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
61 篇 期刊文献

馆藏范围

11,298 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

8,507 篇 工学
- 6,305 篇 计算机科学与技术...
- 5,278 篇 软件工程
- 2,083 篇 信息与通信工程
- 1,280 篇 电气工程
- 1,244 篇 控制科学与工程
- 1,023 篇 生物工程
- 895 篇 电子科学与技术（可...
- 756 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...
- 641 篇 光学工程
- 581 篇 安全科学与工程
- 558 篇 仪器科学与技术
- 531 篇 化学工程与技术
- 516 篇 交通运输工程
- 457 篇 土木工程
- 400 篇 材料科学与工程（可...
- 385 篇 建筑学
4,300 篇 理学
- 2,107 篇 数学
- 1,236 篇 物理学
- 1,138 篇 生物学
- 841 篇 统计学（可授理学、...
- 556 篇 化学
- 398 篇 系统科学
2,749 篇 管理学
- 1,823 篇 管理科学与工程(可...
- 1,199 篇 图书情报与档案管...
- 1,014 篇 工商管理
665 篇 医学
- 613 篇 临床医学
- 591 篇 基础医学(可授医学...
465 篇 法学
433 篇 经济学
- 433 篇 应用经济学
276 篇 农学
193 篇 教育学
43 篇 军事学
17 篇 文学
2 篇 艺术学
1 篇 哲学

主题

584 篇 big data
190 篇 deep learning
185 篇 data mining
182 篇 internet of thin...
171 篇 machine learning
152 篇 convolutional ne...
144 篇 blockchain
113 篇 feature extracti...
110 篇 forecasting
108 篇 artificial intel...
94 篇 accuracy
87 篇 data models
84 篇 object detection
84 篇 support vector m...
82 篇 cloud computing
78 篇 software enginee...
73 篇 predictive model...
71 篇 computational mo...
64 篇 decision making
62 篇 convolution

机构

113 篇 karnataka bangal...
93 篇 chitkara univers...
83 篇 maharishi school...
68 篇 school of comput...
60 篇 department of ph...
54 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 erlangen centre ...
51 篇 iii. physikalisc...
51 篇 département de p...
51 篇 school of physic...
50 篇 dept. of physics...
50 篇 dept. of astrono...
50 篇 dept. of physics...
49 篇 columbia astroph...
49 篇 technical univer...
49 篇 department of ph...

作者

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

语言

10,152 篇 英文
1,127 篇 其他
50 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 11298 条记录，以下是4761-4770 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：

Detecting Alzheimer's Disease using Multi-Modal data: An Approach Combining Transfer Learning and Ensemble Learning 5

Detecting Alzheimer's Disease using Multi-Modal Data: An App...

引用

5th international conference on Control, Communication and Computing, ICCC 2023

作者： Shijin Knox, G.U. Anurenjan, P.R. Sreeni, K.G. College of Engineering Computer Vision Lab Kerala Trivandrum India Rajiv Gandhi Institute of Technology Kerala Kottayam India APJ Abdul Kalam Technological University Kerala India

ISBN: (纸本)9798350334128

Alzheimer's Disease (AD) is a serious and irreversible brain condition that leads to the degeneration of cognitive and memory functions. the medical field has found deep-learning models to be effective in addressing this neuro-degenerative disorder causing brain damage and mental deterioration. Deep-learning methods are found to be effective in tasks such as identifying patterns in medical images and assisting with diagnostic decisions. Transfer learning, which utilizes a pre-trained model for a new task, can be particularly beneficial when data is limited. Using transfer learning, researchers have been able to accurately detect AD. In this work, a fusion of deep-transfer learning models and custom models are used to process clinical data and MRI images of AD patients as well as normal cohorts. Features from input MRI axial slices are extracted using EfficientNet-B3 and ResNet-152, and a two-layer fully connected network are employed to obtain features from clinical data, resulting in an accuracy of 99.65% in AD and NC classification through a fivefold cross-validation. © 2023 IEEE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Semiconductor Material Porosity Segmentation in Flame Retardant Materials SEM Images Using data Augmentation and Transfer Learning 5

Semiconductor Material Porosity Segmentation in Flame Retard...

引用

5th international conference on Computer Systems and Communication technology, ICCSCT 2023

作者： Lu, Siwei Zhao, Xiaofang Liu, Huazhu Liang, Hongjie College of Electronic and Information Engineering Shenzhen University Shenzhen City China International School of Microelectronics Dongguan University of Technology Dongguan City China

ISBN: (纸本)9781643684963

Non-halogenated flame retardants are becoming the trend in the development of polymer flame retardant materials due to their high flame retardant efficiency and low generation of toxic smoke gases. Non-halogenated flame retardants achieve flame retardancy by forming a dense char layer and generating non-combustible gases, with the micro-porous structure of the char residue being crucial for studying the flame retardant mechanism. this study focuses on the segmentation of pores in scanning electron microscopy (SEM) images of the combustion char layer of non-halogenated flame retardant materials, which are cropped and labeled to form a unified dataset. We investigate the SEM image pore segmentation using data augmentation and transfer learning, addressing the challenge of limited sample size. We explore the impact of different data augmentation techniques and transfer learning on model performance. Additionally, we compare convolutional neural network (CNN) segmentation algorithms with traditional segmentation methods. Experimental results demonstrate that CNN segmentation algorithms outperform traditional methods in terms of segmentation accuracy. Offline data augmentation enhances model stability compared to online data augmentation, and adopting transfer learning significantly improves model performance metrics. Specifically, when training with VGG backbone weights through transfer learning, the average pixel accuracy and average intersection over union reach 94.49% and 89.88%, respectively. © 2024 the Authors.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Wavelet-Based Time Series Forecasting for Wireless Sensor Networks 5th

Wavelet-Based Time Series Forecasting for Wireless Sensor Ne...

引用

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

作者： Murugan, R. Arya, Rakesh Kokila, S. Mishra, Awakash Karnataka Bangalore India Department of Computer Science and Engineering School of Engineering and Computing Dev Bhoomi Uttarakhand University Navgaon Manduwala Dehradun India School of Computer Science and Engineering Presidency University Karnataka Bengaluru India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India

ISBN: (纸本)9789819780426

Wavelet-primarily based time series forecasting has been an effective device for Wi-Fi sensor network (WSN) packages. this approach has proven to provide correct forecasts for a selection of situations whilst enabling strength performance through decreased statistics storage and transmission bandwidth necessities. By means of extracting the vital time-related functions from sensor facts streams, records compression is executed at the same time as retaining the accuracy of the forecasts. Furthermore, with the aid of taking advantage of the multi resolution decomposition belongings of wavelets, this method can appropriately seize the temporal dynamics of the authentic signal. this permits better approximation of the underlying signal’s temporal correlations while as compared to other kinds of forecasting strategies. Additionally, wavelet-primarily based methods permit robust and green adaptation of the prediction fashions to changing sensor records, for this reason adapting the overall performance of the forecasts to exclusive situations. All these homes make wavelet-based time series forecasting an appealing choice for WSN programs. © the Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

RSKCNN – Introducing Randomly-Sparse-Kernel CNN 5

RSKCNN – Introducing Randomly-Sparse-Kernel CNN

引用

5th international conference on Computer Vision and Information technology, CVIT 2024

作者： Feng, Zhexi He, Yutao Li, Yucheng Department of Computer Science Jilin University China Department of Computer Science Nanjing University China Department of Computer Science Beijing Normal University Hong Kong Baptist University United International College China

ISBN: (纸本)9781510686755

Convolutional neural networks (CNNs) perform excellently in many image processing and computer vision tasks. However, their complex structure and the vast number of parameters require substantial computational and storage resources. this makes them challenging to implement, especially on mobile or embedded devices. Furthermore, CNNs often face issues limited transferability and susceptibility to overfitting. Sparsity and pruning are commonly used techniques to address these issues. Current methods include SpatialDropout, block sparsity, structured pruning, dynamic pruning, and model-independent retraining-free sparsity. Our algorithm enhances CNNs by implementing a Dropout-like operation within the convolutional kernels. Drawing inspiration from sparse CNN and ROCKET methods, this approach employs randomly sparse convolutional kernels to reduce the data density processed during convolution operations. this novel method improves performance and efficiency, demonstrating its potential as a significant advancement in CNN architecture. the method is tested on serval popular datasets by adjusting parameters within the same model and on different hardware. It demonstrates improved training speed and accuracy reduced overfitting - compared to traditional CNNs - as measured by FLOPs and validation dataset accuracy. © 2024 SPIE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Agri-Guard: IoT-Based Network for Agricultural Health Monitoring with Fault Detection 10

Agri-Guard: IoT-Based Network for Agricultural Health Monito...

引用

10th international conference on Internet of things, big data and Security, IoTBDS 2025

作者： Singh, Kushagra Momin, Kafil Abbas Nishal, M. Sultania, Chinmay Rao, Madhav Dept. of Electronics and Communication Engineering International Institute of Information Technology Bangalore Karnataka India

ISBN: (纸本)9789897587504

Agricultural sector is increasingly adopting advanced technologies to enhance crop productivity and sustainability. Precision agriculture leverages IoT devices, sensors, and data analytics to monitor and manage various environmental parameters, addressing challenges such as global food demand, climate change, and resource optimization. Previous research has demonstrated the efficacy of wireless sensor networks (WSNs) and remote sensing technologies in improving irrigation efficiency and early disease detection. However, these systems often assume that all components continue to operate, thereby offering an incomplete view. this study presents an advanced agricultural monitoring system referred to as Agri-Guard that integrates a wide array of sensors to measure temperature, humidity, soil moisture, and gases like CO2, methane and ammonia. By utilizing an ESP8266 microcontroller and IoT connectivity, the system ensures seamless data transmission and real-time processing. Additionally, a centralized hub, equipped with a Raspberry Pi 5 and a thermal camera, enhances the detection of crop anomalies, and an inoperative sensor hub. the sensor hub in the form of a cone is optimally designed to detect environmental parameters besides being rainproof. the proposed Agri-Gaurd setup clearly demonstrated the lack of manure and water from the sensors’ data, whereas thermal imaging showcased the classification of 92.7% between a dead and alive plant. the anomaly between an operating and non-operating Agri-cone was found to be in complete agreement (100%). the proposed system represents a significant improvement over existing solutions, empowering farmers with precise data and faulty hub detection, leading to quick recovery and more sustainable farming practices. Copyright © 2025 by SCITEPRESS - Science and technology Publications, Lda.

关键词： Agricultural robots

来源：评论

学校读者我要写书评

暂无评论

Recognition of multi-stage apoptosis of Hela cells using a single phase contrast image based on the CB-ResUNet model 24

Recognition of multi-stage apoptosis of Hela cells using a s...

引用

5th international Symposium on Artificial Intelligence for Medicine Science, ISAIMS 2024

作者： Hou, Jingyu Wan, Jianhui Zhang, Weina Zhong, Liyun School of Information Engineering Guangdong University of Technology Guangdong Guangzhou China Guangdong University of Technology Institute of Advanced Photonics Technology Guangdong Guangzhou China

ISBN: (纸本)9798400717826

Apoptosis is key in maintaining tissue homeostasis, development, immune response, and disease occurrence. By analyzing the characteristics of different stages, the dynamic changes and regulatory mechanisms of apoptosis can be fully revealed, thereby improving the accuracy and efficiency of the experiment. At present, apoptosis detection mainly relies on traditional techniques, such as immunofluorescence staining and flow cytometry. However, these biochemical detection techniques are destructive to cells and are not conducive to the subsequent tracking of cells. In pursuit of noninvasive, high-precision, and high-throughput apoptosis detection and identification, this paper introduces a deep learning approach grounded in CB-ResUNet. this method enables the precise recognition of multi-stage apoptosis in HeLa cells from single-phase contrast images. We use residual structure and convolutional block attention module (CBAM) to construct a UNet-like network architecture, named CB-ResUNet. We utilize CB-ResUNet to distinguish among non-apoptotic, pre-apoptotic, and late-apoptotic HeLa cells, as well as other cellular elements such as debris and necrosis. Compared with traditional UNet, CB-ResUNet has more advantages in capturing global context information. Our method achieved an accuracy of 93.74% on the test set. Experiments conducted on the iPSCs dataset substantiated the robustness of the proposed model, demonstrating its ability to generalize effectively.. this apoptosis recognition method will provide important data support for disease research and drug development, and promote progress in the biomedical field. © 2024 Copyright held by the owner/author(s).

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

A Spatial-Spectral Decoupling Fusion Framework for Visible and Near-Infrared Images 5

A Spatial-Spectral Decoupling Fusion Framework for Visible a...

引用

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

作者： Tang, Zhenglin Hu, Hai-Miao Beijing Key Laboratory of Digital Media School of Computer Science and Engineering Beihang University Beijing China Hangzhou Innovation Institute of Beihang University Hangzhou China State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China

ISBN: (纸本)9798400702051

the visible and near-infrared image fusion aims to generate an image that integrates complementary information from images captured in different spectral bands. However, existing fusion methods either only focus on the fusion of spatial information, or fuse spatial and spectral information without decoupling, resulting in undesirable effects such as halo artifacts, information loss, and inferior visual quality. To address these issues, we propose a Spatial-Spectral Decoupling Fusion (SSDF) framework that can effectively fuse the spatial and spectral information of visible and near-infrared images. the SSDF framework decomposes the image pairs into two main branches: the Spatial Feature Enhancement (SFE) branch and the Spectral Characteristic Preservation (SCP) branch. the SFE branch enhances the salient details in the fused image by exploiting the contrast between spatial features and generating region-based fusion weights, while the SCP branch preserves the intrinsic spectral characteristics of the scene by fusing the reflectance characteristics of visible and near-infrared images. the final image is obtained by combining the spatial and spectral information. We conduct extensive experiments to show that our SSDF method can achieve superior fusion performance in subjective visual quality and objective metrics compared with state-of-the-art methods. © 2023 Copyright held by the owner/author(s).

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

Mushroom Classification Using CNN and Gradient Boosting Models 5

Mushroom Classification Using CNN and Gradient Boosting Mode...

引用

5th international conference on Electronics and Sustainable Communication Systems, ICESC 2024

作者： Sharma, Rishabh Gupta, Shikhar Chitkara University Institute of Engineering and Technology Chitkara University Centre for Research Impact & Outcome Punjab Rajpura140401 India Chitkara University Chitkara Centre for Research and Development Himachal Pradesh 174103 India

ISBN: (纸本)9798350379945

this research study suggests a new method to differentiate three commonly found species of mushrooms namely Button, Oyster, and Shiitake widely available in India, using CNN and GB models. With the help of the carefully selected dataset of around 9 thousand images of high resolution integrated methodology has yielded an astounding average accuracy of 93. 18%. CNN provided a very efficient features extraction for the complex visual patterns, while GB naturally dealt with additional features achieving accurate classification models. Using performance evaluation, a high precision, recall, and F1 score was achieved on all the mushroom classes meaning that the models were able to perform well in differentiating between different classes especially those which are unique from each other. Comparative analysis placed models as being more advantageous in comparison to the current techniques illustrated in Figure 3. Apart from their efficiency, these models can be easily implemented on a large scale and work in an autonomous manner, which has a vast impact on agriculture, food services, and medicine. thus, the feature proves the effectiveness of CNNs and GB in precise classification of mushrooms for their further application in a variety of spheres. Further works could look at other, potentially larger data sets and at the integration of machine explicable AI methodologies to relate the facets of the models even more accurately and transparently. All in all, the study paves way for embracing an era that can potentially bring 'mushroom perfect' in classification for the varieties of mushrooms so that India can have new vistas for mushroom farming, culinary world and healthcare sector. © 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

TagVibra: push the limit of RFID-based vibration sensing 9

TagVibra: push the limit of RFID-based vibration sensing

引用

9th international conference on big data Computing and Communications, bigCom 2023

作者： Li, Jian Li, Ping Zhu, Biaokai Dong, Chong Gong, Chao Lv, Zhao Anhui University Anhui Province Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Hefei230601 China Anhui University of Technology Anhui Engineering Research Center for Intelligent Applications and Security of Industrial Internet Ma'anshan243032 China Shanxi Police College Taiyuan030401 China

ISBN: (纸本)9798350331240

RFID-based mechanical vibration detection is considered a promising method for many Internet of things (IoT) applications. However, existing methods are affected by ambient interference and leakage from the reader signature, which makes it difficult to obtain high-precision detection results. To overcome this limitation, this paper introduces TagVibra, a high-precision non-contact vibration sensing system based on RFID technology. By leveraging the nonlinear effect inside the tag and the modulation mechanism of RFID, TagVibra can achieve sub-millimeter level vibration detection accuracy. We implement TagVibra on our Universal Software Radio Peripheral (USRP) platform and evaluate its performance via experiments. the experimental results show that TagVibra can detect vibration with amplitude as low as 0.3mm, and the average estimation error below 0.7Hz when the vibration frequency is 100Hz. © 2023 IEEE.

关键词： Frequency estimation

来源：评论

学校读者我要写书评

暂无评论

Analysis of Blockchain technology to Protect data Access Using Intelligent Contract Mechanism for 5G Networks 6

Analysis of Blockchain Technology to Protect Data Access Usi...

引用

6th international conference on Contemporary Computing and Informatics, IC3I 2023

作者： William, P. Rai, Anjani Kumar Madan, Parul Kumar, C Praveen Shrivastava, Anurag Rana, Ajay Sanjivani College of Engineering Department of Information Technology Savitribai Phule Pune University Maharashtra Pune India Institute of Engineering & Technology GLA University Uttar Pradesh Mathura India Graphic Era Deemed to Be University Department of Computer Science & Engineering Uttarakhand Dehradun India Institute of Aeronautical Engineering Department of Computer Science and Engineering Telangana Hyderabad India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Tamilnadu Chennai India Amity University Uttar Pradesh Greater Noida India

ISBN: (纸本)9798350304480

With constantly changing internet models automating and digitising countless residential and industrial applications, the world of today has made significant progress in the sharing of healthcare data and the implementation of crucial actions. the two most crucial factors in the setting of healthcare data exchange today are privacy and data integrity. In order to prevent unauthorised individuals from viewing or accessing sensitive data, such as medical information, encryption is essential. the intermediary nodes shouldn't be given too much weight because conventional encryption techniques could not be deployable through them. the current security alternatives for IoT-driven healthcare monitoring frameworks are discussed in this article along with the numerous security challenges that exist in the current 5G network design and how blockchain technology may be used to encrypt data between nodes. the suggested approach outperformed the alternatives and the present strategies for IoT-driven healthcare monitoring frameworks'security solutions, according to a variety of performance factors utilised to test it. A number of performance parameters were used to test the suggested technique, and the results showed that it performed better than the alternatives. © 2023 IEEE.

关键词： Block chain data Integrity Encryption Healthcare IoT Security

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 << < 473 474 475 476 477 478 479 480 481 482 > >>

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：