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

1,834 篇 期刊文献
1,680 篇 会议
1 册 图书

馆藏范围

3,515 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

2,105 篇 工学
- 834 篇 计算机科学与技术...
- 634 篇 软件工程
- 544 篇 电子科学与技术（可...
- 485 篇 电气工程
- 344 篇 材料科学与工程（可...
- 328 篇 信息与通信工程
- 321 篇 化学工程与技术
- 319 篇 光学工程
- 260 篇 生物工程
- 246 篇 控制科学与工程
- 235 篇 生物医学工程（可授...
- 182 篇 仪器科学与技术
- 170 篇 动力工程及工程热...
- 130 篇 机械工程
- 105 篇 冶金工程
- 93 篇 力学（可授工学、理...
1,727 篇 理学
- 986 篇 物理学
- 493 篇 数学
- 393 篇 化学
- 341 篇 生物学
- 191 篇 统计学（可授理学、...
- 74 篇 系统科学
321 篇 管理学
- 196 篇 管理科学与工程(可...
- 128 篇 图书情报与档案管...
- 106 篇 工商管理
224 篇 医学
- 179 篇 临床医学
- 143 篇 基础医学(可授医学...
- 75 篇 药学(可授医学、理...
66 篇 教育学
- 59 篇 教育学
61 篇 法学
45 篇 经济学
45 篇 农学
4 篇 文学
3 篇 军事学
1 篇 哲学
1 篇 艺术学

主题

51 篇 deep learning
45 篇 accuracy
44 篇 training
42 篇 feature extracti...
39 篇 computer science
39 篇 computational mo...
39 篇 machine learning
33 篇 metamaterials
31 篇 neural networks
30 篇 optimization
30 篇 silicon
30 篇 photonics
29 篇 graphene
25 篇 computer archite...
23 篇 three-dimensiona...
23 篇 predictive model...
22 篇 support vector m...
22 篇 real-time system...
22 篇 topology
22 篇 liquid crystals

机构

53 篇 interdisciplinar...
49 篇 department of el...
47 篇 centre of interd...
47 篇 maharishi school...
43 篇 renewable and su...
34 篇 department of el...
34 篇 department of el...
32 篇 photonics initia...
30 篇 department of ph...
30 篇 photonics initia...
28 篇 department of ph...
28 篇 department of ma...
24 篇 physics program ...
22 篇 renewable and su...
22 篇 department of el...
21 篇 department of el...
21 篇 department of el...
21 篇 applied physics ...
20 篇 division of phys...
20 篇 school of comput...

作者

50 篇 yoon sungroh
41 篇 andrea alù
41 篇 smalyukh ivan i.
36 篇 alù andrea
33 篇 ivan i. smalyukh
29 篇 kono junichiro
25 篇 jasra ajay
24 篇 niyato dusit
24 篇 lukas
23 篇 zhang byoung-tak
20 篇 balandin alexand...
18 篇 kargar fariborz
18 篇 heryadi yaya
18 篇 du hongyang
17 篇 tay fuyang
17 篇 weiss sharon m.
17 篇 baydin andrey
15 篇 yaya heryadi
15 篇 hakan bagci
14 篇 shih wei-chuan

语言

3,372 篇 英文
105 篇 其他
23 篇 中文
7 篇 朝鲜文
1 篇 日文

检索条件"机构=Interdisciplinary Program of Electrical Engineering and Computer Science"

共 3515 条记录，以下是121-130 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：

Purify Unlearnable Examples via Rate-Constrained Variational Autoencoders 41

Purify Unlearnable Examples via Rate-Constrained Variational...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Yu, Yi Wang, Yufei Xia, Song Yang, Wenhan Lu, Shijian Tan, Yap-Peng Kot, Alex C. Rapid-Rich Object Search Lab Interdisciplinary Graduate Programme Nanyang Technological University Singapore School of Electrical and Electronic Engineering Nanyang Technological University Singapore PengCheng Laboratory Shenzhen China School of Computer Science and Engineering Nanyang Technological University Singapore

Unlearnable examples (UEs) seek to maximize testing error by making subtle modifications to training examples that are correctly labeled. Defenses against these poisoning attacks can be categorized based on whether specific interventions are adopted during training. The first approach is training-time defense, such as adversarial training, which can mitigate poisoning effects but is computationally intensive. The other approach is pre-training purification, e.g., image short squeezing, which consists of several simple compressions but often encounters challenges in dealing with various UEs. Our work provides a novel disentanglement mechanism to build an efficient pre-training purification method. Firstly, we uncover rate-constrained variational autoencoders (VAEs), demonstrating a clear tendency to suppress the perturbations in UEs. We subsequently conduct a theoretical analysis for this phenomenon. Building upon these insights, we introduce a disentangle variational autoencoder (D-VAE), capable of disentangling the perturbations with learnable class-wise embeddings. Based on this network, a two-stage purification approach is naturally developed. The first stage focuses on roughly eliminating perturbations, while the second stage produces refined, poison-free results, ensuring effectiveness and robustness across various scenarios. Extensive experiments demonstrate the remarkable performance of our method across CIFAR-10, CIFAR-100, and a 100-class ImageNet-subset. Code is available at https://***/yuyi-sd/D-VAE. Copyright 2024 by the author(s)

关键词： Variational techniques

来源：评论

学校读者我要写书评

暂无评论

Prior-Guided Parallel Residual Bi-Fusion Network in USV Obstacle Detection

Prior-Guided Parallel Residual Bi-Fusion Network in USV Obst...

引用

IEEE International Conference on Consumer Electronics-Taiwan (ICCE-TW)

作者： Chih-Chung Hsu Sophia Yang Xiu-Yu Hou Yu-An Jhang Institute of Data Science National Cheng Kung University Interdisciplinary Program of Electrical Engineering and Computer Science National Tsing Hua University

In this paper, we propose a novel Prior-Guided Parallel Residual Bi-Fusion Feature Pyramid Network (PPRB-FPN) for accurate obstacle detection in unmanned surface vehicle (USV) sailing. Our method tackles the challenge of detecting small objects, which are prone to information vanishing. To the end, we leverage the PRB-FPN for small object detection and YOLOv7 as a single-stage object detector to effectively identify obstacles. Our experimental results on the Obstacle Detection Challenge dataset at the 1st Workshop on Maritime computer Vision (MaCVi) demonstrate that our method outperforms both Mask R-CNN (mrcnn) and YOLOv7, achieving an F_avg score of 0.514.

关键词：

来源：评论

学校读者我要写书评

暂无评论

RUL Estimation for Power Electronic Devices Using RNNs

RUL Estimation for Power Electronic Devices Using RNNs

引用

Prognostics and System Health Management Conference (PHM)

作者： Congrui Cai Zhonghai Lu Embedded Systems Master Program School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Department of Electrical Engineering School of Electrical Engineering and Computer Science KTH Royal Institute of Technology

ISBN: (数字)9798350360585

ISBN: (纸本)9798350360592

Recurrent Neural Networks (RNNs) are commonly used in data-driven approaches to estimate the Remaining Useful Lifetime (RUL) of power electronic devices. RNNs are preferred because their intrinsic feedback mechanisms are better suited to model time-series data. However, the impact of RNN complexity on estimation accuracy is rarely discussed in the literature. This issue is important because choosing a lower-complexity model that delivers the same or similar performance as a higher-complexity model can increase implementation efficiency. In the paper, we use three RNN models, namely, the vanilla version, LSTM (Long Short Term Memory) and GRU (Gated Recurrent Unit) to conduct RUL estimation for power electronic devices. We use two accelerated aging datasets, one dataset targeting the package failure of MOSFETs, and the other dataset targeting package failure of power diodes. Our study shows that a lower-complexity RNN does not necessarily deliver a lower performance. Similarly, a higher-complexity model does not assure a higher performance. As such, our work highlights the importance of selecting a proper neural network for RUL estimation not biased towards complex models. This is especially useful and important for implementing such RUL estimation techniques in embedded resource-constrained and speed-limited computins platforms.

关键词： Performance evaluation Semiconductor device modeling Recurrent neural networks Computational modeling Estimation Power electronics Data models

来源：评论

学校读者我要写书评

暂无评论

Semantic Token Reweighting for Interpretable and Controllable Text Embeddings in CLIP

Semantic Token Reweighting for Interpretable and Controllabl...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Kim, Eunji Shim, Kyuhong Chang, Simyung Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Korea Republic of Qualcomm AI Research an initiative of Qualcomm Technologies Inc. Qualcomm Korea YH Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of

ISBN: (纸本)9798891761681

A text encoder within Vision-Language Models (VLMs) like CLIP plays a crucial role in translating textual input into an embedding space shared with images, thereby facilitating the interpretative analysis of vision tasks through natural language. Despite the varying significance of different textual elements within a sentence depending on the context, efforts to account for variation of importance in constructing text embeddings have been lacking. We propose a framework of Semantic Token Reweighting to build Interpretable text embeddings (SToRI), which incorporates controllability as well. SToRI refines the text encoding process in CLIP by differentially weighting semantic elements based on contextual importance, enabling finer control over emphasis responsive to data-driven insights and user preferences. The efficacy of SToRI is demonstrated through comprehensive experiments on few-shot image classification and image retrieval tailored to user preferences. © 2024 Association for Computational Linguistics.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

MarUCOD: Unknown but Concerned Object Detection in Maritime Environments 27th

MarUCOD: Unknown but Concerned Object Detection in Maritim...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Yoon, Hajung Lee, Yoonji Lee, Hwijun Um, Daeho Choi, Hong Seok Choi, Jin Young Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul08826 Korea Republic of Department of Electrical and Computer Engineering Seoul National University Seoul08826 Korea Republic of NexReal Inc. 178 Digital-ro Geumcheon-gu Seoul Korea Republic of

ISBN: (纸本)9783031784460

Detection of unknown but concerned objects such as diverse unknown suspicious objects in the sea area is a critical problem in military defense applications, but the problem is challenging because 1) a pre-trained detector cannot easily detect unknown but concerned objects, 2) it detects too many unconcerned objects such as usual objects in the coastal land area, and 3) we cannot easily establish a well-performing discriminator to divide the detected objects into unknown and known objects, as well as concerned and unconcerned objects because the unknown objects are not available, whereas the concerned and unconcerned objects are not clearly defined. To tackle this challenge, this paper proposes a real-time framework for unknown but concerned object detection in maritime environments by integrating object detection, segmentation, and out-of-distribution (OOD) detection techniques. In our framework, an object detector finds all object-like foregrounds by setting a low threshold and a segmentation deep-learning network filters out unconcerned foregrounds detected in the coastal land area. After that, to discriminate known or unknown objects among concerned objects detected in the sea area, a discriminator performs unsupervised OOD detection using bisecting K-means clustering. To boost the performance of the proposed framework, we apply a pre-processing scheme and a contrastive separation loss for segmentation. The proposed framework achieves a high detection rate of unknown but concerned objects with minimal detection of unconcerned objects (i.e., minimal false positives), surpassing baseline methods and demonstrating potential for enhanced maritime safety and security. The codes are open at https://***/AIX-Coast-Defense-PIL/MarUCOD. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

Reconstruction of Layered Rough Surfaces Using a Two-Step RTM Scheme

Reconstruction of Layered Rough Surfaces Using a Two-Step RT...

引用

Antennas and Propagation & USNC/URSI National Radio science Meeting

作者： Ahmet Sefer Hakan Bagci Electrical and Computer Engineering (ECE) Program Computer Electrical and Mathematical Science and Engineering (CEMSE) Division King Abdullah University of Science and Technology (KAUST) Thuwal Saudi Arabia

ISBN: (数字)9798350369908

ISBN: (纸本)9798350369915

An imaging scheme, which uses the frequency- domain reverse time migration (RTM) method to reconstruct two rough surfaces between three dielectric media from the scattered field measurements, is developed. The proposed method requires two steps for the reconstructions. At the first step, the RTM function that is computed using the scattered field measurements reveals only the upper rough surface. At the second step, it is first assumed that there is only one surface, the upper one. The forward scattering problem is solved for this scenario. Then, to reconstruct the lower surface, the difference between the scattered fields obtained from this forward scattering problem and the scattered field measurements is used to compute the RTM function of the second step. This second RTM function reveals the lower surface. Numerical experiments demonstrate that the proposed two-step scheme is effective and promising.

关键词： Surface reconstruction Time-frequency analysis Integral equations Imaging Media Surface roughness Dielectric measurement

来源：评论

学校读者我要写书评

暂无评论

Reconstruction of Rough Surface Profiles using a CNN-enhanced RTM-based Inversion Scheme

Reconstruction of Rough Surface Profiles using a CNN-enhance...

引用

International Review of Progress in Applied Computational Electromagnetics (ACES)

作者： Ahmet Sefer Guang Ooi Shehab Ahmed Hakan Bagci Electrical and Computer Engineering (ECE) Program Computer Electrical and Mathematical Science and Engineering (CEMSE) Division King Abdullah University of Science and Technology (KAUST) Thuwal Saudi Arabia

ISBN: (数字)9781733509671

ISBN: (纸本)9798350362978

Numerical methods that can accurately reconstruct rough surface profiles are used in various fields of engineering such as remote sensing, microwave imaging, optics, nondestructive testing, etc. These methods express the electromagnetic scattered fields measured away from the surface itself as an integral function of the surface profile. This mapping is highly nonlinear and ill-posed (D. Colton and R. Kress, 1998, SpringerVerlag, Berlin), and therefore its inversion for reconstruction of the surface profile from measured scattered fields is challenging. This inversion can done using semi-analytic asymptotic approaches such as the small perturbation and the Rytov approximation methods (A.G. Voronovich, 2013, Springer-Verlag, Berlin), however the range of applicability of these approaches is rather limited. Fully numerical methods that rely on Newton-type iterative linearization techniques and regularization schemes such as those in (S. Arhab, et al., PIERS, pp. 3495–3500, 2017) and (A. Sefer, A. Yapar, IEEE Trans. Geosci Remote Sens., vol. 59, pp. 1041–1051, 2021) have a wider range of applicability but they suffer from convergence and accuracy issues.

关键词： Microwave measurement Surface reconstruction Perturbation methods Nondestructive testing Optical variables measurement Optics Surface roughness

来源：评论

学校读者我要写书评

暂无评论

Electromagnetic Inversion Regularized by a Plug-and-Play Deep Neural Network Denoiser

Electromagnetic Inversion Regularized by a Plug-and-Play Dee...

引用

Antennas and Propagation & USNC/URSI National Radio science Meeting

作者： Lingqi Gao Hakan Bagci Electrical and Computer Engineering (ECE) Program Computer Electrical and Mathematical Science and Engineering (CEMSE) Division King Abdullah University of Science and Technology (KAUST) Thuwal Saudi Arabia

ISBN: (数字)9798350369908

ISBN: (纸本)9798350369915

A plug-and-play scheme that relies on a deep neural network for image denoising is used to regularize the nonlinear electromagnetic (EM) inversion. It is shown that any state-of-the-art denoiser can be plugged into the conventional inversion framework as an implicit regularization step. Thus, a pretrained Swin-Conv-UNet (SCUNet) is employed in the EM inversion. SCUNet combines the advantages of residual convolutional layers and swin transformer blocks in accounting for different image priors and it is remarkably effective in image denoising. Nu-merical results obtained using this framework clearly shows its benefits over existing inversion algorithms.

关键词： Conferences Artificial neural networks Transformers Antennas and propagation Electromagnetics Image denoising

来源：评论

学校读者我要写书评

暂无评论

A Ratio-Norm Regularization for Sparsity-Promoting Electromagnetic Inversion

A Ratio-Norm Regularization for Sparsity-Promoting Electroma...

引用

International Review of Progress in Applied Computational Electromagnetics (ACES)

ISBN: (数字)9781733509671

ISBN: (纸本)9798350362978

A nonlinear electromagnetic inversion method that promotes the sparsity in the model gradient is proposed for reconstruction of dielectric profiles. For regularization, the method uses the ratio of $l_{1}$ -norm to $l_{2}$ -norm ( $l_{1}/l_{2}$ -norm) which is a better approximation to $l_{0}$ -norm than $l_{1}$ -norm due to its scale-invariant property. To deal with the non-convexity of the resulting optimization problem, the alternating direction method of mul-tipliers is used to split the quotient structure of the $l_{1}/l_{2}$ -norm. Consequently, the optimization problem is separated into several sub-steps that are executed iteratively in an alternating fashion. Numerical results show that the proposed method produces more accurate reconstructions of spatially sparse dielectric profiles (by preserving edges and reducing artifacts) compared to the methods relying on Tikhonov and total variation regularization.

关键词： Accuracy Computational electromagnetics Dielectrics Electromagnetics Optimization

来源：评论

学校读者我要写书评

暂无评论

A Wide-angle and Polarization-independent Plasmonic Absorber for UV to Near-IR Range

A Wide-angle and Polarization-independent Plasmonic Absorber...

引用

Antennas and Propagation & USNC/URSI National Radio science Meeting

作者： Partha Mondal Omar Alkhazragi Boon S. Ooi Hakan Bagci Electrical and Computer Engineering (ECE) Program Computer Electrical and Mathematical Science and Engineering (CEMSE) Division King Abdullah University of Science and Technology (KAUST) Thuwal Saudi Arabia

ISBN: (数字)9798350369908

ISBN: (纸本)9798350369915

A metamaterial-based plasmonic absorber is designed, fabricated, and characterized. The absorber consists of a periodic array of Ti unit-cells at the top, a layer of Al at the bottom, and a thin SiO 2 layer that is sandwiched between the top and the bottom layers. Simulations and experiments show that the proposed design supports an average absorption of 96% over the wavelength range changing from 280 nm to 1000 nm (frequency range between ultraviolet [UV] and near-infrared [IR]). Furthermore, the absorption spectrum is polarization insensitive and has a large incidence angle tolerance. The proposed absorber has the potential to be used in photovoltaic applications such as solar cells and photo-detectors.

关键词： Silicon compounds Photovoltaic systems Absorption Photovoltaic cells Conferences Plasmons Antennas and propagation

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352页 << < 9 10 11 12 13 14 15 16 17 18 > >>

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：