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

41,181 篇 会议
6,910 篇 期刊文献
314 册 图书

馆藏范围

48,405 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

29,955 篇 工学
- 17,995 篇 计算机科学与技术...
- 14,896 篇 软件工程
- 8,176 篇 信息与通信工程
- 5,800 篇 电子科学与技术（可...
- 5,563 篇 电气工程
- 5,075 篇 控制科学与工程
- 2,621 篇 生物工程
- 2,332 篇 光学工程
- 2,228 篇 生物医学工程（可授...
- 2,040 篇 机械工程
- 2,026 篇 动力工程及工程热...
- 1,928 篇 仪器科学与技术
- 1,503 篇 化学工程与技术
- 1,168 篇 材料科学与工程（可...
- 914 篇 安全科学与工程
- 885 篇 交通运输工程
- 780 篇 建筑学
15,727 篇 理学
- 8,312 篇 数学
- 5,234 篇 物理学
- 2,851 篇 生物学
- 2,682 篇 统计学（可授理学、...
- 1,927 篇 系统科学
- 1,570 篇 化学
6,144 篇 管理学
- 3,757 篇 管理科学与工程(可...
- 2,615 篇 图书情报与档案管...
- 2,115 篇 工商管理
1,712 篇 医学
- 1,497 篇 临床医学
- 1,387 篇 基础医学(可授医学...
- 927 篇 药学(可授医学、理...
1,095 篇 法学
- 898 篇 社会学
772 篇 经济学
527 篇 教育学
474 篇 农学
193 篇 文学
126 篇 军事学
47 篇 艺术学
3 篇 哲学
1 篇 历史学

主题

1,039 篇 computational mo...
1,019 篇 accuracy
796 篇 feature extracti...
753 篇 training
727 篇 computer science
542 篇 deep learning
507 篇 optimization
483 篇 machine learning
471 篇 predictive model...
459 篇 real-time system...
424 篇 support vector m...
411 篇 internet of thin...
401 篇 computer archite...
378 篇 data models
367 篇 neural networks
353 篇 bandwidth
340 篇 reliability
322 篇 mathematical mod...
314 篇 robustness
307 篇 monitoring

机构

167 篇 dept. of electri...
83 篇 institut univers...
82 篇 north-west unive...
79 篇 infn sezione di ...
79 篇 national centre ...
76 篇 infn sezione di ...
69 篇 institute of inf...
66 篇 università di ca...
63 篇 dept. of electr....
60 篇 dept. of electri...
58 篇 dept. of informa...
56 篇 dept. of compute...
52 篇 dept. of electri...
52 篇 school of automa...
48 篇 leiden universit...
48 篇 tno technical sc...
44 篇 dept. of compute...
43 篇 in2p3 lpc campus...
42 篇 infn lnf via enr...
42 篇 dept. of electri...

作者

85 篇 ferrara g.
85 篇 ardid m.
84 篇 calvo d.
84 篇 gal t.
84 篇 bozza c.
81 篇 chen a.
76 篇 kalekin o.
73 篇 díaz a.f.
66 篇 huang f.
59 篇 boumaaza j.
55 篇 coleiro a.
54 篇 kulikovskiy v.
42 篇 benoit d.m.
42 篇 eddymaoui a.
42 篇 labalme m.
41 篇 gagliardini s.
40 篇 gozzini s.r.
38 篇 androulakis g.
36 篇 khatun a.
35 篇 de palma m.

语言

44,109 篇 英文
3,518 篇 其他
561 篇 中文
208 篇 朝鲜文
37 篇 日文
4 篇 德文
1 篇 阿拉伯文
1 篇 法文
1 篇 斯洛文尼亚文
1 篇 土耳其文

检索条件"机构=Dept. of Electrical and Computer Engineering and Computer Science University of Cincinnati"

共 48405 条记录，以下是4711-4720 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：

Addressing the Long-Tailed Data Distribution in Bone Marrow Cell Identification through Class Balance Deep Classification Model

Addressing the Long-Tailed Data Distribution in Bone Marrow ...

引用

Integrated Circuits and Communication Systems (ICICACS), IEEE International Conference on

作者： Rakesh Shankar Ghosh Pintu Chandra Shill Dept. of Computer Science and Engineering Khulna University of Engineering & Technology Khulna Bangladesh

The accurate classification of bone marrow cells has long been a critical component of diagnosing blood diseases. However, traditional methods rely on subjective human interpretation and lack standardized quantitative criteria. To address this challenge, this research proposes a Class Balance Deep Classification Model (CBDCM) designed to classify bone marrow cells using EfficientNet to handle the long-tailed data distribution problem. In order to validate the propose model by applying it to proper dataset and analyzing the experimental outcomes of the propose method. Notably, CBDCM attains impressive precision, sensitivity, and specificity values of 86.14%, 87.53%, and 99.45%, respectively. Simulation results show that CBDCM outperforms, demonstrating superior performance in a detailed comparison with both deep neural networks and traditional machine learning techniques. The findings of this study, with significant implications for addressing class imbalance in datasets, hold promise for standardizing the classification of bone marrow cells, potentially revolutionizing the diagnosis of blood diseases.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Keep It Simple: CNN Model Complexity Studies for Interference Classification Tasks

Keep It Simple: CNN Model Complexity Studies for Interferenc...

引用

2023 IEEE INFOCOM Conference on computer Communications Workshops, INFOCOM WKSHPS 2023

作者： Oyedare, Taiwo Shah, Vijay K. Jakubisin, Daniel J. Reed, Jeffrey H. Virginia Tech Bradley Dept. of Electrical and Computer Engineering Blacksburg United States George Mason University Dept. of Cybersecurity Engineering Fairfax United States Virginia Tech National Security Institute BlacksburgVA United States

ISBN: (纸本)9781665494274

The growing number of devices using the wireless spectrum makes it important to find ways to minimize interference and optimize the use of the spectrum. Deep learning models, such as convolutional neural networks (CNNs), have been widely utilized to identify, classify, or mitigate interference due to their ability to learn from the data directly. However, there have been limited research on the complexity of such deep learning models. The major focus of deep learning-based wireless classification literature has been on improving classification accuracy, often at the expense of model complexity. This may not be practical for many wireless devices, such as, internet of things (IoT) devices, which usually have very limited computational resources and cannot handle very complex models. Thus, it becomes important to account for model complexity when designing deep learning based models for interference classification. To address this, we conduct an analysis of CNN based wireless classification that explores the trade-off amongst dataset size, CNN model complexity, and classification accuracy under various levels of classification difficulty: namely, interference classification, heterogeneous transmitter classification, and homogeneous transmitter classification. Our study, based on three wireless datasets, shows that a simpler CNN model with fewer parameters can perform just as well as a more complex model, providing important insights into the use of CNNs in computationally constrained applications. © 2023 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Dynamic Continual Learning: Harnessing Parameter Uncertainty for Improved Network Adaptation

Dynamic Continual Learning: Harnessing Parameter Uncertainty...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Christopher F. Angelini Nidhal C. Bouaynaya Dept. of Electrical and Computer Engineering Rowan University Glassboro New Jersey USA

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

When fine-tuning Deep Neural Networks (DNNs) to new data, DNNs are prone to overwriting network parameters required for task-specific functionality on previously learned tasks, resulting in a loss of performance on those tasks. We propose using parameter-based uncertainty to determine which parameters are relevant to a network’s learned function and regularize training to prevent change in these important parameters. We approach this regularization in two ways: (1), we constrain critical parameters from significant changes by associating more critical parameters with lower learning rates, thereby limiting alterations in those parameters; (2), important parameters are restricted from change by imposing a higher regularization weighting, causing parameters to revert to their states prior to the learning of subsequent tasks. We leverage a Bayesian Moment Propagation framework which learns network parameters concurrently with their associated uncertainties while allowing each parameter to contribute uncertainty to the network’s predictive distribution, avoiding the pitfalls of existing sampling-based methods. The proposed approach is evaluated for common sequential benchmark datasets and compared to existing published approaches from the Continual Learning community. Ultimately, we show improved Continual Learning performance for Average Test Accuracy and Backward Transfer metrics compared to sampling-based methods and other non-uncertainty-based approaches.

关键词： Continuing education Training Uncertain systems Uncertainty Limiting Measurement uncertainty Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

A Comparative Analysis of Transformer Models in Zero-Shot Text Classification

A Comparative Analysis of Transformer Models in Zero-Shot Te...

引用

International Conference on Information, Intelligence, Systems and Applications (IISA)

作者： Konstantinos Kyritsis Charalampos M. Liapis Nikolaos Spatiotis Isidoros Perikos Michael Paraskevas Electrical & Computer Engineering Dept. University of Peloponnese Patras Greece Mathematics Dept. University of Patras Patras Greece Computer Technology Institute & Press “Diophantus” Patras Greece Computer Engineering & Informatics Dept. University of Patras Patras Greece

ISBN: (数字)9798350368833

ISBN: (纸本)9798350368840

Ahstract-Zero-shot text classification leverages pre-trained transformer models to categorize texts without the need for task-specific training. This paper analyzes a variety of transformer-based pre-trained methods on the task of zero-shot text classi-fication. Specifically, we present a deep comparative analysis of various transformer models, such as BART, DeBerta, DistiIBART, RoBERTa, and their variants, and evaluate their performance in various zero-shot text classification schemes. Furthermore, we examine the models' generalization capabilities. The findings highlight key strengths and weaknesses of each model, providing insights into their suitability for different text categorization tasks. Our research contributes to the broader understanding of transformer-based approaches and offers guidance for selecting models for zero-shot text classification.

关键词： Training Analytical models Text categorization Transformers

来源：评论

学校读者我要写书评

暂无评论

IMU-Based Model for Precise Toothbrush Stroke and Orientation Tracking

IMU-Based Model for Precise Toothbrush Stroke and Orientatio...

引用

IEEE Region 10 International Conference TENCON

作者： Mohammad Ariful Islam Bhuyan Md Mayen Uddin Hyeon Cheol Kim Dept. of Electrical Electronic and Computer Engineering University of Ulsan Ulsan South Korea

ISBN: (数字)9798350350821

ISBN: (纸本)9798350350838

This paper presents a model designed for precise orientation estimation and stroke distance tracking of toothbrush activity. The model leverages Inertial Measurement Unit (IMU) technology, which includes accelerometers and gyroscopes, to capture detailed motion data during the activity. The proposed Corrective Fusion Filter Technique (CFFT) helps integrate accelerometer and gyroscope data with several corrective steps to estimate orientation precisely, and the combined sensor data accurately measures stroke distance. This filtering method also minimizes sensor noise and drifting issues, enhancing the model's reliability and performance.

关键词： Accelerometers Measurement units Tracking Filtering Noise Inertial navigation Gyroscopes Reliability Tuning IEEE Regions

来源：评论

学校读者我要写书评

暂无评论

EARLY STOPPING IN DEEP NETWORKS: DOUBLE DESCENT AND HOW TO ELIMINATE IT 9

EARLY STOPPING IN DEEP NETWORKS: DOUBLE DESCENT AND HOW TO E...

引用

9th International Conference on Learning Representations, ICLR 2021

作者： Heckel, Reinhard Yilmaz, Fatih Furkan Dept. of Electrical and Computer Engineering Technical University of Munich Germany Dept. of Electrical and Computer Engineering Rice University United States

Over-parameterized models, such as large deep networks, often exhibit a double descent phenomenon, where as a function of model size, error first decreases, increases, and decreases at last. This intriguing double descent behavior also occurs as a function of training epochs and has been conjectured to arise because training epochs control the model complexity. In this paper, we show that such epoch-wise double descent occurs for a different reason: It is caused by a superposition of two or more bias-variance tradeoffs that arise because different parts of the network are learned at different epochs, and mitigating this by proper scaling of stepsizes can significantly improve the early stopping performance. We show this analytically for i) linear regression, where differently scaled features give rise to a superposition of bias-variance tradeoffs, and for ii) a wide two-layer neural network, where the first and second layers govern bias-variance tradeoffs. Inspired by this theory, we study two standard convolutional networks empirically and show that eliminating epoch-wise double descent through adjusting stepsizes of different layers improves the early stopping performance. © 2021 ICLR 2021 - 9th International Conference on Learning Representations. All rights reserved.

关键词： Commerce

来源：评论

学校读者我要写书评

暂无评论

Hybridization of Sparrow Search Algorithm and Sine Cosine Algorithm for Epileptic Seizure Detection 3

Hybridization of Sparrow Search Algorithm and Sine Cosine Al...

引用

3rd Odisha International Conference on electrical Power engineering, Communication and Computing Technology, ODICON 2024

作者： Mohapatra, Sumant Kumar Swain, Kaliprasanna Mallik, Puspanjali Mali, Sabita Ali, Farida A. Trident Academy of Technology Odisha Bhubaneswar India Shailabala Women's Autonomous College Dept. of Computer Science Cuttack India Iter Soa University Faculty of Engineering Bhubaneswar India

ISBN: (纸本)9798350354379

An imbalance in electrical signal flow among neurons causes epilepsy, a complex brain disease that affects other parts of the body and results in seizures. Researchers and neurologists have put their efforts into devising powerful electroencephalogram devices to address the importance of health issues. In this context, machine learning algorithms are used to accurately detect the presence of a seizure signal. This experiment uses the hybridization of two meta-heuristic optimization algorithms: the sparrow search algorithm and the sine cosine algorithm. To conduct the research, this experiment uses the publicly available CHB-MIT EEG dataset, and for feature extraction, it uses the discrete wavelet transform (DWT). ANOVA We use feature selection to identify similar groups. This study uses three classifiers: support vector machines (SVM), Adaptive Neuro Fuzzy Inference System (ANFIS), and Extreme Learning ANFIS (ELANFIS). We got 99.8% accuracy, 98.35% sensitivity, 99.02% specificity, 98% positive predictive value, and 1 for area-under-curve for SSA-SCA-DWT-ELANFIS. This shows that it works better than SSA-SCA-DWT-SVM, SSA-SCA-DWT-ANFIS, and other methods that are already out there. In the future, we can integrate this study with the Internet of Things (IoT). © 2024 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Comparative Study of Transmission Expansion Planning with Conventional and Unconventional High Surge Impedance Loading (HSIL) Lines

Comparative Study of Transmission Expansion Planning with Co...

引用

IEEE General Meeting Power& Energy Society

作者： Bhuban Dhamala Mona Ghassemi Dept. of Electrical and Computer Engineering The University of Texas at Dallas Richardson TX USA

ISBN: (数字)9798350381832

ISBN: (纸本)9798350381849

The strategic planning of transmission expansion is paramount in ensuring the reliability and efficiency of power systems, particularly in the context of growing electricity demand and the integration of renewable energy sources. This paper investigates the utilization of unconventional high surge impedance loading (HSIL) lines in transmission expansion planning (TEP) and offers a comparative analysis of their performance against conventional line-based TEP methods. Commencing with a 17-bus 500 kV test system known for its robust operation under normal and all single contingencies at different loading scenarios, the objective is to connect a new load at a new location. Meticulously examining and comparing the number of lines and right of way (ROW) required for both methods while maintaining uniform conductor weight per circuit, the effectiveness of unconventional HSIL lines within the TEP context is assessed.

关键词： Renewable energy sources Power transmission lines Systems operation Loading Contingency management Strategic planning Conductors Impedance Reliability Surges

来源：评论

学校读者我要写书评

暂无评论

Contribution of Algorithm Visualizations to Students' Learning Skills: A Pedagogical Approach

Contribution of Algorithm Visualizations to Students' Learni...

引用

International Symposium on Digital Forensic and Security (ISDFS)

作者： Harem Ali Kheder Asaf Varol Dept. of Computer Engineering College of Engineering and Computer Sciences Lebanese French University Erbil Iraq Dept. of Engineering Management and Technology College of Engineering and Computer Science The University of Tennessee at Chattanooga Chattanooga TN US

ISBN: (数字)9798350330366

ISBN: (纸本)9798350330373

The Domain Algorithm visualizations are multimedia-based representations of algorithms that help students learn how they operate and behave. Algorithm visualizations provide numerous benefits to instructors and students, including an improved understanding of difficult algorithms in programming. By stripping down the complexities of algorithms and presenting them in simplified visual ways, students can obtain a more thorough knowledge of how they perform. Instructional approaches, such as guided instruction or discovery learning, are critical to the pedagogical effectiveness of algorithm representations. Guided instructions can considerably boost learners' overall performance in problem-solving activities that incorporate visualizations. At the same time, discovery education promotes exploration and experimentation, yet it may result in longer learning times and increased mental demands. A combination of these approaches is required for optimal effectiveness of instruction. In this paper, we investigate how the pedagogical effectiveness of algorithm visualizations should be determined by a variety of elements, including student characteristics, visual and cognitive processing ability, algorithm representation, and instructional context based on a literature review and interviews with field experts, and a bunch of recommendations is provided that has witnessed by authors during their long teaching periods.

关键词： Visualization Education Linguistics computer science education Complexity theory Security Problem-solving

来源：评论

学校读者我要写书评

暂无评论

D2CoPlan: A Differentiable Decentralized Planner for Multi-Robot Coverage

D2CoPlan: A Differentiable Decentralized Planner for Multi-R...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Vishnu Dutt Sharma Lifeng Zhou Pratap Tokekar Dept. of Computer Science University of Maryland College Park MD USA Dept. of Electrical and Computer Engineering Drexel University Philadelphia PA USA

Centralized approaches for multi-robot coverage planning problems suffer from the lack of scalability. Learning-based distributed algorithms provide a scalable avenue in addition to bringing data-oriented feature generation capabilities to the table, allowing integration with other learning-based approaches. To this end, we present a learning-based, differentiable distributed coverage planner (D2CoP LAN ) which scales efficiently in runtime and number of agents compared to the expert algorithm, and performs on par with the classical distributed algorithm. In addition, we show that D2CoP LAN can be seamlessly combined with other learning methods to learn end-to-end, resulting in a better solution than the individually trained modules, opening doors to further research for tasks that remain elusive with classical methods.

关键词：

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 << < 468 469 470 471 472 473 474 475 476 477 > >>

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：