检索结果-南通市图书馆

A NONMONOTONE SECOND-ORDER STEPLENGTH METHOD FOR UNCONSTRAINED MINIMIZATION

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

Journal of Computational mathematics 2007年第1期25卷 104-112页

作者： qun-yan zhou wen-yu sun Department of Basic science Jiangsu Teachers University of Technology Changzhou 213001 China school of mathematics and computer science Nanjing Normal University Nanjin9 210097 China school of mathematics and computer science Nanjing Normal University Nanjing 210097 China

In this paper, a nonmonotone method based on McCormick＇s second-order Armijo＇s step-size rule [7] for unconstrained optimization problems is proposed. Every limit point of the sequence generated by using this procedure is proved to be a stationary point with the second-order optimality conditions. Numerical tests on a set of standard test problems are presented and show that the new algorithm is efficient and robust.

关键词： Nonmonotone method Armijo's line search Direction of negative curvature,Unconstrained optimization.

Analysis and comparison of retinal vascular parameters under different glucose metabolic status based on deep learning

在线全文

学校读者我要写书评

暂无评论

International Journal of Ophthalmology(English edition) 2024年第9期17卷 1581-1591页

作者： yan Jiang Di Gong Xiao-Hong Chen Lin yang Jing-Jing Xu Qi-Jie Wei Bin-Bin Chen Yong-Jiang Cai wen-qun Xi Zhe Zhang Departments of Laboratory Medicine the Second Affiliated HospitalZhejiang University School of MedicineHangzhou 310009Zhejiang ProvinceChina Shenzhen Eye Hospital Jinan UniversityShenzhen 518040Guangdong ProvinceChina Center of Health Management Peking University Shenzhen HospitalShenzhen 518036Guangdong ProvinceChina Visionary Intelligence Ltd. Beijing 100080China Ophthalmology Center the Second Affiliated HospitalZhejiang University School of MedicineHangzhou 310009Zhejiang ProvinceChina

AIM:To develop a deep learning-based model for automatic retinal vascular segmentation,analyzing and comparing parameters under diverse glucose metabolic status(normal,prediabetes,diabetes)and to assess the potential of artificial intelligence(AI)in image segmentation and retinal vascular parameters for predicting prediabetes and ***:Retinal fundus photos from 200 normal individuals,200 prediabetic patients,and 200 diabetic patients(600 eyes in total)were *** U-Net network served as the foundational architecture for retinal arteryvein *** automatic segmentation and evaluation system for retinal vascular parameters was trained,encompassing 26 ***:Significant differences were found in retinal vascular parameters across normal,prediabetes,and diabetes groups,including artery diameter(P=0.008),fractal dimension(P=0.000),vein curvature(P=0.003),C-zone artery branching vessel count(P=0.049),C-zone vein branching vessel count(P=0.041),artery branching angle(P=0.005),vein branching angle(P=0.001),artery angle asymmetry degree(P=0.003),vessel length density(P=0.000),and vessel area density(P=0.000),totaling 10 ***:The deep learning-based model facilitates retinal vascular parameter identification and quantification,revealing significant *** parameters exhibit potential as biomarkers for prediabetes and diabetes.

关键词： deep learning retinal vascular parameters segmentation model diabetes prediabetes

Rhythm dynamics of complex neuronal networks with mixed bursting neurons

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

Chinese Physics B 2013年第4期22卷 167-171页

作者：吕永兵石霞郑艳红 school of science Beijing University of Posts and Telecommunications school of mathematics and computer science Fujian Normal University

The spatiotemporal order and rhythm dynamics of a complex neuronal network with mixed bursting neurons are studied in this paper. A quantitative characteristic, the width factor, is introduced to describe the rhythm dynamics of an individual neuron, and the average width factor is used to characterize the rhythm dynamics of a neuronal network. An r parameter is introduced to denote the ratio of the short bursting neurons in the network. Then we investigate the effect of the ratio on the rhythm dynamics of the neuronal network. The critical value of r is derived, and the neurons in the network always remain short bursting when the r ratio is larger than the critical value.

关键词： rhythm dynamics complex network neuron

无穷凹角区域椭圆边值问题的重叠型区域分解算法

在线全文

学校读者我要写书评

暂无评论

数值计算与计算机应用 2004年第2期25卷 90-99页

作者：杨敏杜其奎河海大学理学院南京210098 南京师范大学数学与计算机科学学院南京210097

In this paper, we investigate an overlapping domain decomposition algorithm for elliptic boundary value problems over an infinite domain with concave *** algorithm is constructed, and its convergence is discussed. The finite element method and natural boundary element are alternatively applied to solve a bounded subdomain and a typical unbounded subdomain. It has overcome the difficulty met in standard domain decomposition method for problems with unbounded *** convergence rate is analysed in details for a typical domain. Finally, some numerical example are presented to show effectiveness of our method.

关键词：偏微分方程边值问题边界算法

A Tiny Example Based Procedural Model for Real-Time Glinty Appearance Rendering

在线全文

学校读者我要写书评

暂无评论

Journal of computer science & Technology 2024年第4期39卷 771-784页

作者： You-Xin Xing Hao-wen Tan yan-Ning Xu Lu Wang school of Software Shandong UniversityJinan 250101China NetEase(Hangzhou)Network Co. LtdHangzhou 310052China

The glinty details from complex microstructures significantly enhance rendering ***,the previous methods use high-resolution normal maps to define each micro-geometry,which requires huge memory *** paper observes that many self-similarity materials have independent structural characteristics,which we define as tiny example *** propose a procedural model to represent microstructures implicitly by performing spatial transformations and spatial distribution on tiny ***,we precompute normal distribution functions(NDFs)by 4D Gaussians for tiny examples and store them in multi-scale NDF *** with a tiny example based NDF evaluation method,complex glinty surfaces can be rendered simply by texture *** experimental results show that our tiny example based the microstructure rendering method is GPU-friendly,successfully reproducing high-frequency reflection features of different microstructures in real time with low memory and computational overhead.

关键词： real-time rendering reflectance modeling glinty material photorealistic rendering microstructure

A Practice Guide of Software Aging Prediction in a Web Server Based on Machine Learning

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

china Communications 2016年第6期13卷 225-235页

作者： Yongquan yan Ping Guo school of computer science and Technology Beijing Institute of TechnologyBeijing 100081China school of System science Beijing Normal UniversityBeijing 100875China

In the past two decades, software aging has been studied by both academic and industry communities. Many scholars focused on analytical methods or time series to model software aging process. While machine learning has been shown as a very promising technique in application to forecast software state: normal or aging. In this paper, we proposed a method which can give practice guide to forecast software aging using machine learning algorithm. Firstly, we collected data from a running commercial web server and preprocessed these data. Secondly, feature selection algorithm was applied to find a subset of model parameters set. Thirdly, time series model was used to predict values of selected parameters in advance. Fourthly, some machine learning algorithms were used to model software aging process and to predict software aging. Fifthly, we used sensitivity analysis to analyze how heavily outcomes changed following input variables change. In the last, we applied our method to an IIS web server. Through analysis of the experiment results, we find that our proposed method can predict software aging in the early stage of system development life cycle.

关键词： software aging software rejuvenation machine learning web server

The Optimization of Binary Randomized Response Based on Lanke Privacy and Utility Analysis

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2024年

作者： Yihui zhou wenli WANG Jun yan Zhenqiang WU Laifeng LU school of computer science Shaanxi Normal University school of mathematics and Statistics Shaanxi Normal University school of mathematics and computer Applications Shangluo College

Currently, it has become a consensus to enhance privacy protection. Randomized response(RR) technique, as the mainstream perturbation mechanism for local differential privacy, has been widely studied. However,most of the research in literature managed to modify existing RR schemes and propose new mechanisms with better privacy protection and utility, which are illustrated only by numerical experiments. We study the properties of generalized binary randomized response mechanisms from the perspectives of Lanke privacy and utility. The mathematical expressions of privacy and utility for the binary RR mechanism are given respectively. Moreover, the comparison principle for privacy and utility of any two mechanisms is proved. Finally, the optimization problem of the binary RR mechanism is discussed. Our work is based on a rigorous mathematical proof of privacy and utility for the general binary RR mechanism, and numerical verification illustrates the correctness of the conclusions. It can provide theoretical support for the design of binary RR mechanism and can be applied in data collection, analysis and publishing.

关键词：

Knowledge-embedded spatio-temporal analysis for euploidy embryos identification in couples with chromosomal rearrangements

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Chinese Medical Journal 2024年第6期137卷 694-703页

作者： Fangying Chen Xiang Xie Du Cai Pengxiang yan Chenhui Ding yangxing wen yanwen Xu Feng Gao Canquan zhou Guanbin Li Qingyun Mai Reproductive Medicine Center The First Affiliated Hospital of Sun Yat-sen UniversityGuangzhouGuangdong 510080China Guangdong Provincial Key Laboratory of Reproductive Medicine GuangzhouGuangdong 510080China school of computer science and Engineering Sun Yat-sen UniversityGuangzhouGuangdong 510006China Department of General Surgery(Colorectal Surgery) The Sixth Affiliated Hospital of Sun Yat-sen UniversityGuangzhouGuangdong 510655China Guangdong Provincial Key Laboratory of Colorectal and Pelvic Floor Diseases The Sixth Affiliated HospitalSun Yat-sen UniversityGuangzhouGuangdong 510655China Biomedical Innovation Center The Sixth Affiliated HospitalSun Yat-sen UniversityGuangzhouGuangdong 510655China Shanghai Artificial Intelligence Laboratory Shanghai 200232China

Background:The goal of the assisted reproductive treatment is to transfer one euploid blastocyst and to help infertile women giving birth one healthy *** algorithms have been used to assess the ploidy status of embryos derived from couples with normal chromosome,who subjected to preimplantation genetic testing for aneuploidy(PGT-A)***,it is currently unknown whether artificial intelligence model can be used to assess the euploidy status of blastocyst derived from populations with chromosomal ***:From February 2020 to May 2021,we collected the whole raw time-lapse videos at multiple focal planes from in vitro cultured embryos,the clinical information of couples,and the comprehensive chromosome screening results of those blastocysts that had received PGT ***,we developed a novel deep learning model called the Attentive Multi-Focus Selection Network(AMSNet)to analyze time-lapse videos in real time and predict blastocyst *** upon AMSNet,we integrated additional clinically predictive variables and created a second deep learning model,the Attentive Multi-Focus Video and Clinical Information Fusion Network(AMCFNet),to assess the euploidy status of *** efficacy of the AMCFNet was further tested in embryos with parental chromosomal *** receiver operating characteristic curve(ROC)was used to evaluate the superiority of the ***:A total of 4112 embryos with complete time-lapse videos were enrolled for the blastocyst formation prediction task,and 1422 qualified blastocysts received PGT-A(n=589)or PGT for chromosomal structural rearrangement(PGT-SR,n=833)were enrolled for the euploidy assessment task in this *** AMSNet model using seven focal raw time-lapse videos has the best real-time *** real-time accuracy for AMSNet to predict blastocyst formation reached above 70%on the day 2 of embryo culture,and then increased to 80%on the day 4 of embryo ***

关键词： Euploidy status Embryo Time-lapse imaging Deep learning Spatio-temporal analysis Preimplantation genetic testing for chromosomal structural rearrangement

A Hierarchical Method for Locating the Interferometric Fringes of Celestial Sources in the Visibility Data

在线全文

学校读者我要写书评

暂无评论

Research in Astronomy and Astrophysics 2024年第3期24卷 110-128页

作者： Rong Ma Ruiqing yan Hanshuai Cui Xiaochun Cheng Jixia Li Fengquan Wu Zongyao Yin Hao Wang wenyi Zeng Xianchuan yu school of Artificial Intelligence Beijing Normal UniversityBeijing 100875China Department of computer science Swansea UniversitySwanseaSA18ENUK National Astronomical Observatories Chinese Academy of SciencesBeijing 100101China

In source detection in the Tianlai project,locating the interferometric fringe in visibility data accurately will influence downstream tasks drastically,such as physical parameter estimation and weak source *** that traditional locating methods are time-consuming and supervised methods require a great quantity of expensive labeled data,in this paper,we first investigate characteristics of interferometric fringes in the simulation and real scenario separately,and integrate an almost parameter-free unsupervised clustering method and seeding filling or eraser algorithm to propose a hierarchical plug and play method to improve location ***,we apply our method to locate single and multiple sources’interferometric fringes in simulation ***,we apply our method to real data taken from the Tianlai radio telescope ***,we compare with unsupervised methods that are state of the *** results show that our method has robustness in different scenarios and can improve location measurement accuracy effectively.

关键词： methods data analysis-techniques image processing-techniques interferometric