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

8,812 篇 会议
8 篇 期刊文献

馆藏范围

8,820 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

7,455 篇 工学
- 5,763 篇 计算机科学与技术...
- 4,862 篇 软件工程
- 2,244 篇 信息与通信工程
- 959 篇 控制科学与工程
- 702 篇 生物工程
- 637 篇 电气工程
- 553 篇 生物医学工程（可授...
- 509 篇 电子科学与技术（可...
- 451 篇 机械工程
- 418 篇 光学工程
- 405 篇 仪器科学与技术
- 330 篇 化学工程与技术
- 326 篇 安全科学与工程
- 316 篇 动力工程及工程热...
- 315 篇 网络空间安全
- 279 篇 交通运输工程
3,281 篇 理学
- 1,894 篇 数学
- 785 篇 生物学
- 742 篇 统计学（可授理学、...
- 512 篇 物理学
- 376 篇 系统科学
- 296 篇 化学
2,596 篇 管理学
- 1,504 篇 管理科学与工程(可...
- 1,281 篇 图书情报与档案管...
- 800 篇 工商管理
543 篇 医学
- 464 篇 临床医学
- 450 篇 基础医学(可授医学...
- 309 篇 公共卫生与预防医...
447 篇 法学
- 368 篇 社会学
374 篇 经济学
- 373 篇 应用经济学
242 篇 农学
211 篇 教育学
130 篇 文学
51 篇 军事学
13 篇 艺术学
1 篇 哲学

主题

272 篇 data mining
247 篇 big data
155 篇 internet of thin...
122 篇 convolutional ne...
108 篇 machine learning
105 篇 support vector m...
103 篇 feature extracti...
100 篇 deep learning
99 篇 blockchain
92 篇 data models
87 篇 forecasting
84 篇 data acquisition
84 篇 classification (...
82 篇 information mana...
80 篇 cryptography
75 篇 students
61 篇 cloud computing
59 篇 semantics
58 篇 adversarial mach...
58 篇 wireless sensor ...

机构

59 篇 beijing institut...
40 篇 the islamic univ...
35 篇 chitkara univers...
29 篇 beijing institut...
27 篇 graphic era deem...
25 篇 university of el...
24 篇 national univers...
24 篇 beijing institut...
22 篇 applied science ...
22 篇 graphic era deem...
22 篇 karpagam academy...
19 篇 vishwakarma inst...
19 篇 beijing institut...
18 篇 chitkara univers...
18 篇 shenyang ligong ...
17 篇 pune
16 篇 tsinghua univers...
16 篇 college of techn...
15 篇 department of co...
15 篇 ncba&e school of...

作者

22 篇 liu yang
21 篇 pareek piyush ku...
20 篇 liu quanhua
18 篇 li yang
15 篇 wang jian
15 篇 kukreja vinay
14 篇 raman ramakrishn...
14 篇 ding zegang
13 篇 wang wei
12 篇 li jun
12 篇 chen yen-wei
11 篇 dong zhen
11 篇 chen liang
11 篇 yang jian
10 篇 zhang lei
10 篇 wang jing
10 篇 srinivasan c.
10 篇 china
9 篇 wang tao
9 篇 huang pingping

语言

8,168 篇 英文
367 篇 其他
285 篇 中文

检索条件"任意字段=2nd IEEE Conference on Information Technology and Data Science, CITDS 2022"

共 8820 条记录，以下是41-50 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：

Comparison of SVM and Random Forest for Detection of Malicious Node in Wireless Sensor Networks 2

Comparison of SVM and Random Forest for Detection of Malicio...

引用

2nd International conference on Machine Learning and Autonomous Systems, ICMLAS 2025

作者： Thamma, Sankara Reddy Gurumoorthi, E. Prakash, C. Om Muthusundar, S.K. Nidhya, M.S. Maram, Balajee Deloitte Consulting LLP 28027 United States DC Technical Delivery Master II Information Technology ConcordNC28027 United States School of Engineering Malla Reddy University India CMR University Bengaluru India Chennai Institute of Technology college Dept of AI & DS Chennai India School of Computer Applications Dayananda Sagar University Bangalore India School of Computer Science and Artificial Intelligence SR University Ananthasagar Hasanparthy Warangal India

ISBN: (纸本)9798331505745

Wireless Sensor Networks (WSNs) are used in various contexts and offer a wide range of applications, despite being a decentralized, resource-scarce network type;this is why this study deals with the problem of malicious nodes. Identifying such nodes is important to preventing the compromise of the network and all the nodes in it. In this paper, a comparative study of two popular classifiers named Support Vector Machine (SVM) and Random Forest (RF) in order to detect hostile nodes in WSNs. By nature, a malicious node in a network will cause significant problems to the users. There are number of models also there to detect the malicious node. Based on the above-discussed parameters the paper compares these algorithms in terms of detection accuracy, computational complexity, scalability and performance measure of imbalanced data. The comparison draws on different targets such as accuracy, capacity/large scale, speed, and small sample imbalance, and noise. As stated in this paper, both SVM and Random Forest have its own strengths where the selection between them mainly depends on the network environment and the features of the malicious activity. © 2025 ieee.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

An AI Analytical Model for Human's Posture Analysis: Posture Correction with MediaPipe 2

An AI Analytical Model for Human's Posture Analysis: Posture...

引用

2nd International conference on Advanced Innovations in Smart Cities, ICAISC 2025

作者： Al-Barhamtoshy, Hassanin M. Alharbi, Khaled Rashad, Atef Faculty of Computing King Abdulaziz University Information Technology Dept Jeddah Saudi Arabia Sports Sciences Faculty Jeddah University Sports Training Dept Jeddah Saudi Arabia

ISBN: (纸本)9798331506995

The posture analysis has received considerable interest across various fields such as healthcare, sports science, and human-computer interaction due to its impact on physical performance, prevention of injuries, and ergonomic design. This paper seeks to deliver a thorough overview of the datasets available specifically for posture analysis, emphasizing their appropriateness for training and assessing machine learning models in pose estimation tasks. We systematically classify the existing datasets, including those related to diverse scenarios like sports, everyday activities, and medical evaluations, taking into account aspects such as dataset size, diversity, annotation quality, and the inclusion of temporal data. Additionally, we evaluate the applicability of each dataset in responding to specific research inquiries while outlining their advantages and drawbacks. We also address common evaluation metrics used in posture analysis-such as accuracy, mean average precision (mAP), and percentage of correct keypoints (PCK)-and discuss their utility in validating model performance across varying datasets. Through this synthesis of information, we aim to assist researchers and practitioners in selecting suitable datasets for their studies on posture analysis, thereby aiding the progression of this field within both academic and industrial contexts. This system identifies an individual from an optimal side perspective and assesses the tilt of the neck and torso concerning a designated reference axis. It tracks the angle of inclination as the individual bends beyond a specified threshold. Additional functionalities include tracking the duration of specific postures and ensuring proper camera alignment. The package includes a solution script designed to implement an alert system for poor posture, utilizing MediaPipe Pose Solution and OpenCV. © 2025 ieee.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Secure Pilgrims Assistance System Using an Augmented Reality 2

Secure Pilgrims Assistance System Using an Augmented Reality

引用

2nd International conference on Advanced Innovations in Smart Cities, ICAISC 2025

作者： Alsulami, Amnah A. Mahfouz, Ammar A. Bin Alenazy, Raghad M. Al-Afranji, Zane S. Alnadawi, Aamer A. Khalil, Hannan A. Computer Science and Information Technology Jeddah International College Jeddah Saudi Arabia

ISBN: (纸本)9798331506995

The Hajj and the Umrah are the two main pilgrimages that Muslims make to Makkah, Saudi Arabia. Umrah can be done at any time, while Hajj takes place from the 8th to the 13th of Dhul Hijjah. The Hajj is considered the largest annual assembly in the world, is obligatory for every physically and financially capable Muslim at least once. During the Hajj, pilgrims travel 15 kilometers using a variety of transportation modes. The journey begins in Mina, the world's largest tent city, which houses more than 10,000 fire-resistant tents. Every year, approximately three million Muslims from more than 183 countries participate. Thus, this research aims to develop an Augmented Reality (AR) application that assists pilgrims in recognizing important sites and rituals during the Hajj pilgrimage. Furthermore, the system improves pilgrimage planning by assisting with accommodation selection and route optimization, as well as integrating national ID and mobile verification for secure identification. Also, it offers reminder notifications in Arabic and English as well as a trip planning tool to assist pilgrims in efficiently managing their time. Additionally, a specialized dashboard assists healthcare professionals and organizations, while a streamlined interface ensures effective communication with the Adahi software. User feedback mechanisms enable data-driven improvements, resulting in better decisionmaking and overall user satisfaction. © 2025 ieee.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

A 51.6TFLOPs/W Full-datapath CIM Macro Approaching Sparsity Bound and -30Loss for Compound AI 72

A 51.6TFLOPs/W Full-Datapath CIM Macro Approaching Sparsity ...

引用

72nd ieee International Solid-State Circuits conference, ISSCC 2025

作者： Yue, Zhiheng Xiang, Xujiang Wang, Yang Guo, Ruiqi Han, Huiming Wei, Shaojun Hu, Yang Yin, Shouyi Tsinghua University Beijing China

ISBN: (纸本)9798331541019

Large-language models (LLM) are widely used with exceptional performance, but their prohibitive size and cost limits deployment on edge devices. The compound-AI combines several specialized small models to achieve matched or even superior accuracy on target downstream tasks [1,2]: e.g., RevCol [3] fuses multiple convolutional models and surpasses the 7.2B-parameter monolithic LLM model [4] on the ImageNet classification task by 1.64%. Therefore, the shift to compound systems opens opportunities for edge deployment in addition to model-size scaling. SRAM-based floating point (FP) CIM promises accelerated edge-AI models [5-14]. Figure 14.4.1 shows a conventional FP CIM macro, which faces three challenges for compound-AI acceleration: (1) Previous FP CIMs rely on a Gaussian data distribution to reduce alignment loss, where data is distributed around its mean [11]. However, compound-AI employs diverse models, with multiple data distributions, leading to an accuracy degradation of more than 5% [15]. (2) In variable compound-AIs, the CIM only performs MAC operations [16-23];however, partial-sum/residual accumulation requires data movement and accounts for 26-72% power consumption, especially for bit-serial CIMs. (3) Conventional CIMs explore sparsity according to specific model features [11,12], but compound-AI models have flexible sparse patterns, causing a gap between the actual and theoretical speedup (1/1-sparsity). © 2025 ieee.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient SpMM Kernels for GATs and GCNs on a CGLA

Energy-Efficient SpMM Kernels for GATs and GCNs on a CGLA

引用

2nd International conference on Machine Learning and Autonomous Systems, ICMLAS 2025

作者： Asahina, Koki Kim, Dohyun Akabe, Tomoya Duong Le, Vu Trung Nakashima, Yasuhiko Nara Institute of Science and Technology Nara Ikoma630-0192 Japan

ISBN: (纸本)9798331505745

Graph Neural Networks (GNNs) have shown excellent performance in various fields, such as atomic structure estimation, chemical reaction modeling, and information retrieval aids in Large Language Models (LLMs). Among GNN models, Graph Convolutional Networks (GCNs) and Graph Attention Networks (GATs) are widely applied due to their computational efficiency and scalability. GATs provide higher inference accuracy through the Attention mechanism. Despite their advantages, these models face a significant bottleneck in Sparse Matrix-Matrix Multiplication (S $p$MM). Current SpMM platforms, which include potent CPUs, GPUs, and existing hardware accelerators, struggle to balance high performance and low power consumption, making them unsuitable for low-power graph applications. To address these challenges, we propose S $p$MM kernels that leverages the Coarse-Grained Reconfigurable Array (CGRA)-based accelera-tor IMAX3 (In-Memory Accelerator eXtension 3). Since the data flow in IMAX3 is static, padding is required to align the number of nonzero elements in each row, increasing data volume. To minimize this overhead, we introduced a new data format with minimal padding and optimized instruction mapping for seamless operations on IMAX3. We estimated the performance when converted to an ASIC using TSMC's 28nm process libraries. The results show that IMAX3 achieves a significant improvement in energy-delay product (EDP), outperforming the CPU i9-10940X by factors ranging from 20.24 x to 1,334.12x, the GPU RTX3090 by up to 1.54x, and NVIDIA Jetson AGX Orin by up to 172.31x. Compared to prior accelerator work, our kernel delivers EDP improvements ranging from 46.71x to 3,542.76x. These results highlight the exceptional efficiency and scalability of the proposed IMAX3-based SpMM kernel in overcoming GNN bottlenecks. © 2025 ieee.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

Improving Software Quality Assurance Using a Cross-Context-Attentive Cosine Convolutional Model 2

Improving Software Quality Assurance Using a Cross-Context-A...

引用

2nd International conference on Machine Learning and Autonomous Systems, ICMLAS 2025

作者： Sunil, Deena Dabke, Devika Saini, Surendra Kumar Singh Jandail, Ravendra Ratan Maduranga, M.W.P. Raw, Sharada Nandan Indira Gandhi National Tribal University Department of Mathematics Madhya Pradesh Amarkantak India Central University of Karnataka Department of Mathematics Karnataka Gulbarga India Indira Gandhi National Tribal University Department of Mathematics MadhyaPradesh Amarkantak India South Asian University Department of Computer Science New Delhi New Delhi India University of Sri JayewardenepuraNugegoda Department of Electrical and Electronic Engineering India National Institute of Technology Raipur Department of Mathematics Chhattisgarh Raipur India

ISBN: (纸本)9798331505745

The software quality determines system performance and reliability. As software systems are becoming increasingly complex, this is an important determinant. Detection of defects at the early stages of the development lifecycle improves software reliability and reduces costs. Traditional Software Defect Prediction (SDP) models suffer from class imbalance, complexity of datasets, and inefficient use of contextual information, which affect the accuracy of their predictions. Therefore, the development of reliable software systems still requires a more robust and efficient defect prediction model. In this manuscript, Improving Software Quality Assurance Using a Cross-Context-Attentive Cosine Convolutional Model (Sox-CNN-XA) is proposed. This study uses the NASA-MDP dataset containing historical records of software defects and various software metrics. data pre-processing included data cleaning, normalization, and splitting, which was done in order to enhance the quality of the data and make it ready for training and validation purposes. A new framework for Software Defect Prediction (SDP) has been proposed by using the integration of Cosine Convolutional Neural Networks (Cos-CNN) and Cross-Contextual Attention (XCA), which captures spatial and contextual features of data effectively. The hyperparameters in this model have been fine-tuned with Sardine Optimization Algorithm (SOA) in order to get improved performances over diverse datasets. Experimental results show that the proposed framework achieves an accuracy of 99.9%, a true positive rate of 99.9%, and a precision of 99.8% while maintaining a false positive rate of 7.2%. The results clearly prove that the model is performing better than traditional methods. The conclusion shows that the framework can increase the reliability of defect prediction, thus enabling software practitioners to deliver high-quality and maintainable software within tight deadlines and budgets © 2025 ieee.

关键词： Reliability analysis

来源：评论

学校读者我要写书评

暂无评论

Predictive Analysis of Kidney Diseases with Artificial Intelligence and data science

Predictive Analysis of Kidney Diseases with Artificial Intel...

引用

2025 International conference on Visual Analytics and data Visualization, ICVADV 2025

作者： Eswar, G. Hariharan, C. Lavein, S. Akilandeswari, V. Velammal College of Engineering and Technology Department of Computer Science and Engineering India

ISBN: (纸本)9798331521394

In the Field of Medical diagnosis, nowadays there are many new methods are getting introduced each day and also gets advanced by many people around the world. The Kidney is one of the most vital organ of a Human body that helps a lot by filtering blood and throws the waste toxic contents through excretory organs. But the food habits and other bad habits can affect the process of Kidney and further even affects kidney. As a result our kidney can also suffer from various disease. Most vital Kidney diseases can include Chronic Kidney Disease(CKD), Diabetic Nephropathy at the 2nd stage of Diabetes, and still many more. In the process of predicting of these diseases, we can use machine learning algorithms like Random Forest with Decision Tree and Supervised Learning algorithms we can train a model that can use the previous datasets to clarify if the new person is diagnosed with the particular Kidney disease. The Random Forest algorithm provides around 90% accuracy that is better in prediction of results for the collected information. Using these techniques we can detect the problem at early stage which can give a greater chance to prevent it from getting worse. © 2025 ieee.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

A 133.6-µW 1kHz-BW Multi-Bit 2nd-Order Incremental ADC Achieving 115.4-dB SndR with Low-Cost Coarse-Sorting DEM and Zip-Extended-Counting

A 133.6-µW 1kHz-BW Multi-Bit 2nd-Order Incremental ADC Achi...

引用

Custom Integrated Circuits conference (CICC)

作者： Yajie Zhao Yongjie Ye Shaokai Yuan Yajie Qin School of Information Science and Technology Fudan University China

ISBN: (数字)9798331517458

ISBN: (纸本)9798331517465

Incremental ADCs (IADCs) are gaining popularity in sensor interfaces and instrumentation applications for their ability to achieve both high resolution and multiplexing-friendly Nyquist-rate conversion [1]. To improve resolution and bandwidth in an energy-efficient manner, high-order and multi-bit methods are commonly employed in IADCs. However, element mismatch in multi-bit DACs can directly impair the IADC linearity. For free-running Delta-Sigma ADCs, dynamic element matching (DEM) techniques such as data weighted averaging (DWA), are potential solutions. Unfortunately, the effectiveness of these methods has been degraded due to the non-uniform weighting in high-order IADCs [2], which places limitations on achieving high SndR. In [3], a Smart-DEM algorithm was proposed to dynamically and serially cancel out elements' mismatch based on the weights. However, the Smart-DEM operates with a high-speed clock (N 2 x Fs), where N is the number of elements, and its hardware complexity grows logarithmically with the oversampling rate (OSR), leading to significant hardware and power consumption overhead.

关键词： Multiplexing Power demand Instruments Heuristic algorithms Energy resolution Linearity Hardware Energy efficiency Complexity theory Clocks

来源：评论

学校读者我要写书评

暂无评论

Generative AI in Computer science Education: Insights from Topic Modeling and Text Network Analysis

Generative AI in Computer Science Education: Insights from T...

引用

Advanced Innovations in Smart Cities (ICAISC), International conference on

作者： May Alashwal Department of Computer Science and Information Technology Jeddah International College Jeddah Saudi Arabia

ISBN: (数字)9798331506995

ISBN: (纸本)9798331507008

The rapid evolution of generative artificial intelligence (AI) is reshaping educational landscapes., particularly in computer science education. This study investigates research trends in generative AI applications through text network and topic modeling analyses. A comprehensive literature review across ieee Xplore., Scopus., and Web of science identified 151 studies published between 2023 and 2024. Text network analysis revealed that “AI.,” “student.,” “education.,” “learning.,” and “performance” were the most frequently occurring terms., highlighting key research themes. Ego-network analysis demonstrated strong interconnectivity between educational AI tools and student learning outcomes. Using Latent Dirichlet Allocation (LDA)., four major research topics emerged: educational chatbots (35.1 %)., AI literacy (25.8%)., exam performance (21.8%)., and technology integration (17.2 % ). Findings indicate a dominant focus on chatbots for student engagement., while ethical concerns and multimodal AI applications remain underexplored. The study underscores the necessity of addressing AI literacy gaps and enhancing interdisciplinary AI integration in educational settings. Despite its potential., generative AI adoption is hindered by privacy risks., uneven technological access., and the lack of standardized policies. Future research should focus on ethical AI frameworks., multimodal AI tools., and long-term learning outcomes. This study provides a data-driven foundation for understanding the evolving role of generative AI in education and its implications for educators., policymakers., and researchers.

关键词： Ethics Analytical models Privacy Generative AI Computational modeling Education Network analyzers Chatbots Market research Computer science education

来源：评论

学校读者我要写书评

暂无评论

Torch: Software Package For The Search Of Linear Binary Codes 2

Torch: Software Package For The Search Of Linear Binary Code...

引用

2nd ieee conference on information technology and data science, citds 2022

作者： Hannusch, Carolin Major, Sandor Roland University of Debrecen Kassai Út Faculty of Informatics Department of Computer Science Kassai ut 26 Debrecen26 H-4028 Hungary

ISBN: (数字)9781665496537

ISBN: (纸本)9781665496537

We describe a software package created by the authors that can be used to search for linear binary codes with almost arbitrary conditions. The package is easily extensible and reconfigurable to suit the specific needs of the search. The main function can be used to search for currently unknown linear codes, or to quickly generate examples of known codes. © 2022 ieee.

关键词： Software packages

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 << < 1 2 3 4 5 6 7 8 9 10 > >>

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：