检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

5,634 篇 会议
90 篇 期刊文献
10 册 图书

馆藏范围

5,734 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

2,774 篇 工学
- 2,332 篇 计算机科学与技术...
- 1,329 篇 软件工程
- 567 篇 信息与通信工程
- 466 篇 电气工程
- 200 篇 生物工程
- 174 篇 控制科学与工程
- 174 篇 生物医学工程（可授...
- 109 篇 机械工程
- 84 篇 交通运输工程
- 83 篇 化学工程与技术
- 80 篇 电子科学与技术（可...
- 79 篇 光学工程
- 69 篇 仪器科学与技术
- 65 篇 动力工程及工程热...
- 55 篇 土木工程
- 55 篇 安全科学与工程
897 篇 理学
- 478 篇 数学
- 235 篇 生物学
- 231 篇 物理学
- 191 篇 统计学（可授理学、...
- 119 篇 系统科学
- 66 篇 化学
589 篇 管理学
- 327 篇 图书情报与档案管...
- 305 篇 管理科学与工程(可...
- 163 篇 工商管理
289 篇 医学
- 243 篇 临床医学
- 144 篇 基础医学(可授医学...
- 80 篇 药学(可授医学、理...
- 52 篇 公共卫生与预防医...
76 篇 法学
- 71 篇 社会学
54 篇 经济学
45 篇 教育学
39 篇 农学
26 篇 文学
2 篇 军事学
1 篇 历史学
1 篇 艺术学

主题

1,600 篇 data models
535 篇 predictive model...
530 篇 training
498 篇 machine learning
461 篇 data mining
416 篇 big data
405 篇 computational mo...
343 篇 feature extracti...
333 篇 task analysis
327 篇 prediction algor...
268 篇 deep learning
255 篇 machine learning...
245 篇 classification a...
238 篇 analytical model...
191 篇 clustering algor...
190 篇 support vector m...
183 篇 neural networks
158 篇 natural language...
142 篇 training data
141 篇 mathematical mod...

机构

19 篇 sun yat sen univ...
19 篇 daffodil interna...
12 篇 univ chinese aca...
11 篇 tsinghua univers...
11 篇 university of ch...
11 篇 school of data a...
10 篇 carnegie mellon ...
9 篇 renmin univ chin...
9 篇 lviv polytechnic...
8 篇 shenzhen researc...
7 篇 shanghai jiao to...
7 篇 college of compu...
7 篇 university of el...
7 篇 school of comput...
7 篇 national univers...
7 篇 harbin institute...
7 篇 beijing key lab ...
7 篇 natl univ def te...
7 篇 renmin univ chin...
6 篇 university of sc...

作者

7 篇 li li
7 篇 wang wei
7 篇 xiao yanghua
6 篇 wen ji-rong
6 篇 cui bin
6 篇 zhao wayne xin
6 篇 ying liu
6 篇 syed akhter hoss...
5 篇 yang tong
5 篇 liu yang
5 篇 li zhang
5 篇 jia weijia
5 篇 chen liu
5 篇 yang yang
5 篇 xiao hongbo
5 篇 nguyen trong-the
5 篇 yu jie
5 篇 albert bifet
5 篇 wang bin
5 篇 carlos ordonez

语言

5,596 篇 英文
130 篇 其他
14 篇 中文
2 篇 俄文
1 篇 乌克兰文

检索条件"任意字段=2020 International Conference on Data Processing Algorithms and Models, ICDPAM 2020"

共 5734 条记录，以下是701-710 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Interpretability of Black Box models Through data-View Extraction and Shadow Model Creation 27th

Interpretability of Black Box Models Through Data-View Extra...

引用

27th international conference on Neural Information processing

作者： Patir, Rupam Singhal, Shubham Anantaram, C. Goyal, Vikram Indraprastha Inst Informat Technol Delhi India

ISBN: (纸本)9783030638221;9783030638238

Deep learning models trained using massive amounts of data, tend to capture one view of the data and its associated mapping. Different deep learning models built on the same training data may capture different views of the data based on the underlying techniques used. For explaining the decisions arrived by Black box deep learning models, we argue that it is essential to reproduce that model's view of the training data faithfully. This faithful reproduction can then be used for explanation generation. We investigate two methods for data-view extraction: Hill Climbing approach and a GAN-driven approach. We then use this synthesized data for explanation generation by using methods such as Decision-Trees and Permutation Importance. We evaluate these approaches on a Black box model trained on public datasets and show its usefulness in explanation generation.

关键词： Interpretability data-view extraction data synthesis

来源：评论

学校读者我要写书评

暂无评论

Automatic Landmark Localization in 3D Medical CT Images: Few-Shot Learning through Optimized data Pre-processing and Network Design 10

Automatic Landmark Localization in 3D Medical CT Images: Few...

引用

10th international conference on Bioinformatics Research and Applications, ICBRA 2023

作者： Wang, Yifan Lenarz, Thomas Kral, Andrej John, Samuel HörSys GmbH Hannover Medical School Germany Department of Otolaryngology Head & Neck Surgery Hannover Medical School Germany Institute of AudioNeuroTechnology & Cluster of Excellence Hearing4all Department of Experimental Otology ENT Department Hannover Medical School Germany HörSys GmbH Feodor-Lynen-Str. 35 Hannover30625 Germany

ISBN: (纸本)9798400708152

As surgeons increasingly rely on computed tomography (CT) scans, including low-dose cone beam CT, it has become critical to effectively understand and annotate these medical images, not only for improved treatment planning, but also for robotic and implant surgery. However, in clinical practice, accurate localization and annotation of specific landmarks still relies heavily on manual efforts. Consequently, we present an automatic landmark localization pipeline with few-shot learning, specifically designed for 3D CT scans. In this paper, we focus on the cochlea structure with its three landmarks (apex point, basal point, round window center). The pipeline leverages an optimized data processing in conjunction with a novel designed 2D Convolutional Neural Network (CNN) model. To evaluate the effectiveness of our pipeline in a few-shot learning context, we used 31 volumetric CT scans along with their corresponding annotated landmarks, where 20 volumes are reserved for testing exclusively, while with varying quantities volumes for training, ranging from 1 up to 11. A comparative analysis was conducted among models trained on different numbers of CT volumes. We began by using the weighted F1 score to evaluate the landmark classification performance within the extracted 2D sub-images. A model trained with only 5 CT volumes achieves its peak performance with median weighted F1 scores of around 0.99 (apex), 0.985 (basal), 0.98 (round window center), 0.98 (background). By manually providing an initial point placed near the cochlea, the automatic localization for all three landmarks within the 3D CT volume was then accomplished using a sliding window approach. Compared to manually defined ground truth, the 5-volume-trained model attained an average Euclidean distance error of 0.70 mm (apex), 1.15 mm (basal) and 0.84 mm (round window center) on 3D CT volumes from test set. This demonstrates the efficiency and accuracy of this pipeline. © 2023 Copyright held by the owner/author(

关键词： Pipelines

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Machine Unlearning 1

引用

17th international conference on Learning and Intelligent Optimization, LION-17 2023

作者： Zhu, HongBin Xia, YuXiao Li, YunZhao Li, Wei Liu, Kang Gao, Xianzhou Big Data Center State Grid of China Beijing100012 China State Grid Smart Grid Research Institute Shanghai200016 China State Key Laboratory for Novel Software Technology Department of Computer Science and Technology Nanjing University Nanjing200016 China

ISBN: (数字)9783031445057

ISBN: (纸本)9783031445040

In recent years, deep neural networks have enjoyed tremendous success in industry and academia, especially for their applications in visual recognition and natural language processing. While large-scale deep models bring incredible performance, their massive data requirements pose a huge threat to data privacy protection. With the growing emphasis on data security, the study of data privacy leakage in machine learning, such as machine unlearning, has become increasingly important. There have been many works on machine unlearning, and other research has proposed training several submodels to speed up the retraining process, by dividing the training data into several disjoint fragments. When the impact of a particular data point in the model is to be removed, the model owner simply retrains the sub-model containing this data point. Nevertheless, current learning methods for machine unlearning are still not widely used due to model applicability, usage overhead, etc. Based on this situation, we propose a novel hierarchical learning method, Hierarchical Machine Unlearning (HMU), with the known distribution of unlearning requests. Compared with previous methods, ours has better efficiency. Using the known distribution, the data can be partitioned and sorted, thus reducing the overhead in the data deletion process. We propose to train the model using the hierarchical data set after partitioning, which further reduces the loss of prediction accuracy of the existing methods. It is also combined with incremental learning methods to speed up the training process. Finally, the effectiveness and efficiency of the method proposed in this paper are verified by multiple experiments. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： data privacy

来源：评论

学校读者我要写书评

暂无评论

Research on 3D Cloud Modeling based on the Combination of Meteorological data and Multiple Noises

Research on 3D Cloud Modeling based on the Combination of Me...

引用

Computers, Information processing and Advanced Education (CIPAE), 2020 international conference on

作者： He Ren Xiaoxi He Liang Hu Yunhui Guo Jinwei Chen Min Wang The School of Software Engineering Chengdu University of Information Technology Chengdu China

ISBN: (数字)9798331527662

ISBN: (纸本)9798331527679

In order to create a more realistic cloud simulation environment, volumetric cloud modeling combined with real meteorological data is usually considered. At present, cloud simulation based on real meteorological data basically adopts physical modeling methods, such as solving fluid dynamics equations and particle system modeling, etc. However, these methods involve a large amount of calculation for solving calculus equations, so they are often limited in the scale of drawing, and it is difficult to perform real-time simulation in large-scale scenes. The authenticity and real-time performance of volumetric cloud simulation still need to be further improved. Therefore, through the analysis of existing research, a three-dimensional volumetric cloud construction method based on meteorological data is proposed. The specific method is to generate a two-dimensional cloud map based on humidity data, and then combine the cloud map with an improved height density function to make the shape and density of the cloud change with height and meteorological data, and combine it with multiple noises to construct the shape and details of the cloud. Finally, the Raymarching algorithm is used for rendering, and finally a large-scale volumetric cloud that matches the meteorological data is constructed. This paper combines meteorological data with non-physical modeling methods effectively. Experimental results show that the volumetric cloud modeled by this method matches the cloud map generated by meteorological data, and is more realistic in shape and appearance. The cloud body modeling results have more realistic details without distortion.

关键词： Solid modeling Three-dimensional displays Shape Clouds Morphology Rendering (computer graphics) Distortion data models Mathematical models Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Platform for Extreme Scale Computing on Compressed IoT data

Machine Learning Platform for Extreme Scale Computing on Com...

引用

2022 IEEE international conference on Big data, Big data 2022

作者： Tirupathi, Seshu Salwala, Dhaval Zizzo, Giulio Rawat, Ambrish Purcell, Mark Kejser Jensen, Soren Thomsen, Christian Ho, Nguyen Muniz Cuza, Carlos E. Brusokas, Jonas Bach Pedersen, Torben Alexiou, Giorgos Giannopoulos, Giorgos Gidarakos, Panagiotis Kalimeris, Alexandros Maroulis, Stavros Papastefanatos, George Psarros, Ioannis Stamatopoulos, Vassilis Terrovitis, Manolis Ibm Research Europe Dublin Ireland Aalborg University Denmark Athena Research Center Greece

ISBN: (纸本)9781665480451

With the lowering costs of sensors, high-volume and high-velocity data are increasingly being generated and analyzed, especially in IoT domains like energy and smart homes. Consequently, applications that require accurate short-term forecasts and predictions are also steadily increasing. In this paper, we provide an overview of a novel end-to-end platform that provides efficient ingestion, compression, transfer, query processing, and machine learning-based analytics for high-frequency and high-volume time series from IoT. The performance of the platform is evaluated using real-world dataset from RES installations. The results show the importance of high-frequency analytics and the surprisingly positive impact of error bounded lossy compression on machine learning in the form of AutoML. For example, when detecting yaw misalignments in wind turbines, an improvement of 9% in accuracy was observed for AutoML models on lossy compressed data compared to the current industry standard of 10-minute aggregated data. Thus, these small-scale experiments show the potential of the platform, and larger pilots are planned. © 2022 IEEE.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Research on the Effect of New Computer data processing Technology on the Development of Modern Avionics Equipment

Research on the Effect of New Computer Data Processing Techn...

引用

2020 international conference on Mechanical Automation and Computer Engineering, MACE 2020

作者： Jia, Xu Guangzhou Civil Aviation College Guangzhou510470 China

For now, the continuous advancement of computer data processing technology has brought about earth-shaking improvements in the infrastructure and basic technology models of various industries in our society. In the course of the development of modern avionics equipment, the application of data processing skills has firmly grasped the air control authority of aviation electronic equipment. For the future progress of modern avionics, this is an epoch-making breakthrough in computer skills. This article analyzes the development of various aspects of avionics equipment from different perspectives. In addition, this article also conducts a rough analysis and exploration of computer skills related to equipment that can break through modern avionics to help study the practicability of the equipment assisted by it. © Published under licence by IOP Publishing Ltd.

关键词： data handling

来源：评论

学校读者我要写书评

暂无评论

Control-Oriented In Situ Imaging and data Analytics for Coaxial Monitoring of Powder Bed Fusion Additive Manufacturing 5

Control-Oriented In Situ Imaging and Data Analytics for Coax...

引用

5th ASTM international conference on Additive Manufacturing, ICAM 2020

作者： Jiang, Tianyu Leng, Mengying Chen, Xu Mechanical Engineering University of Washington 3900 E. Stevens Way NE SeattleWA98195 United States

ISBN: (纸本)9780803177215

Despite recent advancements in powder bed fusion additive manufacturing, in-process monitoring and quality assurance remain insufficient for wide applications in production. One obstacle is the interpretation and evaluation of the intense monitoring data. The objective of this study is to discuss a data processing infrastructure for coaxial sensing toward consistent and repetitive additive manufacturing. The infrastructure is developed based on an image database collected from an in-house-developed powder bed fusion platform. This work first addresses salient issues in the raw data (e.g., noises, inconsistent illumination, and low contrast) leveraging several preprocessing algorithms. By utilizing graph-based segmentation, the authors' approach then leads to an innovation to isolate laser-fused materials from the unmolten powder bed. In the experiment of printing an overhang structure, this study provides detection of the formation of an overheating defect and proposes new features that correlate to part geometry and process parameters. These results can be further used to bridge the gap between spatially resolved process monitoring and ultimate model-based control for robust and high-throughput additive manufacturing. Copyright © 2022 by ASTM international, 100 Barr Harbor Drive, PO Box C700, West Conshohocken, PA 19428-2959.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Privacy Protection and data Security Enhancement (PPDSE) Model in Student Management Information Systems

Privacy Protection and Data Security Enhancement (PPDSE) Mod...

引用

Electronics and Sustainable Communication Systems (ICESC), 2020 international conference on

作者： Baoli Pan Shandong Agriculture and Engineering University School of Humanities Jinan China

ISBN: (数字)9798350379945

ISBN: (纸本)9798350379952

The implementation of a Privacy Protection and data Security Enhancement (PPDSE) model within Student Management Information Systems (SMIS) is critical for protecting sensitive information in educational institutions. This study presents a novel approach that integrates advanced cryptographic techniques to enhance data security in SMIS. The model uses the Paillier encryption algorithm to ensure homomorphic encryption, which allows secure data operations without exposing the underlying information. The designed SMIS architecture, based on J2EE and. NET technologies, is carefully crafted to optimize performance and security. Experiments were conducted using four real-world datasets from the UCI public machine learning repository, each meticulously annotated to ensure data accuracy. Computational and communication overheads were measured over a range of data sizes. The results show that the computational overhead ranged from 0.08 seconds for 256 data points to 1.013 seconds for 2048 data points. Similarly, the communication overhead increased from 6,231 KB to 50,233 KB for the same data sizes.

关键词： data privacy Java Machine learning algorithms Management information systems Machine learning Computer architecture Size measurement data models Protection Homomorphic encryption

来源：评论

学校读者我要写书评

暂无评论

The digital data processing concepts of the Large Area Detector and the Wide Field Monitor onboard eXTP

The digital data processing concepts of the Large Area Detec...

引用

conference on Space Telescopes and Instrumentation - Ultraviolet to Gamma Ray Part of SPIE Astronomical Telescopes and Instrumentation conference

作者： Xiong, Hao Argan, Andrea Baudin, David Bayer, Joerg Bouyjou, Florent De Angelis, Nicolas Del Monte, Ettore Evangelista, Yuri Favre, Yannick Feroci, Marco Galvez, Jose-Luis Gevin, Olivier Hedderman, Paul Hernanz, Margarita Kole, Merlin Reynard Meuris, Aline Pliego-Caballero, Samuel Santangelo, Andrea Tenzer, Chris Trois, Alessio Wang, Xianqi Zampa, Gianluigi IAAT Univ Tubingen Sand 1 D-72076 Tubingen Germany INAF IAPS Via Fosso Cavaliere 100 I-00133 Rome Italy INFN Roma Tor Vergata Via Ric Sci I-00133 Rome Italy Univ Paris Saclay CEA IRFU F-91191 Gif Sur Yvette France Univ Geneva DPNC 24 Quai Ernest Ansermet CH-1205 Geneva Switzerland Inst Ciencies Espai ICE CSIC Campus UAB Cerdanyola De Valles 08193 Barcelona Spain Inst Estudis Espacials Catalunya IEEC Gran Capita 2-4 Barcelona 08034 Spain INAF Osservatorio Astron Cagliari Via Sci 5 I-09047 Selargius CA Italy INFN Trieste Padriciano 99 I-34149 Trieste Italy

ISBN: (纸本)9781510653443;9781510653436

The enhanced X-ray Timing and Polarimetry (eXTP) mission is a large innovative observatory in the field of X-ray astronomy, designed to study the properties of matter under extreme conditions of density, gravity, and magnetic fields. It is developed by an international consortium led by the Institute of High Energy Physics (IHEP) of the Chinese Academy of Sciences (CAS) and is currently completing Phase B with a launch foreseen in 2027. Two of the four instruments onboard eXTP will be provided by a European consortium: the Large Area Detector (LAD) and the Wide Field Monitor (WFM). These two instruments use a high number of largearea Silicon Drift Detectors (SDDs) that are organized in 40 modules of 16 detectors each for the LAD and in 6 coded-aperture cameras with 4 detectors each for the WFM. The high multiplicity and modularity of this concept as well as the high data rates call for a novel, hierarchical data processing scheme. A similar concept is applied in the data acquisition and processing system of the LAD and the WFM. Silicon Drift Detector and Front End Electronics using ASIC technology constitute the Detector Assembly. data processing is performed in an FPGA-based digital circuit using only ITAR-free components in order to facilitate export to the launch site in China. The design of the digital electronics is not yet finally frozen, but the development and manufacturing of demonstrator models have been already completed. The FPGA firmware based on the pipeline data processing concept has been developed in VHDL. This concept allows real-time data processing capabilities and reduces dead time, thus improving the detection capacity for high flux sources.

关键词： eXTP LAD WFM digital data processing

来源：评论

学校读者我要写书评

暂无评论

Queue Profile Identification at Signalized Intersections with High-Resolution data from Drones 7

Queue Profile Identification at Signalized Intersections wit...

引用

7th international conference on models and Technologies for Intelligent Transportation Systems (MT-ITS)

作者： Zhou, Qishen Mohammadi, Roozbeh Zhao, Weiming Zhang, Kaihang Zhang, Lihui Wang, Yibing Roncoli, Claudio Hu, Simon Zhejiang Univ Sch Civil Engn ZJU UIUC Inst Haining 314400 Peoples R China Aalto Univ Dept Built Environm Espoo Finland Zhejiang Univ Sch Civil Engn & Architecture Hangzhou 310058 Peoples R China

ISBN: (纸本)9781728189956

Queue profile is a crucial measure for traffic management in the vicinity of signalized intersections. In this study, we develop a method to identify queue profile using high resolution data, which can be provided from various sources such as drones. Our methodology has three main components which are signal state estimation, queue profile identification, and lane detection. The developed algorithms are tested on the real-world dataset collected by drones as a case study for validation. Remarkably, our method only uses drone data as input and it is independent from any other data source such as geographic information system data. The results demonstrate satisfactory performance of the methodology in extracting queue profile information from raw drone data. The developed algorithm can be also applied on data collected via connected vehicles in future.

关键词： queue length traffic management high resolution data trajectory data clustering

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共500页 << < 67 68 69 70 71 72 73 74 75 76 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：