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

5,626 篇 会议
90 篇 期刊文献
10 册 图书

馆藏范围

5,726 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

2,768 篇 工学
- 2,326 篇 计算机科学与技术...
- 1,324 篇 软件工程
- 566 篇 信息与通信工程
- 466 篇 电气工程
- 200 篇 生物工程
- 176 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
- 81 篇 电子科学与技术（可...
- 79 篇 光学工程
- 70 篇 仪器科学与技术
- 65 篇 动力工程及工程热...
- 55 篇 安全科学与工程
- 54 篇 土木工程
- 52 篇 环境科学与工程（可...
899 篇 理学
- 478 篇 数学
- 235 篇 生物学
- 232 篇 物理学
- 191 篇 统计学（可授理学、...
- 119 篇 系统科学
- 67 篇 化学
589 篇 管理学
- 326 篇 图书情报与档案管...
- 307 篇 管理科学与工程(可...
- 164 篇 工商管理
290 篇 医学
- 244 篇 临床医学
- 144 篇 基础医学(可授医学...
- 80 篇 药学(可授医学、理...
76 篇 法学
- 71 篇 社会学
55 篇 经济学
45 篇 教育学
40 篇 农学
26 篇 文学
2 篇 军事学
1 篇 历史学
1 篇 艺术学

主题

1,599 篇 data models
534 篇 predictive model...
529 篇 training
498 篇 machine learning
461 篇 data mining
416 篇 big data
404 篇 computational mo...
343 篇 feature extracti...
333 篇 task analysis
326 篇 prediction algor...
267 篇 deep learning
255 篇 machine learning...
245 篇 classification a...
238 篇 analytical model...
191 篇 clustering algor...
190 篇 support vector m...
182 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

5,682 篇 英文
36 篇 其他
9 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 5726 条记录，以下是171-180 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：

data Science in Supporting Hotel Management: Application of Predictive models to *** Guest Evaluations 1

引用

international conference on Tourism, Technology and Systems (ICOTTS)

作者： Martins, Ana Filipa Silva, Luis M. Marques, Jorge Univ Aveiro Dept Social Polit & Terr Sci P-3810193 Aveiro Portugal Univ Aveiro CIDMA Ctr Res & Dev Math & Applicat Dept Math P-3810193 Aveiro Portugal Univ Portucalense Dept Tourism Heritage & Culture REMIT Res Econ Management & Informat Technol P-4200072 Porto Portugal Univ Coimbra CEGOT Ctr Studies Geog & Spatial Planning P-3004530 Coimbra Portugal

ISBN: (数字)9789819997589

ISBN: (纸本)9789819997572;9789819997589;9789819998821

data science is a multidisciplinary area that gathers several branches, such as statistics, databases, and computer science and whose importance has become more substantial over the last few years. Using several techniques and algorithms from machine learning allows us to understand how certain variables are related, as well as to visualize data and make predictions. This paper aims to use data science as a strategic instrument for the hospitality industry by proposing a model that can help to predict which characteristics will be more valued by guests. By better understanding which features guests value most when evaluating a stay at a hotel, it will be easier for hotel managers to make informed decisions about which service operations management strategies should be used. It can also be helpful in terms of investment decisions, as it can indicate which aspects will be most important to value in a hotel. In this research, it was possible to conclude that guests' ratings are related primarily to the commodities available at the hotels, followed by cleanliness, staff, location, price-quality relation, and comfort.

关键词： data science Hospitality Hotel management Hotels Rating systems

来源：评论

学校读者我要写书评

暂无评论

Neuro-Symbolic Class Expression Learning 32

Neuro-Symbolic Class Expression Learning

引用

32nd international Joint conference on Artificial Intelligence (IJCAI)

作者： Demir, Caglar Ngomo, Axel-Cyrille Ngonga Paderborn Univ Data Sci Res Grp Paderborn Germany

ISBN: (纸本)9781956792034

models computed using deep learning have been effectively applied to tackle various problems in many disciplines. Yet, the predictions of these models are often at most post-hoc and locally explainable. In contrast, class expressions in description logics are ante-hoc and globally explainable. Although state-of-the-art symbolic machine learning approaches are being successfully applied to learn class expressions, their application at large scale has been hindered by their impractical runtimes. Arguably, the reliance on myopic heuristic functions contributes to this limitation. We propose a novel neuro-symbolic class expression learning model, DRILL, to mitigate this limitation. By learning non-myopic heuristic functions with deep Q-learning, DRILL efficiently steers the standard search procedure in a quasi-ordered search space towards goal states. Our extensive experiments on 4 benchmark datasets and 390 learning problems suggest that DRILL converges to goal states at least 2.7 times faster than state-of-the-art models on all learning problems. The results of our statistical significance test confirms that DRILL converges to goal states significantly faster (p-value < 1%) than state-of-the-art models on all benchmark datasets. We provide an open-source implementation of DRILL, including pre-trained models, training and evaluation scripts.

关键词： Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

Simulator-Based Inference with WALDO: Confidence Regions by Leveraging Prediction algorithms and Posterior Estimators for Inverse Problems 26

Simulator-Based Inference with WALDO: Confidence Regions by ...

引用

26th international conference on Artificial Intelligence and Statistics (AISTATS)

作者： Masserano, Luca Dorigo, Tommaso Izbicki, Rafael Kuusela, Mikael Lee, Ann B. Carnegie Mellon Univ Dept Stat & Data Sci Pittsburgh PA 15213 USA Carnegie Mellon Univ NSF AI Planning Inst Data Driven Discovery Phys Pittsburgh PA 15213 USA INFN Sez Padova Padua Italy Univ Fed Sao Carlos Dept Stat Sao Carlos Brazil

Prediction algorithms, such as deep neural networks (DNNs), are used in many domain sciences to directly estimate internal parameters of interest in simulator-based models, especially in settings where the observations include images or complex high-dimensional data. In parallel, modern neural density estimators, such as normalizing flows, are becoming increasingly popular for uncertainty quantification, especially when both parameters and observations are high-dimensional. However, parameter inference is an inverse problem and not a prediction task;thus, an open challenge is to construct conditionally valid and precise confidence regions, with a guaranteed probability of covering the true parameters of the data-generating process, no matter what the (unknown) parameter values are, and without relying on large-sample theory. Many simulator-based inference (SBI) methods are indeed known to produce biased or overly confident parameter regions, yielding misleading uncertainty estimates. This paper presents WALDO, a novel method to construct confidence regions with finite-sample conditional validity by leveraging prediction algorithms or posterior estimators that are currently widely adopted in SBI. WALDO reframes the well-known Wald test statistic, and uses a computationally efficient regression-based machinery for classical Neyman inversion of hypothesis tests. We apply our method to a recent high-energy physics problem, where prediction with DNNs has previously led to estimates with prediction bias. We also illustrate how our approach can correct overly confident posterior regions computed with normalizing flows.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

3rd international conference on Dynamic data Driven Application Systems, DDDAS 2020

3rd International Conference on Dynamic Data Driven Applicat...

引用

3rd international conference on Dynamic data Driven Application Systems, DDDAS 2020

ISBN: (纸本)9783030617240

The proceedings contain 43 papers. The special focus in this conference is on Dynamic data Driven Application Systems. The topics include: A DDDAS Protocol for Real-Time Large-Scale UAS Flight Coordination;data-Driven State Awareness for Fly-by-Feel Aerial Vehicles via Adaptive Time Series and Gaussian Process Regression models;preface;predictive Digital Twins: Where Dynamic data-Driven Learning Meets Physics-Based Modeling;Integrated Planning, Decision-Making, and Weather Modeling for UAS Navigating Complex Weather;Microgrid Operational Planning Using Deviation Clustering Within a DDDAS Framework;dynamic data-Driven Self-healing Application for Phasor Measurement Unit Networks;interpretable Deep Attention Model for Multivariate Time Series Prediction in Building Energy Systems;overcoming Stealthy Adversarial Attacks on Power Grid Load Predictions Through Dynamic data Repair;Uncertainty Analysis of Self-healed Composites with Machine Learning as Part of DDDAS;active Search Methods to Predict Material Failure Under Intermittent Loading in the Serebrinksy-Ortiz Fatigue Model;dynamic data-Driven Distribution Tracking of Nanoparticle Morphology;machine Learning algorithms for Improved Thermospheric Density Modeling;Dynamic Transfer Learning from Physics-Based Simulated SAR Imagery for Automatic Target Recognition;Dynamic data-Driven Application Systems for NASA’s Science Mission Directorate;uncertainty Estimation for Semantic Segmentation of Hyperspectral Imagery;Spectral Super Resolution with DCT Decomposition and Deep Residual Learning;active Scene Classification via Dynamically Learning Prototypical Views;informative Ensemble Kalman Learning for Neural Structure;reachability Analysis Based Tracking: Applications to Non-cooperative Space Object Tracking;sparse Regression and Adaptive Feature Generation for the Discovery of Dynamical Systems;improving Prediction Confidence in Learning-Enabled Autonomous Systems;towards Provably Correct Probabilistic Flight Systems;data

关键词：

来源：评论

学校读者我要写书评

暂无评论

Classification-Aware Neural Topic Model CombinedWith Interpretable Analysis - For Conflict Classification

Classification-Aware Neural Topic Model CombinedWith Interpr...

引用

2023 international conference Recent Advances in Natural Language processing: Large Language models for Natural Language processing, RANLP 2023

作者： Liang, Tianyu Mu, Yida Kim, Soonho Kuate, Darline Larissa Kengne Lang, Julie Vos, Rob Song, Xingyi Department of Computer Science University of Sheffield Sheffield United Kingdom International Food Policy Research Institute WashingtonDC United States

ISBN: (纸本)9789544520922

A large number of conflict events are affecting the world all the time. In order to analyse such conflict events effectively, this paper presents a Classification-Aware Neural Topic Model (CANTM-IA) for Conflict Information Classification and Topic Discovery. The model provides a reliable interpretation of classification results and discovered topics by introducing interpretability analysis. At the same time, interpretation is introduced into the model architecture to improve the classification performance of the model and to allow interpretation to focus further on the details of the data. Finally, the model architecture is optimised to reduce the complexity of the model. © 2023 Incoma Ltd. All rights reserved.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

FULLY AUTOMATIC CERVICAL VERTEBRAE SEGMENTATION VIA ENHANCED U²-NET 30

FULLY AUTOMATIC CERVICAL VERTEBRAE SEGMENTATION VIA ENHANCED...

引用

30th IEEE international conference on Image processing (ICIP)

作者： Zhang, Fan Zheng, Linya Chen, Yinran Lin, Chen Huang, Liping Bai, Yuming Luo, Xiongbiao Xiamen Univ Dept Comp Sci & Technol Xiamen 361005 Peoples R China Xiamen Univ Natl Inst Data Sci Hlth & Med Xiamen 361102 Peoples R China Xiamen Med Coll Stomatol Hosp Xiamen 361016 Peoples R China

ISBN: (纸本)9781728198354

Accurate segmentation of the cervical vertebrae in CT images can assist clinicians in analyzing the adolescent patient's growth and development and establishing an effective orthodontic plan. This work develops an enhanced U2-Net architecture for fully automatic cervical vertebrae segmentation in CT images. Specifically, such an enhanced architecture first creates a deepwise separable residual U-shape module (DUM) in different levels and a convolutional attention module embedded into a U-structure for encoding and decoding and obtains a coarse segmentation. Then, it reuses a DUM to refine the segmentation. We evaluated our method on 60 CT scans, with the experimental results showing that our method attains much better segmentation performance than state-of-the-art network models. Particularly, it can improve the dices similarity coefficient, intersection over union, precision, and recall from (0.9586, 0.9207, 0.9584, 0.9591) to (0.9755, 0.9524, 0.9832, 0.9708), respectively, while it can reduce the model parameters from 44.0M to 16.5M.

关键词： Medical Image Segmentation Cervical Vertebrae Segmentation Deep Learning U2-Net

来源：评论

学校读者我要写书评

暂无评论

SMART: A Robustness Evaluation Framework for Neural Networks 29th

SMART: A Robustness Evaluation Framework for Neural Networks

引用

29th international conference on Neural Information processing

作者： Xiong, Yuanchun Zhang, Baowen Shanghai Jiao Tong Univ Inst Cyber Sci & Technol Shanghai 200240 Peoples R China Shanghai Key Lab Integrated Adm Technol Informat Shanghai 200240 Peoples R China

ISBN: (纸本)9789819916382;9789819916399

Robustness is urgently needed when neural network models are deployed under adversarial environments. Typically, a model learns to separate data points into different classes while training. A more robust model is more resistant to small perturbations within the local microsphere space of a given data point. In this paper, we try to measure the model's robustness from the perspective of data separability. We propose a modified data separability index Mahalanobis Distance-based Separability Index (MDSI), and present a new robustness evaluation framework Separability in Matrix-form for Adversarial Robustness of neTwork (SMART). Specifically, we use multiple attacks to find adversarial inputs, and incorporate them with clean data points. We use MDSI to evaluate the separability of the new dataset with correct labels and the model's prediction, and then compute a SMART score to show the model's robustness. Compared with existing robustness measurement, our framework builds up a connection between data separability and the model's robustness, showing openness, scalability, and pluggability in architecture. The effectiveness of our method is verified in experiments.

关键词： Neural network robustness data separability Adversarial inputs MDSI SMART

来源：评论

学校读者我要写书评

暂无评论

Fed-Tra: Improving Accuracy of Deep Learning Model on Non-iid in Federated Learning 21st

Fed-Tra: Improving Accuracy of Deep Learning Model on Non-ii...

引用

21st international conference on algorithms and Architectures for Parallel processing (ICA3PP)

作者： Xiao, Wenjie Tang, Xuehai Zhou, Biyu Wang, Wang Dong, Yangchen Zang, Liangjun Han, Jizhong Hu, Songlin Chinese Acad Sci Inst Informat Engn Beijing Peoples R China Univ Chinese Acad Sci Beijing Peoples R China

ISBN: (纸本)9783030953843;9783030953836

Federated Learning (FL) has received more and more attention from researches and industries in that it can break the data island while protecting the data privacy. However, the original federated average algorithm proposed in FL ignores the difference in distribution of data from multiple participants (widespread in reality), which seriously undermine the performance of deep learning models. It is more serious when the gap of data-volume is large. In this paper, we propose a novel and universal federated learning method, named Fed-Tra, to effectively weaken biases in the model training to build high-precision models. Fed-Tra does this with dynamically adjusting the weight of local training samples for each round in all participants. Moreover, our evaluation on real-world datasets shows that the Fed-Tra achieves nearly +28% improvement of F1-Score compared with the original federated average algorithm.

关键词： Federated learning Distributed machine learning Weight adjustment data privacy

来源：评论

学校读者我要写书评

暂无评论

Multi-scale coupling mechanism between monolithic models and multisource data 4

Multi-scale coupling mechanism between monolithic models and...

引用

4th international conference on Geoscience and Remote Sensing Mapping, GRSM 2022

作者： Zhang, Tianjia Huo, Liang Shen, Tao Zhang, Xiaoyong Li, Miaolin Han, Fulin School of Geomatic and Urban Spatial Information Beijing University of Civil Engineering and Architecture Beijing100044 China Key Laboratory of Urban Spatial Information Ministry of Natural Resources Beijing China Chinese Academy of Fishery Sciences Beijing100141 China

ISBN: (数字)9781510662179

ISBN: (纸本)9781510662162

Monomerization is one of the important aspects of tilt photography models in practical applications, but the monomerized models lack rich semantic information. In this paper, a multi-scale coupling mechanism of semantic information and monomerization model is designed. Firstly, semantic consistency processing is performed on the crowd source data to obtain rich semantic information. Then a semantic information classification table is constructed, and two-dimensional semantic information based on CityGML level of detail fusion rules are designed to join the multi-scale functional areas based on CityGML. Finally, multi-scale semantic information is assigned to the monolithic model based on the inclusion relationship between functional areas and buildings. The results of this paper show that the proposed method can integrate the query of the structure and location of 3D monolithic models as well as their rich semantic information, thus providing data support for the application of 2D and 3D systems for data analysis. © 2023 SPIE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A Model Sharing Technology Between Smart Substations and Dispatching Master Stations and Its Engineering Application

A Model Sharing Technology Between Smart Substations and Dis...

引用

IEEE international conference on Electrical Engineering, Big data and algorithms (EEBDA)

作者： Wang, Wei Cai, Dongfei Zhou, Jun Song, Li Wang, Shunjiang Wang, Lipeng State Grid Liaoning Power Co Ltd Liaoyang Power Co Liaoyang 450001 Peoples R China

ISBN: (纸本)9781665416061

At present, the control systems of dispatching master stations mainly adopt the IEC61970 protocol to create the models of substations. It is very different from the IEC61850 model of substations. This causes the systems of master stations and substations to be modeled according to their respective protocols. The amount of information collected by the substations is huge, but only part of the key information is needed for dispatching and monitoring. It is necessary to filter the information collected by the substations to form an information point table, and then manually check the information after the configuration of the master stations and substations. The existing traditional modeling and information checking methods require a significant amount of time. Based on fully comparing the differences between the two protocols, combined with the actual production flow, this paper proposes a method of automatic generation for models of dispatching master stations based on substations' SCD(Substation Configuration Description) files. RCD(Remote Configuration Description) files are generated according to the needs of monitoring business and automatically written into the SCADA(Supervisory Control And data Acquisition) system and the database of the gateway of substations' data communication network, so as to realize one-time maintenance of models' information points of master stations and substations. The test systems are built in new substations, and the simulation terminals are used to automatically compare the information, which verifies the effectiveness of the method.

关键词： smart substation IEC 61850 data Communication gateway remote configuration description

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 << < 14 15 16 17 18 19 20 21 22 23 > >>

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：