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

29,613 篇 会议
20,483 篇 期刊文献
503 册 图书

馆藏范围

50,599 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

31,149 篇 工学
- 18,344 篇 计算机科学与技术...
- 14,729 篇 软件工程
- 8,042 篇 信息与通信工程
- 5,700 篇 电气工程
- 5,674 篇 电子科学与技术（可...
- 5,443 篇 控制科学与工程
- 3,611 篇 生物工程
- 3,159 篇 光学工程
- 2,882 篇 生物医学工程（可授...
- 2,125 篇 机械工程
- 2,111 篇 动力工程及工程热...
- 1,942 篇 化学工程与技术
- 1,882 篇 材料科学与工程（可...
- 1,877 篇 仪器科学与技术
- 1,100 篇 交通运输工程
- 1,067 篇 网络空间安全
18,864 篇 理学
- 8,838 篇 数学
- 7,002 篇 物理学
- 4,061 篇 生物学
- 3,234 篇 统计学（可授理学、...
- 2,261 篇 系统科学
- 2,246 篇 化学
6,952 篇 管理学
- 4,595 篇 管理科学与工程(可...
- 2,537 篇 图书情报与档案管...
- 2,281 篇 工商管理
2,996 篇 医学
- 2,404 篇 临床医学
- 2,133 篇 基础医学(可授医学...
- 1,266 篇 药学(可授医学、理...
- 1,259 篇 公共卫生与预防医...
1,422 篇 法学
- 1,232 篇 社会学
841 篇 经济学
542 篇 农学
476 篇 教育学
262 篇 文学
101 篇 军事学
55 篇 艺术学
7 篇 哲学
6 篇 历史学

主题

1,192 篇 accuracy
1,123 篇 deep learning
1,069 篇 computer science
894 篇 machine learning
887 篇 computational mo...
762 篇 training
752 篇 feature extracti...
663 篇 internet of thin...
565 篇 optimization
559 篇 real-time system...
514 篇 predictive model...
482 篇 artificial intel...
458 篇 convolutional ne...
426 篇 support vector m...
402 篇 data models
376 篇 neural networks
353 篇 robustness
339 篇 analytical model...
336 篇 wireless sensor ...
327 篇 computer archite...

机构

618 篇 department of el...
189 篇 department of co...
155 篇 school of electr...
128 篇 school of automa...
128 篇 school of comput...
120 篇 department of co...
115 篇 school of electr...
115 篇 school of electr...
110 篇 college of compu...
110 篇 school of comput...
106 篇 department of ph...
102 篇 faculty of scien...
102 篇 department of co...
101 篇 departamento de ...
100 篇 faculté des scie...
98 篇 school of comput...
93 篇 department of ph...
93 篇 department of ph...
92 篇 north-west unive...
87 篇 department of ph...

作者

322 篇 niyato dusit
116 篇 han zhu
96 篇 ferrara g.
95 篇 ardid m.
94 篇 calvo d.
93 篇 chen a.
91 篇 c. alexa
90 篇 j. m. izen
90 篇 s. veneziano
90 篇 g. bella
90 篇 d. calvet
90 篇 c. amelung
90 篇 y. tayalati
89 篇 j. strandberg
89 篇 n. orlando
89 篇 g. spigo
89 篇 v. chiarella
89 篇 f. siegert
88 篇 f. buehrer
88 篇 a. t. law

语言

46,267 篇 英文
3,821 篇 其他
495 篇 中文
32 篇 日文
10 篇 德文
8 篇 法文
4 篇 朝鲜文
2 篇 荷兰文
2 篇 俄文
1 篇 斯洛文尼亚文

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

共 50599 条记录，以下是731-740 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 Credit Card Fraud Detection: A Comparative Analysis of Anomaly Detection Models

Enhancing Credit Card Fraud Detection: A Comparative Analysi...

引用

2024 IEEE International Conference on computer Vision and Machine Intelligence, CVMI 2024

作者： Sherwin Akshay, J.G. Vinusha, T. Sharon Bianca, R. Sarath Krishna, C.K. Radhika, G. Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350376876

Financial fraud poses a major threat to financial service institutions and clients, necessitating advanced anomaly detection capabilities. This paper delves into related deep learning models which can be be used to differentiate and detect fraudulent transactions from normal transactions and flag anomalies. Challenges include evolving attack strategies, class imbalance, and model interpret-ability. The proposed methods utilize of a synergistic combination of ensemble learning techniques and unsupervised deep neural networks, like autoencoders and recurrent neural networks. The outcomes exhibit reliable results on credit card transaction datasets. A comprehensive comparative analysis follows to compare the proposed approach to traditional fraud detection methods, demonstrating its superiority in accurately identifying fraudulent transactions, adapting to emerging threats, handling high-dimensional data, and mitigating class imbalances with respect to data privacy and security. © 2024 IEEE.

关键词： Contrastive Learning

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

Yolo-based Deep Learning Techniques for Identifying Floating Bottles in Inland Water: A Comprehensive Analysis 15

Yolo-based Deep Learning Techniques for Identifying Floating...

引用

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

作者： Devi, B Saranya Gupta, Deepa Singh, Rimjhim Padam Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350370249

Floating trash like bottles are one of the main causes of the serious environmental threat posed by the growing pollution of inland water bodies. Conservation efforts are hampered by the lack of effective and affordable techniques for locating and retrieving these bottles. Real-time object detection algorithms in conjunction with unmanned boats can offer ways to remove floating trash from rivers. A popular real-time object detection model is the You Only Look Once (Yolo) Series. Based on efficacy and accuracy rate, each YOLO model gets better than the other. The study presents an extensive analysis of YOLO designs, such as YOLOv5, YOLOv7, YOLOv8, and YOLO-NAS, for bottle identification in inland water. The dataset used is a floating trash in the river, and the performance metrics such as precision, recall and mean average precision are employed, to compare and experimentally validate each algorithm's detection efficiency and accuracy. The methodology trains each architecture for 200 epochs. Regarding the precision of detection, the experimental results shows that YOLOv8-x model has high value of 85.5% and mAP @[IoU=0.5: 0.95] of 43.5%. YOLO-NAS variations have high recall, they are applicable for minimizing missed detection. YOLO-NAS m has a higher recall value of 90%. © 2024 IEEE.

关键词： bottle detection computer vision deep learnings floating trash Flow-Img object detection YOLONAS YOLOv8

来源：评论

学校读者我要写书评

暂无评论

Controlling of Cursor movement with Eyeball using Hidden Markov Model 3

Controlling of Cursor movement with Eyeball using Hidden Mar...

引用

3rd International Conference for Innovation in Technology, INOCON 2024

作者： Havirbhavi, P. Tanusha, G. Ashwini, K. Amrita School of Computing Amrita Vishwa Vidyapeetham Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350381931

In this study, a novel method for moving cursor positions using eye-ball movements with the aid of HMM. Conventional cursor control techniques frequently depend on physical input devices like touchpads or mice, which restricts accessibility for those with motor disabilities. By utilizing the accuracy of eye-tracking technology, our solution creates a smooth interface between digital engagement and human visual attention. We examine the complex patterns of eye movements as users move through their visual environment using HMM. An innovative development in human-computer interaction is the incorporation of an intuitive and adaptable control system that converts complex patterns of eye gaze data into cursor motions. This novel method makes use of state-of-the-art machine learning techniques to identify the relationships between cursor behavior and eye movements. This allows for a degree of accuracy, awareness of context, and instantaneous control over the cursor that is not possible with conventional input techniques. By automatically matching gaze patterns to cursor movements, this intelligent system not only improves user experience but also continually adjusts to the unique behaviors of each user, resulting in a smooth and customized connection with technology. A new frontier in the merging of machine intelligence and human cognition is reflected in the dynamic and responsive interface that emerges as a result. Because of its versatility, our proposed method can improve user experience and overall efficiency by learning and adjusting to the unique behaviors of each user. © 2024 IEEE.

关键词： Eye tracking

来源：评论

学校读者我要写书评

暂无评论

Optimizing Lung Cancer Classification Prediction based on Random Forest and SMOTE Techniques 3

Optimizing Lung Cancer Classification Prediction based on Ra...

引用

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

作者： Bhuvaneswari, R. Roshan, S. Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science Engineering Chennai India

ISBN: (纸本)9798350369083

Lung cancer is the most familiar and deadliest varieties of most cancers global, representing a considerable public health situation. It is a main purpose for cancer-associated deaths among the human race globally, with a remarkable range of new cases identified each 12 months. Despite advances in analysis and treatment, the analysis for lung most cancers sufferers stay poor, highlighting the pressing need for persevered research into etiology, prevention, early detection, and remedy. This examine employs superior statistics analytics and supervised gadget gaining knowledge of techniques, focusing on a comparative evaluation of algorithms such as Random Forest, K-Nearest Neighbor (KNN), Decision Tree, Naive Bayes, and Support Vector Machine (SVM), to classify and predict lung cancer severity. Utilizing dataset from Kaggle optimized using SMOTE technique, the examine demonstrates the Random Forest set of rules's superior overall performance, reaching an accuracy of 98%. The facts, meticulously organized and pleasant-tuned, supports the ability of gadget mastering in enhancing early detection and remedy outcomes. This painting underscores the trans-formative potential of era in healthcare, in particular in addressing complex sicknesses like lung cancer. The research findings have vast implications for records-driven healthcare techniques and customized remedy tactics, paving the manner for modern solutions to fight lung cancer. © 2024 IEEE.

关键词： Lung cancer

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

Enhancing Disaster Awareness using BERT-Based Analysis of Twitter Chat 15

Enhancing Disaster Awareness using BERT-Based Analysis of Tw...

引用

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

作者： Charan Kumar, M. Keya, D. Spoorthi Bharathi Mohan, G. Rithani, M. Pallavi, Gundala Kumar, R. Prasanna Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350370249

Disaster management and response are critical for minimizing the impact of natural and man-made disasters. Social media platforms, particularly Twitter, have emerged as valuable sources of real-time information during disasters. This paper presents a novel approach to enhance disaster awareness through the analysis of Twitter chat using Bidirectional Encoder Representations from Transformers (BERT). BERT is a powerful natural language processing model that has shown remarkable performance in various text analysis tasks. This work illustrates BERT for analyzing tweets related to disasters to improve situational awareness. This work uses disaster-related tweets dataset and preprocess them for analysis and and the data is fine-tuned using pre-trained BERT model. This research demonstrate that the BERT-based approach outperforms traditional methods like BILSTM-Glove with accuracy of 84.25% and BERT-BILSTM-CNN with accuracy of 95% in classifying disaster-related tweets. © 2024 IEEE.

关键词： BERT Disaster Management Disaster Response Natural Language Processing Text Analysis Twitter

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 << < 70 71 72 73 74 75 76 77 78 79 > >>

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：