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

107,183 篇 会议
678 篇 期刊文献
565 册 图书
2 篇 学位论文

馆藏范围

108,427 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

60,908 篇 工学
- 49,897 篇 计算机科学与技术...
- 39,812 篇 软件工程
- 13,426 篇 信息与通信工程
- 11,482 篇 生物工程
- 8,512 篇 控制科学与工程
- 6,739 篇 电气工程
- 6,349 篇 生物医学工程（可授...
- 3,866 篇 光学工程
- 3,332 篇 机械工程
- 2,984 篇 电子科学与技术（可...
- 2,763 篇 网络空间安全
- 2,719 篇 安全科学与工程
- 2,516 篇 动力工程及工程热...
- 2,319 篇 化学工程与技术
- 2,188 篇 仪器科学与技术
25,996 篇 理学
- 12,113 篇 生物学
- 12,065 篇 数学
- 5,172 篇 物理学
- 4,919 篇 统计学（可授理学、...
- 3,515 篇 系统科学
- 2,330 篇 化学
17,450 篇 管理学
- 11,016 篇 管理科学与工程(可...
- 7,614 篇 图书情报与档案管...
- 5,174 篇 工商管理
13,621 篇 教育学
- 13,420 篇 教育学
6,408 篇 医学
- 5,469 篇 临床医学
- 5,220 篇 基础医学(可授医学...
- 3,406 篇 药学(可授医学、理...
- 2,887 篇 公共卫生与预防医...
3,377 篇 法学
- 2,923 篇 社会学
1,965 篇 文学
1,766 篇 农学
1,661 篇 经济学
267 篇 艺术学
106 篇 军事学
11 篇 历史学
10 篇 哲学

主题

7,214 篇 machine learning
7,071 篇 deep learning
5,537 篇 accuracy
5,104 篇 training
4,929 篇 computational mo...
4,222 篇 education
3,838 篇 students
3,623 篇 feature extracti...
3,070 篇 support vector m...
3,068 篇 predictive model...
3,061 篇 machine learning...
3,029 篇 convolutional ne...
2,594 篇 real-time system...
2,397 篇 data models
2,245 篇 neural networks
2,010 篇 cloud computing
1,840 篇 teaching
1,497 篇 reinforcement le...
1,472 篇 artificial intel...
1,412 篇 internet of thin...

机构

826 篇 chitkara univers...
145 篇 lovely professio...
105 篇 computer science...
98 篇 karnataka bangal...
94 篇 college of compu...
89 篇 school of comput...
79 篇 chitkara univers...
76 篇 school of comput...
72 篇 department of co...
70 篇 department of co...
67 篇 department of co...
63 篇 department of co...
58 篇 school of comput...
58 篇 department of co...
52 篇 department of in...
49 篇 chitkara univers...
43 篇 department of me...
42 篇 school of automa...
41 篇 chennai
40 篇 vellore institut...

作者

70 篇 shiva mehta
70 篇 anjali t.
53 篇 li yang
42 篇 sharma vikrant
40 篇 wang lei
40 篇 kukreja vinay
39 篇 rakesh kumar
36 篇 gill kanwarparta...
35 篇 sharma neha
33 篇 wang jing
32 篇 vinay kukreja
31 篇 lei wang
31 篇 zhang lei
30 篇 huang yueh-min
29 篇 yu wang
28 篇 liu bo
27 篇 li xin
26 篇 amandeep nagpal
25 篇 vinay gautam
25 篇 shang wang

语言

91,086 篇 英文
16,987 篇 其他
949 篇 中文
23 篇 西班牙文
12 篇 葡萄牙文
5 篇 阿拉伯文
3 篇 法文
3 篇 土耳其文
2 篇 俄文
1 篇 捷克文

检索条件"任意字段=International Conference on Learning and Teaching in Computing and Engineering"

共 108428 条记录，以下是3961-3970 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：

An Innovative Way of Empirical Analysis of Various Structures used in DL Algorithms for the Better Practices 4

An Innovative Way of Empirical Analysis of Various Structure...

引用

4th IEEE international conference on Advance computing and Innovative Technologies in engineering, ICACITE 2024

作者： Kumar, Himanshu Jasim, Laith Gehlot, Anita Devi, Guntoju Kalpana Yadav, Kanchan Kumar, Neelam Sanjeev Chitkara University Chitkara Centre for Research and Development Himachal Pradesh 174103 India The Islamic University Najaf Iraq Uttaranchal Institute of Technology Uttaranchal University Department of Electronics & Communication Engineering Dehradun248007 India Cmr Technical Campus Department of Cse Telangana Hyderabad India Gla University Department of Electrical Engineering Mathura India Srm Institute of Science & Technology Department of Computer Science & Engineering Chennai Vadapalani26 India

ISBN: (纸本)9798350360165

The importance of deep learning is growing with artificial intelligence. It operates quickly. Entangled nerve fibres (CNNs), a well-known deep learning method, have shown impressive results in painting, classification, and semantic division. The actuator function-a crucial part of CNNs -was looked at in the context of low velocities in this book study, engineering Vehicle Rear System Programme. The text begins with a comprehensive analysis of all four conventional activation functions, including the well recognised sigmoid function, and a summary of their respective benefits. It then discusses the potential benefits. Swish, FTS, and Relu- are the three new operating systems that are offered with SoftPlus. The research then includes a combination of new activators and extra activation functions. It operates at the TensorFlow framework level. On the CIFAR-10 dataset, more image recognition comparisons are carried out. According to the results, using a combination of novel activation functions produces better recognition accuracy than using just one new activation function. Moreover, the hybrid technique shows higher convergence speeds and shorter average processing times, indicating its effectiveness in real-world applications. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Using Focus to Personalise learning and Feedback in Software engineering Education 23

Using Focus to Personalise Learning and Feedback in Software...

引用

IEEE/ACM 45th international conference on Software engineering - Software engineering Education and Training (ICSE-SEET)

作者： Modi, Bansri Amish Cain, Andrew Wood-Bradley, Guy Renzella, Jake Deakin Univ Melbourne Vic Australia Univ New South Wales Sydney NSW Australia

ISBN: (纸本)9798350322590

learning can be greatly enhanced by effective feedback. Traditional assessment approaches in higher education often result in feedback being used to justify marks awarded, which is often disregarded once the assessment is complete. In this paper, we explore the idea of incorporating a focus mechanism to connect feedback between assessment tasks and units, discuss how this can be applied to enhance software engineering education, and present results from several staff focus groups exploring the idea. The focus groups discussed the model, its application within software engineering units, and its limitations, with staff helping co-create the enhancements to the model through discussing experiences/sharing opinions/providing insights on assessment within their units. Results indicate that staff believe that the changes will benefit their teaching and highlighted several opportunities for this initiative to encourage students to have a more holistic view of their studies. The main challenges identified were staff workload and complexity for students which must be addressed in implementing this idea.

关键词： Assessment Rubrics Formative Feedback

来源：评论

学校读者我要写书评

暂无评论

Power Quality Disturbances Classification Based on CNN Combining Knowledge Distillation and Incremental learning 5

Power Quality Disturbances Classification Based on CNN Combi...

引用

5th international conference on Power engineering, ICPE 2024

作者： Wu, Yiran Ren, Lintao Wang, Fei Hu, Jinglu Shanghai University School of Mechatronic Engineering and Automation Shanghai China Waseda University Graduate School of Information Production and Systems Fukuoka Japan

ISBN: (纸本)9798331531140

With the integration of renewable energy sources and new power electronic devices, power grid complexity has increased, leading to frequent power quality disturbances. Existing classification models often require retraining when dealing with new disturbance types, resulting in long update periods and significant use of computing resources. This paper proposes the FKDIL-CNN, a convolutional neural network model that combines knowledge distillation and incremental learning, enabling the enabling rapid adaptation to new disturbances without requiring full retraining. The FKDIL-CNN transfers identification knowledge for the known old types from a high-accuracy teacher model to the student model. By introducing a dynamic weight mechanism to improve the traditional knowledge distillation loss function, the student model efficiently distills old knowledge from the teacher model and performs incremental learning on new knowledge. Compared with the existing methods, our proposed FKDIL-CNN significantly reduces the training time and computing resource consumption while maintaining high classification accuracy. Additionally, this model demonstrates strong noise immunity, making it a practical solution for PQDs monitoring in complex power grid. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Multimodal Intelligent Emotion Perception Framework by Data-driven and Knowledge-guided 2

A Multimodal Intelligent Emotion Perception Framework by Dat...

引用

2nd international conference on Electronic Information engineering and Computer Technology, EIECT 2022

作者： Tao, Xiaomei Zhang, Yuan Guangxi Normal University Guangxi Key Lab of Multi-Source Information Mining & Security Guilin541004 China Guangxi Normal University School of Computer Science and Engineering Guilin541004 China

ISBN: (纸本)9798350399561

With the improvement of network environment quality and the enrichment of teaching content, video learning has become a powerful supplement to the normal teaching process. It is necessary to perceive the emotional states of the learners to improve the quality of video teaching and learning effects. In view of the particularity of online video learning, we analyzed and explored the factors that affect learners' emotions, and proposed an intelligent emotion perception framework based on multimodal data-driven and knowledge-guided collaborative computing. Combining the physiological characteristics of learners with the semantic information about stimulus materials can more accurately and efficiently perceive the emotional state of online video learners. © 2022 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Unveiling the Synergy - The Intersection of Deep learning and Object identification 2

Unveiling the Synergy - The Intersection of Deep Learning an...

引用

2nd international conference on Advanced computing and Communication Technologies, ICACCTech 2024

作者： Sharma, Harsh Kumar Soni, Keshav Rai, Arin Shree, Shreya Sharma, Abhinav Banerjee, Subhroneel Chandigarh University Department of Computer Science and Engineering Mohali India

ISBN: (纸本)9798331519056

The evolution that has been observed in the dynamic field of object identification in the past few years is remarkable, because of the integration of sophisticated learning techniques. The review presented in this paper presents a detailed analysis of revealing the combination or discussing the amalgamation of deep learning with object identification. In light of this background, we look into the historical development of object identification approach wherein we analyze the traditional approaches and then show how deep learning has disrupted this field. We provide a clear analysis of the object identification domain by comparing various influential deep learning architectures, performance, accuracy, and efficiency, thereby demonstrating the current status of the field and its practical uses and developments. Disadvantages and drawbacks of deep learning for the object identification method are further discussed in terms of computation, data, and possible prejudice. In order to combat these challenges, this paper also offers some novel ideas and research advancements together with key applications and implementation. In the future directions, we highlight the potential methods and further refinements that may contribute to the development of the object identification with deep learning and present the trends that may influence the field. This review paper is very useful for the researchers, engineers, and practitioners as a reference of the history, current state, and direction of the deep learning-based object identification. © 2024 IEEE.

关键词： Contrastive learning

来源：评论

学校读者我要写书评

暂无评论

Partial Distributed Deep learning Inference Model for Image based Edge Device Cluster 24

Partial Distributed Deep Learning Inference Model for Image ...

引用

8th international conference on Electronic Information Technology and Computer engineering, EITCE 2024

作者： Xiao, Dun Wang, Xiaogang Yang, Zhihe Huang, Chao School of Electronic and Information Shanghai Dianji University Shanghai China

ISBN: (纸本)9798400710094

In recent years, the development of AI technology has driven the development of network edge applications such as smart manufacturing, smart factories, and smart cities. Deep neural networks are increasingly being deployed in smart manufacturing edge application scenarios to carry out edge detection tasks. However, there is a gap between the expensive DNN computing network and the limited computing power of the edge devices. To deploy compute-intensive neural networks on resource-constrained edge devices, traditional approaches rely either on offloading workloads to a remote central cloud or on optimizing compute on local edge devices. However, the method of uploading tasks to the central cloud is significantly affected by the unreliability and delay of the WAN, and the sensitive information of users is easy to be leaked during transmission, and the local computing method is also limited by the computing power. The latest machine learning models have great demands on memory, computing, and energy, which poses challenges to distributed computing and data aggregation for heterogeneous and resource-constrained edge devices. In order to address these challenges, this paper proposes solutions for different image types in intelligent manufacturing scenarios. When images are processed in the production process of intelligent manufacturing, this paper adopts the method of horizontal partitioning of the DNN model to perform DNN-based inference tasks on the edge device cluster. In order to reduce the consumption of network bandwidth, a dynamic priority scheduling algorithm is used to optimize the distribution of inference tasks at the edge nodes to improve the inference speed. Finally, experiments show that the edge node optimization scheduling method proposed in this paper has a good effect on the performance of running time, communication cost and energy consumption of edge devices. © 2024 Copyright held by the owner/author(s).

关键词： Smart manufacturing

来源：评论

学校读者我要写书评

暂无评论

Domain-Aware Model Training as a Service for Use-Inspired Models 12

Domain-Aware Model Training as a Service for Use-Inspired Mo...

引用

12th international conference on Cloud engineering

作者： Zhang, Zichen Stewart, Christopher Ohio State Univ Columbus OH 43210 USA

ISBN: (纸本)9798331528690;9798331528706

Use-inspired artificial intelligence (AI) tailors deep-learning models for image processing tasks in targeted scientific domains. These use-inspired models meet domain requirements for accuracy while parsimoniously using compact and efficient model architectures needed for inference in the field. However, before settling upon a model, domain experts repeatedly train and test models over a wide range of hyperparameters, contextual settings, and data configurations, making model training bespoke, time-consuming, and costly. Model-training-as-a-Service (MTaaS), i.e., cloud services designed for generic training workloads, can reduce training costs, but domain-aware designs and runtime adaptations could yield further reductions. This paper characterizes the potential for domain-aware design and runtime adaptation for MTaaS in digital agriculture. First, we studied the time to train models for 10 use-inspired agricultural datasets using pre-trained model weights derived from other agricultural datasets versus pre-trained weights derived from ImageNet, a widely used benchmark. Using agricultural datasets sped training time by up to 2X for some datasets, but provided modest speedups (< 1.07) in the common case;Choosing the right dataset is critical. Next, we present an approach to predict training time given domain-aware pre-trained weights. Our predictions are strongly correlated with training time (r = 0.93). Finally, we studied the use of domain-aware pre-trained weights in a MTaaS under Poisson and bursty arrival patterns for training tasks. Under bursty arrivals and tight memory constraints, domain-aware MTaaS reduced training time by 2.8X and 12.2X compared to model training using pre-trained ImageNet weights and from scratch, respectively.

关键词： Transfer learning Cloud Service Dataset Similarity Neural Network Distributed System Model-Training-as-a-Service

来源：评论

学校读者我要写书评

暂无评论

The Structure of Motivation in Online Translation learning and the Role of L2 Motivation Self System 21st

The Structure of Motivation in Online Translation Learning a...

引用

21st international conference on Web-Based learning / 7th international Symposium on Emerging Technologies for Education (ICWL/SETE)

作者： Hu, Yukai Ma, Xuange Gao, Yike Wang, Qi Univ Sci & Technol China Sch Humanities & Social Sci Hefei Peoples R China West Anhui Hlth Vocat Coll Luan Peoples R China

ISBN: (纸本)9783031330223;9783031330230

With the advancement of online learning technologies, translation learning, teaching, and learning motivation have been influenced and even reshaped. So, there is a need for empirical investigations on the motivation in learning translation online. Under the framework of the L2 Motivation Self System, this study uses exploratory factor analysis and structural equation model to analyze 150 college students' motivation for online translation learning and identifies six motivation factors: IL2S Factor, Escape/Stimulation Factor, Social Contact Factor, Social Service Factor, L2LE Factor, and OL2S Factor. The research findings show that motivation in online translation learning is not instrumental, and the Ideal L2 Self is the most significant and dominant motivation in online translation learning.

关键词： Online Translation learning L2 Motivation Self System Structure of Motivation

来源：评论

学校读者我要写书评

暂无评论

Traffic Detection and Forecasting from Social Media Data Using a Deep learning-Based Model, Linguistic Knowledge, Large Language Models, and Knowledge Graphs 16

Traffic Detection and Forecasting from Social Media Data Usi...

引用

16th international conference on Knowledge engineering and Ontology Development, KEOD 2024 as part of 16th international Joint conference on Knowledge Discovery, Knowledge engineering and Knowledge Management, IC3K 2024

作者： Melhem, Wasen Abdi, Asad Meziane, Farid Department of Computing and Mathematics Faculty of Science and Engineering University of Derby United Kingdom

ISBN: (纸本)9789897587160

Traffic data analysis and forecasting is a multidimensional challenge that extracts details from sources such as social media and vehicle sensor data. This study proposes a three-stage framework using Deep learning (DL) and natural language processing (NLP) techniques to enhance the end-to-end pipeline for traffic event identification and forecasting. The framework first identifies relevant traffic data from social media using NLP, context, and word-level embeddings. The second phase extracts events and locations to dynamically construct a knowledge graph using deep learning and slot filling. A domain-specific large language model (LLM), enriched with this graph, improves traffic information relevancy. The final phase integrates Allen's interval algebra and region connection calculus to forecast traffic events based on temporal and spatial logic. This framework’s goal is to improve the accuracy and semantic quality of traffic event detection, bridging the gap between academic research and real-world systems, and enabling advancements in intelligent transport systems (ITS). © 2024 by SCITEPRESS – Science and Technology Publications, Lda.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

A Survey on Evolutionary Algorithms Based Machine learning Approaches for Medical Diagnosis

A Survey on Evolutionary Algorithms Based Machine Learning A...

引用

2024 IEEE international conference on Modeling, Simulation and Intelligent computing, MoSICom 2024

作者： Hossen, Md. Jakir Ramanathan, Thirumalaimuthu Thirumalaiappan Raja, Joseph Emerson Multimedia University Faculty of Engineering and Technology Melaka Malaysia

ISBN: (纸本)9798331533311

The use of extended time series to gather and store huge datasets has been made simpler by information science and data capture technologies. In many fields, such as astronomy, the environment, economics, business, medical, data analysis, and knowledge mining, these datasets are growing in popularity. Finding hidden patterns, connections, and anomalies in massive databases using statistical analysis and machine learning is known as data mining. You can use this information to help with comprehending complex phenomena, generating predictions, and making decision. The evolutionary computational techniques and machine learning techniques play a main role in the data mining process. This paper reviews various machine learning approaches that are based on different evolutionary algorithms such as genetic algorithm, particle swarm optimization, and ant colony optimization for the classification of medical datasets. The comparison and discussion are made between different evolutionary algorithms-based techniques for the medical data classification process. The review of evolutionary algorithms-based classification approaches showed that the performance of evolutionary algorithms varied according to the medical datasets. The reviewed classification approaches also lead to the conclusion that evolutionary algorithms are essential for the data preprocessing and parameters tuning in machine learning based classifiers. © 2024 IEEE.

关键词： Adversarial machine learning

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 << < 393 394 395 396 397 398 399 400 401 402 > >>

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：