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

2,402 篇 会议
1,336 篇 期刊文献
37 册 图书

馆藏范围

3,775 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

2,311 篇 工学
- 1,658 篇 计算机科学与技术...
- 1,351 篇 软件工程
- 626 篇 信息与通信工程
- 379 篇 控制科学与工程
- 302 篇 生物工程
- 291 篇 电气工程
- 230 篇 生物医学工程（可授...
- 217 篇 电子科学与技术（可...
- 182 篇 光学工程
- 160 篇 网络空间安全
- 158 篇 机械工程
- 139 篇 化学工程与技术
- 129 篇 安全科学与工程
- 113 篇 动力工程及工程热...
- 107 篇 交通运输工程
- 104 篇 仪器科学与技术
- 94 篇 核科学与技术
1,360 篇 理学
- 609 篇 数学
- 479 篇 物理学
- 329 篇 生物学
- 217 篇 统计学（可授理学、...
- 158 篇 化学
- 113 篇 系统科学
696 篇 管理学
- 436 篇 管理科学与工程(可...
- 293 篇 图书情报与档案管...
- 157 篇 工商管理
220 篇 医学
- 162 篇 基础医学(可授医学...
- 160 篇 临床医学
- 111 篇 公共卫生与预防医...
127 篇 法学
- 106 篇 社会学
66 篇 经济学
65 篇 农学
36 篇 教育学
34 篇 文学
20 篇 军事学
5 篇 艺术学
1 篇 哲学

主题

171 篇 accuracy
140 篇 deep learning
102 篇 feature extracti...
100 篇 hadron colliders
99 篇 machine learning
89 篇 computational mo...
89 篇 training
85 篇 convolutional ne...
70 篇 real-time system...
66 篇 support vector m...
64 篇 predictive model...
62 篇 artificial intel...
54 篇 optimization
53 篇 internet of thin...
49 篇 reliability
46 篇 genetic algorith...
45 篇 security
45 篇 cloud computing
45 篇 data models
44 篇 semantics

机构

133 篇 yerevan physics ...
130 篇 national and kap...
130 篇 centro brasileir...
130 篇 istanbul technic...
128 篇 university of sp...
128 篇 indian institute...
127 篇 universidad iber...
126 篇 brunel universit...
125 篇 università di to...
125 篇 academy of scien...
125 篇 charles universi...
125 篇 infn sezione di ...
124 篇 department of ph...
123 篇 zhejiang univers...
123 篇 irfu cea univers...
122 篇 infn sezione di ...
121 篇 university of de...
121 篇 department of ph...
119 篇 imperial college...
119 篇 rwth aachen univ...

作者

125 篇 m. lu
95 篇 g. tonelli
95 篇 d. barney
95 篇 l. valencia palo...
95 篇 t. liu
95 篇 c. hensel
95 篇 a. garcia-bellid...
95 篇 a. steen
95 篇 n. cartiglia
95 篇 d. eliseev
94 篇 a. babaev
94 篇 v. karjavine
93 篇 n. colino
93 篇 f. moortgat
92 篇 b. clerbaux
91 篇 g. sultanov
91 篇 a. mallampalli
91 篇 m. a. ciocci
91 篇 k. lamichhane
91 篇 s. maselli

语言

3,438 篇 英文
291 篇 其他
47 篇 中文
2 篇 日文
1 篇 德文
1 篇 法文

检索条件"机构=Computer Science Engineering and Application"

共 3775 条记录，以下是501-510 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：

Lightweight object detection algorithm for road scenes based on YOLOV8 4

Lightweight object detection algorithm for road scenes based...

引用

4th International Conference on Machine Learning and computer application, ICMLCA 2023

作者： Huang, Chengqin Yang, Degang Zhang, Xin College of Computer and Information Science Chongqing Normal University Chongqing401331 China Chongqing Engineering Research Center of Educational Big Data Intelligent Perception and Application Chongqing Normal University Chongqing401331 China

ISBN: (数字)9781510680265

ISBN: (纸本)9781510680258

Object detection in road scenes is a crucial component of autonomous driving. Due to the significant variations in target scales, it is prone to false positives, false negatives, and some underperforming devices cannot deploy the state-of-the-art detectors. To address these issues, we propose a lightweight algorithm based on an improved YOLOv8. We simplify the model by using the FasterNet Block from FasterNet to replace the BottleNeck module in YOLOv8's backbone network C2f, reducing parameters and floating-point computations. We also enhance feature extraction by substituting RFCAConv for the downsampling standard convolution in C2f. Additionally, we introduce Wise-IoU to replace the original activation function, directing the network's focus towards anchor boxes of average *** promote effective fusion of original, shallow, and deep features, we introduce the BiFPN structure to replace YOLOv8's PAN structure. Furthermore, a small object detection layer is added to the head to handle the drastic scale variations in road scenes. Experimental results on the SODA10M dataset demonstrate that the improved YOLOv8 model achieves a 55.8% mAP@0.5 and a 35.5% mAP@0.5:0.95. The model's parameter count, size, and floating-point computations decrease by 58.3%, 57.0%, and 21.1%, respectively. Analysis of the experimental results confirms that the proposed model is effective and superior, striking a balance between detection accuracy and model lightweightness. © 2024 SPIE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Analyzing the Efficiency of Key Management Techniques Used in Information Security Models for Networked applications 5th

Analyzing the Efficiency of Key Management Techniques Used i...

引用

5th International Conference on Data science, Machine Learning and applications, ICDSMLA 2023

作者： Beemkumar, N. Singh, Vaishali Shree, Ritu Batra, Raman Karnataka Bangalore India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India Department of Computer Science & Application Vivekananda Global University Jaipur India Department of Mechanical Engineering Noida Institute of Engineering and Technology Uttar Pradesh Greater Noida India

ISBN: (纸本)9789819780426

This study aims to investigate the performance of numerous key manipulation strategies utilized in modern statistics protection models. Especially, this painting examines the use of public key infrastructures (PKI), symmetric key infrastructures (SKI), and identity-based totally encryption (IBE) for securing application conversation in networked environments. By way of analyzing the strengths and weaknesses of each gadget, potential improvements are diagnosed. Moreover, a comparison among the unique fashions is done to pinpoint feasible weaknesses and endorse feasible mitigation strategies. The research results will enable the improvement of greater comfortable and green key management structures for networked programs, which can offer effective protection against malicious assaults. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Infrastructures Pinpoint Protection Symmetric Weaknesses

来源：评论

学校读者我要写书评

暂无评论

Fall Detection and Alerts in Hearing Aids for Deaf using Generative AI

Fall Detection and Alerts in Hearing Aids for Deaf using Gen...

引用

Computational Intelligence, Communication Technology and Networking (CICTN), International Conference on

作者： Bharat Tripathi Madan Lal Saini Manish Jain Apoorva Saxena Narendra Pal Department of Computer Application Allenhouse Institute of Technology Kanpur India Department of Computer Science and Engineering Apex Institute of Technology Chandigarh University Punjab India Department of Computer Application Allenhouse Business School Kanpur India Department of Computer Science & Engineering Axis Institute of Technology & Management Kanpur India Department of Computer Science & Engineering Invertis University Bareilly India

ISBN: (数字)9798331530389

ISBN: (纸本)9798331530396

Individuals with sensorineural hearing loss often experience difficulty comprehending speech when background noise is present. This paper investigates the extent of this problem in various listening scenarios and with different types of background sounds. Additionally, the section explores the contributing factors to this challenge such as reduced audibility, reduced frequency selectivity, loudness recruitment, and dead regions in the cochlea where there are no surviving inner hair cells and or neurons. The sections evaluate different techniques for compensating for the effects of these factors. While signal-processing methods using the output of a single microphone to compensate for reduced frequency selectivity have had limited success, techniques utilizing multiple microphones have proven effective. Amplitude compression has also been effective in compensating for the effects of loudness recruitment, enabling individuals to understand speech across a wide range of sound levels. Next, the paper delves into the technical aspects of implementing fall detection systems in hearing aids. learning algorithms are also investigated for their potential in enhancing fall detection accuracy and minimizing false alarms. Furthermore, the importance of user-friendly interfaces and customization features in ensuring the effectiveness and acceptance of fall detection alerts is also highlighted. The paper also addresses the ethical and privacy considerations associated with fall detection in hearing aids. It emphasizes the need for transparent data handling practices and user consent, while also addressing potential concerns related to user autonomy and intrusion.

关键词： Hair Privacy Neurons Signal processing algorithms Signal processing Hearing aids Fall detection Transient analysis Recruitment Microphones

来源：评论

学校读者我要写书评

暂无评论

Network Security and Protection Strategies for Big Data: Challenges and Innovations 6

Network Security and Protection Strategies for Big Data: Cha...

引用

6th International Conference on Contemporary Computing and Informatics, IC3I 2023

作者： Gupta, Manish Kumar Rai, Ashok Kumar Farooq, Mansoor Santhiya, P. Madan Mohan Malaviya University of Technology Department of Information Technology & Computer Application UP Gorakhpur India Madan Mohan Malaviya University of Technology Department of Computer Science & Engineering UP Gorakhpur India University of Kashmir Department of Management Studies Jammu & Kashmir India Sathyabama Institute of Science and Technology Department of Computer Science & Engineering Tamilnadu Chennai India

ISBN: (纸本)9798350304480

The emergence of Big Data (BD) has enabled organizations to process large and intricate datasets, uncover hidden patterns, gain valuable insights, and facilitate data sharing across networks. However, the transmission of data within organizational networks often involves sensitive information that necessitates an efficient and secure platform. Consequently, network security has become a paramount concern in the era of big data. Existing network security platforms must contend with vast and complex information to effectively predict and prevent potential real-time attacks. Nevertheless, these platforms typically rely on conventional approaches, rendering them inadequate for safeguarding big data. This paper focuses primarily on network security and protection strategies for big data. Firstly, we discuss the factors that impact network security platforms in the era of big data. Subsequently, we explore various strategies for ensuring security across networks, while also surveying recent research in the field. © 2023 IEEE.

关键词： Big data Datasets Network Privacy Security

来源：评论

学校读者我要写书评

暂无评论

Domain Transfer Learning for Medical Image Segmentation Tasks 5th

Domain Transfer Learning for Medical Image Segmentation Task...

引用

5th International Conference on Data science, Machine Learning and applications, ICDSMLA 2023

作者： Kharbas, Vikas Kumar Srivastava, Pulkit Bargavi, Manju Pandeya, Megha Department of Computer Science and Application Vivekananda Global University Jaipur India Department of Mechanical Engineering Noida Institute of Engineering and Technology Uttar Pradesh Greater Noida India Karnataka Bangalore India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India

ISBN: (纸本)9789819780426

Domain transfer learning is a powerful device for clinical image Segmentation duties. It involves transferring information from a source domain to a goal area so that related tasks on those domains can be advantageous from every difference. This era allows improving and robust clinical photo segmentation models by exploiting the prevailing area information and facts from a source area. This approach has been used to enhance the performance of sure segmentation responsibilities in medical imaging together with the segmentation of pathologies from imaging, segmentation of anatomic structures, and system getting to know-based total segmentation. The most critical domain version strategies encompass domain-adversarial neural networks, generative fashions, and meta-getting to know. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Rice quality Prediction using Convolution Neural Network 2

Rice quality Prediction using Convolution Neural Network

引用

2nd IEEE International Conference on Distributed Computing and Electrical Circuits and Electronics, ICDCECE 2023

作者： Rekha, V. Shiny, R.M. Ramya, J. Sakthivel, B. Pratheep, V.G. Kumar, Ashok AgurchandManmull Jain College Department of Bachelors's in Computer Application Chennai India Velammal Institute of Technology Department of Artificial Intelligence and Data Science Thiruvallur India St. Joseph's College of Engineering Department of Computer Science Engineering Chennai India Vivekanandha College of Engineering for Women Department of Electronics and Communication Engineering Namakkal India Kongu Engineering College Department of Mechatronics Engineering Perundurai India Banasthali Vidyapith Department of Computer Science Banasthali India

ISBN: (纸本)9798350347456

Rice is the most widely grown crop in Asia. In Asia, 60% of the population relies on rice, China, Indonesia especially India consumes the majority of it. Food is the single most direct way for an individual to become infected with any ailment. Predicting the quality of rice is a crucial aspect as it is one of the most consumed foods in Asia. In this study, the quality of the rice is predicted using a Deep Learning (DL) model to predict the quality more precisely. The dataset required for this study is collected from the Kaggle website composed of a total of 5000 images of 5 different rice varieties. The collected raw dataset is then pre-processed using several methods to make them compatible with the DL model. The pre-proceed images are then subjected to the prediction of the quality of the rice using the Convolutional Neural Network (CNN), a DL model. Performance metrics such as accuracy, loss, and time are calculated to validate the precision of the model. The experimental result showed that the model has the highest accuracy of about 98.6% when compared to the other existing models. The model demonstrated a very minimal loss percentage of only about 1.24% and the model predicts the result in about 25 microseconds. The proposed DL model can be utilized for better and more objectively evaluate the quality of the rice at trading points inside the rice marketing chain due to its fairly high precision. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

GPS Based Automated Attendance System 5

GPS Based Automated Attendance System

引用

5th IEEE International Conference on Advances in Electronics, computers and Communications, ICAECC 2023

作者： Bhatt, Chandradeep Rawat, Adarsh Chauhan, Rahul Bhatt, Pashupati Singh, Teekam Sharma, Sanjay Graphic Era Hill University CSE Department Dehradun India Computer Science and Engineering Graphic Era Hill University Dehradun India Institute of Technology & Management Department of Information Technology Uttarakhand India Computer Science and Engineering Graphic Era Deemed to Be University Dehradun India SGRRITS Computer Application Department Dehradun India

ISBN: (纸本)9798350305449

Attendance management systems are important part of an organization, helps them to track real time employee data. From the past few decades, we have plenty of methods or models for the system, but they come with their limitations. These traditional systems in workplaces are often results a data with inefficiencies and inaccuracies. GPS based attendance management system is an effective way to overcome these past limitations. It utilizes GPS technology for employee tracking, and provide us less time consuming and optimal performance. In Model, Both the parties are free from data processing and handling. A web application implementation of system makes it handier with provide a basic and simple user interface to the user. System is totally centric around the admin, which have max privileges in the system. The main gist of the system is abstracted in the backend processes. Haversine formula is important here, which is for distance calculation between two geographical coordinates. System uses geolocation API (application programming interface) for coordinates generation and believes on other more accurate ways or method of coordinates generation. Reputed organization like Google, Microsoft etc. utilizes GPS based systems in their workplaces. © 2023 IEEE.

关键词： Data handling

来源：评论

学校读者我要写书评

暂无评论

ZKCross: An Efficient and Reliable Cross-Chain Authentication Scheme Based on Lightweight Attribute-Based Zero-Knowledge Proof 24th

ZKCross: An Efficient and Reliable Cross-Chain Authenticati...

引用

24th International Conference on Algorithms and Architectures for Parallel Processing, ICA3PP 2024

作者： Xu, Yuwei Cai, Hailang Chen, Jialuo Xiang, Qiao Xu, Jingdong Cheng, Guang School of Cyber Science and Engineering Southeast University Nanjing China Purple Mountain Laboratories for Network and Communication Security Nanjing China Engineering Research Center of Blockchain Application Supervision and Management Nanjing China School of Informatics Xiamen University Xiamen China College of Computer Science Nankai University Tianjin China

ISBN: (纸本)9789819615506

The consortium blockchain finds wide application in finance and logistics. However, these independent networks create information silos. Cross-chain authentication aims to bridge these gaps. It verifies qualifications across different blockchains, yet it can risk leaking sensitive data. The main methods include Attribute-Based Signatures (ABS) and Attribute-Based Zero-Knowledge Proof (ABZKP). ABZKP better handles key management, general applicability, and attribute verification than ABS. However, the current ABZKP suffers from large proof files and slow verification. Additionally, many schemes can’t handle sets of multiple attributes and may introduce centralization. Overall, the current schemes based on zero-knowledge proof still struggle to strike a balance between security and efficiency. We propose a reliable cross-chain authentication scheme. Our lightweight zero-knowledge proof algorithm enhances verification speed and reduces file size. We also introduce parallel verification to address security concerns. Security analysis and experiments show that ZKCross when properly configured, achieves near-perfect accuracy and outperforms others in size and speed. Thus, ZKCross stands as an efficient and dependable cross-chain authentication scheme. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Authentication Protocol

来源：评论

学校读者我要写书评

暂无评论

Health Fit system in Current Era using React JS 5

Health Fit system in Current Era using React JS

引用

5th IEEE International Conference on Advances in Electronics, computers and Communications, ICAECC 2023

作者： Bhatt, Chandradeep Negi, Ayush Singh Chauhan, Rahul Bhatt, Pashupati Singh, Teekam Sharma, Sanjay Graphic Era Hill University CSE Department Dehradun India Computer Science and Engineering Graphic Era Hill University Dehradun India Institute of Technology & Management Department of Information Technology Uttarakhand India Computer Science and Engineering Graphic Era Deemed to Be University Dehradun India SGRRITS Computer Application Department Dehradun India

ISBN: (纸本)9798350305449

The purpose of this system is to update the existing systems with the help of computer technology (i.e. to improve the API's which current systems lacked a lot) and the best computers to meet their needs, so that valuable information/data can be stored for a longer period of time and made it easily accessible and functional. Software and hardware should be simple and easy to use. As mentioned above, the Gym fit system provides error free, safe, secure and fast administration. It helps users focus on other activities rather than focusing on data storage. Therefore, it will help the organization make better use of resources. Organizations can store information on computers without further access. This means that people can access information without being hindered by irrelevant information. The aim is to keep the best computers information to make the current book uses with the help of computer hardware and to meet their needs / useful information can be stored for a longer time and easily accessed and used. Basically, the work describes how to manage to achieve quality and serve customers better. © 2023 IEEE.

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

Automated Anomaly Detection in Medical Imaging Using Support Vector Machines 5th

Automated Anomaly Detection in Medical Imaging Using Support...

引用

5th International Conference on Data science, Machine Learning and applications, ICDSMLA 2023

作者： Goyal, Manish Kumar Shahid, Mohammad Karthikeyan, M.P. Kumar, Ritesh Department of Computer Science & Application Vivekananda Global University Jaipur India Noida Institute of Engineering and Technology Uttar Pradesh Greater Noida India Karnataka Bangalore India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India

ISBN: (纸本)9789819780426

Clinical imaging techniques such as X-ray, Magnetic Resonance Imaging (MRI), and laptop Tomography (CT) scanners are used to diagnose, compare, and deal with sufferers. Automatic Anomaly Detection is an automatic technique for identifying and diagnosing abnormalities in clinical imaging. It has been diagnosed that Support Vector Machines (SVM) can be effectively used to generate correct automatic anomaly detection for scientific imaging. SVM is an approach that uses supervised getting-to-know to create a choice boundary between classes, with the decision primarily based on the information to be had. The gain of SVM is that it plays an automatic function extracting from the medical imaging facts and uses those extracted capabilities for anomaly detection. It combines photograph segmentation and classification to classify the abnormal regions in an image. So one can enhance the accuracy of SVM;it's miles viable to use an expansion of kernel capabilities and unique parameter tuning. Moreover, introducing an automatic pipeline from training to deploying SVM reduces the efforts of manual feature extraction from photos. Consequently, aid Vector Machines is a feasible approach for automatic anomaly detection in scientific imaging. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Image segmentation

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378页 << < 47 48 49 50 51 52 53 54 55 56 > >>

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：