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

207 篇 期刊文献
169 篇 会议
2 册 图书

馆藏范围

378 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

232 篇 工学
- 149 篇 计算机科学与技术...
- 128 篇 软件工程
- 50 篇 生物工程
- 39 篇 信息与通信工程
- 37 篇 生物医学工程（可授...
- 26 篇 光学工程
- 24 篇 电气工程
- 22 篇 控制科学与工程
- 19 篇 土木工程
- 14 篇 化学工程与技术
- 11 篇 电子科学与技术（可...
- 10 篇 仪器科学与技术
- 10 篇 动力工程及工程热...
- 9 篇 建筑学
- 9 篇 安全科学与工程
- 8 篇 机械工程
- 8 篇 材料科学与工程（可...
- 8 篇 船舶与海洋工程
142 篇 理学
- 58 篇 生物学
- 42 篇 数学
- 33 篇 物理学
- 22 篇 化学
- 20 篇 统计学（可授理学、...
52 篇 管理学
- 30 篇 图书情报与档案管...
- 24 篇 管理科学与工程(可...
- 16 篇 工商管理
26 篇 医学
- 24 篇 临床医学
- 20 篇 基础医学(可授医学...
- 12 篇 药学(可授医学、理...
10 篇 法学
8 篇 教育学
- 7 篇 教育学
6 篇 经济学
3 篇 农学
1 篇 军事学

主题

15 篇 accuracy
13 篇 deep learning
13 篇 training
8 篇 neural networks
8 篇 computational mo...
8 篇 machine learning
7 篇 feature extracti...
7 篇 computer vision
7 篇 convolutional ne...
6 篇 deep neural netw...
6 篇 predictive model...
6 篇 real-time system...
6 篇 forecasting
5 篇 magnetic resonan...
5 篇 adversarial mach...
5 篇 navigation
5 篇 testing
4 篇 roads
4 篇 distillation
4 篇 safety

机构

57 篇 interdisciplinar...
47 篇 department of el...
11 篇 department of el...
10 篇 department of el...
9 篇 department of co...
9 篇 interdisciplinar...
8 篇 interdisciplinar...
8 篇 interdisciplinar...
7 篇 dept. of electri...
7 篇 division of digi...
7 篇 interdisciplinar...
6 篇 department of mo...
6 篇 department of bi...
6 篇 dept. of electri...
6 篇 department of co...
6 篇 vector institute...
6 篇 department of co...
6 篇 bachelor degree ...
5 篇 leeds institute ...
5 篇 center for psych...

作者

56 篇 yoon sungroh
16 篇 jung dahuin
13 篇 kim young min
13 篇 sungroh yoon
12 篇 lee saehyung
11 篇 hwang uiwon
8 篇 young min kim
8 篇 kim eunji
8 篇 jang hyemi
7 篇 bae ho
7 篇 kim junho
7 篇 kim siwon
7 篇 kim sun
7 篇 hwang min-shiang
6 篇 park junsung
6 篇 piao yinhua
6 篇 dahuin jung
6 篇 lee jonghyun
6 篇 mok jisoo
6 篇 suharjito

语言

280 篇 英文
96 篇 其他
2 篇 中文
1 篇 德文
1 篇 法文

检索条件"机构=Bachelor of Engineering Program in Computer Engineering and Artificial Intelligence"

共 378 条记录，以下是51-60 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：

A Hybrid Inference Engine to Predict Uncertain Sugar Content for Sugar Industry 9th

A Hybrid Inference Engine to Predict Uncertain Sugar Content...

引用

9th International Conference on computer Science and Computational intelligence, ICCSCI 2024

作者： Asrol, Muhammad Napthaleni Utama, Ditdit Nugeraha Suharjito Harito, Christian Syafrudin, Muhammad Industrial Engineering Department BINUS Graduate Program Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program Bina Nusantara University Jakarta11480 Indonesia Department of Artificial Intelligence and Data Science Sejong University Seoul05006 Korea Republic of

The sugar industry is facing challenges in increasing productivity to meet consumer demand. One opportunity for productivity improvement lies in ensuring sugar content. This study proposes a hybrid model to predict sugar content by considering uncertainty factors. A hybrid model combining fuzzy subtractive clustering, and a fuzzy inference system is proposed to predict sugar content. The clustering results using silhouette and fuzzy subtractive clustering successfully identified 6 cluster centres from 2225 datasets collected in a sugar industry in East Java Province. The hybrid inference engine model is designed with fuzzy rules derived from the clustered data. Two inference models are developed: triangular and Gaussian fuzzy numbers. The testing results indicate that the hybrid model with triangular fuzzy numbers shows the smallest error with an R2 value of 0.95. This model is possible to applied in the sugar industry for decision makers in improving productivity with taking attention into uncertain factors influencing sugar content. © 2024 The Authors.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Introducing spectral attention for long-range dependency in time series forecasting 24

Introducing spectral attention for long-range dependency in ...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Bong Gyun Kang Dongjun Lee HyunGi Kim DoHyun Chung Sungroh Yoon Interdisciplinary Program in Artificial Intelligence Seoul National University Department of Electrical and Computer Engineering Seoul National University Department of Future Automotive Mobility Seoul National University Interdisciplinary Program in Artificial Intelligence Seoul National University and Department of Electrical and Computer Engineering Seoul National University

ISBN: (纸本)9798331314385

Sequence modeling faces challenges in capturing long-range dependencies across diverse tasks. Recent linear and transformer-based forecasters have shown superior performance in time series forecasting. However, they are constrained by their inherent inability to effectively address long-range dependencies in time series data, primarily due to using fixed-size inputs for prediction. Furthermore, they typically sacrifice essential temporal correlation among consecutive training samples by shuffling them into mini-batches. To overcome these limitations, we introduce a fast and effective Spectral Attention mechanism, which preserves temporal correlations among samples and facilitates the handling of long-range information while maintaining the base model structure. Spectral Attention preserves long-period trends through a low-pass filter and facilitates gradient to flow between samples. Spectral Attention can be seamlessly integrated into most sequence models, allowing models with fixed-sized look-back windows to capture longrange dependencies over thousands of steps. Through extensive experiments on 11 real-world time series datasets using 7 recent forecasting models, we consistently demonstrate the efficacy of our Spectral Attention mechanism, achieving state-of-the-art results.

关键词：

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

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

ReMP: Reusable Motion Prior for Multi-domain 3D Human Pose Estimation and Motion Inbetweening

ReMP: Reusable Motion Prior for Multi-domain 3D Human Pose E...

引用

IEEE Workshop on Applications of computer Vision (WACV)

作者： Hojun Jang Young Min Kim Dept. of Electrical and Computer Engineering Seoul National University Interdisciplinary Program in Artificial Intelligence and INMC Seoul National University

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

We present Reusable Motion prior (ReMP), an effective motion prior that can accurately track the temporal evolution of motion in various downstream tasks. Inspired by the success of foundation models, we argue that a robust spatio-temporal motion prior can encapsulate underlying 3D dynamics applicable to various sensor modalities. We learn the rich motion prior from a sequence of complete parametric models of posed human body shape. Our prior can easily estimate poses in missing frames or noisy measurements despite significant occlusion by employing a temporal attention mechanism. More interestingly, our prior can guide the system with incomplete and challenging input measurements to quickly extract critical information to estimate the sequence of poses, significantly improving the training efficiency for mesh sequence recovery. ReMP consistently outperforms the baseline method on diverse and practical 3D motion data, including depth point clouds, LiDAR scans, and IMU sensor data. Project page is available in https://***/ReMP.

关键词： Training Point cloud compression Three-dimensional displays Accuracy Tracking Shape Pose estimation Noise Parametric statistics Noise measurement

来源：评论

学校读者我要写书评

暂无评论

Offensive Chinese Text Detection Based on Multi-Feature Fusion 4

Offensive Chinese Text Detection Based on Multi-Feature Fusi...

引用

4th International Symposium on computer engineering and Intelligent Communications, ISCEIC 2023

作者： Li, Na Li, Shaomei Hong, Jiahao Zhengzhou University Academy of Cyberspace Security Zhengzhou China Strategic Support Force Information Engineering University National Engineering Research Center for Digital Program-Controlled Switching System Zhengzhou China Zhengzhou University School of Computer and Artificial Intelligence Zhengzhou China

ISBN: (纸本)9798350306323

To purify the online environment, it is essential to identify objectionable content, including offensive texts. However, some offensive texts are expressed in a more subtle manner, making it difficult to detect their literal characteristics. To enhance the effectiveness of detecting offensive Chinese text, we propose a multi-feature fusion-based method. First, we combine the word vectors obtained from Wobert with the character vectors obtained from ALBERT. The attention mechanism assigns greater importance to key features within the word vectors. Next, we merge the fusion vector with the sentence vector generated by ALBERT, which encompasses contextual semantics and syntactic information. This results in a new fusion vector that captures information at the character, word, and sentence levels. Finally, we employ a fully connected layer to process the three-level fusion vector and obtain the detection outcome. Experimental results demonstrate that this approach provides a comprehensive characterization of offensive text by fusing information from multiple levels. It substantially enhances the detection performance for offensive Chinese text. © 2023 IEEE.

关键词： Vectors

来源：评论

学校读者我要写书评

暂无评论

Acoustic Scene Classification Using Perceptually Weighted Log Mel Spectrogram and Buttom-up Broadcast Neural Network

Acoustic Scene Classification Using Perceptually Weighted Lo...

引用

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

作者： Riyad Ali Ahmad Abuirbaiha Chang-Hsing Lee Cheng Chang Lien Ph.D. Program in Engineering Science Chung Hua University Hsinchu Taiwan Bachelor Program in Industrial Artificial Intelligence Ming Chi University of Technology New Taipei City Taiwan Department of Computer Science and Information Engineering Chung Hua University Hsinchu Taiwan

ISBN: (数字)9798350386844

ISBN: (纸本)9798350386851

The study explores various 2D feature representations including spectrogram, MFCC spectrogram, log Mel-spectrogram, and the perceptual weighted log Mel-spectrogram (PW-LMSP) for acoustic scene classification (ASC). These 2D feature representations were classified using a bottom-up broadcast neural network (BBNN). The experimental results have shown that PW-LMSP outperforms other 2D representations. Further, the proposed method (PW-LMSP with BBNN) achieves accuracies of 91.2% and 91.6% respectively on the DCASE2018 and DCASE2019 development datasets, outperforming all the submissions in DCASE2018 and DCASE2019, as well as state-of-the-art approaches.

关键词： Scene classification Accuracy Neural networks LoRa Feature extraction Acoustics Mel frequency cepstral coefficient

来源：评论

学校读者我要写书评

暂无评论

Human Activity Classification: A LSTM and MediaPipe Approach for Intelligent Systems Application 6

Human Activity Classification: A LSTM and MediaPipe Approach...

引用

6th International Conference on Control and Robotics, ICCR 2024

作者： Chen, Yi-An Yang, Pei-Ching Chang Jung Christian University Master Degree Program in Information and Design Tainan Taiwan Chang Jung Christian University Department of Computer Science and Information Engineering Tainan Taiwan Chang Jung Christian University Artificial Intelligence Research Center Tainan Taiwan

ISBN: (纸本)9798331518158

With advancements in artificial intelligence, computer vision technologies have seen significant progress, enabling applications like facial recognition, autonomous driving, and medical imaging. This study leverages the Multi-Camera Action Dataset (MCAD) and MediaPipe Pose to create a skeletal dataset for training a Long Short-Term Memory (LSTM) model to recognize 18 types of daily actions. Evaluation using confusion matrix and F1 score reveals that Action 16 (Object Carry) is often misclassified as Action 7 (Walk) due to similar leg movements, and Action 9 (Cell to Ear) as Action 1 (Wave) due to similar hand movements. Future work aims to enhance model accuracy and explore broader applications in physical activity and exercise analysis. © 2024 IEEE.

关键词： Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Applying ant colony optimization algorithm to solve flying probe inspection problem

Applying ant colony optimization algorithm to solve flying p...

引用

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

作者： Chih-Yung Chen Yu-Ming Chang Bachelor Program in Artificial Intelligence and Mechatronics National Pingtung University of Science and Technology Pingtung Taiwan Department of Computer Science and Information Engineering Shu-Te University Kaohsiung Taiwan

This paper applies ant colony optimization (ACO) algorithm for the dual-pin flying probe circuit board inspection optimal path searching problem. First, the proposed approach creates a representation for circuit inspection path, which groups and encodes the measurement endpoints into a sequence. Moreover, the ant colony algorithm with the sequence can be used to solve the complex circuit optimal problem. The experimental results show that the best solutions of ACO are performed better than other algorithms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CLeAR: continual learning on algorithmic reasoning for human-like intelligence 23

CLeAR: continual learning on algorithmic reasoning for human...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Bong Gyun Kang HyunGi Kim Dahuin Jung Sungroh Yoon Interdisciplinary Program in Artificial Intelligence Seoul National University Department of Electrical and Computer Engineering Seoul National University Interdisciplinary Program in Artificial Intelligence Seoul National University and Department of Electrical and Computer Engineering Seoul National University

Continual learning (CL) aims to incrementally learn multiple tasks that are presented sequentially. The significance of CL lies not only in the practical importance but also in studying the learning mechanisms of humans who are excellent continual learners. While most research on CL has been done on structured data such as images, there is a lack of research on CL for abstract logical concepts such as counting, sorting, and arithmetic, which humans learn gradually over time in the real world. In this work, for the first time, we introduce novel algorithmic reasoning (AR) methodology for continual tasks of abstract concepts: CLeAR. Our methodology proposes a one-to-many mapping of input distribution to a shared mapping space, which allows the alignment of various tasks of different dimensions and shared semantics. Our tasks of abstract logical concepts, in the form of formal language, can be classified into Chomsky hierarchies based on their difficulty. In this study, we conducted extensive experiments consisting of 15 tasks with various levels of Chomsky hierarchy, ranging from in-hierarchy to inter-hierarchy scenarios. CLeAR not only achieved near zero forgetting but also improved accuracy during following tasks, a phenomenon known as backward transfer, while previous CL methods designed for image classification drastically failed.

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38页 << < 2 3 4 5 6 7 8 9 10 11 > >>

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：