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

4,072 篇 会议
892 篇 期刊文献
73 册 图书

馆藏范围

5,037 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

3,134 篇 工学
- 1,879 篇 计算机科学与技术...
- 1,563 篇 软件工程
- 730 篇 信息与通信工程
- 655 篇 控制科学与工程
- 528 篇 电气工程
- 508 篇 电子科学与技术（可...
- 252 篇 生物工程
- 248 篇 机械工程
- 227 篇 动力工程及工程热...
- 224 篇 光学工程
- 212 篇 生物医学工程（可授...
- 178 篇 仪器科学与技术
- 165 篇 化学工程与技术
- 123 篇 材料科学与工程（可...
- 117 篇 交通运输工程
- 98 篇 建筑学
- 98 篇 安全科学与工程
1,652 篇 理学
- 915 篇 数学
- 451 篇 物理学
- 285 篇 统计学（可授理学、...
- 281 篇 生物学
- 255 篇 系统科学
- 162 篇 化学
694 篇 管理学
- 477 篇 管理科学与工程(可...
- 295 篇 工商管理
- 256 篇 图书情报与档案管...
171 篇 医学
- 147 篇 临床医学
- 128 篇 基础医学(可授医学...
119 篇 法学
- 99 篇 社会学
100 篇 经济学
- 99 篇 应用经济学
94 篇 教育学
47 篇 农学
13 篇 文学
11 篇 军事学
6 篇 艺术学

主题

95 篇 accuracy
87 篇 computational mo...
79 篇 training
77 篇 optimization
70 篇 feature extracti...
61 篇 predictive model...
61 篇 machine learning
58 篇 artificial intel...
54 篇 data models
49 篇 control systems
49 篇 mathematical mod...
48 篇 neural networks
45 篇 computer archite...
44 篇 protocols
44 篇 software
43 篇 deep learning
40 篇 wireless communi...
40 篇 robustness
39 篇 servers
38 篇 computer science

机构

56 篇 dept. of systems...
34 篇 dept. of systems...
24 篇 optical sciences...
17 篇 dept. of electri...
14 篇 dept. of systems...
14 篇 dept. of electri...
14 篇 dept. of electri...
12 篇 networking and i...
12 篇 ieee
12 篇 school of engine...
11 篇 international is...
11 篇 school of automa...
11 篇 dept. of compute...
10 篇 dept. of electri...
10 篇 dept. of electri...
10 篇 international is...
10 篇 cssc systems eng...
9 篇 dept. of electri...
9 篇 department of ph...
9 篇 dept. of electri...

作者

35 篇 wainer gabriel
21 篇 tan mengxi
21 篇 xu xingyuan
21 篇 moss david j.
18 篇 gabriel wainer
15 篇 yangquan chen
13 篇 xi zhang
13 篇 mitchell arnan
13 篇 mesaritakis char...
12 篇 sakamoto makoto
12 篇 dushan boroyevic...
11 篇 reiner lisa
11 篇 ito takao
11 篇 fotiadis dimitri...
11 篇 furutani hiroshi
11 篇 bavarian behzad
11 篇 morandotti rober...
11 篇 corcoran bill
11 篇 bogris adonis
10 篇 woodside murray

语言

4,866 篇 英文
102 篇 其他
52 篇 中文
8 篇 日文
7 篇 朝鲜文
1 篇 德文
1 篇 俄文

检索条件"机构=Computer Systems and Program Engineering Dept."

共 5037 条记录，以下是21-30 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 Augmentation Framework for Improving Image Recognition Using cycleGAN 18

Data Augmentation Framework for Improving Image Recognition ...

引用

18th International Conference on Ubiquitous Information Management and Communication, IMCOM 2024

作者： Kim, Sangmin Deribe, Selome Tesfaye Byun, Gyurin Joo, Kyeongjin Pyo, Jeongwon Kuc, Taeyong Choo, Hyunseung Sungkyunkwan University Dept. of Electrical and Computer Engineering Suwon Korea Republic of Sungkyunkwan University Dept. of AI Systems Engineering Suwon Korea Republic of

ISBN: (纸本)9798350331011

This paper proposes a novel framework that significantly enhances the performance of semantic segmentation models in recognizing specific objects. Leveraging the capabilities of Generative Adversarial Networks (GANs), particularly Cycle-GAN, this framework focuses on augmenting high-quality data to improve object recognition in autonomous driving and other applications. The study utilizes a dataset of 5,005 road images, enriched with polygon labels for precise object recognition. Key advancements in this research include the implementation of feature matching and fact forcing techniques to stabilize and integrate GAN performance, thereby overcoming common challenges like mode collapse, slow training, and overfitting. In the performance-enhanced GAN model, we improved the Discriminator Loss from the original 1.0517 to 0.0001, achieving convergence to zero 66.67% faster. © 2024 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Activity Recognition from Channel State Information for Few-Sampled Scenarios

Activity Recognition from Channel State Information for Few-...

引用

2023 IEEE Globecom Workshops, GC Wkshps 2023

作者： Diaz, Guillermo Sobron, Iker Eizmendi, Iñaki Landa, Iratxe Velez, Manuel Dept. of Communications Engineering Bilbao Spain Dept. of Computer Languages and Systems Bilbao Spain

ISBN: (纸本)9798350370218

Human Activity Recognition (HAR) using channel state information (CSI) from wireless systems has been a field in progress for the last few years. In particular, amplitudes of WiFi-based CSI have been widely used for HAR in indoor scenarios. In contrast, CSI phases are less exploited due to higher sensitivity to timing errors in channel estimation. This paper further explores a recent phase processing method to obtain environmental information from CSI and improves classification using a Convolutional Neural Network in few-sampled scenarios. For this purpose, a new dataset has been generated with measurements of three receivers on different days and with different people, for activity recognition and people counting. In addition, we incorporate a transfer learning strategy using fine-tuning along with a data fusion model from different receivers to improve accuracy metrics by training the model and validating it on data taken on different days. Promising results with accuracies higher than 80 % have been obtained with transfer learning between days using 5 % of data for fine-tuning. © 2023 IEEE.

关键词： activity recognition CSI few-shot learning fine-tuning people counting phase

来源：评论

学校读者我要写书评

暂无评论

Improving Fake News Detection with a Mixture of Experts: Leveraging Sentiment Analysis and Sarcasm Detection as Core Expert Models 6

Improving Fake News Detection with a Mixture of Experts: Lev...

引用

6th International Conference on Advancements in Computing, ICAC 2024

作者： Gunasekara, Tharindu Thihan, Disira Kodithuwakku, Sansika Dissanayake, Dinuka Fernando, Harinda Vidhanaarachchi, Samitha Sindhujan, Archchana Sri Lanka Institute of Information Technology Malabe Dept. of Software Engineering Sri Lanka Sri Lanka Institute of Information Technology Malabe Dept. of Computer Computer Systems Engineering Sri Lanka University of Surrey Dept. of Computer Science and Electronic Engineering United Kingdom

ISBN: (纸本)9798331517878

Fake news continues to proliferate, posing an increasing threat to public discourse. The paper proposes a framework of a Mixture of Experts, Sentiment Analysis, and Sarcasm Detection experts for improved fake news detection. This approach captures the emotional cues in the text through a Sentiment Analysis expert, which is based on bidirectional encoder representations from Transformers (BERT) models with sentiment vectors generated using SentiWordNet and Integrated Gradients. It combines a sarcasm detection expert based on BERT, recognizing sarcasm and its type to help classify fake news. By fusing these experts through a Mixture of Experts gateway, subtle linguistic cues often found in fake news are more effectively analyzed, leading to improved accuracy in detecting misinformation. Experimental results are presented as 96% for the Sarcasm expert with the BERT base model and 83% for the Sentiment Analysis expert with the distilled version of the BERT (DistilBERT) base model, proving the effectiveness of the proposed approach in beating traditional methods. © 2024 IEEE.

关键词： fake news detection gateway mixture of experts sarcasm detection sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Dynamic SpikFormer: Low-Latency & Energy-Efficient Spiking Neural Networks with Dynamic Time Steps for Vision Transformers

Dynamic SpikFormer: Low-Latency & Energy-Efficient Spiking N...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Datta, Gourav Liu, Zeyu Li, Anni Beerel, Peter A. Dept. of Electrical Computer & Systems Engineering Case Western Reserve University Cleveland United States Ming Hsieh Dept. of Electrical and Computer Engineering University of Southern California Los Angeles United States

ISBN: (纸本)9798350368741

Spiking Neural Networks (SNNs) have emerged as a popular spatio-temporal computing paradigm for complex vision tasks. Recently proposed SNN training algorithms have significantly reduced the number of time steps (down to 1) for improved latency and energy efficiency, however, they target only convolutional neural networks (CNN). These algorithms, when applied to the recently spotlighted vision transformers (ViT), either require a large number of time steps or fail to converge. Based on the analysis of the histograms of the ANN and SNN activation maps, we hypothesize that each ViT block has a different sensitivity to the number of time steps. We propose a novel training framework that dynamically allocates the number of time steps to each ViT module depending on a trainable score assigned to each timestep. In particular, we generate a scalar binary time step mask that filters spikes emitted by each neuron in a leaky-integrate-and-fire (LIF) layer. The resulting SNNs have high activation sparsity and require only accumulate operations (AC), except for the input embedding layer, in contrast to expensive multiply-and-accumulates (MAC) needed in traditional ViTs. This yields significant improvements in energy efficiency. We evaluate our training framework and resulting SNNs on image recognition tasks including CIFAR10, CIFAR100, and ImageNet with different ViT architectures. We obtain a test accuracy of 95.97% with 4.97 time steps with direct encoding on CIFAR10. © 2025 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Pseudo-Holographic Display of Plant Models based on Pepper's Ghost Illusion 13

Pseudo-Holographic Display of Plant Models based on Pepper's...

引用

Joint 13th International Conference on Soft Computing and Intelligent systems and 25th International Symposium on Advanced Intelligent systems, SCIS and ISIS 2024

作者： Umezu, Nobuyuki Iijima, Satoshi Ibaraki University Dept. of Computer and Information Sciences Hitachi Japan Ibaraki University Dept. of Mechanical Systems Engineering Hitachi Japan

ISBN: (纸本)9798350373332

We propose a new display method for visualizing flower models using a pseudo-holographic technique known as the Pepper's ghost illusion. This classic optical illusion technique creates the appearance of floating objects by reflecting them off a transparent panel, thereby producing a convincing visual effect that simulates three-dimensionality. In our approach, we utilized this illusion to display six distinct flower models obtained from a comprehensive photogrammetry archive of various plant species. These models were rendered to overlay onto a transparent glass vase, enhancing the realism of quality. To facilitate user interaction with the displayed models, we incorporated a dept. sensor (Intel D415) to track the user's hand position. A user study revealed that participants were notably attracted to the display, indicating successful capture of their attention. Feedback, however, suggested that the system requires enhancements in usability and dept. perception to improve the overall user experience. Our future work includes addressing these limitations by developing a larger display setup that could accommodate more complex interactions and by integrating motion-parallax techniques to enhance the three-dimensional view. This could be implemented using head-tracking technology, further advancing the effectiveness of the pseudo-holographic display. © 2024 IEEE.

关键词： Holographic displays

来源：评论

学校读者我要写书评

暂无评论

Interactive Museum Kiosk for Visualizng Visitor Activities 13

Interactive Museum Kiosk for Visualizng Visitor Activities

引用

13th IEEE Global Conference on Consumer Electronic, GCCE 2024

作者： Umezu, Nobuyuki Nishida, Saku Ibaraki University Dept. of Computer and Information Sciences Hitachi Japan Ibaraki University Dept. of Mechanical Systems Engineering Hitachi Japan

ISBN: (纸本)9798350355079

We propose an interactive information kiosk for tracking and visualizing visitor activities in museums. Each visitor is assigned a sheet of paper with one's own QR code and recocnized by presenting the code before interacting with our kiosks and other exhibits. The proposed kiosk has a 32 inch LCD built into a wooden stand and a inexpensive two-dimensional LiDAR sensor mounted at the top to detect visitor interactions of hand gestures towards the display surface. We implemented a four-choice quiz with 40 questions, an personal review of visitor activity, and a museum floor guide which can be scrolled using hand gestures. A server system has been also developed to collect information from kiosks and summarize it. A series of experiments was conducted in a local science museum for two days to evaluate the proposed system to track and visualize visitor activities. Our future work includes improving the system with various sensors and larger-scale experiments with more kiosks with multiple types of content. © 2024 IEEE.

关键词： Liquid crystal displays

来源：评论

学校读者我要写书评

暂无评论

Passing Practice Support for Soccer Players Using First-Person Videos 13

Passing Practice Support for Soccer Players Using First-Pers...

引用

Joint 13th International Conference on Soft Computing and Intelligent systems and 25th International Symposium on Advanced Intelligent systems, SCIS and ISIS 2024

作者： Umezu, Nobuyuki Imada, Yuya Ibaraki University Dept. of Computer and Information Sciences Hitachi Japan Ibaraki University Dept. of Mechanical Systems Engineering Hitachi Japan

ISBN: (纸本)9798350373332

We propose a novel visualization system to enhance soccer passing practice by providing potential pass courses and their scores. The proposed system is based on a first-person video footage captured during soccer play and extracts frames for pass-course suggestions using the rate of ground-surface pixels in the frame and dept. estimation. Possible pass courses were scored according to their direction and distance to the closest player. To validate the proposed method's effectiveness, we conducted a series of experiments involving 17 participants, comprising 12 museum visitors and five university students. The estimated score of visualized pass courses using the proposed method was generally successful, whereas some pass courses received lower scores from participants owing to limitations in the system's ability to accurately detect the color of players' uniforms, which affected the overall evaluation of certain passing options. © 2024 IEEE.

关键词： Visualization

来源：评论

学校读者我要写书评

暂无评论

Inverse-Designed 16-Channel Time-of-Flight Receiver in 45nm Silicon Photonic Process

Inverse-Designed 16-Channel Time-of-Flight Receiver in 45nm ...

引用

2024 Integrated Photonics Research, Silicon and Nanophotonics, IPR 2024

作者： Rollinson, John Karlicek, Robert Hella, Mona Dept. of Electrical Computer and Systems Engineering Rensselaer Polytechnic Institute TroyNY United States

A 16-channel monolithic electronic-photonic receiver for flash time-of-flight LIDAR is demonstrated in 45nm silicon photonic process. Enverse-designed grating array antennas are utilized for efficient, low-noise coupling of free-space light, thus improving signal-to-noise ratio and extending sensing range of the free-space optical receiver. © 2024 The Author (s).© Optica Publishing Group 2024

关键词： Silicon photonics

来源：评论

学校读者我要写书评

暂无评论

Interactive Floor Projection in a Museum for Learning Small Creatures 13

Interactive Floor Projection in a Museum for Learning Small ...

引用

13th IEEE Global Conference on Consumer Electronic, GCCE 2024

作者： Umezu, Nobuyuki Nakagawa, Koki Ibaraki University Dept. of Computer and Information Sciences Hitachi Japan Ibaraki University Dept. of Mechanical Systems Engineering Hitachi Japan

ISBN: (纸本)9798350355079

We propose an interactive projection system that uses two projectors and a two-dimensional LiDAR sensor. A mirror was used to reflect a portion of the scanning plane of the sensor to detect the location of the user on the floor and that of the touch. Three-dimensional colored models of small creatures, such as frogs and mantis, were displayed on the floor screen, whereas the front screen on the wall was used to provide mini quizzes and information about the creature. User experiments were conducted at a science museum to evaluate the proposed system. Seventeen participants rated our system at 4.23 on a scale of 1 to 5 in terms of interest, usability, and helpfulness. © 2024 IEEE.

关键词： 2D LiDAR sensor creature shape models mirror quiz silhouette zoom-out

来源：评论

学校读者我要写书评

暂无评论

Closed-Loop System Identification of an Unstable Nonlinear System Using Koopman Operator 4

Closed-Loop System Identification of an Unstable Nonlinear S...

引用

4th International Symposium on Instrumentation, Control, Artificial Intelligence, and Robotics, ICA-SYMP 2025

作者： Maneeloke, Benjaset Boonto, Sudchai Sanposh, Peerayot Tipsuwan, Yodyium Chinthaned, Natthawut Tanaprasitpattana, Warit Kasetsart University Dept. of Electrical Engineering Bangkok Thailand King Mongkut's University of Technology Thonburi Dept. of Control Systems and Instrumentation Engineering Bangkok Thailand Kasetsart University Dept. of Computer Engineering Bangkok Thailand

ISBN: (纸本)9798331505400

This paper presents a novel methodology for closed-loop system identification of unstable nonlinear systems using the Koopman operator with Extended Dynamic Mode Decomposition with control (EDMDc). The study highlights the critical role of selecting appropriate observable functions to develop accurate and efficient Koopman models. We demonstrate that the resulting Koopman models exhibit excellent fitting and validation properties and retain the stabilizability of the original nonlinear systems. These models are verified through time and frequency responses under closed-loop control using a Linear Quadratic Regulator (LQR), confirming their effectiveness. Future work will extend this framework to more complex systems and incorporate machine learning techniques to refine the selection of observable functions. This approach aims further to enhance the adaptability and robustness of Koopman-based control strategies. © 2025 IEEE.

关键词： Dynamic mode decomposition

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 << < 1 2 3 4 5 6 7 8 9 10 > >>

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：