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

3,067 篇 期刊文献
2,627 篇 会议
25 册 图书

馆藏范围

5,719 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

3,696 篇 工学
- 2,779 篇 计算机科学与技术...
- 2,298 篇 软件工程
- 815 篇 信息与通信工程
- 530 篇 生物工程
- 498 篇 控制科学与工程
- 486 篇 电气工程
- 359 篇 生物医学工程（可授...
- 346 篇 光学工程
- 312 篇 电子科学与技术（可...
- 202 篇 机械工程
- 155 篇 化学工程与技术
- 150 篇 交通运输工程
- 146 篇 安全科学与工程
- 141 篇 网络空间安全
- 130 篇 动力工程及工程热...
- 121 篇 仪器科学与技术
2,143 篇 理学
- 1,139 篇 数学
- 591 篇 生物学
- 531 篇 物理学
- 408 篇 统计学（可授理学、...
- 194 篇 系统科学
- 183 篇 化学
1,054 篇 管理学
- 628 篇 管理科学与工程(可...
- 472 篇 图书情报与档案管...
- 314 篇 工商管理
374 篇 医学
- 319 篇 临床医学
- 268 篇 基础医学(可授医学...
- 163 篇 公共卫生与预防医...
- 153 篇 药学(可授医学、理...
196 篇 法学
- 165 篇 社会学
111 篇 经济学
76 篇 农学
64 篇 教育学
10 篇 文学
7 篇 军事学
6 篇 艺术学
1 篇 历史学

主题

186 篇 deep learning
173 篇 accuracy
147 篇 training
144 篇 machine learning
141 篇 feature extracti...
113 篇 computational mo...
109 篇 semantics
101 篇 data models
92 篇 predictive model...
89 篇 real-time system...
88 篇 convolutional ne...
80 篇 federated learni...
75 篇 graph neural net...
73 篇 reinforcement le...
64 篇 internet of thin...
64 篇 deep neural netw...
62 篇 optimization
60 篇 contrastive lear...
56 篇 task analysis
56 篇 image segmentati...

机构

272 篇 college of compu...
120 篇 school of data a...
118 篇 beijing advanced...
103 篇 national enginee...
92 篇 school of comput...
88 篇 nanyang technolo...
72 篇 school of comput...
50 篇 school of comput...
50 篇 college of intel...
50 篇 university of ch...
49 篇 national enginee...
44 篇 school of comput...
42 篇 peng cheng labor...
42 篇 key laboratory o...
41 篇 school of comput...
41 篇 institute of dat...
39 篇 national enginee...
36 篇 school of comput...
35 篇 the college of c...
34 篇 school of comput...

作者

178 篇 niyato dusit
102 篇 hai jin
68 篇 jin hai
43 篇 tao dacheng
40 篇 cheng xueqi
37 篇 zheng wei-shi
30 篇 xiaofei liao
28 篇 peng hao
27 篇 guo jiafeng
26 篇 jin xiaolong
25 篇 hu shengshan
24 篇 sun geng
24 篇 rajeswari d.
24 篇 shen linlin
23 篇 li jianxin
23 篇 kang jiawen
21 篇 yang yang
19 篇 liu yang
19 篇 dusit niyato
19 篇 xiwang dong

语言

4,869 篇 英文
812 篇 其他
52 篇 中文

检索条件"机构=School Of Computing And Data Science"

共 5719 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：

Evolutionary Neural Architecture Search for 3D Point Cloud Analysis

Evolutionary Neural Architecture Search for 3D Point Cloud A...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Yang, Yisheng Du, Guodong Toa, Chean Khim Tang, Ho-Kin Goh, Sim Kuan School of Computing and Data Science Xiamen University Malaysia Malaysia China School of Electrical Engineering and Artificial Intelligence Xiamen University Malaysia

ISBN: (纸本)9781665410205

Neural architecture search (NAS) automates neural network design by using optimization algorithms to navigate architecture spaces, reducing the burden of manual architecture design. While NAS has achieved success, applying it to emerging domains, such as analyzing unstructured 3D point clouds, remains underexplored due to the data lying in non-Euclidean spaces, unlike images. This paper presents Success-History-based Self-adaptive Differential Evolution with a Joint Point Interaction Dimension Search (SHSADE-PIDS), an evolution-ary NAS framework that encodes discrete deep neural network architectures to continuous spaces and performs searches in the continuous spaces for efficient point cloud neural architectures. Comprehensive experiments on challenging 3D segmentation and classification benchmarks demonstrate SHSADE-PIDS's capabilities. It discovered highly efficient architectures with higher accuracy, significantly advancing prior NAS techniques. For segmentation on SemanticKITTI, SHSADE-PIDS attained 64.51% mean IoU using only 0.55M parameters and 4.5GMACs, reducing overhead by over 22-26X versus other top methods. For ModelNet40 classification, it achieved 93.4% accuracy with just 1.31M parameters, surpassing larger models. SHSADE-PIDS provided valuable insights into bridging evolutionary algorithms with neural architecture optimization, particularly for emerging frontiers like point cloud learning. © 2024 IEEE.

关键词： Cloud computing architecture

来源：评论

学校读者我要写书评

暂无评论

Creating a Blueprint for Success in First-Year computing

Creating a Blueprint for Success in First-Year Computing

引用

2023 ASEE Annual Conference and Exposition - The Harbor of Engineering: Education for 130 Years, ASEE 2023

作者： Kreimendahl, Frank Schuster, Micah Suresh-Menon, Durga School of Computing and Data Science Wentworth Institute of Technology BostonMA United States

First-year computing is the most important pathway to undergraduate degrees and student success in computing, data science, engineering, and related fields. While there is an abundance of research in the area, we still lack retention of students in first-year computing. This is due to many factors including, but not limited to, 1) student math preparation and readiness from high school, 2) adjunct faculty teaching classes where no common coursework is employed, 3) faculty teaching the same courses in different ways, creating inconsistency in material covered, and 4) lack of tutoring for students who are struggling, behind, or do not understand the material. This paper presents task force results from a collaboration between faculty and academic support specialists. The paper focuses on two high-impact areas of improvement: standardizing curricula and building support scaffolding outside the classroom. The results, a comprehensive course blueprint, include core resources for a first-semester computing course and recommendations for identification and support of struggling students. © American Society for Engineering Education, 2023.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Enhanced study on Deep learning model for kidney segmentation using DCE-MRI

Enhanced study on Deep learning model for kidney segmentatio...

引用

2023 IEEE International Conference on Research Methodologies in Knowledge Management, Artificial Intelligence and Telecommunication Engineering, RMKMATE 2023

作者： Nagarajan, S. Ramprasath, M. Department of Data Science and Business Systems School of Computing SRM Institute of Science and Technology Chengalpattu India

ISBN: (纸本)9798350305708

Medical imaging is capturing pictures of bodily components for diagnostic or research reasons. Because of advancements in image-handling techniques, which include picture recognition, examination, and upgrading, clinical imaging is expanding swiftly. Picture division is a vital subject in picture handling and PC vision with applications, for example, scene grasping, clinical picture examination, mechanical discernment, video observation, expanded reality, and picture pressure, among numerous others. Numerous picture segmentation methods have been created and are available in the literature. There has been a lot of work done to develop techniques for segmenting pictures using deep-learning models since they have proved effective in various vision applications. Deep learning has turned into a functioning exploration point in the field of clinical picture examination. Compared to the laborious and lengthy conventional technique, deep learning (DL) automatic detection algorithms can speed up diagnostics, increase test accuracy, lower expenses, and lessen the workload on the radiologist. Kidney segmentation is an integral part of any non-intrusive computer-assisted diagnostic (CAD) system for rapidly recognising severe renal repudiation because of the intensity of inhomogeneity brought on by errors in the image capture process, efficient kidney segmentation is challenging in evaluating and therapeutic planning of kidney-related disorders. This article addresses recent developments in DL-based kidney tumor segmentation systems. We highlight their fundamental components and numerous approaches as we discuss the main medical image kinds, segmentation methods, and evaluation standards for segmentation outcomes in kidney tumor++ segmentation. © 2023 IEEE.

关键词： Automatic Detection algorithms Computer-Assisted diagnostic system Deep Learning Kidney tumor segmentation Vision applications

来源：评论

学校读者我要写书评

暂无评论

Time-Series data Prediction Using Convolutional-LSTM Network 6

Time-Series Data Prediction Using Convolutional-LSTM Network

引用

6th IEEE International Conference on Power, Intelligent computing and Systems, ICPICS 2024

作者： Liang, Jiesong Ran, Yuzhu School of Computing and Data Science Xiamen University Malaysia Selangor Malaysia School of International Studies Chongqing University of Technology Chongqing China

ISBN: (纸本)9798350374315

Time-series data prediction aims to predict future data according to previous data. Following the temporal correlation of data, the data can be forecasted via recurrent network, considering the neighboring data. By leveraging the powerful discriminative capability of convolutional neural networks, we combine convolutional neural networks with recurrent neural networks to perform time series data prediction, using time-series data as the subject of analysis. Our network includes 4 layers fully connected layer and a 2 layer LSTM network, the full connection layer is used to low dimensional feature mapping to high dimensional, LSTM network is used to learn the timing trend. Our method obtains the mean square error (MSE) of 0.0782 in our evaluation data. This paper provides a good benchmark algorithm in the field of data mining, which lays a foundation for the subsequent application of deep learning. © 2024 IEEE.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

Towards Enhancing Children's science Education using Augmented Reality and Computer Vision 14

Towards Enhancing Children's Science Education using Augment...

引用

14th IEEE Global Engineering Education Conference, EDUCON 2023

作者： Joshi, Sahi Agbo, Friday Joseph Jormanainen, Ilkka School of Computing University of Eastern Finland Joensuu Finland Willamette University Computing and Data Science SalemOR United States

ISBN: (纸本)9798350399431

Today's technological advancements in mobile technologies and the growing number of mobile devices are extremely beneficial in the mobile learning process. This study is a work in progress that discusses the possibilities of integrating Augmented Reality (AR) and computer vision (CV) into science education which uses deep learning to detect animals in real-time and teach children to classify animals, and learn about their habitat, sound, and important facts. In this study, the Design science Research (DSR) is used which is a pragmatic approach to creating substantial knowledge for problem-solving through the development of artifacts. The mobile application - AnimalCircle - was developed following the DSR method, and initial users' study was conducted to investigate the efficacy of the use of AR and CV in mobile learning on children's science education and if it can enhance children learning experience. Semi-structured interviews were conducted with children studying at primary level class in Kathmandu district of Nepal between the age groups of 6-12. The findings show that children are positive toward usage of AnimalCircle app in their learning process because they find it beneficial and effective in their learning. However, most children also found it difficult and complained of getting confused during their initial usage. Therefore, significant efforts are required to improve the usage of these technologies in the mobile app and to provide a child-friendly learning experience. © 2023 IEEE.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Crochet-Together: Cultivating Positive Emotional Well-being with the Touch of Technology-Enhanced Learning 12

Crochet-Together: Cultivating Positive Emotional Well-being ...

引用

12th International Conference on Information and Education Technology, ICIET 2024

作者： Ramachandiran, Chandra Reka Hui, Tan Jia Mahmud, Malissa Maria Kanaparan, Geetha Subramaniam, Preethi Medi, Imran School Of Computing And Data Science Xiamen University Malaysia Sepang Malaysia School Of Education Sunway University Selanor Bandar Sunway Malaysia School Of Computing Asia Pacific University Kuala Lumpur Malaysia

ISBN: (纸本)9798350371772

Emotional well-being is a growing concern in Malaysia, and this study aims to address it by proposing the mobile application 'Crochet-Together' as a tool to promote positive emotional well-being among young adults. By leveraging the therapeutic benefits of crocheting and the Technology-Enhanced Learning, Crochet-Together serves as a platform to cultivate the hobby while nurturing emotional well-being. An online survey was conducted prior to the application's development to explore the impact of crocheting on young adults' well-being and gather user requirements. Upon development, a separate survey was done to assess users' perceived effectiveness in addressing emotional well-being and to evaluate the application's usability using the System Usability Scale. The findings suggest that engaging in crocheting has a positive impact on young adults, enhancing their mood, reducing stress, and promoting relaxation. Besides that, the study also highlights the potential of the Technology-Enhanced Learning to promote emotional well-being. The high SUS score (89) obtained underlines the favorable usability evaluation of Crochet-Together. By utilizing the insights gained, future enhancements in terms of the functionality of the tool can be made to further support these users' needs and enhance their crocheting skills and experiences amongst young crocheters. © 2024 IEEE.

关键词： Behavioral research

来源：评论

学校读者我要写书评

暂无评论

Intention Analysis Makes LLMs A Good Jailbreak Defender 31

Intention Analysis Makes LLMs A Good Jailbreak Defender

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Zhang, Yuqi Ding, Liang Zhang, Lefei Tao, Dacheng School of Computer Science Wuhan University China The University of Sydney Australia College of Computing and Data Science Nanyang Technological University Singapore639798 Singapore

ISBN: (纸本)9798891761964

Aligning large language models (LLMs) with human values, particularly when facing complex and stealthy jailbreak attacks, presents a formidable challenge. Unfortunately, existing methods often overlook this intrinsic nature of jailbreaks, which limits their effectiveness in such complex scenarios. In this study, we present a simple yet highly effective defense strategy, i.e., Intention Analysis (IA). IA works by triggering LLMs' inherent self-correct and improve ability through a two-stage process: 1) analyzing the essential intention of the user input, and 2) providing final policy-aligned responses based on the first round conversation. Notably, IA is an inference-only method, thus could enhance LLM safety without compromising their helpfulness. Extensive experiments on varying jailbreak benchmarks across a wide range of LLMs show that IA could consistently and significantly reduce the harmfulness in responses (averagely -48.2% attack success rate). Encouragingly, with our IA, Vicuna-7B even outperforms GPT-3.5 regarding attack success rate. We empirically demonstrate that, to some extent, IA is robust to errors in generated intentions. Further analyses reveal the underlying principle of IA: suppressing LLM's tendency to follow jailbreak prompts, thereby enhancing safety. © 2025 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

A Macro- and Micro-Hierarchical Transfer Learning Framework for Cross-Domain Fake News Detection 25

A Macro- and Micro-Hierarchical Transfer Learning Framework ...

引用

34th ACM Web Conference, WWW 2025

作者： Yang, Xuankai Wang, Yan Zhang, Xiuzhen Wang, Shoujin Wang, Huaxiong Lam, Kwok Yan School of Computing Macquarie University Sydney Australia School of Computing Technologies RMIT University Melbourne Australia Data Science Institute University of Technology Sydney Sydney Australia School of Physical and Mathematical Sciences Nanyang Technological University Singapore Singapore College of Computing and Data Science Nanyang Technological University Singapore Singapore

ISBN: (纸本)9798400712746

Cross-domain fake news detection aims to mitigate domain shift and improve detection performance by transferring knowledge across domains. Existing approaches transfer knowledge based on news content and user engagements from a source domain to a target domain. However, these approaches face two main limitations, hindering effective knowledge transfer and optimal fake news detection performance. Firstly, from a micro perspective, they neglect the negative impact of veracity-irrelevant features in news content when transferring domain-shared features across domains. Secondly, from a macro perspective, existing approaches ignore the relationship between user engagement and news content, which reveals shared behaviors of common users across domains and can facilitate more effective knowledge transfer. To address these limitations, we propose a novel macro- and micro- hierarchical transfer learning framework (MMHT) for cross-domain fake news detection. Firstly, we propose a micro-hierarchical disentangling module to disentangle veracity-relevant and veracity-irrelevant features from news content in the source domain for improving fake news detection performance in the target domain. Secondly, we propose a macro-hierarchical transfer learning module to generate engagement features based on common users’ shared behaviors in different domains for improving effectiveness of knowledge transfer. Extensive experiments on real-world datasets demonstrate that our framework significantly outperforms the state-of-the-art baselines. © 2025 Copyright held by the owner/author(s).

关键词： Tweets

来源：评论

学校读者我要写书评

暂无评论

An in-depth investigation of sparse rate reduction in transformer-like models 24

An in-depth investigation of sparse rate reduction in transf...

引用

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

作者： Yunzhe Hu Difan Zou Dong Xu School of Computing and Data Science The University of Hong Kong School of Computing and Data Science & Institute of Data Science The University of Hong Kong

ISBN: (纸本)9798331314385

Deep neural networks have long been criticized for being black-box. To unveil the inner workings of modern neural architectures, a recent work [45] proposed an information-theoretic objective function called Sparse Rate Reduction (SRR) and interpreted its unrolled optimization as a Transformer-like model called Coding Rate Reduction Transformer (CRATE). However, the focus of the study was primarily on the basic implementation, and whether this objective is optimized in practice and its causal relationship to generalization remain elusive. Going beyond this study, we derive different implementations by analyzing layer-wise behaviors of CRATE, both theoretically and empirically. To reveal the predictive power of SRR on generalization, we collect a set of model variants induced by varied implementations and hyperparameters and evaluate SRR as a complexity measure based on its correlation with generalization. Surprisingly, we find out that SRR has a positive correlation coefficient and outperforms other baseline measures, such as path-norm and sharpness-based ones. Furthermore, we show that generalization can be improved using SRR as regularization on benchmark image classification datasets. We hope this paper can shed light on leveraging SRR to design principled models and study their generalization ability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Estimation of Neurological Diseases and Age Using Brain MRI 4th

Estimation of Neurological Diseases and Age Using Brain MRI

引用

4th International Conference on Smart Systems: Innovations in computing, SSIC 2023

作者： Ashokkumar, K. Dharshan, K. Ragupathi, T. Pritam, Anem Sagar, Amujuru Gnana Department of Computer Science Engineering Sathyabama Institute of Science and Technology Chennai India School of Computing and Mathematical Sciences University of Leicester Leicester United Kingdom Data Science and Business systems School of Computing SRM Institute of Science and Science and Technology Kattankulathur Chennai India

ISBN: (纸本)9789819736898

Leveraging D-NN trained on neuroimaging data, we can effectively estimate the chronological ages of normal persons;this projected brain age has potential as a biomarker for identifying age-related disorders. The suggested technique employs a CNN cascade network from DL and the Support Vector Machine (SVM) algorithm from ML (SVM). These techniques have been employed to train MRI scans of the brain, classifying them into regular (unaffected by illness), Alzheimer’s disorder (AD), and neurocognitive disability. That we also have the ability to determine ages thanks to the age classifications on the photos. The brain MRI collection is trained using CNN and SVM, on which the classifications and age estimate will be carried out. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Support vector machines

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 << < 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：