检索结果-内蒙古大学图书馆

Natural image classification based on multi-parameter optimization in deep convolutional neural network

International Journal of Performability engineering 2019年第9期15卷 2515-2521页

作者： Wang, Lei Zhang, Yanning Xi, Runping Ling, Lu School of Computer Northwestern Polytechnical University Xi'an710072 China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Xi'an710072 China Jiangxi Engineering Technology Research Center of Nuclear Geoscience Data Science and System East China University of Technology Nanchang330013 China

Traditional machine learning algorithms cannot adequately train the parameters of networks using massive data. A deep convolutional neural network based on multi-parameter optimization by the TensorFlow deep learning framework is designed in this paper. In order to improve the training speed and prevent over-fitting, we improve and optimize the multi-parameters, including the batch value, dropout, and momentum in the network structure. The experiment involves training and testing on the standard natural image data sets in cifar-10 and cifar-100. The experimental results show that the method achieve better classification accuracy in less time compared with other algorithms, such as Conv-KN, ImageNet-2010, SVM, LR, and Boosting. © 2019 Totem Publisher, Inc. All rights reserved.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Design of vehicle management reader based on STM32

引用

Journal of Physics: Conference Series 2020年第3期1650卷

作者： Chenglong Ding Zhifeng Liu Yuefeng Xu Zhihao Shu Jiangxi Engineering Technology Research Center of Nuclear Geoscience Data Science and System East China University of Technology Nanchang 330013 Jiangxi China. School of Information Engineering East China University of Technology China.

This paper mainly studies the parking lot counting system, which is a modern and new system integrating detection and conversion technology, computer technology, information processing, digital technology and other technologies. This work uses STM32F103 single-chip microcomputer as the MCU processor, and uses 2 infrared modules to detect vehicle access. Through the single-chip microcomputer, information is collected to detect vehicle access. LCD12864 is used to display vehicle parking information for drivers to watch.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Design and Implementation of an Augmented Reality Scheme Based on Netty Communication

引用

Journal of Physics: Conference Series 2020年第1期1575卷

作者： Yongping Gao Jie Wang Jingzhong Zhang Jiangxi Engineering Laboratory on Radioactive Geoscience and Big Data Technology East China University of Technology Nanchang 330013 Jiangxi China Jiangxi Engineering Research Center of Nuclear Geoscience Data Science and System East China University of Technology Nanchang 330013 Jiangxi China Jiangxi ZhongYe Light Culture Technology Limited Company Nanchang 330006 Jiangxi China

This paper introduces a whole project of augmented reality interaction mode based on netty communication method, determines the main technical difficulties in the implementation process, and finds the solution by means of system architecture design and communication protocol development. In this paper, the netty framework is adopted to deal with network IO and business logic, and the communication between each terminal device, virtual environment and server is established through long connection, This paper adopts the netty framework to deal with network IO and business logic, establishes communication between each terminal device and virtual environment and server through long connection, so as to realize fast and natural real-time interaction between various interactive devices and other augmented reality devices and virtual environments under multiple users. It can also solve the problem of high concurrency of real-time communication between various devices and the virtual environment in augmented reality.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A fundamental theorem for eco-environmental surface modelling and its applications

引用

science China Earth sciences 2020年第8期63卷 1092-1112页

作者： Tianxiang YUE Na ZHAO Yu LIU Yifu WANG Bin ZHANG Zhengping DU Zemeng FAN Wenjiao SHI Chuanfa CHEN Mingwei ZHAO Dunjiang SONG Shihai WANG Yinjun SONG Changqing YAN Qiquan LI Xiaofang SUN Lili ZHANG Yongzhong TIAN Wei WANG Ying’an WANG Shengnan MA Hongsheng HUANG Yimin LU Qing WANG Chenliang WANG Yuzhu WANG Ming LU Wei ZHOU Yi LIU Xiaozhe YIN Zong WANG Zhengyi BAO Miaomiao ZHAO Yapeng ZHAO Yimeng JIAO Ufra NASEER Bin FAN Saibo LI Yang YANG John PWILSON State Key L aboratory of Resources and Environment Information System Institute of Geographical Sciences and Natural Resources ResearchChinese Academy of SciencesBeijing 100101China College of Resources and Environment University of Chinese Academy of SciencesBeijing 100049China College of Land Resources and Environment Jiangxi Agricultural UniversityNanchang 330045China College of Geomatics Shandong University of Science and TechnologyQingdao 266590China College of Forestry Beijing Forestry UniversityBeijing 100083China School of Land and Resources China West Normal UniversityNanchong 637002China College of Geographical Information and Tourism Chuzhou UniversityChuzhou 239000China Institutes of Science and Development Chinese Academy of SciencesBeijing 100190China Department of Information Engineering Shandong University of Science and TechnologyTai'an 271019China College of Resources Sichuan Agricultural UniversityChengdu 611130China College of Geography and Tourism Qufu Normal UniversityRizhao 276828China Aerospace Information Research Institute Chinese Academy of SciencesBeijing 100101China School of Geographical Science Southwest UniversityChongqing 400715China National Disaster Reduction Center of China Ministry of Emergency ManagementBeijing 100721China Department for Population Data China Population and Development Research CenterBeijing 100081China Department for Industrial Standard China Standardization AdministrationBeijing 100088China The Academy of Digital China Fuzhou UniversityFuzhou 350002China National Institute of Environmental Health Chinese Center for Disease Control and PreventionBeijing 100021China School of Information Engineering China University of GeoscienceBeijing 100083China Qian Xuesen Laboratory of Space Technology Beijing 100094China College of Architecture and Urban Planning Chongqing Jiaotong UniversityChongqing 400074China Jiangsu Center for Collaborative Innovation in Geographical Information Resource Development and Application Nanjing

We propose a fundamental theorem for eco-environmental surface modelling(FTEEM) in order to apply it into the fields of ecology and environmental science more easily after the fundamental theorem for Earth’s surface system modeling(FTESM). The Beijing-Tianjin-Hebei(BTH) region is taken as a case area to conduct empirical studies of algorithms for spatial upscaling, spatial downscaling, spatial interpolation, data fusion and model-data assimilation, which are based on high accuracy surface modelling(HASM), corresponding with corollaries of FTEEM. The case studies demonstrate how eco-environmental surface modelling is substantially improved when both extrinsic and intrinsic information are used along with an appropriate method of HASM. Compared with classic algorithms, the HASM-based algorithm for spatial upscaling reduced the root-meansquare error of the BTH elevation surface by 9 m. The HASM-based algorithm for spatial downscaling reduced the relative error of future scenarios of annual mean temperature by 16%. The HASM-based algorithm for spatial interpolation reduced the relative error of change trend of annual mean precipitation by 0.2%. The HASM-based algorithm for data fusion reduced the relative error of change trend of annual mean temperature by 70%. The HASM-based algorithm for model-data assimilation reduced the relative error of carbon stocks by 40%. We propose five theoretical challenges and three application problems of HASM that need to be addressed to improve FTEEM.

关键词： HASM FTEEM Spatial upscaling Spatial downscaling Spatial interpolation data fusion Model-data assimilation Model coupling

来源：评论

学校读者我要写书评

暂无评论

Efficient MedSAMs: Segment Anything in Medical Images on Laptop

arXiv

引用

arXiv 2024年

作者： Ma, Jun Li, Feifei Kim, Sumin Asakereh, Reza Le, Bao-Hiep Nguyen-Vu, Dang-Khoa Pfefferle, Alexander Wei, Muxin Gao, Ruochen Lyu, Donghang Yang, Songxiao Purucker, Lennart Marinov, Zdravko Staring, Marius Lu, Haisheng Dao, Thuy Thanh Ye, Xincheng Li, Zhi Brugnara, Gianluca Vollmuth, Philipp Foltyn-Dumitru, Martha Cho, Jaeyoung Mahmutoglu, Mustafa Ahmed Bendszus, Martin Pflüger, Irada Rastogi, Aditya Ni, Dong Yang, Xin Zhou, Guang-Quan Wang, Kaini Heller, Nicholas Papanikolopoulos, Nikolaos Weight, Christopher Tong, Yubing Udupa, Jayaram K. Patrick, Cahill J. Wang, Yaqi Zhang, Yifan Contijoch, Francisco McVeigh, Elliot Ye, Xin He, Shucheng Haase, Robert Pinetz, Thomas Radbruch, Alexander Krause, Inga Kobler, Erich He, Jian Tang, Yucheng Yang, Haichun Huo, Yuankai Luo, Gongning Kushibar, Kaisar Amankulov, Jandos Toleshbayev, Dias Mukhamejan, Amangeldi Egger, Jan Pepe, Antonio Gsaxner, Christina Luijten, Gijs Fujita, Shohei Kikuchi, Tomohiro Wiestler, Benedikt Kirschke, Jan S. de la Rosa, Ezequiel Bolelli, Federico Lumetti, Luca Grana, Costantino Xie, Kunpeng Wu, Guomin Puladi, Behrus Martín-Isla, Carlos Lekadir, Karim Campello, Victor M. Shao, Wei Brisbane, Wayne Jiang, Hongxu Wei, Hao Yuan, Wu Li, Shuangle Zhou, Yuyin Wang, Bo AI Collaborative Centre University Health Network Department of Laboratory Medicine and Pathobiology University of Toronto Vector Institute Toronto Canada Peter Munk Cardiac Centre University Health Network Toronto Canada Toronto General Hospital Research Institute University Health Network Department of Computer Science University of Toronto University Health Network Vector Institute Toronto Canada University of Science Vietnam National University Ho Chi Minh City Viet Nam Institute of Computer Science University of Freiburg Freiburg Germany School of Medicine and Health Harbin Institute of Technology Harbin China Division of Image Processing Department of Radiology Leiden University Medical Center Leiden Netherlands Department of System and Control Engineering School of Engineering Institute of Science Tokyo Formerly Tokyo Institute of Technology Tokyo Japan Institute for Anthropomatics and Robotics Karlsruhe Institute of Technology Karlsruhe Germany School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu China School of Electrical Engineering and Computer Science University of Queensland Brisbane Australia School of Cyberspace Hangzhou Dianzi University Hangzhou China Division for Computational Radiology and Clinical AI The Department of Neuroradiology University Hospital Bonn Germany Division for Computational Radiology and Clinical AI The Department of Neuroradiology University Hospital Bonn Germany Department of Neuroradiology Heidelberg University Hospital Heidelberg Germany Division for Computational Radiology and Clinical AI Department of Neuroradiology University Hospital Bonn Germany School of Biomedical Engineering Shenzhen University Shenzhen China School of Biological Science and Medical Engineering Southeast University Nanjing China Department of Urology Cleveland Clinic Cleveland United States Department of Computer Science University of Minnesota Minneapolis United St

Promptable segmentation foundation models have emerged as a transformative approach to addressing the diverse needs in medical images, but most existing models require expensive computing, posing a big barrier to their adoption in clinical practice. In this work, we organized the first international competition dedicated to promptable medical image segmentation, featuring a large-scale dataset spanning nine common imaging modalities from over 20 different institutions. The top teams developed lightweight segmentation foundation models and implemented an efficient inference pipeline that substantially reduced computational requirements while maintaining state-of-the-art segmentation accuracy. Moreover, the post-challenge phase advanced the algorithms through the design of performance booster and reproducibility tasks, resulting in improved algorithms and validated reproducibility of the winning solution. Furthermore, the best-performing algorithms have been incorporated into the open-source software with a user-friendly interface to facilitate clinical adoption. The data and code are publicly available to foster the further development of medical image segmentation foundation models and pave the way for impactful real-world applications. © 2024, CC BY-NC-SA.

关键词： Open source software

来源：评论

学校读者我要写书评

暂无评论

Corrigendum to “Oscillation-free source term inversion of atmospheric radionuclide releases with joint model bias corrections and non-smooth competing priors” [J. Hazard. Mater. 440 (2022) 129806]

引用

Journal of Hazardous Materials 2023年 445卷

作者： Sheng Fang Xinwen Dong Shuhan Zhuang Zhijie Tian Tianfeng Chai Yuhan Xu Yungang Zhao Li Sheng Xuan Ye Wei Xiong Institute of Nuclear and New Energy Technology Collaborative Innovation Centre of Advanced Nuclear Energy Technology Key Laboratory of Advanced Reactor Engineering and Safety of Ministry of Education Tsinghua University Beijing 100084 China China Institute for Radiation Protection Taiyuan 030006 China NOAA Air Resources Laboratory (ARL) NOAA Center for Weather and Climate Prediction 5830 University Research Court College Park MD 20740 USA Cooperative Institute for Climate and Satellites University of Maryland College Park MD 20740 USA Key Laboratory of Beam Technology of Ministry of Education College of Nuclear Science and Technology Beijing Normal University Beijing 100875 China CTBT Beijing National Data Centre and Beijing Radionuclide Laboratory Beijing 100085 China CMA Earth System Modeling and Prediction Center (CEMC) Beijing 100081 China

来源：评论

学校读者我要写书评

暂无评论

A Study of Combined Peak-Searching Method for Symmetric Zero Area and Gaussian Product Function Based on γ-ray Spectrum

A Study of Combined Peak-Searching Method for Symmetric Zero...

引用

2018 4th Workshop on Advanced research and technology in Industry Applications(WARTIA 2018)

作者： He Jianfeng Huang Sheng Ye Zhixiang Wang Xueyuan Li Xiang Zhou Shirong Fundamental Science on Radioactive Geology and Exploration Technology Laboratory East China Institute of Technology Jiangxi Engineering Laboratory on Radioactive Geoscience and Big Data Technology East China University of Technology Jiangxi Engineering Technology Research Center of Nuclear Geoscience Data Science and System East China University of Technology Jiangxi Food and Drug Administration

The peak position of each peak is determined accurately in the spectra, which is a key problem in the analysis of γ-ray spectrum. In this paper, basis of comparing the Gaussian product function method and the symmetrical zero area method, the IAEA-approved G-1200 is selected as the peak-searching test spectra, the simulation experiment based on MATLAB is used for the test analysis and to extract the corresponding characteristic parameters of the spectral line. Aiming at the respective advantages of the two peak searching methods in γ-ray spectrum analysis, a method of combined peak-searching for symmetric zero area and Gaussian product function is proposed, which the statistical fluctuation of spectral data is effectively reduced, the background effect is eliminated, the peak positions information is highlighted, and the true peaks or false peaks can be identified according to the preset conditions. The result of experiment represents that symmetric zero area and Gaussian product function combined peak-searching method to peak-searching is also suitable for unsmooth data, this method has the advantages of small calculation amount, fast searching speed and obvious effect.

关键词： γ-ray Energy Spectra Gaussian Product Function Method Symmetric Zero Area Method Combined Peak-Searching

来源：评论

学校读者我要写书评

暂无评论

research and Implementation of Big data technology Laboratory Equipment Reservation Management system

引用

IOP Conference Series: Earth and Environmental science 2019年第4期252卷

作者： Yiting Wang Zhenhua Wei Junwu Cao Zhifeng Liu Jiangxi Engineering Laboratory on Radioactive Geoscience and Big Data Technology East China University of Technology Nanchang 330013 Jiangxi China School of Information Engineering East China University of Technology Nanchang 330013 Jiangxi China Jiangxi Engineering Technology Research Center of Nuclear Geoscience Data Science and System East China University of Technology Nanchang 330013 Jiangxi China

At present, the laboratory management system of most universities lacks functions and expansibility, so it cannot be adapted to laboratories with high degree of customization. Based on the analysis of the past experience of the laboratory management system in colleges and universities, this paper explores the construction of a comprehensive system suitable for the appointment management of laboratory equipment in colleges and universities. The system adopts Java Web related technology, Web database interaction technology and B/S architecture to form a modular structure with complete functions and flexible management. The construction of the system has realized the standardization, process and integration management of university laboratories, and promoted the effective utilization of university laboratory equipment in colleges and universities.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Visualization research of STL Model Based on OpenGL technology

引用

Journal of Physics: Conference Series 2020年第1期1437卷

作者： Xu, Wei Jia, Hongwei East China University of Technology Economic Development Zone Guanglan Avenue 418 Nanchang330013 China Jiangxi Engineering Technology Research Center of Nuclear Geoscience Data Science and System Economic Development Zone Guanglan Avenue 418 Nanchang330013 China East China University of Technology Economic Development Zone Guanglan Avenue 418 Nanchang330013 China

With the OpenGL visualization as the background, some important attributes in the OpenGL application data table are processed by using the STL model visualization method. According to the advantages and disadvantages of OpenGL technology, it is rationally optimized. According to the computer display mode, the scale of visual graphics is designed. The OpenGL visualization data and the OpenGL STL model visualization method are reasonably combined, and the corresponding human-computer interaction technology is applied, which allows the user to customize the data according to the task goals.

关键词：

来源：评论

学校读者我要写书评

暂无评论

research on the Captcha Recognition Method Based On Neural Network

引用

IOP Conference Series: Earth and Environmental science 2019年第5期252卷

作者： Zhifeng Liu Xiaohu Tang Zhenhua Wei Jiangxi Engineering Technology Research Center of Nuclear Geoscience Data Science and System East China University of Technology Nanchang 330013 China. East China University of Technology Nanchang 330013 China.

In this paper, the CAPTCHA recognition is studied by using neural network algorithm. Because the traditional BP neural network itself has problems such as uncertain structural parameters, low convergence rate and easy to fall into local minimum, this paper identifies the words in the image according to the pixel value of the verification code. In this paper, the image is divided into individual letters, and then the identified letters are spelled into words. Experimental results show that The accuracy of individual letters was higher, but the accuracy of letters identified from each small image was much lower. The accuracy can be improved by adding dictionaries to the prediction function to find the most matching words.

关键词：

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：