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

40,746 篇 会议
2,947 册 图书

馆藏范围

43,692 篇 电子文献
3 种 纸本馆藏

日期分布

学科分类号

40,000 篇 工学
- 38,643 篇 计算机科学与技术...
- 7,089 篇 软件工程
- 3,996 篇 信息与通信工程
- 3,136 篇 电气工程
- 2,304 篇 控制科学与工程
- 761 篇 生物医学工程（可授...
- 431 篇 生物工程
- 320 篇 机械工程
- 293 篇 交通运输工程
- 158 篇 测绘科学与技术
- 156 篇 土木工程
- 145 篇 光学工程
- 136 篇 建筑学
3,350 篇 管理学
- 1,879 篇 管理科学与工程(可...
- 1,145 篇 图书情报与档案管...
- 860 篇 工商管理
3,075 篇 理学
- 1,889 篇 数学
- 815 篇 生物学
- 456 篇 统计学（可授理学、...
- 340 篇 物理学
- 178 篇 系统科学
1,487 篇 医学
- 937 篇 临床医学
- 683 篇 基础医学(可授医学...
- 235 篇 特种医学
- 138 篇 药学(可授医学、理...
1,478 篇 教育学
- 1,396 篇 教育学
550 篇 文学
- 371 篇 外国语言文学
- 178 篇 新闻传播学
415 篇 经济学
- 317 篇 理论经济学
374 篇 法学
- 340 篇 社会学
177 篇 艺术学
95 篇 历史学
59 篇 农学
11 篇 军事学

主题

1,862 篇 artificial intel...
1,187 篇 machine learning
898 篇 deep learning
779 篇 computer communi...
668 篇 information syst...
558 篇 computer applica...
328 篇 computer systems...
314 篇 cloud computing
304 篇 clustering
299 篇 security
288 篇 internet of thin...
276 篇 classification
264 篇 software enginee...
235 篇 information syst...
229 篇 computer imaging...
224 篇 data mining
218 篇 software enginee...
208 篇 data mining and ...
205 篇 ontology
180 篇 computers and ed...

机构

83 篇 univ chinese aca...
76 篇 univ dist franci...
69 篇 chinese acad sci...
67 篇 shanghai univ sc...
48 篇 tsinghua univers...
43 篇 natl res univ hi...
39 篇 huazhong univers...
35 篇 harbin inst tech...
33 篇 tsinghua univ de...
30 篇 shanghai jiao to...
30 篇 pontificia univ ...
29 篇 harbin universit...
27 篇 polytechnic inst...
27 篇 chinese acad sci...
26 篇 lomonosov moscow...
25 篇 chongqing univ s...
25 篇 beijing univ pos...
24 篇 university of cr...
24 篇 hunan univ coll ...
23 篇 univ nacl colomb...

作者

58 篇 kim tai-hoon
53 篇 lima jose
43 篇 o'connor rory v.
37 篇 wang lei
34 篇 liu yang
33 篇 zhang lin
31 篇 kim seoksoo
30 篇 wang jing
28 篇 sabu m. thampi
28 篇 crawford broderi...
26 篇 zhang lei
25 篇 li yang
25 篇 li li
24 篇 wang jian
21 篇 zhang min
20 篇 hassanien aboul ...
19 篇 li peng
19 篇 serra roberto
18 篇 valencia-garcia ...
18 篇 li xin

语言

43,527 篇 英文
655 篇 中文
1 篇 丹麦文

检索条件"丛书名=Communications in Computer and Information Science"

共 43693 条记录，以下是1451-1460 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：

Enhancing Writer Retrieval in Handwritten Documents Through Fusion of Deep Features and Multi-oriented Histograms 4th

Enhancing Writer Retrieval in Handwritten Documents Through ...

引用

4th International Conference on Intelligent Systems and Pattern Recognition-ISPR

作者： Bouibed, Mohamed Lamine Nemmour, Hassiba Arab, Naouel Chibani, Youcef Univ Sci & Technol Houari Boumediene USTHB Lab Ingn Syst Intelligents & Commun LISIC Fac Elect Engn Algiers 16111 Algeria

ISBN: (纸本)9783031821554;9783031821561

In this study, we introduce a novel approach to writer retrieval systems, fundamental in handwritten document analysis, comprising feature generation and dissimilarity computation steps. Our innovation lies in the introduction of a new shape descriptor based on the Multi-Oriented calculation of Histogram Of Templates (HOT), designed to enhance the characterization of handwritten documents by incorporating orientation concepts without relying on a central pixel. Additionally, in the retrieval phase, we employ an SVM classifier based on dissimilarity learning, combining MO-HOT features with deep features. We conduct performance assessments on the CVL dataset, containing handwritten documents from 300 individuals, where our combined system outperforms several state-of-the-art systems, achieving a Mean Average Precision (MAP) of 92.89%.

关键词： Dissimilarity learning Multi-oriented Histogram Of Templates ResNet-20 VGG-16 SVM-based Writer retrieval

来源：评论

学校读者我要写书评

暂无评论

Complex Environment-Based Multiagent Swarm Cooperative Encirclement of Unmanned Surface Vehicle Clusters 5th

Complex Environment-Based Multiagent Swarm Cooperative Encir...

引用

5th China Intelligent Robotics Academic Conference

作者： Mu, Dongdong Wang, Fei Han, Xinjie Fan, Yunsheng Dalian Maritime Univ Maritime Elect Engn Dalian 116026 Peoples R China

ISBN: (纸本)9789819616138;9789819616145

This paper conducts an in-depth study on the task of unmanned surface vehicle (USV) swarm encirclement in complex maritime environments by employing a novel network-based model known as the game theoretic utility tree (GUT). Specifically, the GUT model, which can handle the potential relationships between multiple agents and provides a utility maximization decision framework for each agent, is first utilized. In the field of pursuit-evasion games, it offers a cooperative pursuit strategy for capturing evaders, where agents in the multiagent system (MAS) can adopt appropriate decision-making strategies on the basis of their respective tasks and objectives. In addition, how to achieve effective collaborative operations of the USV swarm in complex maritime environments to complete the encirclement task is further investigated. The effectiveness of the proposed methods is verified through simulation experiments, which demonstrate that when factors such as the number of encirclement vehicles and obstacles are considered, the GUT model significantly improves the efficiency and success rate of encirclement. These studies, address how to guide the USV swarm to carry out effective encirclement in complex maritime environments via the game theoretic utility tree model, thereby increasing the execution efficiency and success rate of encirclement missions.

关键词： USV encirclement evasion obstacles game theory cooperative control

来源：评论

学校读者我要写书评

暂无评论

High-Capacity Coverless Steganography Using Pixel Gradient Analysis 4th

High-Capacity Coverless Steganography Using Pixel Gradient A...

引用

4th International Conference on Advanced Network Technologies and Intelligent Computing-ANTIC-Annual

作者： Ghosh, Aditya Sayeef, Md Patra, Aritra Kumar Indu, Pabak Bhattacharyya, Souvik Univ Burdwan Univ Inst Technol Dept CSE Bardhaman 713104 West Bengal India Univ Engn & Management Dept CSE AIML & CSBS Inst Engn & Management Kolkata 700091 West Bengal India Inst Engn & Management Dept CSE AIML & CSBS IEM Ctr Excellence Cloud Comp & IoT Kolkata 700091 India Inst Engn & Management IEM Ctr Excellence Data Sci Dept CSE AIML & CSBS Kolkata 700091 India

ISBN: (纸本)9783031837920;9783031837937

Since the dawn of Internet, we have been able to do so much more work in a fixed amount of time. As time passed, the technologies involved became faster and more efficient in transmission and processing of data. Nowadays important information's like banking details and passwords are saved digitally within a computer. As more and more people are using internet for communication and other requirements, they are becoming vulnerable to cyber-attacks. Safety and security of personal data has become utmost priority at this point. Tools like steganography become useful in this regard. We will be looking at a coverless image steganography method leveraging pixel gradient analysis to securely embed data into synthetic images. The process utilizes StyleGAN2 with Adaptive Data Augmentation (ADA) to generate synthetic images. This method focuses on RGB images, splitting them into their respective R, G and B channels and further subdividing the images layers into smaller cells. Every cell is used to map a particular portion of the secret information. Since this technique uses mostly mapping and only requires modification, when necessary, the amount of data that gets changed or manipulated is very less. The technique ensures minimal changes to the image, keeping modifications below 2 values every 9 values in the worst case. The proposed method can be highly scalable and secure solution for hiding large amounts of data without drawing attention, as it doesn't modify the image's visibly distinct features. It proves robust against steganalysis tools and offers higher capacity and security compared to prior models, making it an ideal approach for covert data transmission.

关键词： StyleGAN2 Steganography Coverless

来源：评论

学校读者我要写书评

暂无评论

Detecting Raspberry Ripeness Across Different Growth Stages Using YOLOv8 4th

Detecting Raspberry Ripeness Across Different Growth Stages ...

引用

4th International Conference on Intelligent Systems and Pattern Recognition-ISPR

作者： Alkhudaydi, Tahani Univ Tabuk Dept Comp Sci Tabuk 71491 Saudi Arabia

ISBN: (纸本)9783031821523;9783031821530

Raspberries, valued at $1.5 billion in 2018 face challenges in cultivation especially in monitoring growth stages. Manual monitoring is labor intensive and impractical which can lead to poor crop management and productivity issues. The use of computer vision technology, particularly, the YOLO algorithm known for its real time object detection performance has transformed agriculture by enabling efficient crop monitoring. However its application in detecting raspberries at different growth stages is still relatively unexplored. This study presents a comprehensive analysis of four YOLOv8 variations to identify and locate raspberries by their ripeness levels. It focuses on the RaspberrySet, a challenging dataset with densely overlapped raspberries from various growth stages. Through experiments involving 15 configurations of YOLOv8 we were able to determine the effective hyperparameters for this task. The results indicate that tuning specific hyperparameters significantly enhances classification accuracy with all variants of YOLOv8 outperforming the baseline model by an average of 5.91%. The YOLOv8l model emerged as the accurate among them achieving the mAP50 and mAP50 95 scores at 78.6% and 47.5%, respectively. However it struggles when it comes to identifying damaged buds due to insufficient training data. Despite its accuracy, the YOLOv8l model exhibited the longest inference time which indicate the need for faster and more efficient models suitable for deployment in agricultural environments. The next phase of research aims to develop a lightweight model that leverages YOLOv8l knowledge to enhance performance while maintaining acceptable speed.

关键词： YOLOv8 Yield estimation Crop Monitoring Raspberry Deep Learning

来源：评论

学校读者我要写书评

暂无评论

Feature Representation Learning Based on Graph Curvature-Revised Deep Graph Learning 4th

Feature Representation Learning Based on Graph Curvature-Rev...

引用

4th International Conference on Artificial Intelligence Logic and Applications

作者： Hou, Jiawei Li, Yangyang Fei, Chaoqun Shanghai Ocean Univ Coll Informat Shanghai 201306 Peoples R China Chinese Acad Sci Acad Math & Syst Sci Beijing 100190 Peoples R China

ISBN: (纸本)9789819603534;9789819603541

Feature representation learning is the task of learning appropriate low-dimensional representations from raw high-dimensional data. Graph learning is a feasible method for this task. Due to the shallow graph learning approaches can not capture deep structure, deep graph learning approaches like Graph Neural Networks (GNNs) are more suitable approaches for mining the deep structure within data. However, GNNs cannot be directly applied to image data. Existing approaches applying GNNs to image data have issues with high computational complexity, large memory consumption, and difficulties in data annotation. Therefore, we proposed a novel learning framework to deal with this problem. We first construct the affinity graph based on the k-nearest neighbor method, then utilize graph curvature to revise the weight relationships between graph nodes, and finally integrate revised weight information into GNN to learn the representation of nodes. Experiments on public datasets demonstrate that our method outperforms both the methods based on shallow graph learning and the methods of direct application of GNNs to image data, validating the effectiveness of our approach.

关键词： Deep Graph Learning Graph Neural Network Graph Curvature

来源：评论

学校读者我要写书评

暂无评论

Rapid Detection of Formaldehyde Emission from Wood-Based Panels Based on the IPOA-XGBoost 5th

Rapid Detection of Formaldehyde Emission from Wood-Based Pan...

引用

5th International Conference on Neural Computing for Advanced Applications (NCAA)

作者： Wang, Yinuo Zheng, Huanqi Wu, Qiang Zhou, Yucheng Shandong Jianzhu Univ Sch Informat & Elect Engn Jinan 250101 Shandong Peoples R China Shandong Jianzhu Univ Sch Architecture & Urban Planning Jinan 250101 Shandong Peoples R China Natl Ctr Qual Inspect & Test Decorat Mat Jinan 250102 Peoples R China

ISBN: (纸本)9789819770038;9789819770045

Aiming at the complexity of the process of analyzing formaldehyde composition by physicochemical methods in the process of formaldehyde emission detection by the full-scale chamber method, and the problem of bias in the accuracy of sensor method, the IPOA-XGBoost formaldehyde emission modified deviation model for a class of panels is proposed for the fast and accurate detection of formaldehyde emission from wood-based panels. The model utilizes data obtained from the electrochemical sensor as input. The output is the formaldehyde emission measured by the full-scale chamber method. The model is fitted using the extreme gradient boosting (XGBoost). To address the weak optimization ability in the pelican optimization algorithm (POA), random opposition-based learning is employed to establish the initial population. Additionally, nonlinear weighting factors and a sparrow alert mechanism perturbation strategy are introduced to enhance the ability of global optimization and escape local optimal solution. The improved POA (IPOA) is used to optimize the key parameters of XGBoost, and then the modified deviation model of formaldehyde emission of the IPOA-XGBoost wood-based panel is constructed, and compared with four machine learning models. Experimental results indicate that the proposed model achieves a coefficient of determination of 0.9701 and a root mean square error of 2.7648e-03. Furthermore, it exhibits lower prediction errors compared to other models tested herein. This provides an effective and reliable solution for rapid detection of formaldehyde emission in wood-based panels.

关键词： The full-scale chamber Improved pelican optimization algorithm Extreme gradient boosting Formaldehyde emission detection

来源：评论

学校读者我要写书评

暂无评论

Exploring and Learning Structure: Active Inference Approach in Navigational Agents 5th

Exploring and Learning Structure: Active Inference Approach ...

引用

5th International Workshop on Active Inference

作者： de Tinguy, Daria Verbelen, Tim Dhoedt, Bart Univ Ghent Ghent Belgium Verses AI New Westminster BC Canada

ISBN: (纸本)9783031771378;9783031771385

Drawing inspiration from animal navigation strategies, we introduce a novel computational model for navigation and mapping, rooted in biologically inspired principles. Animals exhibit remarkable navigation abilities by efficiently using memory, imagination, and strategic decision-making to navigate complex and aliased environments. Building on these insights, we integrate traditional cognitive mapping approaches with an Active Inference Framework (AIF) to learn an environment structure in a few steps. Through the incorporation of topological mapping for long-term memory and AIF for navigation planning and structure learning, our model can dynamically apprehend environmental structures and expand its internal map with predicted beliefs during exploration. Comparative experiments with the Clone-Structured Graph (CSCG) model highlight our model's ability to rapidly learn environmental structures in a single episode, with minimal navigation overlap. This is achieved without prior knowledge of the dimensions of the environment or the type of observations, showcasing its robustness and effectiveness in navigating ambiguous environments.

关键词： exploration active inference topological graph structure learning

来源：评论

学校读者我要写书评

暂无评论

Computational Performance Analysis of PCA Enhanced AnEn Method

Computational Performance Analysis of PCA Enhanced AnEn Meth...

引用

4th International Conference on Advanced Research in Technologies information Innovation and Sustainability-ARTIIS-Annual

作者： Breve, Murilo Montanini Camargos, Ana Flavia P. Rufino, Jose Balsa, Carlos NETZSCH Ind & Comercio Equipamentos Moagem Ltd BR-89107000 Pomerode SC Brazil CEFET RJ campus Maracan Ave Maracana 229 BR-20271110 Rio De Janeiro RJ Brazil Inst Politecnol Braganca Res Ctr Digitalizat & Intelligent Robot CeDRI Lab Sustentabilidade & Tecnol Regioes Montana Sus P-5300253 Braganca Portugal

ISBN: (纸本)9783031834349;9783031834356

The Analog Ensemble (AnEn) method allows to reconstruct incomplete time series, based on correlated series with full records. It has been extensively applied to meteorological data, which may involve many variables and stations, and span many years, slowing down the reconstruction. To accelerate this process, Principal Component Analysis (PCA) may be employed, to combine several input series into a few principal components (PCs), over which AnEn is then applied for a faster data reconstruction. The integration of PCA with K-means clustering further amplifies efficiency. In this paper, multicore-based implementations of non-PCA and PCA-based methods, in MATLAB, R, and Python, were scrutinized to ascertain numerical consistency and evaluate relative performance. The experiments show that when using PCA, accuracy is kept, or even improved, despite lowering the number of input time series. Performance-wise, the experiments revealed a distinct edge for the Python code, for which the benefits of parallel processing were most evident. Preliminary results are also shown for a Python variant that exploits GPUs for the analog search, with very promising speedups.

关键词： Meteorological records reconstruction Analog ensemble K-means clustering PCA MATLAB R Python CUDA

来源：评论

学校读者我要写书评

暂无评论

Optimized LeNET Based CNN and Convolutional BLSTM with He Initialization for Character-Level Classification in Tal-Patra Manuscripts 4th

Optimized LeNET Based CNN and Convolutional BLSTM with He In...

引用

4th International Conference on Advanced Network Technologies and Intelligent Computing-ANTIC-Annual

作者： Devi, M. Poornima SRIHER Sri Ramachandra Fac Engn & Technol Chennai Tamil Nadu India

ISBN: (纸本)9783031837920;9783031837937

This paper gives a systematic evaluation of character categorization for the Tal-Patra script, which is one of the most difficult task in contemporary research. Pre-processed and segmented characters from the Tal-Patra manuscript, particularly related to healthcare science, were used for classification. Additionally, datasets such as the Tamil vowels character dataset, the University of Jaffna Tamil character dataset, and the Arabic handwritten character dataset were employed to assess the performance of the proposed models. Two models were proposed: an optimized LeNet-based Convolutional Neural Network (CNN) and a Convolutional Bidirectional Long Short-Term Memory (BLSTM) model. He initialization was applied for weight optimization. The classification of Tamil Tal-Patra manuscript characters achieved 97.9% accuracy with the optimized LeNet-based CNN and 85.2% with the convolutional BLSTM. The optimized LeNet-based CNN outperformed state-of-the-art models, establishing new benchmarks in the analysis of the Tamil Tal-Patra manuscript.

关键词： BLSTM CNN LeNET Tal-Patra He initialization

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Approach to the Recognition of Sensitive Health information: LLM and Regular Expressions

A Hybrid Approach to the Recognition of Sensitive Health Inf...

引用

2024 International Workshop on Deidentification of Electronic Medical Record Notes

作者： Huang, Tsai-Yuan Shih, Jun-Fu Hsieh, Yun-Chien Feng, Hui-Hsien Natl Kaohsiung Univ Sci & Technol Dept English 1 Univ Rd Kaohsiung 824005 Taiwan

ISBN: (纸本)9789819779659;9789819779666

In the era of digital technology, it is crucial to prioritize privacy protection in healthcare. While Electronic Health Records text notes (EHR text notes) are widely used, securely removing patients' private information from these records presents a significant challenge. This study investigates the utilization of a combination of large language models (LLM) and regular expression techniques to improve the extraction and standardization of Sensitive Health information (SHI) from medical records sourced from Australian institutions. In response to the limitations identified in the initial Pythia language model, a hybrid approach was developed, incorporating both deep learning and regular expressions. The primary aim of the current studywas to enhance the accuracy of SHI recognition in medical records. The study utilized 2294 records for training and 950 records for testing from the institutions, i.e., the University of New South Wales, the Lowy Cancer Research Centre, and the Health science Alliance Biobank. The study employed PyTorch for model training and regular expressions for SHI identification. The results indicated that the hybrid approach highly improved the accuracy of SHI recognition, leading to more satisfactory and complete outcomes. This study contributes to the discussion on optimizing SHI recognition in healthcare datasets and emphasizes the synergy between deep learning and regular expressions. The findings have practical implications for refining healthcare information systems, highlighting the potential of combining advanced language models with rule-based approaches to enhance precision in medical data extraction and standardization.

关键词： Large Language Model Regular Expressions Sensitive Health information Pythia

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 << < 142 143 144 145 146 147 148 149 150 151 > >>

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：