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

11,147 篇 会议
90 册 图书
60 篇 期刊文献

馆藏范围

11,297 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

8,501 篇 工学
- 6,303 篇 计算机科学与技术...
- 5,277 篇 软件工程
- 2,082 篇 信息与通信工程
- 1,278 篇 电气工程
- 1,243 篇 控制科学与工程
- 1,022 篇 生物工程
- 894 篇 电子科学与技术（可...
- 755 篇 机械工程
- 734 篇 动力工程及工程热...
- 723 篇 生物医学工程（可授...
- 638 篇 光学工程
- 580 篇 安全科学与工程
- 556 篇 仪器科学与技术
- 529 篇 化学工程与技术
- 515 篇 交通运输工程
- 456 篇 土木工程
- 399 篇 材料科学与工程（可...
- 385 篇 建筑学
4,295 篇 理学
- 2,105 篇 数学
- 1,233 篇 物理学
- 1,137 篇 生物学
- 841 篇 统计学（可授理学、...
- 555 篇 化学
- 398 篇 系统科学
2,748 篇 管理学
- 1,822 篇 管理科学与工程(可...
- 1,200 篇 图书情报与档案管...
- 1,015 篇 工商管理
665 篇 医学
- 612 篇 临床医学
- 590 篇 基础医学(可授医学...
465 篇 法学
434 篇 经济学
- 434 篇 应用经济学
277 篇 农学
194 篇 教育学
43 篇 军事学
17 篇 文学
2 篇 艺术学
1 篇 哲学

主题

586 篇 big data
191 篇 deep learning
186 篇 data mining
182 篇 internet of thin...
174 篇 machine learning
149 篇 convolutional ne...
144 篇 blockchain
113 篇 feature extracti...
110 篇 forecasting
109 篇 artificial intel...
92 篇 accuracy
86 篇 data models
84 篇 object detection
84 篇 support vector m...
83 篇 cloud computing
78 篇 software enginee...
73 篇 predictive model...
71 篇 computational mo...
64 篇 decision making
62 篇 convolution

机构

114 篇 karnataka bangal...
91 篇 chitkara univers...
86 篇 maharishi school...
69 篇 school of comput...
55 篇 maharishi school...
52 篇 department of ph...
52 篇 dept. of astrono...
52 篇 dept. of physics...
52 篇 dept. of physics...
52 篇 iii. physikalisc...
52 篇 erlangen centre ...
51 篇 dept. of physics...
51 篇 département de p...
51 篇 school of physic...
51 篇 dept. of physics...
50 篇 columbia astroph...
50 篇 department of ph...
50 篇 department of ph...
49 篇 technical univer...
49 篇 department of ph...

作者

61 篇 coleman a.
51 篇 haungs a.
50 篇 fan k.l.
50 篇 bourbeau e.
50 篇 fritz a.
50 篇 halve l.
50 篇 de clercq c.
50 篇 böttcher j.
50 篇 ha minh m.
50 篇 glauch t.
50 篇 delaunay j.j.
49 篇 fürst p.
49 篇 günther c.
48 篇 chen z.
48 篇 butterfield d.
48 篇 alameddine j.m.
48 篇 chattopadhyay s.
48 篇 feigl n.
48 篇 athanasiadou s.
48 篇 diaz a.

语言

6,939 篇 英文
4,339 篇 其他
72 篇 中文
3 篇 俄文

检索条件"任意字段=Proceedings of the 2023 5th International Conference on Big Data Engineering and Technology"

共 11297 条记录，以下是4471-4480 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：

Role of Blockchain in Spectrum Sharing in B5G Networks Service 5

Role of Blockchain in Spectrum Sharing in B5G Networks Servi...

引用

5th international conference on Blockchain Computing and Applications, BCCA 2023

作者： Zaman, Saleha Fathima Zaman, Faisal Bhagya, R. R. V. College of Engineering Bengaluru India University of Ottawa Ottawa Canada

ISBN: (纸本)9798350339239

Beyond 5G (B5G) Networks are envisioned to support a wide range of services with varying data profiles and traffic requirements. Unlike previous generations of wireless communication where improving BW and latency was the main theme, the primary objective of B5G is to provide the flexibility needed to support diverse network services required by different sectors of the industry (also referred to as verticals). One of the key enablers to support the heterogeneous network envisioned as part of the Industry 4.0 revolution is the introduction of unlicensed spectrum bands (mmWave and Terahertz). Optimal utilization of spectrum is crucial for the seamless working of different services in the B5G network. One of the proposals to provide on-demand spectrum usage is to use Blockchain for managing the spectrum. In this paper, we focus on a Blockchain-enabled B5G network for spectrum management. First, we provide a brief introduction to different services envisioned to be part of the B5G network based on the 3GPP vision. Second, we discuss recent work on Blockchain-enabled B5G networks and highlight the pros and cons of the proposals. the objective of this paper is to position Blockchain in the B5G framework and to demystify the pros and cons of using Blockchain focusing on spectrum management. Finally, we perform a simulation to study the effects of spectrum allocation strategies on a Blockchain network size. the results suggest that the strategy of how transactions are allocated in a Blockchain network can have either a positive or negative impact on the overall QoS of a service. © 2023 IEEE.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

Achieving Privacy-Preserving Multi-View Consistency with Advanced 3D-Aware Face De-identification 5

Achieving Privacy-Preserving Multi-View Consistency with Adv...

引用

5th ACM international conference on Multimedia in Asia, MMAsia 2023

作者： Cao, Jingyi Liu, Bo Wen, Yunqian Xie, Rong Song, Li Institute of Image Communication and Network Engineering Shanghai Jiao Tong University Shanghai China School of Computer Science University of Technology Sydney Sydney Australia

ISBN: (纸本)9798400702051

the widespread application of face recognition technology has exacerbated privacy threats. Face de-identification is an effective means of protecting visual privacy by concealing identity information. While deep learning-based methods have greatly improved de-identification results, most existing algorithms rely on 2D generative models that struggle to produce identity-consistent results for multiple views. In this paper, we focus on identity disentanglement within the latest 3D-aware face generation model, and propose an advanced face de-identification framework that can be applied to various scenarios. Our proposed framework disentangles identity from other facial features, modifies only the former and generates the de-identified face using a 3D generator. this approach results in high-quality, identity-consistent de-identification that preserves other facial features. We demonstrate our approach on StyleNeRF, one of the most widely-used style-based neural radiation field models. through extensive experiments, we demonstrate the effectiveness of our approach in achieving face de-identification both for a single image and group images with the same identity. Our work is a significant step forward in the field of face de-identification, opening up new possibilities for practical applications. © 2023 Copyright held by the owner/author(s).

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

An Experimental Investigation on the Emotion Recognition Using Power Spectrum Density and Machine Learning Algorithms in EEG Signals 5th

An Experimental Investigation on the Emotion Recognition Usi...

引用

5th EAI international conference on big data Innovation for Sustainable Cognitive Computing, BDCC 2022

作者： Babu, Nirmal Varghese Kanaga, E. Grace Mary Department of Computer Science and Engineering Karunya Institute of Technology and Sciences Tamil Nadu Coimbatore India

ISBN: (纸本)9783031283239

Emotion recognition is a technique for identifying and classifying human emotions by combining biosensing, face recognition, speech and voice recognition, machine learning, and pattern recognition. the electroencephalogram (EEG), which is based on brain signals, is used in the proposed work to identify the emotions. Here, the DEAP dataset is used to gather information about human emotional states, and machine learning algorithms like SVM, KNN, and MLP were used as the classifiers. In this proposed work, we used Power Spectrum Density as the Feature Extraction Technique and Welch’s Periodogram as the Signal Decomposition Technique. It was observed that gamma signals show more Valence, whereas Alpha signals show Arousal. To Cross validation system has been used to validate the performance of classifiers used in the work. Based on the locations of the electrode, EEG bands, and classifiers, accuracy comparisons were done. Out of the three classifiers, KNN scored more accuracy than other classifiers used. © 2023, the Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Pre-planning of individualized talus implants based on computed tomography-automated segmentation 5

Pre-planning of individualized talus implants based on compu...

引用

5th international conference on Artificial Intelligence and Computer Science, AICS 2023

作者： He, Jie Guo, Zhexiao Zeng, Yunxia Su, Xiuyun Pei, Guoxian Southern University of Science and Technology Hospital Guangdong Shenzhen518055 China Department of Chinese and Bilingual Studies The Hong Kong Polytechnic University 100872 Hong Kong

ISBN: (纸本)9781510668621

Fractures of the talar neck and body are associated with spine fractures and scoliosis deformity, which affect cosmetic appearance and cause difficulty in ambulation. the implant design for talus surgery is thriving as a functional alternative in case of severe talar destruction, focusing on segmentation and reconstruction of the talus’s shape. However, manual segmentation of the talus is time-consuming and subjective. In this study, we exploited the automatic segmentation framework to efficiently train a deep learning-based model to accurately segment the talus based on computed tomography imaging. We developed three model configurations with nnU-Net and investigated their Dice similarity coefficients (DSC) and 95% Hausdorff distances (HD95) for talus segmentation on a CT image dataset. the three configurations performed well (DSC>0.95, HD95 © 2023 SPIE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A Lightweight detector for Steel Surface Defects Based on Channel Pruning 24

A Lightweight detector for Steel Surface Defects Based on Ch...

引用

5th international conference on Computer Information and big data Applications, CIBDA 2024

作者： Zhang, Jingtao Song, Tao Li, Weiwei Xiong, Hailong Ye, Dingxing Chongqing Key Laboratory of Fiber Optic Sensing and Photoelectric Detection Chongqing University of Technology 400054 China Chongqing Industrial Big Data Innovation Center Co. Ltd. 400708 China

ISBN: (纸本)9798400718106

Product surface defect detection plays a very important role in improving production efficiency and production quality. With the development of artificial intelligence technology, deep learning-based object surface defect detection technology has gradually replaced manual detection. However, the high-precision target detection model requires a large amount of arithmetic power as well as storage support, which is difficult to deploy on platforms with limited arithmetic power such as embedded devices, limiting its further application in industrial production. To this end, this paper proposes a model lightweighting method based on channel pruning, which calculates the channel importance at the global level through the two parameters of the BN layer, and then iteratively removes the unimportant channels to achieve model lightweighting. In addition, in order to deal with the channel coupling caused by the residual structure, the coupled channels are found out by depth-first search algorithm, and then deleted at the same time by means of shared masks during pruning, so as to improve the efficiency of pruning. Experiments were conducted on the NEU-DET dataset using ResNet-50 and ResNet-101 based RetinaNet detectors, respectively. RetinaNet-R50 improves the mAP by 0.2% when the compression rate reaches 30%, and the number of model parameters decreases to 33.92%, which improves the inference speed by 13.5% on the RTX3090. RetinaNet-R101, when the model volume is compressed to 10.74% of the original model, the mAP only decreases by 0.2%, and the inference speed is improved by 23.9%. © 2024 ACM.

关键词： Surface defects

来源：评论

学校读者我要写书评

暂无评论

Pedestrian re-identification domain generalization algorithm based on causal strong and weak alignment 5

Pedestrian re-identification domain generalization algorithm...

引用

5th international conference on Artificial Intelligence and Computer Science, AICS 2023

作者： Mo, Jianwen Hu, Junliang Yuan, Hua Lin, Leping School of Information and Communication Guilin University of Electronic Technology Guangxi Guilin541001 China

ISBN: (纸本)9781510668621

the domain generalisation pedestrian re-identification problem aims to generalise features learned in a known pedestrian data domain to an unknown pedestrian target domain. Most traditional domain generalization methods assume that the statistical properties between features and categories remain consistent across data domains. However, actual pedestrian data is often susceptible to domain factors such as lighting, colour shifts, and camera differences. this results in the data distribution of pedestrians under different domains not being identical and hinders the generalisation of the model. To address the above issues, this paper proposes a representation learning algorithm based on causal strong and weak alignment by constructing a structural causal model for the pedestrian domain generalization problem from the perspective of causal inference. the algorithm first performs causal intervention on the input pedestrian data to obtain causally enhanced images, then the image features are fed into the strong alignment module to achieve feature alignment in each dimension and obtain a preliminary invariant representation, finally, the features are then subjected to the constraints of the weak alignment module contrastive loss to further optimise the causal features under different cameras and improve the stability of the model’s cross-domain causal prediction. the method was compared and ablation experiments were carried out on the Market-1501 and DukeMTMC-reID datasets, demonstrating the effectiveness of the proposed method. © 2023 SPIE.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Fungi Recognition Based on Coordinate Attention and EfficientNetV2 5

Fungi Recognition Based on Coordinate Attention and Efficien...

引用

5th IEEE international conference on Artificial Intelligence and big data, ICAIBD 2022

作者： Li, Chuxian Zhao, Wenjing Meng, Lingchun Chen, Zhaohui Zhao, Yongtao Cao, Zhong Guangzhou University School of Electronics and Communication Engineering Guangzhou China Guangdong University of Foreign Studies Center of Network and Information Guangzhou China Chongqing University of Science and Technology School of Mathematics Physics and Data Science Chongqing China Gansu Vocational and Technical College of Nonferrous Metallurgy Department of Mechanical and Electrical Engineering Jinchang China

ISBN: (纸本)9781665499132

Fungi are diverse species, which are widely distributed and have high ecological, economic, and research values. Traditional classification relies on manual work, which is inefficient and not conducive to the research, promotion and application of fungi. Fungal recognition is a fine-grained visual classification (FGVC) problem, which is extremely challenging due to the great diversity of fungi species and their different morphologies. In this paper, we propose a deep learning-based fungal recognition method that improves the convolutional neural network EffentnetV2. We add the coordinate attention module to EffentnetV2 for aggregating feature map spatial location information. Our model achieves an accuracy of 78.41% on the publicly available DF20-mini dataset, outperforming other mainstream neural networks and ViT architectures. We analyzed the improved model using the Grad-CAM visualization tool and demonstrated its effectiveness. © 2022 IEEE.

关键词： Fungi

来源：评论

学校读者我要写书评

暂无评论

Sketched Ridgeless Linear Regression: the Role of Downsampling 40

Sketched Ridgeless Linear Regression: The Role of Downsampli...

引用

40th international conference on Machine Learning

作者： Chen, Xin Zeng, Yicheng Yang, Siyue Sun, Qiang Princeton Univ Dept Operat Res & Financial Engn 98 Charlton St Princeton NJ 08544 USA Chinese Univ Hong Kong Shenzhen Res Inst Big Data 2001 Longxiang Blvd Shenzhen Guangdong Peoples R China Univ Toronto Dept Stat Sci 700 Univ Ave Toronto ON M5G IX6 Canada

Overparametrization often helps improve the generalization performance. this paper presents a dual view of overparametrization suggesting that downsampling may also help generalize. Focusing on the proportional regime m asymptotic to n asymptotic to p, where m represents the sketching size, n is the sample size, and p is the feature dimensionality, we investigate two out-of-sample prediction risks of the sketched ridgeless least square estimator. Our findings challenge conventional beliefs by showing that downsampling does not always harm generalization but can actually improve it in certain cases. We identify the optimal sketching size that minimizes out-of-sample prediction risks and demonstrate that the optimally sketched estimator exhibits stabler risk curves, eliminating the peaks of those for the full-sample estimator. To facilitate practical implementation, we propose an empirical procedure to determine the optimal sketching size. Finally, we extend our analysis to cover central limit theorems and misspecified models. Numerical studies strongly support our theory.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Water Treatment and Crop Recommendation Model Using Artificial Intelligence 5

Water Treatment and Crop Recommendation Model Using Artifici...

引用

5th IEEE international conference on Computing, Power, and Communication Technologies, IC2PCT 2024

作者： Kapoor, Akash Bhatia, Divyanshi Kumar, Anubhav Gupta, Shikha Chandigarh University Apex Institute of Technology Department of Computer Science and Engineering Punjab Mohali India Galgotias University School of Computing Science and Engineering U.P. Greater Noida India

ISBN: (纸本)9798350383522

Modern agriculture has enormous problems due to water constraint and rising food demand. Farmers face unpredictable precipitation and dwindling water supplies as climate change affects weather patterns, demanding creative techniques to optimize water management and increase agricultural output. this research describes a smart agricultural system that combines water treatment with crop suggestion to enhance sustainable farming practices. Potential pollutants and water quality criteria are discovered using real-time data gathering and analysis, allowing farmers to take remedial action and optimize irrigation schedules to reduce water waste and environmental implications. Furthermore, the crop suggestion system analyses environmental data, past crop performance, and soil properties using AI-driven algorithms. the algorithm recommends crop types for a certain location or plot based on parameters such as climate, soil moisture levels, and nutrient content. Farmers can make educated decisions, maximize agricultural productivity, and adjust to changing climatic circumstances as a result of this. the agriculture industry can solve the concerns of water shortages and food security by embracing this technology-driven solution, while also encouraging ecologically conscientious farming practices. © 2024 IEEE.

关键词： Crop recommendation K-NN Machine Learning Random Forest Smart agriculture Sustainability SVM Water management Water treatment

来源：评论

学校读者我要写书评

暂无评论

Improving Medical Image Segmentation through Knowledge Transfer and Deep Learning 5th

Improving Medical Image Segmentation Through Knowledge Trans...

引用

5th international conference on data Science, Machine Learning and Applications, ICDSMLA 2023

作者： Pandeya, Megha Yadav, Surjeet Batra, Raman Gobi, N. Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India Department of Mechanical Engineering Vivekananda Global University Jaipur India Department of Mechanical Engineering Noida Institute of Engineering and Technology Uttar Pradesh Greater Noida India Karnataka Bangalore India

ISBN: (纸本)9789819780426

Clinical image segmentation is vital to offering higher medical analysis and remedy. But, due to the complex nature of clinical images, conventional segmentation algorithms frequently fail to phase the anatomy safely. With the advances in deep learning, it has become feasible to apply the expertise switch and deep gain knowledge of strategies to enhance the overall performance of medical photo segmentation. Information transfer, additionally known as switch mastering, applies know-how obtained from one set of supply statistics to any other set of target facts. this technique can be applied to medical picture segmentation to transfer expertise from the source facts set to the target statistics. Expertise switch entails the switch of characteristic representations among the source and goal facts and can contain modifying the parameters of the target community. Deep gaining knowledge of techniques, such as convolution neural networks (CNNs), was used to improve overall performance in scientific image segmentation. these networks can examine the information, considering higher segmentation results. © the Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： datasets Medical performance segmentation techniques

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 << < 444 445 446 447 448 449 450 451 452 453 > >>

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：