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

1,750 篇 会议
76 册 图书
48 篇 期刊文献

馆藏范围

1,873 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

1,276 篇 工学
- 1,063 篇 计算机科学与技术...
- 564 篇 软件工程
- 213 篇 电气工程
- 213 篇 信息与通信工程
- 211 篇 控制科学与工程
- 103 篇 生物工程
- 90 篇 光学工程
- 81 篇 生物医学工程（可授...
- 76 篇 机械工程
- 57 篇 交通运输工程
- 51 篇 电子科学与技术（可...
- 44 篇 安全科学与工程
- 40 篇 化学工程与技术
- 32 篇 仪器科学与技术
- 24 篇 材料科学与工程（可...
- 21 篇 动力工程及工程热...
- 21 篇 建筑学
430 篇 理学
- 193 篇 数学
- 182 篇 物理学
- 121 篇 生物学
- 63 篇 统计学（可授理学、...
- 42 篇 系统科学
- 34 篇 化学
205 篇 管理学
- 116 篇 管理科学与工程(可...
- 105 篇 图书情报与档案管...
- 42 篇 工商管理
91 篇 医学
- 76 篇 临床医学
- 33 篇 基础医学(可授医学...
- 16 篇 药学(可授医学、理...
28 篇 法学
- 26 篇 社会学
15 篇 教育学
8 篇 农学
7 篇 经济学
7 篇 文学
3 篇 艺术学
2 篇 军事学

主题

244 篇 pattern recognit...
93 篇 real-time system...
91 篇 feature extracti...
83 篇 accuracy
77 篇 artificial intel...
55 篇 face recognition
55 篇 intelligent syst...
54 篇 training
49 篇 deep learning
44 篇 speech recogniti...
41 篇 neural networks
41 篇 machine learning
40 篇 pattern recognit...
38 篇 computer imaging...
38 篇 convolutional ne...
37 篇 object detection
36 篇 learning systems
35 篇 support vector m...
35 篇 object recogniti...
34 篇 cameras

机构

6 篇 hubei key labora...
5 篇 natl inst techno...
5 篇 university of ch...
4 篇 natl inst techno...
4 篇 school of big da...
4 篇 natl inst techno...
4 篇 tongji universit...
4 篇 amrita univ amri...
3 篇 univ chittagong ...
3 篇 csiro ict centre
3 篇 natl. lab. of pa...
3 篇 pattern recognit...
3 篇 university of el...
3 篇 university of an...
3 篇 national laborat...
3 篇 university of mi...
3 篇 universidad esta...
3 篇 birla inst techn...
3 篇 universidad andr...
3 篇 institute of aut...

作者

6 篇 de-shuang huang
5 篇 kang-hyun jo
4 篇 patil nagamma
4 篇 adachi yoshinori
4 篇 sei-ichiro kamat...
4 篇 ma songde
4 篇 donald c. wunsch
4 篇 daniel s. levine
4 篇 anon
4 篇 zhang haitao
4 篇 zhang hao
4 篇 honggang zhang
4 篇 iwahori yuji
3 篇 paul scheunders
3 篇 wilfried philips
3 篇 andersson karl
3 篇 kumar ajay
3 篇 tongwei lu
3 篇 dan popescu
3 篇 soman k. p.

语言

1,814 篇 英文
45 篇 其他
19 篇 中文
1 篇 西班牙文

检索条件"任意字段=4th International Conference on Intelligent Systems and Pattern Recognition-ISPR"

共 1874 条记录，以下是281-290 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：

intelligent Detection Method for URL Injection Attacks Based on Large Models 25

Intelligent Detection Method for URL Injection Attacks Based...

引用

Proceedings of the 2025 4th international conference on Cryptography, Network Security and Communication Technology

作者： Yiyang Zhou Beijing University of Posts and Telecommunications Beijing China

ISBN: (纸本)9798400712623

URL Injection alludes to a sort of network security attack that employs encoding, encryption and obfuscation methods to manipulate URLs to bypass network security measures. Traditional rule-based intrusion detection systems, which depend on fixed patterns, are unable to detect modern similar threats. this paper proposes an intelligent detection method of a fine-tuned version of Llama 3.1-8B model using LoRA, which is denoted as the secure intelligent large model. the method effectively recognized many types of URL injection attacks such as the complex encrypted attacks and the obfuscated attack, by exploiting the advanced pattern recognition capability and semantic understanding potential of the LLM. the system is composed of an offline training phase and real-time intranet threat detection. Upon evaluation of the popular 21,450 URLs (encrypted or obfuscated elements) dataset, it is observed that the encoding- scheme has above 90% accuracy and it also outperforms more traditional rule-based systems by a wide margin when it comes to detection of complex encoding combinations in normal URLs. Our findings demonstrate the viability of using large language models to improve the adaptability of scalable and flexible cyber defense against new evolution of URL injection attack.

关键词： Large language model

来源：评论

学校读者我要写书评

暂无评论

Real time recognition methods for Chinese sign language based on detection model

Real time recognition methods for Chinese sign language base...

引用

Electronic Technology, Communication and Information (ICETCI), IEEE international conference on

作者： Shudan Chi Yangjing Zhou Fu Liu Jianhui Li School of Urban Construction and Intelligent Manufacturing Dongguan City University Dongguan China

ISBN: (数字)9798350361643

ISBN: (纸本)9798350361650

the research on sign language recognition methods is of great significance for enhancing the practicality of human-machine interfaces and constructing barrier free communication modes. Traditional sign language recognition methods lack research on real-time performance optimization of the sign language recognition process, as well as a lack of dedicated sign language datasets. Some technologies are still immature and have high power consumption. this article proposes a Chinese sign language recognition strategy based on a detection model. By designing a sign language recognition algorithm based on the detection model, the real time performance of sign language recognition is improved. Experimental results have shown that the proposed sign language recognition strategy has certain optimization effects.

关键词： YOLO Sign language Power demand Human-machine systems Feature extraction Real-time systems Labeling

来源：评论

学校读者我要写书评

暂无评论

SmartGrade: Automated Assessment with Cheat Detection

SmartGrade: Automated Assessment with Cheat Detection

引用

Ubiquitous Computing and intelligent Information systems (ICUIS), international conference on

作者： Pankaj Kunekar Gargi Dandare Kishan Chaudhary Vedant Dhamane Ayusha Patil Saif Bichu Department Of Information Technology Vishwakarma Institute of Technology Pune India

ISBN: (数字)9798331529635

ISBN: (纸本)9798331529642

this research study proposes “SmartGrade,” an innovative automated assessment tool that leverages advanced technologies to revolutionize the grading process in education. SmartGrade employs Tesseract OCR to accurately transcribe handwritten answer scripts into digital format. Subsequently, the BERT language model evaluates the answers based on predefined marking schemes, providing automated grading with constructive feedback. Furthermore, the system incorporates a plagiarism detection mechanism using a Turnitin-like system to ensure academic integrity. To enhance the system's effectiveness, K-means clustering is utilized to identify potential cases of cheating by detecting similarities between submitted answers. SmartGrade offers a user-friendly interface for seamless integration into the educational workflow, enabling educators to efficiently manage assessments while maintaining academic integrity and enhancing the overall learning experience.

关键词： Plagiarism Optical character recognition Education Clustering algorithms Ubiquitous computing Character recognition Artificial intelligence Information systems

来源：评论

学校读者我要写书评

暂无评论

4th international conference on Wireless Communications and Applications, ICWCA 2020

4th International Conference on Wireless Communications and ...

引用

4th international conference on Wireless Communications and Applications, ICWCA 2020

ISBN: (纸本)9789811651670

the proceedings contain 41 papers. the special focus in this conference is on Wireless Communications and Applications. the topics include: Fuzzy-ADRC Strategy to DFIG Low-Voltage Ride through;Test Methodology and System for 5G Millimeter Wave Terminal RF Conformance;a Survey on Energy Saving Technology of Wireless Sensor Network;the Development of Smart Building Under the Background of Internet+;paradigm for Urban Safety and Risk Management with Big Data;network Teaching Based on Multimedia Technology: An Example of Ideological and Political theory Course;Supervised Learning Epidemic threshold of SIR Model in Complex Networks;research on the Method of Alleviating Depression in Pregnant Women Based on Social Mobile Phone Application;research and Development of Virtual Simulation Software Based on Multimodal Sensory theory;construction of intelligent Information Platform for Preschool Education Based on Big Data;survey on Video Information Superimposition and Interaction Method Oriented to Disaster Knowledge of Power Grid;development and Analysis of Solenoid Valve Controller Based on LoRa Technology;research on Security Technology Requirement for Zero Trust Security Product;research and Application of Automatic recognition and Extraction of Water Body in Remote Sensing Images Based on Deep Learning;Khmer Named Entity recognition Based on LSTM-CRF Model;identification of Transfer Function of Position Servo System;research on the Sound Insulation Measurement of Building Elements Based on intelligent Laboratory Measurement System;research on Application of Somatosensory Interactive Technology in Teaching;the Design and Implementation of the Identification System for Primary Protected Birds in China;analysis on the Installation Art.

关键词：

来源：评论

学校读者我要写书评

暂无评论

intelligent Monitoring Technology of Two-ticket System for Safety Production in Power Grid Enterprise

Intelligent Monitoring Technology of Two-ticket System for S...

引用

New Energy and Power Engineering (ICNEPE), international conference on

作者： Chengwei Huang Jia Zeng Fayan Zhang Wenxiao Zhang Zhaoyang Lai Hezhou Power Supply Bureau of Guangxi Power Grid Co. Ltd. China Guangxi Power Grid Co. Ltd. China College of Information Science and Engineer Hohai University Changzhou China

ISBN: (数字)9798331516086

ISBN: (纸本)9798331516093

this paper studies the advancement of intelligent monitoring methods of the two-ticket system for power grid operations. It is known that the manual monitoring strategies are inadequate for addressing the sophisticated demands of contemporary power grid safety. To bridge this gap, this paper introduces an innovative smart surveillance system that leverages the prowess of artificial intelligence (AI) and edge computing. this system is designed to provide real-time oversight of the two-ticket execution process, ensuring that all safety protocols are adhered to without delay. By integrating AI for pattern recognition and edge computing for on-site data processing, the proposed system enhances the efficiency and reliability of power grid operations, thereby fortifying the overall safety management framework.

关键词： Reviews Safety management Video surveillance Power grids Stability analysis Real-time systems Reliability Security Artificial intelligence Edge computing

来源：评论

学校读者我要写书评

暂无评论

4th international conference on Wireless Communications and Applications, ICWCA 2020

4th International Conference on Wireless Communications and ...

引用

4th international conference on Wireless Communications and Applications, ICWCA 2020

ISBN: (纸本)9789811651632

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on Online Writing Stroke Evaluation Method Based on intelligent Pen

Research on Online Writing Stroke Evaluation Method Based on...

引用

Electronic Information Engineering and Computer Science (EIECS), 2021 international conference on

作者： Chun Wang Dejun Chen Wuhan University of Technology Wuhan City Hubei Province China

ISBN: (数字)9798331531409

ISBN: (纸本)9798331531416

the current Chinese character teaching system not only needs to accurately recognize students' handwritten Chinese characters, but also needs to evaluate and guide their written Chinese characters, that is, evaluate the Chinese characters written by students. Handwritten Chinese character evaluation technology is a hot research topic in recent years, but many previous technologies were based on static images for recognition and evaluation, which cannot provide real-time feedback to students' handwriting. this article evaluates handwritten Chinese characters in real-time from four dimensions: length, slope, position, and pressure, based on the characteristics of Chinese character trajectory data collected by an intelligent pen and combined with an improved FastDTW algorithm. the experimental results show that the method proposed in this article can effectively evaluate Chinese characters not only in terms of stroke quantity and stroke order, but also in terms of overall structure.

关键词： Computer science Handwriting recognition Image recognition Education Writing Real-time systems Trajectory Character recognition

来源：评论

学校读者我要写书评

暂无评论

Butterfly Image Generation and recognition Based on Improved Generative Adversarial Networks 4

Butterfly Image Generation and Recognition Based on Improved...

引用

4th international conference on Robotics, Control and Automation Engineering (RCAE) / 4th international conference on Advanced Mechanical and Electrical Engineering (AMEE)

作者： Min, Feng Xiong, Wenyi Wuhan Inst Technol Hubei Prov Intelligent Robot Key Lab Wuhan Peoples R China

ISBN: (纸本)9781665427302

As one of the important methods for sample generation, Generative Adversarial Networks (GAN) can generate samples based on the data distribution in any given dataset. However, it suffers from problems such as blurred texture, unstable training process and collapse of patterns in the actual training process. To address these problems, a sample generation method based on Deep Convolutional Generative Adversarial Networks (DCGAN) combined with Residual Networks (ResNet) is designed. the method uses residual and convolutional networks to construct generative and discriminative models, the deep residual network can recover rich image textures and effectively alleviate the instability of adversarial network training and the occurrence of pattern collapse. the performance of the algorithm is tested on the Butterfly Image Classification 50 species datasets with loss function curves and FID scores, then the network model is applied to the butterfly-like insect datasets for data augmentation. And we use the two classic deep convolutional neural network models to train and identify the samples. the results show that the proposed method can improve the accuracy of the two models in classification by 1.84% and 2.78% on the butterfly class datasets. the experiment results confirm that the improved DCGAN can effectively generate butterfly-like image data and improve the accuracy of the deep neural network model in classifying butterfly images.

关键词： butterfly recognition DCGAN ResNet FID

来源：评论

学校读者我要写书评

暂无评论

Research and Application of intelligent Monitoring Algorithm for Transmission Lines Based on Artificial Intelligence

Research and Application of Intelligent Monitoring Algorithm...

引用

Information Technology,Big Data and Artificial Intelligence (ICIBA), international conference on IEEE international conference on

作者： Lifeng Wang Xiangyu Ji Biao Su Shipeng Hou Peng Fu Bo Liu Chao Ma Shandong Luruan Digital Technology Co. Ltd. Jinan China

ISBN: (数字)9798350363609

ISBN: (纸本)9798350363616

As the main equipment supporting overhead transmission lines, power towers play an important role in the process of transmitting electricity from power plants to end-users through substations. the typical design service life of a tower is 50 years. the complex geological changes that occur around the tower can easily affect the stability of the tower's fixation, causing the tower to tilt and posing a threat to the safety of the power network. therefore, in order to ensure the safe and stable operation of the tower, the article applies intelligent tilt monitoring technology to the tilt monitoring of the tower. this technology can effectively achieve real-time dynamic remote monitoring of tower status by management personnel. By real-time monitoring of the operation status of power towers and power networks, management personnel can detect and handle potential faults in advance, thereby fully ensuring the safe operation of the power network.

关键词： Vibrations Power transmission lines Poles and towers Feature extraction Vectors Real-time systems pattern recognition Safety Personnel Monitoring

来源：评论

学校读者我要写书评

暂无评论

An Unpackaged Goods Recognizing Method Based on an Improved YOLOv5 Model

An Unpackaged Goods Recognizing Method Based on an Improved ...

引用

Electronic Information Engineering and Computer Science (EIECS), 2021 international conference on

作者： Yuheng Qian Junsheng Wang Information Science and Technology College Dalian Maritime University Dalian Liaoning China

ISBN: (数字)9798331531409

ISBN: (纸本)9798331531416

the digital economy and the liberation of labor are important directions of modernization. Combining artificial intelligence (AI) with commercial activity, designing and realizing an intelligent merchandise identification system is a pressing need of the times. the system is based on the improved IM-YOLOv5 (yolov5s+sim+Hardswish) deep training model, which improves the recognition rate of the traditional yolov5 model, and the data shows that the IM-YOLOv5 model improves the recognition accuracy by 5.26% compared to the yolov5 model. Users can be informed of the types of goods in real time through the device, realizing the intelligent transformation of visual recognition commercialization, portability and universality.

关键词： YOLO Training Visualization Accuracy Computational modeling Pressing Predictive models Data models Real-time systems Artificial intelligence

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188页 << < 25 26 27 28 29 30 31 32 33 34 > >>

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：