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

59,774 篇 会议
10,519 篇 期刊文献
560 册 图书

馆藏范围

70,853 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

46,079 篇 工学
- 35,532 篇 计算机科学与技术...
- 29,592 篇 软件工程
- 10,838 篇 信息与通信工程
- 6,625 篇 控制科学与工程
- 4,450 篇 电气工程
- 4,323 篇 生物工程
- 4,187 篇 电子科学与技术（可...
- 3,387 篇 生物医学工程（可授...
- 2,645 篇 光学工程
- 2,436 篇 机械工程
- 1,909 篇 仪器科学与技术
- 1,795 篇 动力工程及工程热...
- 1,741 篇 化学工程与技术
- 1,433 篇 安全科学与工程
- 1,311 篇 建筑学
- 1,206 篇 交通运输工程
23,935 篇 理学
- 14,850 篇 数学
- 5,390 篇 物理学
- 4,830 篇 生物学
- 4,419 篇 统计学（可授理学、...
- 2,643 篇 系统科学
- 1,873 篇 化学
12,208 篇 管理学
- 6,613 篇 管理科学与工程(可...
- 6,216 篇 图书情报与档案管...
- 3,830 篇 工商管理
2,665 篇 医学
- 2,341 篇 临床医学
- 2,203 篇 基础医学(可授医学...
- 1,427 篇 药学(可授医学、理...
2,151 篇 法学
- 1,798 篇 社会学
1,251 篇 经济学
- 1,250 篇 应用经济学
1,159 篇 教育学
895 篇 农学
287 篇 文学
149 篇 军事学
88 篇 艺术学
42 篇 哲学
18 篇 历史学

主题

1,782 篇 computer science
1,643 篇 accuracy
1,545 篇 computational mo...
1,462 篇 feature extracti...
1,209 篇 training
1,018 篇 deep learning
947 篇 machine learning
832 篇 data mining
795 篇 predictive model...
780 篇 semantics
746 篇 real-time system...
712 篇 support vector m...
708 篇 artificial intel...
696 篇 data models
668 篇 computer archite...
589 篇 visualization
574 篇 optimization
557 篇 convolutional ne...
553 篇 internet of thin...
533 篇 neural networks

机构

90 篇 institute of inf...
84 篇 dept. of compute...
83 篇 north-west unive...
82 篇 dept. of compute...
81 篇 infn sezione di ...
76 篇 infn sezione di ...
74 篇 institut univers...
68 篇 national centre ...
66 篇 università di ca...
60 篇 dept. of compute...
56 篇 dept. of compute...
56 篇 dept. of compute...
54 篇 dept. of informa...
52 篇 school of automa...
46 篇 leiden universit...
44 篇 dept. of compute...
42 篇 infn lnf via enr...
42 篇 in2p3 lpc campus...
39 篇 dept. of compute...
38 篇 dept. of compute...

作者

94 篇 ardid m.
93 篇 ferrara g.
87 篇 calvo d.
80 篇 chen a.
78 篇 gal t.
77 篇 bozza c.
63 篇 ahmad jalal
62 篇 kalekin o.
60 篇 kulikovskiy v.
44 篇 huang f.
42 篇 díaz a.f.
41 篇 gagliardini s.
40 篇 benoit d.m.
40 篇 eddymaoui a.
40 篇 labalme m.
36 篇 androulakis g.
34 篇 de palma m.
31 篇 guru prasad m.s.
30 篇 khatun a.
28 篇 boumaaza j.

语言

64,883 篇 英文
5,292 篇 其他
499 篇 中文
106 篇 日文
59 篇 朝鲜文
11 篇 德文
7 篇 法文
6 篇 西班牙文
5 篇 斯洛文尼亚文
3 篇 葡萄牙文

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

共 70853 条记录，以下是241-250 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：

Flood and Loot Attack in Distributed Routing Protocols in PCNs 17

Flood and Loot Attack in Distributed Routing Protocols in PC...

引用

17th International Conference on COMmunication Systems and NETworkS, COMSNETS 2025

作者： Sharma, Neeraj Kapoor, Kalpesh Indian Institute of Technology Dept. of Computer Science & Engg. Guwahati India Indian Institute of Technology Dept. of Mathematics Guwahati India

ISBN: (纸本)9798331531195

Payment Channel Networks (PCNs) can significantly enhance the scalability of blockchain transactions without requiring major modifications to the underlying distributed ledger protocol. However, to enable efficient and secure payment routing over multiple channels, PCNs necessitate additional components: an onion routing protocol for anonymity and a locking mechanism to prevent race conditions. Unfortunately, these mechanisms can be exploited by malicious actors to launch flood and loot attacks. We investigate the impact of flood and loot attacks on networks that employ local knowledge-based routing algorithms. In these scenarios, malicious nodes can manipulate hash-locks to unfairly capitalize on the benefits of participating nodes. We specifically examine the effects of these attacks on three popular routing algorithms: Swift, Speedy Murmurs, and Silent Whispers. Our analysis employs metrics like attack gain, attack cost, and transaction ratio to assess the impact of the attacks. Our simulation-based results demonstrate that, even with a relatively small fraction of malicious nodes (between 0.66% and 3.3%), the average attack transaction ratio across all evaluated routing algorithms is a concerning 16.23%. © 2025 IEEE.

关键词： Distributed ledger

来源：评论

学校读者我要写书评

暂无评论

Neuro-Insights: Unveiling the Power of Deep Learning for Brain Tumor Detection in Neuroimaging

Neuro-Insights: Unveiling the Power of Deep Learning for Bra...

引用

2024 IEEE International Conference on Computing, Semiconductor, Mechatronics, Intelligent Systems and Communications, COSMIC 2024

作者： Keshava Reddy, V. Dhanush Reddy, Kotte Sai Jayanth, Bobbili Sai Guru Prasad, M.S. Joshi, Aditi Vatsyayan, Shradha Dept. of Computer Science and Engg. Dehradun India

ISBN: (纸本)9798331517892

The accurate identification and segmentation of brain tumors using the medical imaging of the data is crucial for patient treatment planning. This study will look into advanced deep learning techniques, including Residual Networks (RNs), Transfer Learning (TL), Generative Adversarial Networks (GANs), Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Ensemble Learning (EL), and Hybrid Deep Learning (HDL), to achieve their precise and accurate results. Comprehensive evaluation using metrics like F1-score, accuracy, validation loss, precision, recall, and specificity score has been performed on a dataset of 7023 MRI images. The findings highlight the superior performances of RNs, CNNs, and RNNs, with F1 scores of 97.75%, 98.25%, and 98.75%, respectively, along with high accuracies and precisions. GANs demonstrate excellent recall, while TL, EL, and HDL exhibit nuanced trade-offs. TL enhances its performance with limited data, GANs aid data synthesis, and EL combines models for their robust predictions. However, the innovative HDL method integrates with diverse models to capture complementary features, leading to precise brain tumor classification. This synergistic blend of deep learning approaches the representation of a significant advancement towards the intelligent diagnostic system for early and accurate brain tumor detection in the medical imaging field. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

U-NET based CT Image reconstruction and segmentation using Deep Learning Layer structure

U-NET based CT Image reconstruction and segmentation using D...

引用

2024 International Conference on Frontiers of Information Technology, FIT 2024

作者： Abbasi, Altamash Ahmad Farooqi, Ashfaq Hussain Dept. of Computer Science Air University Islamabad Pakistan

ISBN: (纸本)9798331510503

CT imaging is critical for medical diagnostics, yet traditional reconstruction methods often struggle with noise and artifact reduction while maintaining image clarity. In this research work, an advanced methodology for computed tomography image reconstruction leveraging a U-Net model, combined with preprocessing through bilateral filtering and subsequent image segmentation. U-Net model is trained to reconstruct high-fidelity CT images from sparse-view data, ensuring superior detail preservation and artifact minimization. Our approach also incorporates a bilateral filter during preprocessing to enhance edge preservation and reduce noise. Post-reconstruction, we employ segmentation to isolate and highlight critical anatomical structures, further improving the interpretability and diagnostic value of the images. The de-noised image is then segmented using thresholding scheme. 2016 AAPM dataset has been used to check the effectiveness of the proposed methodology, demonstrating significant improvements in image quality metrics compared to conventional reconstruction techniques. Our results indicate that the integration of bilateral filtering and U-Net-based reconstruction, followed by precise segmentation, offers a robust solution for enhancing CT imaging quality. Our proposed approach has obtained PSNR of 30.461, NMSE of 0.036 and SSIM of 0.863. This approach holds substantial potential for clinical applications, providing clearer, more accurate images for diagnosis and treatment planning. © 2024 IEEE.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Invited Paper: Blockchains made Lightweight: A Median Rule for State Machine Replication

Invited Paper: Blockchains made Lightweight: A Median Rule f...

引用

2024 Workshop on Advanced Tools, Programming Languages, and PLatforms for Implementing and Evaluating algorithms for Distributed Systems, ApPLIED 2024, co-located with PODC 2024

作者： Dou, Jinfeng Scheideler, Christian Dept. of Computer Science Paderborn University Paderborn Germany

ISBN: (纸本)9798400706707

In this short paper we present our ongoing research on a lightweight blockchain based on a solution for state machine replication with proofs. More precisely, we show how to adapt a simple median rule for the stabilizing consensus problem [4] to obtain a stabilizing solution for state machine replication and how to extend it with a Merkle hash forest so that clients can easily prove for any of their committed commands that it has indeed been committed. Copyright © 2024 held by the owner/author(s). Publication rights licensed to ACM.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Predicting Blood Hemoglobin Level With Machine Learning And Spectroscopy 2

Predicting Blood Hemoglobin Level With Machine Learning And ...

引用

2nd International Conference on Advances in Computation, Communication and Information Technology, ICAICCIT 2024

作者： Kumar, Atul Kumar, Vikas Debnath, Drubajyoti Sorout, Deepansh Chawla, Pronika Tyagi, Shobha Dept. of Computer Science SET MRIIRS Faridabad India

ISBN: (纸本)9798331541217

Anemia, a widespread health condition characterized by low hemoglobin or red blood cell levels, remains a significant global concern, especially in resource-limited settings. The current methods for diagnosing anemia often require invasive blood tests, which can be costly and inaccessible for routine monitoring. This study presents a Python-based model aimed at providing a non-invasive, automated method for anemia detection by analyzing the conjunctival region of the eye. Utilizing Haar cascade classifiers for precise eye region detection and OpenCV for image processing, the model efficiently extracts and analyzes the RGB values of the conjunctiva. These values are compared to established thresholds indicative of hemoglobin deficiency, allowing for a preliminary diagnosis. The model, trained and tested with real-world image data, offers a promising solution to early anemia detection, combining rapid processing, cost-effectiveness, and accessibility. The strength of this work lies in its automation, affordability, and potential for application in remote or underserved areas where traditional diagnostic methods are not readily available. © 2024 IEEE.

关键词： Photoplethysmography

来源：评论

学校读者我要写书评

暂无评论

Efficient Retraining for Continuous Operability Through Strategic Directives 23

Efficient Retraining for Continuous Operability Through Stra...

引用

23rd IEEE International Conference on Machine Learning and Applications, ICMLA 2024

作者： Nakasone, Gentoku Motokawa, Yoshinari Miyashita, Yuki Sugawara, Toshiharu Waseda University Dept. of Computer Science Tokyo Japan

ISBN: (纸本)9798350374889

We introduce a method to ensure the controllability of agents in pretrained networks, anticipating changes in managerial requirements and environmental conditions. Advances in multi-agent deep reinforcement learning (MADRL) have fostered sophisticated cooperative behaviors in multi-agent systems in which agents share and execute various complex tasks. However, retraining MADRL systems to adapt to new conditions is costly, because many agents are involved. Our approach introduces several types of directives, termed destination channels (DCs), which allow agents to experience diverse coordination patterns during training without detailed instructions. When changes occur, the system manager assigns appropriate DCs to each agent to facilitate adaptation and maintain a continuous operation. We conducted experiments using object-collection games to evaluate our proposed method by comparing the number of objects recovered and the learning speed of our method with those of existing methods, an implicit quantile network (IQN), and a traditional deep Q-network (DQN). The experimental results demonstrate that agents using this method adapt more swiftly to environmental changes during retraining than baseline methods, sustaining performance without significant degradation. © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Drone-based Activity Recognition via Dynamic Features and Deep Learning

Drone-based Activity Recognition via Dynamic Features and De...

引用

2024 International Conference on Frontiers of Information Technology, FIT 2024

作者： Abbas, Yawar Jalal, Ahmad Dept. of Computer Science Air University Islamabad Pakistan

ISBN: (纸本)9798331510503

computer vision technology has improved to the point where it has led to the development of sophisticated algorithms that are able to reliably recognize human actions from RGB videos that have been acquired by drone cameras. In spite of the fact that it has a great deal of potential, human action recognition is confronted with a multitude of obstacles, such as variances in action execution, restricted camera views, and field of view limits. The purpose of this research study is to offer a system that addresses these issues by employing RGB films obtained by drone cameras as input. The first step in the methodology involves breaking the video down into individual frames, which is then followed by the application of preprocessing techniques. Resizing the photos, turning them to grayscale in order to lessen the computing load, and removing background noise are all strategies that are utilized in these techniques. Subsequently, we use YOLOv7 algorithm for recognize human’s activity from the photos and extract the skeleton points of those individuals. At this stage, we proceed to extract a variety of characteristics, such as joint angles, histograms of oriented gradients (HOG), and three-dimensional point clouds. These features are optimized through the use of stochastic gradient descent (SGD), and action categorization is carried out through the utilization of a deep learning assembler. Experiments are carried out with the Drone Action dataset and the UCF-ARG dataset in order to validate the approach. The results of these experiments demonstrate that the approach is capable of achieving notable action recognition accuracies of 85% and 75%, respectively. © 2024 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

The Future of Graphic Novel Translation: Fully Automated Systems

The Future of Graphic Novel Translation: Fully Automated Sys...

引用

2024 International Conference on Knowledge Engineering and Communication Systems, ICKECS 2024

作者： Harshavardhan, G. Kang, Sandeep Singh Kaur, Geet Kiran Singla, Sanjay Chandigarh University Dept. of Computer Science Punjab India

ISBN: (纸本)9798350359688

The paper represents an approach to completely automate the process of translating graphic novels such as comics. With this approach, the aim to significantly lower the barrier caused by linguistic differences. This should help both comic creators and readers. Comics being a combination of both text and images are far more complicated to translate as compared to texts such as novels. Unlike translation of text which can be seen as an ever growing representative of what Natural Language Processing (NLP) can do, comic translation has seen few research publications that tackle the issue. Most approaches are theoretical in nature and even fewer cover the entire process, sticking to automating certain portions of the process instead. To solve this problem, we must first break down the process into a series of tasks that can be handled separately. This approach will be modular in nature where certain steps can be swapped out for more effective ones, as and when they appear. As this project involves a variety of fields such as NLP, Artificial Neural Networks (ANN), and Optical Character Recognition (OCR), each step may use various artificial intelligence or computer vision based techniques. This approach is inspired by the process of translating comics by human which includes various professionals such as translators, cleaners, typesetters, editors, etc. Though inspired by this, it will not strictly be limited to this, as there are various unique challenges and opportunities that arise when using a computer instead of a human. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Wearable Sensor-Based Activity Recognition over Statistical Features Selection and MLP Approach 3

Wearable Sensor-Based Activity Recognition over Statistical ...

引用

3rd International Conference on Emerging Trends in Electrical, Control, and Telecommunication Engineering, ETECTE 2024

作者： Nazar, Fakhra Jalal, Ahmad Dept. of Computer Science Air University Islamabad Pakistan

ISBN: (纸本)9798331504861

Supervising and examining the physical activities of different individuals by using wireless sensors is beneficial in favor of recognizing postural positioning and moving actions in the everyday ambiance. Accelerometers have been exercised in intelligent environments to identify human activities for many years. Using these accelerometer sensors and human activity recognition systems, people going through many sicknesses and illnesses can be proficiently scrutinized, and thus remedial medication can be dispensed in a well-timed approach. In this research paper, a naïve, and intricate technique founded on certain time domain features on the way to classify the physical activities is suggested. Feature extraction is a momentous step in HAR, and in this study, six statistical features were obtained from the preprocessed data. To further optimize the feature set, the Binary Grey Wolf Optimizer (GWO) was integrated. Further, a Multilayer Perceptron (MLP) was utilized for activity recognition to distinguish between the six activity classes. MLP has the advantage of finding non-linear patterns in data, the algorithm possesses powerful features of reducing overfitting in the data and good generality. It also offers resistance to noises usually experienced in the sensor data. Experimental results evaluated that the proposed framework achieved 87.14% recognition accuracy. This validates that the suggested framework can be used to observe physical activities and discriminate between healthy and unhealthy patients. ©2024 IEEE.

关键词： Wearable sensors

来源：评论

学校读者我要写书评

暂无评论

Synthetic Generation of Spatial Polygons On Cloud 3

Synthetic Generation of Spatial Polygons On Cloud

引用

3rd International Conference for Innovation in Technology, INOCON 2024

作者： Ankur, D. Mrunalini Thamankar, D. Rai, Nireeksha D. Veeresh, R.G. Auradkar, Prafullata Pes University Dept. of Computer Science Bangalore India

ISBN: (纸本)9798350381931

Spatial Data generated from varied resources are collected for applications in analysis of land-patterns and population growth among many. While the data collected is vast, majority of it is unavailable in formats or quantity required for research projects. Current data generation tools produce overly rigid geometric objects which do not reflect real-world spatial variations of polygons. We present a web based synthetic generator tool for spatial polygons capable of generating an impressive 0.7 million polygons which would take a range of user inputs including spikiness, irregularity and dataset size to generate requirement quenching data. Generated polygons are thus subject to rigorous benchmarking to ensure that they are close to real-world in addition to being geometrically valid. We further explore the computational problems and propose a spark-based approach of parallel computation, resulting in a remarkable 50% reduction in processing time. © 2024 IEEE.

关键词： Population statistics

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 << < 21 22 23 24 25 26 27 28 29 30 > >>

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：