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

3,622 篇 会议
2,325 篇 期刊文献
17 册 图书

馆藏范围

5,964 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

3,596 篇 工学
- 2,047 篇 计算机科学与技术...
- 1,650 篇 软件工程
- 716 篇 信息与通信工程
- 600 篇 控制科学与工程
- 571 篇 电气工程
- 553 篇 电子科学与技术（可...
- 405 篇 生物工程
- 361 篇 光学工程
- 332 篇 机械工程
- 290 篇 生物医学工程（可授...
- 259 篇 动力工程及工程热...
- 253 篇 仪器科学与技术
- 197 篇 化学工程与技术
- 149 篇 材料科学与工程（可...
- 145 篇 交通运输工程
- 121 篇 土木工程
- 107 篇 建筑学
1,952 篇 理学
- 926 篇 数学
- 610 篇 物理学
- 452 篇 生物学
- 291 篇 统计学（可授理学、...
- 215 篇 系统科学
- 209 篇 化学
871 篇 管理学
- 579 篇 管理科学与工程(可...
- 307 篇 图书情报与档案管...
- 230 篇 工商管理
285 篇 医学
- 240 篇 临床医学
- 181 篇 基础医学(可授医学...
- 112 篇 药学(可授医学、理...
126 篇 法学
- 105 篇 社会学
102 篇 经济学
66 篇 农学
50 篇 教育学
19 篇 文学
17 篇 军事学
9 篇 艺术学

主题

129 篇 feature extracti...
97 篇 deep learning
96 篇 computational mo...
89 篇 accuracy
86 篇 data mining
86 篇 training
83 篇 optimization
82 篇 semantics
75 篇 machine learning
71 篇 computer science
64 篇 mathematical mod...
55 篇 neural networks
53 篇 object detection
53 篇 analytical model...
51 篇 wireless sensor ...
51 篇 predictive model...
50 篇 bandwidth
48 篇 reliability
48 篇 computer archite...
47 篇 support vector m...

机构

102 篇 national enginee...
80 篇 school of comput...
77 篇 school of contro...
52 篇 purdue universit...
47 篇 school of comput...
46 篇 school of comput...
45 篇 national enginee...
41 篇 state key labora...
40 篇 school of optica...
39 篇 school of cyber ...
38 篇 school of comput...
36 篇 school of inform...
31 篇 national enginee...
29 篇 school of electr...
29 篇 department of el...
29 篇 school of comput...
27 篇 huazhong univers...
26 篇 school of comput...
26 篇 hubei province k...
25 篇 hubei key labora...

作者

100 篇 hai jin
64 篇 jin hai
31 篇 yang yang
31 篇 mei-ling shyu
31 篇 xiaofei liao
30 篇 hamid soltanian-...
30 篇 shu-ching chen
27 篇 shen linlin
26 篇 chen shu-ching
26 篇 soltanian-zadeh ...
25 篇 robbi rahim
22 篇 f. malek
21 篇 hu shengshan
19 篇 wang xingjun
19 篇 liao xiaofei
19 篇 shyu mei-ling
18 篇 xiao feng
17 篇 deqing zou
17 篇 ai bo
16 篇 shen yulong

语言

5,268 篇 英文
533 篇 其他
149 篇 中文
11 篇 日文
5 篇 朝鲜文

检索条件"机构=School of System and Computer Engineering"

共 5964 条记录，以下是721-730 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 Brief Comparative Study of Metaheuristic Approaches for Hyperparameter Optimization of Machine Learning Model

A Brief Comparative Study of Metaheuristic Approaches for Hy...

引用

computer Science and Emerging Technologies (CSET), International Conference on

作者： Kumar Dilip G S Pradeep Ghantasala Manisha Rathee Suresh Kallam Priyanka Bathla Department of Computer Science and Engineering Alliance University Bengaluru India School of Computer and System Sciences Jawaharlal Nehru University India School of Computer Science and Engineering Jain Deemed to be University Bengaluru India Chandigarh University Mohali Punjab India

Machine learning models have been successfully applied in numerous fields. Training a model is the most important aspect of machine learning for its successful application for the problem. To improve the training of a machine learning model thereby improve the performance, the selection of features and setting optimal parameters is crucial. Mainly two kinds of parameters are required to deal with, namely internal and external parameters. Internal parameters are model parameters and configurable such as weights of neural networks and their estimation can be done using data set. The hyperparameters such as learning rate, size of layers, number of layers, loss function etc, are external parameters and its values cannot be determined using the data set and it is not the part of the model. Its estimation can be done by the domain expert or using some trial-and-error techniques until it achieves some acceptable values. However, these techniques are highly time-consuming and cannot ensure the optimal values for these hyperparameters. In recent years different metaheuristic techniques have been applied to determine the optimal values of hyper parameters for machine learning models. In this paper we have conducted a brief comparative study of a few popular metaheuristic approaches applied for the hyperparameter optimization for various machine learning models. In this paper various evaluation measures have been considered for comparative analysis of metaheuristic approaches for hyperparameter optimization for deep learning model.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Decision-Making Method for Sound Volume Control in the “Smart House” system

Decision-Making Method for Sound Volume Control in the “Sma...

引用

International computer Sciences and Information Technologies (CSIT)

作者： Tetiana Hovorushchenko Serhii Aleksov Artem Boyarchuk Computer Engineering and Information System Department Khmelnytskyi National University (KhNU) Khmelnytskyi Ukraine Law School Tallinna Tehhnikaülikool (TalTech) Tallinn Estonia

ISBN: (数字)9798331542634

ISBN: (纸本)9798331542641

The developed in this paper decision-making method for sound volume control in the “Smart House” system provides automatic control of sound volume in the “Smart House” system in order to prevent exceeding sound volume standards depending on the type of room and time of day, as well as to ensure a comfortable noise (sound volume) level in the appropriate room. The results of the experiment have shown that the developed decision-making method for sound volume control in the “Smart House” system provides for the recognition of situations (optimal sound volume, high sound volume, unacceptable high sound volume) and automatic decision-making on sound volume control in a room of a certain type (automatic reduction of the sound volume of multimedia devices in the room to the maximum permissible level for it).

关键词： Multimedia systems Decision making Noise Speech recognition Smart homes Cyber-physical systems Control systems Information technology Standards Noise level

来源：评论

学校读者我要写书评

暂无评论

A Novel Ensemble Deep Learning Framework for Breast Cancer Prediction

A Novel Ensemble Deep Learning Framework for Breast Cancer P...

引用

2023 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical systems, ICSES 2023

作者： Shaker Reddy, Pundru Chandra Nithyapriya, S. Sharma, Nipun Maheswari, S. Jayaram, B. Katale, Tejaswini SR University School of Computer Science and Artificial Intelligence Telangana Warangal506371 India Anna University Artificial Intelligence and Data Science Bannari Amman Institute of Technology Tamil Nadu Chennai India Presidency University Bangalore Electronics and Communication Engineering Karnataka India Sathyabama Institute of Science and Technology Department of Mathematics Tamil Nadu Chennai India Computer Science and Business System RMK Engineering College Tamil Nadu Kavaraipettai India Vishwakarma Institute of Technology Department of Computer Engineering Maharashtra Pune India

ISBN: (纸本)9798350319200

Because of its high incidence and high mortality rate, breast cancer requires reliable means of early detection and diagnosis to improve survival rates for its patients. With advantages including increased accuracy and efficiency, deep learning (DL) and machine learning (ML) methods are quickly becoming indispensable in the fight against breast cancer. However, there is a need for additional study because existing approaches have scalability and performance constraints. Utilizing a pre-trained ResNet50V2 and ensemble-based ML approaches, we offer a hybrid approach to reliable breast cancer diagnosis in this study. Learning and extracting latent trends from complex breast-cancer(BC) images is made possible by DL's incorporation, with ML strategies contributing interpretability and generalizability. We performed wide experiments utilizing a openly accessible Invasive-Ductal-Carcinoma(IDC) dataset based on breast histopathology images of varying sample sizes. The resilience and great performance of our hybrid model are supported by the results of our extensive experiments. When compared to state-of-the-art models, our 95% accuracy rate, 94.5 precision, 94.2 recall, and 94.6 F1 score are all improvements. We also found that the best ML model to use with the ResNet50V2 architecture is the Light Boosting Classifier (LGB). This study's findings provide substantial contributions to the field of breast cancer diagnosis thanks to its novel approach, in-depth performance analysis, and trustworthy evaluation. In addition, it may help doctors make better decisions, provide better care, and boost results for people with breast cancer. © 2023 IEEE.

关键词： breast histopathology-image Breast-cancer DL ML transfer-learning

来源：评论

学校读者我要写书评

暂无评论

Expediting Distributed GNN Training with Feature-only Partition and Optimized Communication Planning

Expediting Distributed GNN Training with Feature-only Partit...

引用

IEEE Annual Joint Conference: INFOCOM, IEEE computer and Communications Societies

作者： Bingqian Du Jun Liu Ziyue Luo Chuan Wu Qiankun Zhang Hai Jin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China Department of Electrical and Computer Engineering The Ohio State University USA Department of Computer Science The University of Hong Kong Hong Kong School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9798350383508

ISBN: (纸本)9798350383515

Feature-only partition of large graph data in distributed Graph Neural Network (GNN) training offers advantages over commonly adopted graph structure partition, such as minimal graph preprocessing cost and elimination of cross-worker subgraph sampling burdens. Nonetheless, performance bottleneck of GNN training with feature-only partitions still largely lies in the substantial communication overhead due to cross-worker feature fetching. To reduce the communication overhead and expedite distributed training, we first investigate and answer two key questions on convergence behaviors of GNN model in feature-partition based distribute GNN training: 1) As no worker holds a complete copy of each feature, can gradient exchange among workers compensate for the information loss due to incomplete local features? 2) If the answer to the first question is negative, is feature fetching in every training iteration of the GNN model necessary to ensure model convergence? Based on our theoretical findings on these questions, we derive an optimal communication plan that decides the frequency for feature fetching during the training process, taking into account bandwidth levels among workers and striking a balance between model loss and training time. Extensive evaluation demonstrates consistent results with our theoretical analysis, and the effectiveness of our proposed design.

关键词： Training Time-frequency analysis Costs Computational modeling Distributed databases Bandwidth Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

On Pipelined GCN with Communication-Efficient Sampling and Inclusion-Aware Caching

On Pipelined GCN with Communication-Efficient Sampling and I...

引用

IEEE Annual Joint Conference: INFOCOM, IEEE computer and Communications Societies

作者： Shulin Wang Qiang Yu Xiong Wang Yuqing Li Hai Jin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China School of Cyber Science and Engineering Wuhan University Wuhan China

ISBN: (数字)9798350383508

ISBN: (纸本)9798350383515

Graph convolutional network (GCN) has achieved enormous success in learning structural information from unstructured data. As graphs become increasingly large, distributed training for GCNs is severely prolonged by frequent cross-worker communications. Existing efforts to improve the training efficiency often come at the expense of GCN performance, while the communication overhead persists. In this paper, we propose PSC-GCN, a holistic pipelined framework for distributed GCN training with communication-efficient sampling and inclusion-aware caching, to address the communication bottleneck while ensuring satisfactory model performance. Specifically, we devise an asynchronous pre-fetching scheme to retrieve stale statistics (features, embedding, gradient) of boundary nodes in advance, such that the embedding aggregation and model update are pipelined with statistics transmission. To alleviate communication volume and staleness effect, we introduce a variance-reduction based sampling policy, which prioritizes inner nodes over boundary ones for reducing the access frequency to remote neighbors, thus mitigating cross-worker statistics exchange. Complementing graph sampling, a feature caching module is co-designed to buffer hot nodes with high inclusion probability, ensuring that frequently sampled nodes will be available in local memory. Extensive evaluations on real-world datasets show the superiority of PSC-GCN over state-of-the-art methods, where we can reduce training time by 72%-80% without sacrificing model accuracy.

关键词： Training Estimation error Accuracy Graph convolutional networks Computational modeling Probability Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

START: Automatic Sleep Staging with Attention-based Cross-modal Learning Transformer

START: Automatic Sleep Staging with Attention-based Cross-mo...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Sun, Jingpeng Wang, Rongxiao Zhao, Gangming Chen, Chen Qu, Yixiao Li, Jinpeng Hu, Xiyuan Yu, Yizhou Nanjing University of Science and Technology School of Computer Science and Engineering China Chinese Academy of Sciences Institute of Automation China Xinjiang University College of Mathematics and System Science China The University of Hong Kong Department of Computer Science Hong Kong University of Chinese Academy of Sciences Ningbo Institute of Life and Health Industry China

ISBN: (纸本)9798350337488

Automatic sleep staging is vital to scale up sleep assessment and diagnosis to serve millions experiencing sleep deprivation and disorders and enable longitudinal sleep monitoring in home environments. However, how to learn from multi-channel raw physiological signal inputs (e.g., EEG and EOG) to capture the sleep stage and physiological signal relations remains a big challenge. In this paper, we propose a sleep staging model, named Sleep Staging Cross-modal Transformer (START), which is a transformer-only method for sleep stage classification. Our model is capable of learning a joint representation from both EEG and EOG signals by using a cross-modal fusion strategy. Experimental results show that our model outperforms the state-of-the-art methods on two public datasets. Furthermore, our model provides considerable reductions in parameters and training time compared to previous methods. © 2023 IEEE.

关键词： Attention Mechanism Cross-modal Network Sleep Staging Transformer

来源：评论

学校读者我要写书评

暂无评论

Smart Camping Management Asset using Frequent Pattern-Growth Algorithm

Smart Camping Management Asset using Frequent Pattern-Growth...

引用

International Conference of Information and Communication Technology (ICoICT)

作者： Hussain Hussain Rizka Reza Pahlevi Aulia Arif Wardana Satria Akbar Mugitama School of Computing Telkom University Bandung Indonesia Computer Science and System Engineering Wroclaw University of Science and Technology Poland

Managing camping tools is crucial to ensure the safety of campers and extend the life of the tools. Frequent Pattern-Growth (FP-Growth) Association Rule Algorithms have emerged as a powerful tool for managing assets effectively. This algorithm is used to identify frequent patterns in large datasets, making it an efficient method for discovering association rules to help organizations make informed decisions about their assets. In the context of asset management, FP-Growth Association Rule Algorithms can be used to identify patterns in asset usage, maintenance, and replacement. By analyzing historical data, the algorithm can identify which assets are most frequently used, which require the most maintenance, and which are most likely to fail. This paper proposes managing the assets of camping tools using FP-growth and radio frequency identification (RFID) cards for asset tags. The proposed management asset tools are built on an Android operating system smartphone. This research using 30%, 60%, and 80% minimum support. The experiment results show that the minimum support affects the time needed to build an association. A small minimum support requires a longer time, while a large minimum support requires a faster time. The confidence value is used to determine the relevance of the FP-Growth output results. The results of the tests show that the difference in minimum support affects the speed of building associations, and the confidence value is proportional to the minimum support used. This research can be used for other case studies, using equipment data other than equipment for outdoor activities.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Temporal Enhancement Spatial-Temporal Graph Convolutional Networks 5

Temporal Enhancement Spatial-Temporal Graph Convolutional Ne...

引用

5th International Conference on Machine Learning, Big Data and Business Intelligence, MLBDBI 2023

作者： Chen, Siyu Zhou, Yun Xu, Huahu Zheng, Rui Lin, XinHua Gao, Yiqin Shanghai University School of Computer Engineering and Science Shanghai China ShangHai KingLong IoT Co. Ltd Shanghai China Shanghai Shangda Hairun Information System Co. Ltd Shanghai China Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9798350359930

With the development of computer vision, an increasing number of scholars are paying attention to action recognition based on skeleton models. The extraction and analysis of temporal and spatial information in videos are the focal points of action recognition. For the extraction of spatial information, previous methods employ graph convolution units that simply access temporal information through time links. However, this connection strategy treats the contribution of each frame towards recognition results as equal, making us incapable of focusing computational power on key frames that have a larger impact on the results. This is because for certain actions with short duration and lack of continuity, different temporal frames contribute to the outcome to various degrees. To solve this problem, this paper proposes a temporal enhancement module, which weighs temporal frame data through a Dual-pooling Channel SENet, thereby emphasizing frames that have a greater impact on recognition results. Ultimately, the effectiveness of the model is proven by the test results on two datasets for fall detection and pose recognition. While maintaining the accuracy of recognition for certain common poses, it has further improved the recognition accuracy for some non-continuous poses, such as falls. © 2023 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Assessing Complementarity for Wind and Solar Energy in New Zealand

Assessing Complementarity for Wind and Solar Energy in New Z...

引用

International Conference on Probabilistic Methods Applied to Power systems (PMAPS)

作者： Chantelle M Tomon Nyuk-Min Vong Ramesh Rayudu Power System Development Transpower New Zealand Wellington New Zealand School of Engineering and Computer Science Victoria University of Wellington Wellington New Zealand

ISBN: (数字)9798350372786

ISBN: (纸本)9798350372793

Generation complementarity refers to the negative correlation between different types of generation, which effectively smoothens out intermittencies that have become prevalent with the increasing uptake of non-dispatchable generation such as wind turbine and solar PV generation. This paper presents the findings of temporal, spatial, and spatio-temporal complementarity studies conducted for New Zealand. The study utilizes 5 years’ worth of hourly observational data from local meteorological services and real power outputs of selected operating wind farms. The typical data pre-processing steps were applied after which Spearman’s Rank Correlation, Cross-correlation, and Canonical Correlation techniques were applied to the modelled power data and derived datasets to determine complementarity. Previous correlation studies published in New Zealand have not presented findings on wind-solar complementarity until recently. With the predicted uptake of these intermittent energy sources in multiple regions, this paper can provide a baseline for generation complementarity in New Zealand.

关键词： Wind energy generation Correlation coefficient Correlation Wind energy Solar energy Wind farms Probabilistic logic

来源：评论

学校读者我要写书评

暂无评论

An Improved Semi-Supervised Learning-Based U-Net for Underwater Image Enhancement

An Improved Semi-Supervised Learning-Based U-Net for Underwa...

引用

Artificial Intelligence, Networking and Information Technology (AINIT), International Seminar on

作者： Jiqun Han Xinyu Liu Dongxu Tan Jiehui Zhu School of Computer Science and Engineering Northeastern University Shenyang China Technology Research and Development Department Guangdong Institute of Intelligent Unmanned System Guangzhou China

ISBN: (数字)9798350385557

ISBN: (纸本)9798350385564

The attenuation and scattering of light in underwater environments often lead to degradation issues such as image blurring, color cast, and low contrast. Due to the lack of high-quality paired datasets, the performance of deep learning-based methods is limited. To address these challenges, we propose an improved U-Net architecture based on semi-supervised learning for underwater image enhancement. First, a multi-scale input-level fusion module is proposed to allow our network to fully exploit global spatial information from input images, natural light fields, and depth maps. Second, a multi-branch hybrid convolutional attention residual block is designed to improve the network's feature extraction capability and focus on important spatial and channel information in underwater images. Finally, a semi-supervised learning approach is used to fully exploit unpaired datasets, improving the generalization ability of the network model. Through qualitative and quantitative analysis, the proposed network achieves satisfactory image enhancement results in various underwater scenarios.

关键词： Seminars Measurement Image color analysis Statistical analysis Scattering Learning (artificial intelligence) Semisupervised 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 << < 69 70 71 72 73 74 75 76 77 78 > >>

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：