRS-RCM estimated runoff is better than depth-runoff relationship model, the RRMSE values of MRRS-RCM reach 13%. © 2019 IEEE.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

Investigation of the Salinity Distribution of the Soil along West Main Canal in Ningxia, China

引用

IOP Conference Series: Earth and Environmental Science 2021年第1期697卷

作者： Juntao Wu Hefang Jing Weihong Wang Xiaoxiao Guo Xinxia Guo Research Institute of Numerical Computation and Engineering Applications North Minzu University Yinchuan China School of Mathematics and Information Science North Minzu University Yinchuan China The Key Laboratory of Intelligent Information and Big Data Processing of Ningxia Province North Minzu University Yinchuan China

As one of the main irrigation canals in Ningxia, West Main Canal plays a very important role in the irrigation of the land nearby the canal, such as farms, meadows, and tree farms. Because of the long-term use of the Yellow River water for irrigation, the soil salinization in this area become more serious. In this paper, the problem of soil salinization along the West Main Canal in Ningxia is taken as the research object. 82 sample points in the studied area are chosen and a total number of 164 soil samples are measured for the eight main salt ions and pH value. Correlation analysis and principal component analysis are employed to study the distribution of the soil salinity ions and pH value. In addition, two dimensional interpolation is applied to obtain the spatial distribution of the total saltiness. It can be found that Cl−, SO42−, Ca2+, Na+ and HCO3− are the main salt ions and the main soluble salts are NaCl, KCl, CaSO4, Na2SO4 and CaCl2 in the soil of the studied area. The spatial distribution of the total soil salt is mainly in the patterns of north high and south low, far high and near low, up high and down low.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Experimental Study on Flow Characteristics in a Compound Open Channel with Flexible Vegetation

引用

IOP Conference Series: Earth and Environmental Science 2021年第1期697卷

作者： Xiaoxiao Guo Hefang Jing Weihong Wang Juntao Wu Qiaoling Zhang Research Institute of Numerical Computation and Engineering Applications North Minzu University Yinchuan China School of Mathematics and Information Science North Minzu University Yinchuan China The Key Laboratory of Intelligent Information and Big Data Processing of Ningxia Province North Minzu University Yinchuan China

In order to study the effect of flexible vegetation for the flow in open channels with flood plains, a series of experiments were carried out in a laboratory flume with a two-stage floodplain. Four cases, i.e., dense parallel arrangement, normal parallel arrangement, sparse parallel arrangement and no vegetation condition, were designed with fixed water depth and discharge. By using three dimensional (3D) laser Doppler velocimeter (LDV) and other instruments, under the condition of the four cases,3D flow velocities, water level and turbulence intensity were measured, The experimental results show that, compared with the non-vegetation situation, the arrangement of grasses on the floodplain will increase the water surface gradient, hydraulic gradient and turbulence intensity to a certain extent.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Impact of DG on short circuit current detected by protection

引用

IOP Conference Series: Earth and Environmental Science 2021年第1期675卷

作者： Jing Gong School of Electrical and Information Engineering Beijing University of Civil Engineering and Architecture Beijing 100044 China Beijing Key Laboratory of Intelligent Processing for Building Big Data Beijing 100044 China National Virtual Simulation Experimental Center for Smart City Education Beijing100044 China

DG (distributed generation) access causes the change of current detected by the protection, and then affects the sensitivity of the original protection. In order to solve the problem, the influences of DG capacity, DG access location and short-circuit location on short circuit current are analysed in this paper. When the DG capacity and grid-connected position remain unchanged, the unit current method is used to solve the short-circuit current by solving the transfer impedance. The relationship between the change of short circuit position and the impact degree of DG is discussed in detail, and the calculation formula of extreme point is derived. When the DG capacity and short circuit location remain unchanged, the impact of DG grid-connected position on the upstream and downstream current is analysed. The characteristic curve of the impact of DG position change on protection current detection is given, and the impact of DG grid-connected position on protection sensitivity is explained clearly. The conclusion provides an important reference for the selection of DG grid-connected position and the calculation of relay protection in distribution network with DG.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep representation learning for road detection using siamese network

arXiv

引用

arXiv 2019年

作者： Liu, Huafeng Han, Xiaofeng Li, Xiangrui Yao, Yazhou Huang, Pu Tang, Zhenming School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China Jiangsu Key Laboratory of Big Data Security & Intelligent Processing Nanjing University of Posts and Telecommunications Nanjing210023 China

Robust road detection is a key challenge in safe autonomous driving. Recently, with the rapid development of 3D sensors, more and more researchers are trying to fuse information across different sensors to improve the performance of road detection. Although many successful works have been achieved in this field, methods for data fusion under deep learning framework is still an open problem. In this paper, we propose a Siamese deep neural network based on FCN-8s to detect road region. Our method uses data collected from a monocular color camera and a Velodyne-64 LiDAR sensor. We project the LiDAR point clouds onto the image plane to generate LiDAR images and feed them into one of the branches of the network. The RGB images are fed into another branch of our proposed network. The feature maps that these two branches extract in multiple scales are fused before each pooling layer, via padding additional fusion layers. Extensive experimental results on public dataset KITTI ROAD demonstrate the effectiveness of our proposed approach. Copyright © 2019, The Authors. All rights reserved.

关键词： Roads and streets

来源：评论

学校读者我要写书评

暂无评论

Adaptive NMS: Refining pedestrian detection in a crowd

arXiv

引用

arXiv 2019年

作者： Liu, Songtao Huang, Di Wang, Yunhong Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University State Key Laboratory of Software Development Environment Beihang University School of Computer Science and Engineering Beihang University Beijing100191

Pedestrian detection in a crowd is a very challenging issue. This paper addresses this problem by a novel NonMaximum Suppression (NMS) algorithm to better refine the bounding boxes given by detectors. The contributions are threefold: (1) we propose adaptive-NMS, which applies a dynamic suppression threshold to an instance, according to the target density;(2) we design an efficient subnetwork to learn density scores, which can be conveniently embedded into both the single-stage and two-stage detectors;and (3) we achieve state of the art results on the CityPersons and CrowdHuman benchmarks. Copyright © 2019, The Authors. All rights reserved.

关键词： Machine learning

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：