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

3,206 篇 会议
56 册 图书
26 篇 期刊文献

馆藏范围

3,288 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,719 篇 工学
- 1,325 篇 计算机科学与技术...
- 1,216 篇 软件工程
- 213 篇 控制科学与工程
- 204 篇 信息与通信工程
- 195 篇 电气工程
- 151 篇 机械工程
- 136 篇 材料科学与工程（可...
- 131 篇 安全科学与工程
- 128 篇 生物工程
- 125 篇 生物医学工程（可授...
- 94 篇 土木工程
- 93 篇 交通运输工程
- 85 篇 建筑学
- 79 篇 动力工程及工程热...
- 75 篇 电子科学与技术（可...
- 70 篇 化学工程与技术
- 62 篇 力学（可授工学、理...
703 篇 理学
- 491 篇 数学
- 167 篇 统计学（可授理学、...
- 132 篇 生物学
- 115 篇 物理学
- 113 篇 系统科学
- 60 篇 化学
391 篇 管理学
- 282 篇 管理科学与工程(可...
- 172 篇 图书情报与档案管...
- 129 篇 工商管理
93 篇 医学
- 85 篇 基础医学(可授医学...
- 80 篇 临床医学
56 篇 经济学
- 56 篇 应用经济学
50 篇 教育学
- 49 篇 教育学
43 篇 法学
32 篇 农学
6 篇 文学
5 篇 军事学
1 篇 艺术学

主题

943 篇 predictive model...
265 篇 accuracy
257 篇 data models
235 篇 computational mo...
203 篇 analytical model...
180 篇 prediction algor...
148 篇 training
135 篇 software enginee...
129 篇 feature extracti...
119 篇 software
117 篇 machine learning
116 篇 deep learning
104 篇 neural networks
103 篇 forecasting
97 篇 adaptation model...
83 篇 mathematical mod...
82 篇 machine learning...
76 篇 optimization
70 篇 real-time system...
62 篇 support vector m...

机构

10 篇 school of inform...
7 篇 national enginee...
7 篇 hubei key labora...
7 篇 school of electr...
7 篇 school of automa...
6 篇 school of comput...
6 篇 school of softwa...
6 篇 school of electr...
6 篇 engineering rese...
5 篇 school of comput...
5 篇 school of transp...
5 篇 nanjing univ sta...
5 篇 chitkara univers...
5 篇 school of softwa...
4 篇 school of inform...
4 篇 naval university...
4 篇 school of manage...
4 篇 school of softwa...
4 篇 software enginee...
4 篇 school of electr...

作者

8 篇 labiche yvan
7 篇 menzies tim
6 篇 hassan ahmed e.
5 篇 yang yang
5 篇 mcintosh shane
5 篇 chen li
5 篇 ziadi tewfik
5 篇 yan wang
4 篇 yu wang
4 篇 ming li
4 篇 liu yang
4 篇 hall tracy
4 篇 xintian liu
4 篇 bowes david
4 篇 monden akito
4 篇 min wu
4 篇 matsumoto ken-ic...
4 篇 yu zhang
4 篇 lei zhang
4 篇 briand lionel c.

语言

3,195 篇 英文
82 篇 其他
21 篇 中文
1 篇 俄文

检索条件"任意字段=Proceedings of the 6th International Conference on Predictive Models in Software Engineering"

共 3288 条记录，以下是211-220 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：

DASENet:A Detail Aware U-Net with Shuffle Excitation for Retinal Vessel Segmentation 6

DASENet:A Detail Aware U-Net with Shuffle Excitation for Ret...

引用

6th international conference on software engineering and Computer Science, CSECS 2023

作者： Zhu, Jiqiang Lan, Zhangli Wen, Xinpeng Cai, Songbai Xu, Yuantong School of Information Science and Engineering Chongqing Jiaotong University Chongqing China

ISBN: (纸本)9798350306378

Retinal vessel images serve as valuable tools for early screening and timely diagnosis of ocular disorders. With the advancement of deep learning, a multitude of segmentation models have been utilized for retinal vessel image segmentation tasks. However, the challenge of enhancing feature expression capabilities and refining the accuracy of retinal blood vessel segmentation persists. In this study, we propose an end-to-end retinal vessel segmentation network named DASENet. To capture finer vessel details and enhance feature expression capabilities, a detail aware block (DAB) is proposed for feature extraction and to heighten the network's focus on vessel information. Moreover, shuffle excitation (SE) within skip connections is proposed to capture contextual dependencies between features and reduce differences between feature maps at different depths. Experimental results on the DRIVE, STARE and CHASE_DB1 datasets demonstrate that our DASENet outperforms other related advanced work. © 2023 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Impact of Load models on Elevated Neutral-to-Earth Voltage (NEV) in Distribution Systems 6

Impact of Load Models on Elevated Neutral-to-Earth Voltage (...

引用

6th international conference on Renewable Energy and Power engineering (REPE)

作者： Zulu, Snethemba Le Roux, Peet F. Masina, Mfanfuthi C. Nnachi, Agha F. Tshwane Univ Technol Dept Elect Engn Emalahleni South Africa

ISBN: (纸本)9798350306194;9798350306187

By uniformly grounding the distribution system and the customer's electrical system, neutral-to-earth voltage (NEV) can be moved from the distribution system to grounded objects in a building, like metal water pipes. the customer wiring may also be another possible cause of NEV. Furthermore, NEV is induced by load, leakage, and fault currents flowing through neutral or grounding connections. While ground rods and metallic water lines can channel leakage currents to the earth, every electrical system is subject to voltage-to-earth. Metallic structures connected to neutral or grounding systems will also be at the same NEV. the NEV/stray voltage generally occurs at low voltages and currents, so it is often undetectable. However, when people begin to experience shocks, it becomes a safety issue that, if not addressed, may have a severe impact. Using a backwards/forward sweep approach, this paper examines the effects of various factors on the neutral-to-earth voltage (NEV). An IEEE 13-bus distribution network demonstrates the proposed approach to evaluating NEVs. the results of the study are presented and analyzed. Matlab/Simulink software is used for all simulations.

关键词： Simulink MATLAB NEV thD

来源：评论

学校读者我要写书评

暂无评论

Hybrid ConvLSTM with Attention for Precise Driver Behavior Classification 6

Hybrid ConvLSTM with Attention for Precise Driver Behavior C...

引用

6th IEEE international conference on Artificial Intelligence and Knowledge engineering, AIKE 2023

作者： Mustafa, Ghulam Cho, Seong-Je Hwang, Youngsup Dept. of Computer Engineering Sun Moon University Asan-si Korea Republic of Dept. of Software Science Dankook University Yongin Korea Republic of

ISBN: (纸本)9798350331288

Driving behavior classification plays an important role in many real-world applications, including traffic accident prevention, driver safety, usage-based insurance, and optimizing ridesharing services. In this research, we introduce a novel approach called Hybrid ConvLSTM with Attention for Driver Behavior Classification (HCLA-DBC), designed to achieve precise and reliable driver behavior classification. Our main focus is to distinguish three fundamental driving behavior classes: normal, drowsy, and aggressive, which play a vital role in supporting advanced driver-assistance systems (ADAS). To evaluate the performance of our proposed models, we conducted experiments using the publicly available UAH-DriveSet dataset. the evaluation comprised six distinct models, encompassing two machine learning models (SVM and Gradient Boosting) and four deep learning models (CNN, MLP, LSTM, and HCLADBC). Our HCLA-DBC model outperformed all other models and previous results on the same data. On the test data, it achieved an accuracy of 94.12%, precision of 94.24%, recall score of 94.12%, F1-score of 94.12%, and a macro-average ROC AUC of 98.83. these exceptional outcomes underscore the efficacy of our hybridized approach and its potential to significantly enhance driver behavior classification. the HCLA-DBC model not only promises new possibilities for driver behavior analysis but also paves the way for elevated ADAS capabilities and safer driving experiences. © 2023 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Counterfactual Explanations for models of Code 44

Counterfactual Explanations for Models of Code

引用

ACM/IEEE 44th international conference on software engineering - software engineering in Practice (ICSE-SEIP)

作者： Cito, Juergen Dillig, Isil Murali, Vijayaraghavan Chandra, Satish TU Wien Vienna Austria Meta Platforms Inc Menlo Pk CA USA UT Austin Austin TX USA Meta Menlo Pk CA USA

ISBN: (纸本)9781665495905

Machine learning (ML) models play an increasingly prevalent role in many software engineering tasks. However, because most models are now powered by opaque deep neural networks, it can be difficult for developers to understand why the model came to a certain conclusion and how to act upon the model's prediction. Motivated by this problem, this paper explores counterfactual explanations for models of source code. Such counterfactual explanations constitute minimal changes to the source code under which the model "changes its mind". We integrate counterfactual explanation generation to models of source code in a real-world setting. We describe considerations that impact both the ability to find realistic and plausible counterfactual explanations, as well as the usefulness of such explanation to the developers that use the model. In a series of experiments we investigate the efficacy of our approach on three different models, each based on a BERT-like architecture operating over source code.

关键词： Codes Perturbation methods Neural networks Prototypes predictive models software Task analysis

来源：评论

学校读者我要写书评

暂无评论

DTG-LSTM: A Delaunay Triangulation Graph Network for Human Trajectory Prediction 6

DTG-LSTM: A Delaunay Triangulation Graph Network for Human T...

引用

6th international conference on software engineering and Computer Science, CSECS 2023

作者： Shi, Zhimiao Xiao, Yao School of Intelligent System Engineering Sun Yat-Sen University Shenzhen China

ISBN: (纸本)9798350306378

the prediction of pedestrian trajectories is an essential yet challenging aspect of intelligent transportation systems, particularly relevant for autonomous vehicles and complex pedestrian scenarios. Taking into account the complex dynamics of pedestrian motion, we suggest employing the Long Short-Term Memory network combined with the Delaunay triangulation graph (DTG-LSTM) as a novel approach to capturing these intricacies. the model uniquely integrates the geometric characteristics of Delaunay triangulation to better represent evolving topological relationships among pedestrians, potentially contributing to more realistic trajectory predictions. Our model incorporates an encoder-decoder structure: the encoder amalgamates temporal and interaction trajectory information, while the decoder implements a three-pronged strategy, recursion, teacher-forcing, and a novel mixed teacher-forcing technique, to enhance prediction performance. While there is room for further optimization, our integration of geometric, topological, and graph convolutional elements into a trajectory prediction framework shows potential. Preliminary evaluations on widely-used public datasets (Eth and UCY) suggest promising predictive accuracy. the DTG-LSTM model offers a new avenue for exploration in the field of intelligent transportation systems, inviting further inquiry and development. © 2023 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

25 Years of Teaching at the National Research University "moscow Power engineering Institute" on STEM Technology 6

25 Years of Teaching at the National Research University "mo...

引用

6th international conference on Information Technologies in engineering Education, Inforino 2022

作者： Ochkov, Valery Orlov, Konstantin Chudova, Yulia National Research University MPEI TOT Dept. Moscow Russia

ISBN: (纸本)9781665405775

the article describes more than a quarter-century of teaching courses on STEM technology at the National Research University "Moscow Power engineering Institute"(MPEI). the necessity of opening a STEM specialty in pedagogical universities and STEM journals in Russia is substantiated. Provides links to scripts and tasks for STEM classes. © 2022 IEEE.

关键词： Training Power engineering Pandemics Turning software Mathematical models Task analysis

来源：评论

学校读者我要写书评

暂无评论

Dynamic Analysis of Systems with a Nonlinear Elastomeric Isolator in Simulink 6

Dynamic Analysis of Systems with a Nonlinear Elastomeric Iso...

引用

6th international conference on Information Technologies in engineering Education, Inforino 2022

作者： Poznyak, Elena V. Radin, Vladimir P. Novikova, Olga V. Chirkov, Victor P. Babin, Oleg A. Kuznetsov, Sergey F. National Research University Moscow Power Engineering Institute Department of Robotics Mechatronics Dynamics and Strength of Machines Moscow Russia

ISBN: (纸本)9781665405775

the paper presents Simulink models of nonlinear elastomeric isolator (EI) widely used in mechanical engineering and construction for vibration protection of structures. models with a hysteretic bilinear deformation diagram and, for comparison, with a bilinear diagram without hysteresis are considered. Step and frequency responses are obtained and investigated;conclusions are given. the elements of the study will be helpful for the development of the professional skills and competencies of young engineers in the field of applied problems of vibration and shock protection;it can be a basis for the development of more complex multidimensional systems. © 2022 IEEE.

关键词： Vibrations Isolators Multidimensional systems software packages Numerical analysis Electric shock Mathematical models

来源：评论

学校读者我要写书评

暂无评论

ResNet-18 comparative analysis of various activation functions for image classification 6

ResNet-18 comparative analysis of various activation functio...

引用

6th international conference on Inventive Computation Technologies, ICICT 2023

作者： Pandey, Gaurav Kumar Srivastava, Sumit Computer Science and Engineering Department Birla Institute of Technology Mesra Ranchi India

ISBN: (纸本)9798350398496

Deep neural network and Machine learning are a latestemerging concept in the field of data science. Due to multilayer hierarchical feature extraction in conjunction with control variables like number of hidden layers, activation functions, and variable parameters like learning rates, initial weights, and decay functions, deep network models perform better than machine learning techniques. While most of these parameter control the learning dynamics or complexity of representation a neural network can deal with, it is only activation function which introduces non-linearity in a network and current state of activation function poses multiple challenges to both practitioners and researchers some of which are: • Vanishing & Exploding gradients during back-propagation • Zero-mean and range of outputs • Compute complexity of function • predictive performance Due to this reason our objective in current work in focused to explain with reasoning and experiments the landscape of activation functions available. According to a recent study, we have enough cutting-edge activation functions to modify the architecture of the well-known deep network model. Building on top of widely adopted ResNet-18 network architecture in this study. Subsequently, we evaluate the effectiveness of ResNet-18 for image classification using various activation functions. © 2023 IEEE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Improvement of the predictive Control Method for the High-Level Controller 17

Improvement of the Predictive Control Method for the High-Le...

引用

17th IEEE international conference on Advanced Trends in Radioelectronics, Telecommunications and Computer engineering, TCSET 2024

作者： Budashko, Vitalii Sandler, Albert Glazeva, Oksana Educational and Scientific Institute of Automation and Electrical Engineering National University 'Odessa Maritime Academy' NUOMA Odesa Ukraine National University 'Odessa Maritime Academy' NUOMA Department of the theory of automatic control and computer technology Odesa Ukraine National University 'Odessa Maritime Academy' NUOMA Department of electrical engineering and electronics Odesa Ukraine

ISBN: (纸本)9798331520564

Automation of ship maneuvering in limited sailing conditions usually requires 100% redundancy of thrusters (thRs) of various modifications and their locations in accordance with the matrix. the hierarchy of the motion control system is branched by levels using high-level motion controllers and thRs control distribution algorithms, which allows for a modular design with software, where the high-level controller (HLC) can be designed without comprehensive information about the thruster motors, and the input signal branching and speed limits are handled by the motion controller. But, for certain thRs configurations, this branching leads to the decrease in control efficiency due to the limitation of data on the physical characteristics of the ships and the operation of the motion controller. this research examines different approaches to improving control efficiency using methods of nonlinear predictive control models as a basis for developing motion controllers with decision optimization based on relevant constraints. the implemented branched system is the result of solving two simple problems of ship's motion, which highlight the related problems. the use of different approaches to eliminate the identified shortcomings made it possible to develop the nonlinear controller that combines the motion controller with distributed control of the thRs and ensuring the certain level of system reliability. the modularity of the control system is provided by the expansion of the closed system, which made it possible to achieve an increase in efficiency during the combined mode of operation. the obtained solution of nonlinear control with time-varying constraints made it possible to increase the accuracy of the control with a decrease in the duration of the pause in response to the change of the disturbance within 10% © 2024 IEEE.

关键词： predictive control systems

来源：评论

学校读者我要写书评

暂无评论

Zero-shot Bilingual App Reviews Mining with Large Language models 35

Zero-shot Bilingual App Reviews Mining with Large Language M...

引用

35th IEEE international conference on Tools with Artificial Intelligence (ICTAI)

作者： Wei, Jialiang Courbis, Anne-Lise Lambolais, thomas Xu, Binbin Bernard, Pierre Louis Dray, Gerard Univ Montpellier IMT Mines Ales EuroMov Digital Hlth Mot Ales France Univ Montpellier EuroMov Digital Hlth Mot IMT Mines Ales Montpellier France

ISBN: (纸本)9798350342734

App reviews from app stores are crucial for improving software requirements. A large number of valuable reviews are continually being posted, describing software problems and expected features. Effectively utilizing user reviews necessitates the extraction of relevant information, as well as their subsequent summarization. Due to the substantial volume of user reviews, manual analysis is arduous. Various approaches based on natural language processing (NLP) have been proposed for automatic user review mining. However, the majority of them requires a manually crafted dataset to train their models, which limits their usage in real-world scenarios. In this work, we propose Mini-BAR, a tool that integrates large language models (LLMs) to perform zero-shot mining of user reviews in both English and French. Specifically, Mini-BAR is designed to (i) classify the user reviews, (ii) cluster similar reviews together, (iii) generate an abstractive summary for each cluster and (iv) rank the user review clusters. To evaluate the performance of Mini-BAR, we created a dataset containing 6,000 English and 6,000 French annotated user reviews and conducted extensive experiments. Preliminary results demonstrate the effectiveness and efficiency of Mini-BAR in requirement engineering by analyzing bilingual app reviews.

关键词： Large language model Requirements engineering User feedback

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329页 << < 18 19 20 21 22 23 24 25 26 27 > >>

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：