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

34,403 篇 会议
5,316 篇 期刊文献
272 册 图书

馆藏范围

39,991 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

24,669 篇 工学
- 17,660 篇 计算机科学与技术...
- 14,804 篇 软件工程
- 6,542 篇 信息与通信工程
- 3,979 篇 控制科学与工程
- 3,048 篇 电子科学与技术（可...
- 2,866 篇 电气工程
- 2,641 篇 生物工程
- 2,131 篇 生物医学工程（可授...
- 1,694 篇 光学工程
- 1,620 篇 机械工程
- 1,487 篇 仪器科学与技术
- 1,369 篇 动力工程及工程热...
- 1,110 篇 化学工程与技术
- 984 篇 安全科学与工程
- 812 篇 交通运输工程
- 750 篇 网络空间安全
12,355 篇 理学
- 6,617 篇 数学
- 3,357 篇 物理学
- 2,898 篇 生物学
- 2,198 篇 统计学（可授理学、...
- 1,536 篇 系统科学
- 1,190 篇 化学
6,430 篇 管理学
- 3,831 篇 管理科学与工程(可...
- 2,915 篇 图书情报与档案管...
- 2,006 篇 工商管理
1,863 篇 医学
- 1,594 篇 临床医学
- 1,481 篇 基础医学(可授医学...
- 954 篇 药学(可授医学、理...
- 801 篇 公共卫生与预防医...
1,206 篇 法学
- 979 篇 社会学
735 篇 经济学
569 篇 农学
497 篇 教育学
186 篇 文学
97 篇 军事学
61 篇 艺术学
1 篇 哲学

主题

1,290 篇 accuracy
996 篇 feature extracti...
968 篇 computational mo...
871 篇 deep learning
805 篇 training
782 篇 computer science
657 篇 real-time system...
641 篇 machine learning
616 篇 support vector m...
550 篇 predictive model...
497 篇 internet of thin...
470 篇 convolutional ne...
434 篇 data models
382 篇 reliability
356 篇 data mining
340 篇 computer archite...
340 篇 optimization
316 篇 artificial intel...
312 篇 wireless sensor ...
311 篇 routing

机构

82 篇 north-west unive...
82 篇 institut univers...
80 篇 national centre ...
79 篇 infn sezione di ...
77 篇 institute of inf...
76 篇 infn sezione di ...
69 篇 tno technical sc...
66 篇 università di ca...
62 篇 université de st...
58 篇 dept. of informa...
56 篇 dept. of compute...
52 篇 school of automa...
52 篇 leiden universit...
51 篇 nikhef national ...
50 篇 dept. of compute...
49 篇 dept. of informa...
46 篇 dept. of compute...
44 篇 dept. of compute...
43 篇 dept. of electri...
42 篇 infn lnf via enr...

作者

85 篇 ferrara g.
85 篇 ardid m.
84 篇 calvo d.
84 篇 gal t.
84 篇 bozza c.
81 篇 chen a.
80 篇 kalekin o.
78 篇 díaz a.f.
77 篇 boumaaza j.
73 篇 coleiro a.
68 篇 huang f.
68 篇 gozzini s.r.
58 篇 dallier r.
51 篇 kulikovskiy v.
51 篇 anguita m.
44 篇 del burgo r.
41 篇 benoit d.m.
41 篇 eddymaoui a.
40 篇 gagliardini s.
40 篇 labalme m.

语言

37,786 篇 英文
1,737 篇 其他
367 篇 中文
54 篇 日文
48 篇 朝鲜文
2 篇 德文
2 篇 斯洛文尼亚文
1 篇 法文
1 篇 葡萄牙文

检索条件"机构=Dept.of Computer Engineering and Computer Science"

共 39991 条记录，以下是211-220 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：

Renal Cell Carcinoma Classification: Deep Learning with MLflow, DVC, and AWS CI/CD Deployment 8

Renal Cell Carcinoma Classification: Deep Learning with MLfl...

引用

8th International Conference on Electronics, Communication and Aerospace Technology, ICECA 2024

作者： Niveditha, J. Supreeth, S. Patil, Kirankumari Reva University Dept of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798350367904

One prevalent type of kidney cancer that can be challenging to diagnose and treat is renal cell carcinoma (RCC). This article offers a novel method for applying deep learning techniques to the classification of RCC data. In particular, we examine the performance of three distinct models: ResNet50, VGG16, and a special 2D convolutional neural network (CNN). Our method makes use of cutting-edge machine learning frameworks like MLflow and DVC to streamline model building, experimentation, and version control. We describe an effective deployment pipeline that facilitates seamless integration with healthcare systems using AWS CI/CD infrastructure. The dataset, which includes 8,143 normal images and 1 0, 8 7 8 tumor images, is sourced from the Cancer Imaging Archive. CNN-4 was the classification model that obtained the highest accuracy, and CNN-6, ResNet50, and VGG16 were the detection models that achieved the highest accuracy, with respective results of 99 %, 98 %, and 98%. These results demonstrate how our approach can be utilized to improve patient outcomes and early detection of RCC while simultaneously improving the accuracy of RCC diagnoses. © 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

Enhanced ConvLSTM with Hierarchical Attention Scheme for Unusual Activity Detection in Classrooms or Laboratories

Enhanced ConvLSTM with Hierarchical Attention Scheme for Unu...

引用

2024 IEEE Region 10 Symposium, TENSYMP 2024

作者： Shrivas, Ansh Mahendra Kumar Singh, Dushyant Jain, Rishabh Chandel, Shreyansh Singh Sahu, Abhimanyu Mnnit Computer Science and Engineering Dept. Allahabad India

ISBN: (纸本)9798350364866

Surveillance camera systems have been essential in enhancing security protocols, serving as crucial tools for monitoring and deterring unauthorized or unusual activities across various settings. This paper addresses the significant vulnerability of educational spaces to numerous security threats, such as unauthorized access, theft, vandalism, and risks to the safety of students and staff. In an age where both physical and digital security are critically important, there is an increasing demand for proactive surveillance solutions that can quickly and accurately identify anomalies and potential security breaches. Deep learning techniques have demonstrated remarkable effectiveness in identifying patterns, anomalies, and subtle deviations in behavior within real-time video feeds. We have developed an enhanced ConvLSTM model incorporating spatial and temporal attention mechanisms to extract essential features from raw video footage, which are then processed by the backbone network. The architecture is designed to selectively focus on the most valuable features, thereby reducing computational complexity and enhancing the model's detection performance. The model is fine-tuned to detect and classify activities into usual and unusual categories. The proposed design is trained on videos from the UCF-Crime dataset and fine-tuned on a custom dataset created from YouTube videos, which includes videos of actions that are unusual or anomalous in educational environments. Our approach achieved approximately 99% accuracy on the UCF-Crime dataset, surpassing detection baselines (85.53% to 88.56%) and outperforming other architectures such as C3D, ConvLSTM, and CNN+RNN models with and without attention mechanisms. Evaluation on a custom YouTube dataset yielded a detection accuracy of 82.66%. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

An Effective and Comprehensive Crop Recommendation System Using Machine Learning

An Effective and Comprehensive Crop Recommendation System Us...

引用

2024 IEEE International Conference on Emerging Technologies in computer science for Interdisciplinary Applications, ICETCS 2024

作者： Mohideen Badhusha, S. Athmashree, H.A. Bhoomika, E.R. Anusha Bhuvan, M. AIET Dept.Computer Science and Engineering Moodbidri India

ISBN: (纸本)9798350372502

Agriculture plays a crucial role in Indian economy. However, the agriculture sector is suffering from low productivity and yielding due to various factors. One of the factors is the failure to select suitable crops for a particular type of soil in an agricultural region. Most of the farmers highly depend on the direction of agricultural experts and experienced farmers in the task of crop selection. The shortage of technical knowledge and awareness of the latest technology hinders the progress of the farmers resulting in low yielding. Therefore, a machine learning model is developed to predict a set of best suitable crops that are intended to produce high-yielding for a particular agricultural region based on environmental and soil conditions. In this regard, comprehensive data sets which are intended to produce high yielding for different crop types, are gathered from various regions of the country. Both environmental parameters (viz., temperature, humidity, and moisture) and soil parameters (viz., pH, Nitrogen, Potassium, Phosphorus values) are considered as a feature set for training the proposed model. The comprehensive datasets from different parts are trained and tested based on performance metrics like precision, accuracy, recall, confusion matrix, and F1-score. The proposed model achieves 75% to 80% accuracy in predicting suitable crops for a soil type in a certain region. © 2024 IEEE.

关键词： Crops

来源：评论

学校读者我要写书评

暂无评论

Securing Satellite Communication: Exploring Cybersecurity Measures in Satellite Networks

Securing Satellite Communication: Exploring Cybersecurity Me...

引用

2024 OPJU International Technology Conference on Smart Computing for Innovation and Advancement in Industry 4.0, OTCON 2024

作者： Khare, Shanu Talwandi, Navjot Singh Chandigarh University Dept of Computer Science Engineering Punjab India

ISBN: (纸本)9798350373783

This paper discusses the importance of cybersecurity measures in satellite networks, highlighting potential vulnerabilities and threats that can compromise communication systems. With increasing dependence on satellite-based services for various applications such as navigation, remote sensing, and broadband connectivity, ensuring their security becomes crucial to prevent unauthorized access, data breaches, and service disruptions. The article examines various existing and emerging countermeasures aimed at enhancing the protection of satellite networks against cyber attacks. These include encryption techniques, authentication mechanisms, network segmentation, intrusion detection systems (IDS), and physical security measures. Furthermore, this study emphasizes the need for international cooperation, regulatory framework development, and continuous research and innovation to address evolving challenges in securing satellite communications. © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Skin Disease Detection Using Neural Networks 2

Skin Disease Detection Using Neural Networks

引用

2nd International Conference on Advancements in Smart, Secure and Intelligent Computing, ASSIC 2024

作者： Gupta, Meenu Kumar, Rakesh Nandan Pradhan, Anil Kumar Obaid, Ahmed J. Chandigarh University Department of Computer Science & Engineering Punjab Mohali India University of Kufa Faculty of Computer Science and Mathematics Dept of Computer Science Najaf Iraq College of Engineering Uruk University Baghdad Iraq

ISBN: (纸本)9798350370188

Skin diseases like acne, psoriasis, eczema, and dermatitis affect millions worldwide. Skin cancer and melanoma are diseases that happen due to exposure to UV radiation. The early detection of skin diseases is crucial for effective treatment and prevention of further complications. This work comprehensively reviews various image-based techniques for skin disease detection, including traditional computer vision methods such as Convolutional Neural Network (CNN), Random Forest (RF), Naïve Bayes (NB), k-nearest Neighbour (k-NN), and Support Vector Machine (SVM). ISIC and dermofit datasets comprised 26,150 images divided into three categories: training (20,150), testing (3000), and validation (2000), respectively. Receiver Operating Characteristics (ROC) and Mean Squared Error (MSE) are used to calculate the accuracy and precision of models. As a result, it concluded that CNN outperformed with 94.91% accuracy. The proposed system can aid dermatologists in making accurate diagnoses and improve patient care. © 2024 IEEE.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Classification and Structuring of DL-Based Method for Finding Alzheimer's Disease through MRI Images 5

Classification and Structuring of DL-Based Method for Findin...

引用

5th IEEE International Conference on Computing, Power, and Communication Technologies, IC2PCT 2024

作者： Tripathi, Tripti Kumar, Rakesh Mmmut Dept. of Computer Science and Engineering Gorakhpur India

ISBN: (纸本)9798350383522

Alzheimer's disease (AD) is a type of neurological disorder that progresses over a period and affects a significant number of people worldwide. Early detection of AD is necessary for rapid intervention and improved outcomes for patients. In this paper, we compare the performance of four widely used Deep Convolutional Neural Network (DCNN) architectures: CNN, VGG16, InceptionV3, and DenseNet121. The study focuses on the use of DCNNs for AD identification. Our dataset is collected from the Kaggle website and preprocessed such that the inputs are identical for every model. Several criteria are used to assess the DCNN architecture's performance, including recall, accuracy, precision, and f1-score. By looking at individual architecture's predictive capabilities, we may discover further the benefits and drawbacks of AD detection jobs. Also, transfer learning techniques employ pre-trained weights from large neuroimaging datasets to enhance model performance and generalization abilities. This study contributes to the increasing body of knowledge in AD research by identifying the ideal DCNN architecture for fast and accurate AD diagnosis. © 2024 IEEE.

关键词： AD detection Alzheimer's disease CNN computational efficiency Deep Convolutional Neural Networks DenseNet121 InceptionV3 performance evaluation transfer learning VGG16

来源：评论

学校读者我要写书评

暂无评论

Optimization of Double Wishbone Suspension: Evaluating the Performance of Classes of Algorithms

Optimization of Double Wishbone Suspension: Evaluating the P...

引用

2024 International Conference on Applied Mathematics and computer science, ICAMCS 2024

作者： Arshad, Muhammad Waqas Lodi, Stefano University of Bologna Dept of Computer Science and Engineering Bologna Italy

ISBN: (纸本)9798350363807

Double wishbone suspension systems are employed in high-performance vehicles owing to their superior control over wheel motion. The design of a double-wishbone suspension is a challenging multi-objective problem due to the many inter- related quantities that are key in determining its performance and vary during its motion. The design activity is thus a time-consuming and complex iterative process that aims to tune their variation and minimize deviations from the desired performance characteristics while requiring the satisfaction of mechanical constraints. Computational optimization methods can be integrated into the design activity only after an assessment of their capability to support efficiently and effectively an iterative workflow. In this work, we start with the mathematical modeling of the camber angle of the double wishbone suspension. Then, we use the multi-model optimization approach that includes metaheuristic algorithms (Genetic Algorithms, Particle Swarm Optimization, Gradient Descent, and Ant Colony Optimization) and classical methods (Nelder-Mead, Interior Point, Simulated Annealing, and Random Search). These methods are assessed in terms of objective value, computational time, and memory usage in an effort to minimize the variation of camber angles from the specified constraints. The results prove that the Interior Point method is more accurate and efficient in optimizing the suspension's camber angle across its operational range, followed by other classical methods. © 2024 IEEE.

关键词： Cambers

来源：评论

学校读者我要写书评

暂无评论

Digital Filter Design Using Soft Computing Technique

Digital Filter Design Using Soft Computing Technique

引用

2024 IEEE International Conference on Information Technology, Electronics and Intelligent Communication Systems, ICITEICS 2024

作者： Talwandi, Navjot Singh Swati Chandigarh University Dept of Computer Science Engineering Punjab India

ISBN: (纸本)9798350382693

Digital filter design plays a crucial role in signal processing applications, aiming to enhance, extract, or suppress specific components of a signal. Soft computing techniques have emerged as effective methods for designing digital filters due to their ability to handle complex, non-linear problems. This paper explores the utilization of soft computing approaches, such as neural networks, fuzzy logic, and evolutionary algorithms, in the design and optimization of digital filters. By leveraging the adaptive and learning capabilities of these techniques, this study aims to achieve efficient and optimized filter designs, catering to various signal processing requirements. The comparative analysis of soft computing-based digital filter designs demonstrates their potential in achieving superior performance metrics compared to conventional methods. Moreover, this paper discusses the advantages, challenges, and future directions in employing soft computing techniques for digital filter design, highlighting their potential for addressing complex signal processing tasks in diverse applications. © 2024 IEEE.

关键词： Adaptive filters

来源：评论

学校读者我要写书评

暂无评论

Gender Classification from Thermal Images using CNN

Gender Classification from Thermal Images using CNN

引用

2024 Asia Pacific Conference on Innovation in Technology, APCIT 2024

作者： Gurram, Harika Kethineni, Keerthi Kommineni, Deva Harshini Soumya, Kakani VRSEC Dept. Computer Science & Engineering Vijayawada India

ISBN: (纸本)9798350361537

In this study, two deep learning architectures - AlexNet and InceptionV3 - are used to evaluate gender categorization using thermal imagery. One of the most promising techniques for classifying gender is thermal imaging, which offers distinct insights into physiological traits. Divided into separate training and testing subsets, the dataset is made up of carefully preprocessed thermal pictures. InceptionV3, known for its complex design combining inception modules, and AlexNet, a pioneering convolutional neural network (CNN), are refined on the training data to adjust to the complexities of gender categorization. Then, in order to measure the performance of the trained models, they are rigorously evaluated on the testing set. Specifically, their accuracy is evaluated. Experimental findings show that InceptionV3 performs better than AlexNet, with an accuracy of 92.3% as opposed to 82.6% for AlexNet. This significant disparity highlights how much better InceptionV3 is at identifying subtle thermal patterns and characteristics, which improves gender categorization accuracy. The work makes a substantial contribution to the rapidly developing area of thermal imagingbased gender categorization by highlighting how crucial it is to use advanced deep learning architectures in order to improve performance and accuracy. Subsequent investigations might delve into novel methodologies, including multi-modal fusion or sophisticated methods, to enhance precision and resilience in tasks using thermal-based gender categorization. © 2024 IEEE.

关键词： AlexNet Convolutional Neural networks Deep learning Gender classification Inception V3 Thermal images

来源：评论

学校读者我要写书评

暂无评论

Unveilling the Effectiveness of LSTM with TF-IDF in Assamese Poem Classification:A Comparative Analysis with Conventional and Deep Learning Approaches 15

Unveilling the Effectiveness of LSTM with TF-IDF in Assamese...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Dutta, Bikokhita Neog, Mandira Baruah, Nomi Dibrugarh University Computer Science & Engineering Dept Dibrugarh India

ISBN: (纸本)9798350370249

The classification of Indian poetry extends to various genres reflecting the rich cultural heritage and linguistic diversity. In this paper we are classifying the Assamese poems according to their sentiments and implementing it by using one of the deep learning approach i.e. Long short-term memory (LSTM) with TFIDF (Term Frequency-Inverse Document Frequency) vectorization. For our study we have collected a dataset of 341 Assamese poems, categorized into four themes such as 'biroh' (sadness),'prem' (love),'prokriti' (nature) and 'swadekh prem' (patriotic).We are also comparing the experimental outcome given by our proposed model with some other machine learning and deep learning approaches like Naive Bayes (NB), Support Vector Machine (SVM) and Convolution Neural Network (CNN). Among these our proposed model gives a higher accuracy of 94%, surpassing the performance of other models. © 2024 IEEE.

关键词： Assamese Convolution Neural Network(CNN) Long Short Term Memory(LSTM) NB(Naive Bayes) poem Support Vector Machine(SVM) TF-IDF

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 << < 18 19 20 21 22 23 24 25 26 27 > >>

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：