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

77,941 篇 会议
49,015 篇 期刊文献
1,357 册 图书

馆藏范围

128,313 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

78,115 篇 工学
- 52,438 篇 计算机科学与技术...
- 42,383 篇 软件工程
- 18,898 篇 信息与通信工程
- 12,833 篇 控制科学与工程
- 10,692 篇 电气工程
- 9,893 篇 电子科学与技术（可...
- 9,600 篇 生物工程
- 7,717 篇 生物医学工程（可授...
- 6,820 篇 光学工程
- 5,207 篇 机械工程
- 4,537 篇 化学工程与技术
- 4,282 篇 动力工程及工程热...
- 4,084 篇 仪器科学与技术
- 3,622 篇 材料科学与工程（可...
- 3,264 篇 网络空间安全
- 3,090 篇 安全科学与工程
46,335 篇 理学
- 22,777 篇 数学
- 15,243 篇 物理学
- 11,026 篇 生物学
- 7,578 篇 统计学（可授理学、...
- 5,193 篇 化学
- 4,974 篇 系统科学
20,359 篇 管理学
- 12,774 篇 管理科学与工程(可...
- 8,253 篇 图书情报与档案管...
- 6,034 篇 工商管理
7,976 篇 医学
- 6,453 篇 临床医学
- 5,684 篇 基础医学(可授医学...
- 3,417 篇 药学(可授医学、理...
- 3,376 篇 公共卫生与预防医...
3,837 篇 法学
- 3,254 篇 社会学
2,328 篇 经济学
1,740 篇 农学
1,456 篇 教育学
637 篇 文学
256 篇 军事学
177 篇 艺术学
27 篇 哲学
19 篇 历史学

主题

3,568 篇 accuracy
3,319 篇 computer science
3,153 篇 deep learning
2,759 篇 machine learning
2,595 篇 computational mo...
2,566 篇 feature extracti...
2,387 篇 training
1,705 篇 predictive model...
1,650 篇 internet of thin...
1,636 篇 artificial intel...
1,618 篇 real-time system...
1,607 篇 optimization
1,557 篇 convolutional ne...
1,503 篇 support vector m...
1,350 篇 data models
1,153 篇 data mining
1,143 篇 neural networks
1,117 篇 semantics
1,077 篇 wireless sensor ...
1,019 篇 security

机构

1,090 篇 cavendish labora...
1,018 篇 department of ph...
965 篇 physikalisches i...
952 篇 university of ch...
948 篇 oliver lodge lab...
566 篇 fakultät physik ...
552 篇 department of el...
540 篇 school of physic...
538 篇 horia hulubei na...
538 篇 department of ph...
532 篇 imperial college...
529 篇 school of physic...
512 篇 h.h. wills physi...
504 篇 stfc rutherford ...
500 篇 nikhef national ...
496 篇 school of comput...
483 篇 henryk niewodnic...
478 篇 center for high ...
475 篇 van swinderen in...
475 篇 school of physic...

作者

268 篇 a. gomes
262 篇 niyato dusit
254 篇 barter w.
251 篇 c. alexa
250 篇 d. calvet
248 篇 j. m. izen
242 篇 s. chen
240 篇 c. amelung
239 篇 g. bella
239 篇 j. strandberg
232 篇 beiter a.
229 篇 blake t.
223 篇 bellee v.
223 篇 bowcock t.j.v.
219 篇 betancourt c.
218 篇 amato s.
216 篇 boettcher t.
215 篇 g. spigo
215 篇 brundu d.
215 篇 borsato m.

语言

117,706 篇 英文
9,358 篇 其他
1,203 篇 中文
122 篇 日文
23 篇 德文
13 篇 法文
11 篇 朝鲜文
7 篇 斯洛文尼亚文
4 篇 西班牙文
3 篇 荷兰文
3 篇 俄文

检索条件"机构=Department of Computer Science and Engineering School of Computing"

共 128313 条记录，以下是571-580 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：

AutoGrading Classification of Tamil Descriptive Answers FastText and Roberta-Base Sentence Embedding 5

AutoGrading Classification of Tamil Descriptive Answers Fast...

引用

5th IEEE Global Conference for Advancement in Technology, GCAT 2024

作者： Elango, Vaan Amuthu Pati, Peeta Basa Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798350376685

Considering the challenges associated with manually grading student answer scripts and the significance of the language, an automated approach is developed for assessing Tamil descriptive answers. Three-way assessment system of correct, incorrect, and partially correct is used to improve the autograding categorization accuracy. A total of eight datasets derived from four different dataset's sentence embedding produced by sophisticated natural language processing techniques RoBERTa-Base and FastText was created. To determine the optimal combination of data input, ten models inclusive of deep learning and machine learning models were utilized to perform a grade-based classification. This classification study proved that combination of the QuestionAnswer dataset with FastText embedding yielded the most promising result of F1 Score as 92.1%. The automatic grading methods tailored to the nuances of Tamil language are improved by this research. © 2024 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Automated Short Answer Grading With Word Embedding-Based Semantic Similarity Using PySpark 6

Automated Short Answer Grading With Word Embedding-Based Sem...

引用

6th IEEE International Conference on Recent Advances in Intelligent Computational Systems, RAICS 2024

作者： Akhilesh, P. Amal Krishna, K. Bharadwaj, S Karthick Venugopalan, Manju Amrita School of Computing Department of Computer Science and Engineering Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (纸本)9798350381689

Automated short answer grading, a pivotal advancement in educational assessment methodologies, addresses scalability challenges and streamlines evaluation processes using natural language processing and machine learning. This technology ensures timely, consistent, and objective feedback, replacing manual grading to mitigate biases and variations, thus enhancing the educational experience. The proposed model employs Word2Vec to generate word embeddings for each student response and the corresponding reference answer. By leveraging cosine similarity, the model calculates semantic similarity between the vectors, producing a score ranging from 0 to 1. This cosine similarity score is then scalable, allowing for the computation of final grades based on question-specific weightage, providing a robust and scalable approach for automated short-answer grading. In the context of this work, regression-based evaluation metrics yielded a Mean Squared Error (MSE) of 0.2727 & R2 score of 0.67, demonstrating the efficacy of the automated grading system in achieving accurate and reliable assessments. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Secure Image Transmission with Rubik's, Chaos, DNA, and Homomorphic Approaches 3

Revolutionizing Secure Image Transmission with Rubik's, Chao...

引用

3rd IEEE World Conference on Applied Intelligence and computing, AIC 2024

作者： Rishikesh, Kadiyala Bharadwaj, Nookala Sai Veluchamy, S. Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350384598

This paper presents a framework for secure image encryption with the comparison of qualitative and quantitative aspects of fewnovel and established encryption methods. Rubik's Method, DNA Encoding, Chaotic Systems, and Homomorphic encryption are evaluated for their efficiency in image encryptions. An input image is subjected to successive shifting operations in order to encrypt it using Rubik's method, with the sum of pixel values and predefined keys serving as the basis. The Chaos Map encryption is demonstrated with the use of Arnold Cat map to jumble pixel placements. Further intricacy is introduced by DNA encoding, which converts pixel values into DNA sequences. DNA method is also considered as a hyper-chaotic map. To depict Homomorphic encryption, the Paillier cryptosystem is to perform additive and multiplicative operations on the image. We can learn a lot about the efficiency of encryption from evaluation measures like histograms, Unified Average Changing Intensity, and Computational Costs. © 2024 IEEE.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

A Novel approach for detecting Fibroids in Uterus using Deep Learning models 15

A Novel approach for detecting Fibroids in Uterus using Deep...

引用

15th International Conference on computing Communication and Networking Technologies, ICCCNT 2024

作者： Vyshnavi, Chellu Raj, Chukka Mishal Gopakumar, Gokul Prasanna, Guddeti Bindu Sreevidya, B. Rajesh, M. Department of Computer Science and Engineering Amrita School of Computing Bengaluru Amrita Vishwa Vidyapeetham India

ISBN: (纸本)9798350370249

Uterine fibroids are non-cancerous growths in a woman's uterus and are estimated to occur in 70-80% of women by age 50. Symptoms include heavy menstrual bleeding, pelvic pain, and frequent urination, with complications of anemia, infertility, and reduced quality of life. Deep learning models are being used in many fields like health care, education and so on. Our project, therefore, will focus on the detection of uterine fibroids using deep learning models: CNN, ResNet50, VGG16, InceptionV3, and DCGAN. Although imbalance in the dataset is a problem, we handle it using balancing via SMOTE. They are heterogeneous in appearance, which challenges their detection. Uterine fibroids are thus among the most common complaints for women. We thus employ a variety of deep learning architectures and dataset balancing techniques in order to increase fibroid detection accuracy. Looking at the results, there is promise with increased accuracy and sensitivity—an encouraging sign of our approach in improving diagnostic outcomes for uterine fibroids. Based on the results the most accurate model after balancing the dataset is CNN with an accuracy of 94.843%. ©2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Interpretable AI Insights in Fake News Detection: A Comparative Analysis of CNN and LSTM 15

Interpretable AI Insights in Fake News Detection: A Comparat...

引用

15th International Conference on computing Communication and Networking Technologies, ICCCNT 2024

作者： Kumar, Kanderi Johith Shreya, Kuthati Divakarla, Lasya Priya Nair, Priyanka C. Sampath, Nalini Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350370249

One of the major concerns in today's world is fake news when the majority of people spend most of their time online on social media. People come across various fake news and false information. It is important to acknowledge how such fake news spreads, and it must be prevented. This project combines text processing with the utilization of relevant machine learning techniques, like categorization based on various text features. The model has undergone training using both traditional machine learning algorithms and deep learning techniques, including Logistic Regression, Decision Tree Classifier, Naïve Bayes Classifier, Support Vector Machine (SVM), Long Short-Term Memory (LSTM), and Convolutional Neural Network (CNN). Logistic Regression and CNN have exhibited the highest model accuracy, achieving 95%. Evaluations have been conducted to make comparisons about the efficacy of the machine learning and deep learning approaches utilized. Explainability techniques like Local Interpretable Model Agnostic Explanations (LIME) have been applied to discern the keywords influencing the classification of data into fake or genuine categories. © 2024 IEEE.

关键词： Explainable AI Techniques (XAI) Fake News Text Classification TFIDF Vectorization Word Embeddings

来源：评论

学校读者我要写书评

暂无评论

TweetFeel: Analyzing Emotions in the Twittersphere

TweetFeel: Analyzing Emotions in the Twittersphere

引用

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

作者： Adithya Gokulan, S. Reddy, Mahati Varshith, M. Venugopalan, Manju Amrita School of Computing Amrita Vishwa Vidyapeetham Department of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350359688

The majority of people on the planet now have access to the Internet for text, image, audio, and video communication. Through social media, people from many backgrounds share knowledge about current events and express their own opinions on them. Analyzing people's emotions is necessary to comprehend and identify the behavior of such vast amounts of textual data about them. The study focuses on information gathered from Twitter, one of the most widely used social media platforms, by examining both historical and real-time feeds and extracting emotions from them. The necessary English-language Twitter data is transformed into a vector of six emotions, and supervised learning methods like Logistic Regression, Naive Bayes, SVM, Decision Tree, Random Forest, Gradient Boosting, and Multi-Layer Perceptron are utilized to identify the label of one of the basic human emotions. Gradient Boosting and SVM are the top-performing models that reported the highest F1-Score of 0.88 among the other models. Sadness and joy came out to be the best-performing emotions whereas it was comparatively difficult to predict surprise emotion. © 2024 IEEE.

关键词： Tweets

来源：评论

学校读者我要写书评

暂无评论

AI-Based Posture Correction, Real-Time Exercise Tracking and Feedback using Pose Estimation Technique 3

AI-Based Posture Correction, Real-Time Exercise Tracking and...

引用

3rd International Conference on Communication, Control, and Intelligent Systems, CCIS 2024

作者： Kaushik, M. Kandala, Mahita Vignesh, G.S. Vithyatharshana, N. Palaniswamy, Suja Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798331528201

Physical activity is an essential component of physical and mental health-being. Although physical activity offers numerous advantages, maintaining proper posture could be difficult, especially when it comes to complex movements or poses. This task is even challenging for the ones who exercise at home, those who have disabilities, or social anxiety. In order to deal with this issue, this work proposes an AI gym tracker app powered by advanced pose estimation technology through OpenCV and Mediapipe which are two popular frameworks being used in computer vision to access and solve several real-life problems through pose-estimation. This paper describes an AI-powered gym tracker app built with MediaPipe and OpenCV. It uses real-time pose estimation and joint angle calculation to provide feedback on exercise form as well as expanded rep count. This application employs a unique method by using dynamic angle thresholds and joint distance computations to provide precise feedback about user posture. It demonstrates the application's effectiveness in assisting users in maintaining proper form and tracking their workout progress by demonstrating a counter. Future work is to broaden its functionality to embrace more exercises and to further add other forms of decision feedback system, thus exploring the possible incorporation of this application into various fitness apps which would in-turn enhance the overall experience of the users. © 2024 IEEE.

关键词： mHealth

来源：评论

学校读者我要写书评

暂无评论

Harnessing the Power of web3: A Blockchain Approach to Crowdfunding 15

Harnessing the Power of web3: A Blockchain Approach to Crowd...

引用

15th International Conference on computing Communication and Networking Technologies, ICCCNT 2024

作者： Savant, Richa Vivek Sunder, S. Navin Spoorthi, M. Rajagopal, Shinu M. Balakrishnan, Roshni M. Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science & Engineering Bengaluru India

ISBN: (纸本)9798350370249

Conventional crowdfunding methods frequently involve intermediaries, lack transparency, encounter regulatory challenges, and are not highly secure. Instead, a blockchain-based agreement can be formed, carried out, and enforced between members without the assistance of a third party. To achieve this, creating smart contracts, with blockchain-compatible executable code, is crucial. Additionally, cryptocurrency can be used, for which crypto wallets can securely store private keys, giving users access, control, and ownership over their digital assets while also encouraging decentralization and interoperability. Crypto wallets protect users' assets against cyber threats and unauthorized access by utilizing technologies like encryption, two-factor authentication, and multi-signature support to provide strong authentication and protection. Using a web3 platform like Thirdweb eliminates the need for an administrator by providing automated tools and infrastructure that streamline the creation, management, and deployment of decentralized applications. This study proposes the use of web3 technology to create a multi-user cross-platform blockchain-based crowdfunding DApp which employs Ethereum, smart contracts via solidity and crypto wallets for decentralized fundraising. © 2024 IEEE.

关键词： Authentication Blockchain Crowdfunding Crypto Wallets Cryptocurrency DApp Digital Assets Ethereum Private Keys Smart Contracts Solidity Thirdweb web3 Technology

来源：评论

学校读者我要写书评

暂无评论

Malicious Query Detection Using Lexical Analyzer and Machine Learning 3

Malicious Query Detection Using Lexical Analyzer and Machine...

引用

3rd International Conference on Electrical, Electronics, Information and Communication Technologies, ICEEICT 2024

作者： Prahalya, S.P. Samhitha, Sankepalli Sai Ratan, Vadapalli Sanjana Belwal, Meena Amrita School of Computing Amrita Vishwa Vidyapeetham Department of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350369083

SQL injection attacks continue to pose a serious threat in web security that calls for methods of creative solving. With database systems becoming more dynamic and complex, threat landscapes continuing to change, old techniques often do not work well. To address this issue, the study proposes a framework that involves combining machine learning techniques with a custom lexical analyser to predict normal and abnormal SQL queries that target MySQL data tables. This study uses six machine learning classifiers-Support vector machines, Logistic Regression, Linear Regression, Naïve Bayes, K-Nearest Neighbors and Random Forest for accurately telling apart malicious and non-malicious queries and to identify potential risk of SQL injection, contributing to overall web security. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Smart Surveillence Drone with Navigation System 5

Smart Surveillence Drone with Navigation System

引用

5th IEEE International Conference on computing, Power, and Communication Technologies, IC2PCT 2024

作者： Padmavathi, A. Vyasasreevedansh, B. Amrita School of Computing Amrita Vishwa Vidyapeetham Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350383522

At present, in this time of technological advancement and an urgent necessity for advanced spying abilities, the 'Smart Surveillance Drone with Navigation System' program is leading the way in redefining the field of surveillance and safeguarding. The way in which this project is leading is through the integration of the most advanced drone technology, complex navigation systems, and real-time computer vision, striving to create an independent drone model that can be identified and followed by human subjects in real-time while travelling between predetermined waypoints. The key aims of the program involve the assembling and integrating of a range of sensors, such as GPS, IMU, cameras, ultrasonic sensors, and LiDAR, alongside the production of independent navigation algorithms and computer vision technology. By combining cutting-edge technologies such as wireless communication, real-time data processing, and machine learning, the revolutionising of surveillance in several domains is being set out by this project. The adaptability and reliability of the system will be verified by rigorous field testing, while the experience will be enhanced by user feedback and training. With such advancements, the future of disaster response, agriculture, search and rescue operations, and security is promised to be innovative and efficient. This project that's set to change how we think about surveillance and security is captured by this short summary, and the way is being paved for a safer and more secure world. © 2024 IEEE.

关键词： Autonomous Surveillance Navigation System Real-time Object Detection Security Innovation Surveillance Drone

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 << < 54 55 56 57 58 59 60 61 62 63 > >>

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：