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

1,194 篇 会议
410 篇 期刊文献
20 册 图书

馆藏范围

1,624 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

882 篇 工学
- 626 篇 计算机科学与技术...
- 531 篇 软件工程
- 195 篇 信息与通信工程
- 135 篇 控制科学与工程
- 128 篇 生物工程
- 117 篇 生物医学工程（可授...
- 104 篇 光学工程
- 91 篇 电气工程
- 77 篇 电子科学与技术（可...
- 56 篇 动力工程及工程热...
- 54 篇 化学工程与技术
- 48 篇 力学（可授工学、理...
- 47 篇 仪器科学与技术
- 46 篇 安全科学与工程
- 43 篇 机械工程
584 篇 理学
- 277 篇 数学
- 184 篇 物理学
- 144 篇 生物学
- 119 篇 统计学（可授理学、...
- 66 篇 地球物理学
- 62 篇 化学
- 53 篇 系统科学
254 篇 管理学
- 155 篇 管理科学与工程(可...
- 117 篇 图书情报与档案管...
- 96 篇 工商管理
118 篇 医学
- 97 篇 临床医学
- 89 篇 基础医学(可授医学...
- 56 篇 公共卫生与预防医...
- 52 篇 药学(可授医学、理...
47 篇 法学
- 40 篇 社会学
35 篇 经济学
27 篇 农学
7 篇 教育学
6 篇 文学
5 篇 军事学
1 篇 哲学
1 篇 艺术学

主题

130 篇 accuracy
67 篇 computational mo...
66 篇 real-time system...
59 篇 deep learning
59 篇 machine learning
56 篇 training
52 篇 predictive model...
44 篇 feature extracti...
43 篇 convolutional ne...
40 篇 machine learning...
33 篇 artificial intel...
33 篇 data models
30 篇 analytical model...
27 篇 internet of thin...
27 篇 visualization
26 篇 adaptation model...
24 篇 medical services
24 篇 forecasting
23 篇 reliability
23 篇 prediction algor...

机构

12 篇 dept. of ece the...
10 篇 dept. of compute...
9 篇 space telescope ...
8 篇 dept. of eee por...
7 篇 dept. of compute...
7 篇 nasa ames resear...
7 篇 computational co...
7 篇 dept. of computa...
6 篇 kalinga universi...
6 篇 data science and...
6 篇 dept. of informa...
6 篇 dept. of computa...
6 篇 center for astro...
5 篇 university of th...
5 篇 dept. of computa...
5 篇 artificial intel...
5 篇 theoretical divi...
5 篇 graphic era hill...
5 篇 velagapudi ramak...
5 篇 dept. of artific...

作者

13 篇 sultanus salehin
13 篇 löhner rainald
12 篇 ashwini kodipall...
11 篇 akib jayed islam
10 篇 kodipalli ashwin...
10 篇 munch elizabeth
9 篇 iwata tetsu
9 篇 yuyun
7 篇 baum joseph d.
7 篇 tymochko sarah
7 篇 khasawneh firas ...
7 篇 rao trupthi
7 篇 trupthi rao
6 篇 brill ryan s.
6 篇 ravishankar saip...
6 篇 shoeibi afshin
6 篇 venu nookala
6 篇 deepak upadhyay
6 篇 wyner abraham j.
6 篇 shreya paul

语言

1,536 篇 英文
80 篇 其他
6 篇 朝鲜文
4 篇 日文
1 篇 中文

检索条件"机构=Dept. Computational Data Science and Engineering"

共 1624 条记录，以下是111-120 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：

Classification of Sarcoma Based on Genomic data Using Machine Learning Models 4

Classification of Sarcoma Based on Genomic Data Using Machin...

引用

4th International Conference on Evolutionary Computing and Mobile Sustainable Networks, ICECMSN 2024

作者： Gala, Pratham Pandloskar, Yash Godbole, Shubham Hakim, Fayed Kanani, Pratik Kurup, Lakshmi Dwarkadas J. Sanghvi College of Engineering Mumbai India Dept. of Artificial Intelligence and Data Science Dwarkadas J. Sanghvi College of Engineering Mumbai India

The proposed work provides a new machine-learnt classification approach for the various types of soft tissue sarcoma based on genomics data which addresses a considerable gap in sarcoma diagnostics. The previous studies have investigated various aspects of sarcoma but this study is unique in that it targets the predicting sarcoma variant types using genetic information, which has not been done before. Random Forest was used as the meta-estimator and a stacking ensemble model comprising of Random Forest, Extreme Gradient Boosting and LightGBM were used for this study. The model which was trained and validated on a complete dataset of 206 adult soft tissue sarcoma samples containing genomic alterations, transcriptomic, epigenomic and proteomic data achieved an accuracy of 89.44% at a precision level as high as 91%. Stratified k-fold cross validation is employed to ensure that class imbalance is not a hindrance to performance. This innovative approach outmatches single classifiers and traditional single model methods at great length hence making it possible and effective to use machine learning on genomic data for predicting sarcoma variants. Thus, the findings from this research could change cancer diagnosis forever;they promise more accurate classification as well as personalized treatment modalities while also providing a framework for analogous applications in other rare complex cancers. © 2025 The Authors.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Illumination Effects on Deep Fake Detection: Performance Comparison of CNN Architectures

Illumination Effects on Deep Fake Detection: Performance Com...

引用

2024 International Conference on Artificial Intelligence and Emerging Technology, Global AI Summit 2024

作者： Yangoti, Sai Bhavya Dumpala, Rohith Punyamurthy, Vijay Jatoth, Ravi Kumar Indian Institute of Information Technology Design and Manufacturing Dept. of Artificial Intelligence and Data Science Kurnool India National Institute of Technology Dept. of Electronics and Communication Engineering Warangal India

ISBN: (纸本)9798350379716

While AI has many advantages, it also has a few drawbacks associated with 'deep fakes.' Deep fakes involve the creation of very realistic videos and images realized through technologies that work with facial and voice modalities for deceptive purposes. Researchers have developed various techniques to detect these manipulated videos and images, employing complex neural network models such as convolutional neural networks (CNNs). However, deep fakes are very difficult to identify due to lighting and shadow effects that may hide some signs of manipulation. No one technique of detection could have the ability of identifying the tampered images under all kinds of illumination conditions. This paper compares different CNN models-ResNet50, EfficientNet, and MobileNetV2-to improve detection accuracy so as to be more resistant to new deep fake techniques, in particular under different illumination conditions. The importance of the study lies in arriving at which of the considered CNN models turns out to be most accurate under a specific illumination effect. Such an understanding could, therefore, improve the results of detection even when applied to cases of tampered faces in fake Aadhaar detection and fake id detection, thereby clearly bringing out the usefulness of the research in practice. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Reliability and Packet Transfer Efficiency of Sparkle Topologies 4

Reliability and Packet Transfer Efficiency of Sparkle Topolo...

引用

4th International Conference on Electronics and Sustainable Communication Systems, ICESC 2023

作者： Joshi, A. Subedha, V. Panimalar Engineering College Poonamallee Dept. of Artificial Intelligence & Data Science Chennai India Panimalar Engineering College Poonamallee Dept. of Cse Chennai600123 India

ISBN: (纸本)9798350300093

Distributed computing through topology control involves making changes to the underlying network (modeled as a graph) to decrease the cost of distributed algorithms when executed across the modified networks. Topology construction builds reduced topology and topology maintenance adopts the reduced topology when the current topology is no longer optimal. This study makes major contributions to topology control by constructing new topologies named sparkle topologies using a ring topology, structured web topology, sun topology, and star topology. The efficiency of the sparkle topologies is checked by calculating the reliability using Wiener Index and data transfer using Cisco packet simulation. data transmission times, the number of hops required, and the number of potential failure points are all reduced in sparkle topologies compared to ring topologies. © 2023 IEEE.

关键词： data transfer

来源：评论

学校读者我要写书评

暂无评论

Generalizing Clinical De-identification Models by Privacy-safe data Augmentation using GPT-4

Generalizing Clinical De-identification Models by Privacy-sa...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Kim, Woojin Hahm, Sungeun Lee, Jaejin Korean National Police Agency Seoul Korea Republic of Dept. of Data Science Seoul National University Seoul Korea Republic of Dept. of Computer Science and Engineering Seoul National University Seoul Korea Republic of

ISBN: (纸本)9798891761643

De-identification (de-ID) refers to removing the association between a set of identifying data and the data subject. In clinical data management, the de-ID of Protected Health Information (PHI) is critical for patient confidentiality. However, state-of-the-art de-ID models show poor generalization on a new dataset. This is due to the difficulty of retaining training corpora. Additionally, labeling standards and the formats of patient records vary across different institutions. Our study addresses these issues by exploiting GPT-4 for data augmentation through one-shot and zero-shot prompts. Our approach effectively circumvents the problem of PHI leakage, ensuring privacy by redacting PHI before processing. To evaluate the effectiveness of our proposal, we conduct cross-dataset testing. The experimental result demonstrates significant improvements across three types of F1 scores. © 2024 Association for computational Linguistics.

关键词： Phishing

来源：评论

学校读者我要写书评

暂无评论

Comparison of Convolutional Autoencoder Architectures for Representation Learning of MODIS Aqua and Terra Observations

Comparison of Convolutional Autoencoder Architectures for Re...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Akanksha M Rajak Deepak Subramani Dept. of Computational and Data Sciences Indian Institute of Science Bengaluru India

ISBN: (数字)9798350360325

ISBN: (纸本)9798350360332

Self-supervised representation learning of Earth observation data is important to perform efficient deep neural network training for classification and regression tasks with limited labels. For example, to predict the onset date of Indian summer monsoon from remotely sensed MODIS data, we have only 21 labels (2002 to 2023), making the training of deep neural networks infeasible. Traditionally, linear methods for dimensionality reduction, such as principal component analysis and dynamic mode decomposition, have been used extensively to represent Earth observation data compactly for use in supervisd learning. Convolutional autoencoders are a class of neural networks that can be used for nonlinear dimensionality reduction and representation learning. In the present work, we compare the performance of multiple autoencoder architectures to learn an efficient representation of observations from the MODIS instrument onboard Aqua and Terra satellites. Specifically, we used and compared multiple ResNet-based autoencoders with different latent dimensions and number of layers, trained from scratch. We show that ResNet50 with 7x7x512 latent dimension serves as a good autoencoder for representation learning purposes.

关键词： Representation learning Training Earth Dimensionality reduction Satellites Self-supervised learning Task analysis

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach for Driver Drowsiness Detection using Deep Neural Networks 2

A Novel Approach for Driver Drowsiness Detection using Deep ...

引用

2nd IEEE International Conference for Women in Innovation, Technology and Entrepreneurship, ICWITE 2024

作者： Sharon, K.V. Natarajan, B. Madhumitha, P. Dhanamathi, A. Prabu, S. Saranya, S. Amrita Vishwa Vidyapeetham Amrita School of Computing Dept. of Computer Science and Engineering Chennai India VIT University School of Computer Science and Engineering Tamilnadu Chennai India Panimalar Engineering College Dept. of Artificial Intell. and Data Science Chennai India Roever Engineering College Department of Computer Science and Engineering Tamilnadu Perambalur India K. Ramakrishnan College of Engineering Dept. of Cse Tamil Nadu Tiruchirappalli621112 India

ISBN: (纸本)9798350383287

One major problem that contributes to many traffic accidents that cause injuries and fatalities all over the world is drowsy driving. This research introduces the novel approach for detecting driver drowsiness using deep networks and computer vision techniques aims to solve this issue and improve road safety. The Proposed system employs an InceptionV3-based Convolutional Neural Network (CNN) model to precisely determine whether the driver's eyes are open or closed. A sizable dataset of eye images taken in actual driving situations is used to train the CNN model. Whenever the indicators of drowsiness are detected, the proposed system will identify them in real time and promptly notify the driver. The proposed model not only has strong real-time capabilities but also exhibits superior accuracy based on stringent evaluation metrics, which makes a significant contribution to efforts aimed at promoting road safety. The performance and adaptability of the system are improved and further integrates alarm activation for drowsiness detection in a variety of driving conditions. © 2024 IEEE.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Exploring the Potential of IoT in Healthcare: Challenges and Opportunities 3

Exploring the Potential of IoT in Healthcare: Challenges and...

引用

3rd International Conference on Technological Advancements in computational sciences, ICTACS 2023

作者： Verma, Navneet Rana, Sumit Gaba, Shivani Nagpal, Shally Paniapt Institute of Engineering and Technology Dept. of Computer Science & Engg. Haryana Panipat India Paniapt Institute of Engineering and Technology Dept. of Artificial Intelligence and Data Science Haryana Panipat India

ISBN: (纸本)9798350342338

Due to the propagation of IoT technologies Healthcare cannot remain outside of this paradigm. In latest years, there has been a lot of interest in the Internet of Things (IoT) technology to relieve the strain on healthcare systems brought on by the ageing population and the rise in persistent illnesses. One of the main obstacles preventing advancement in this field is standardization or global connectivity between the Internet of Things (IoT) and the medical surroundings. All from electrical engineers to data engineers have a significant problem in having to integrate everything in a global setting. The difficulties that healthcare IoT confronts, such as security, privacy, and less-energy procedures, are discussed, and suggestions are provided for future research paths. This paper is written to gather data on various Internet of Things architectures now used in Healthcare and analyse how well different academics have applied it. © 2023 IEEE.

关键词： Architecture Connectivity Healthcare Internet of Things Security

来源：评论

学校读者我要写书评

暂无评论

Personalized Stress Detection using a Lightweight Machine Learning Framework With Convenient Wrist-Worn Sensors

Personalized Stress Detection using a Lightweight Machine Le...

引用

2024 IEEE Signal Processing in Medicine and Biology Symposium, SPMB 2024

作者： Hasan, M. Mithun, S. Mahmud, M. Baral, S. Poudel, K. Middle Tennessee State University Computational And Data Science MurfreesboroTN United States University Of Memphis Dept. Of Computer Science TN United States University Of Memphis Dept. Of Electrical And Computer Engineering TN United States Middle Tennessee State University Dept. Of Computer Science MurfreesboroTN United States Univ. Of Tennessee Health Science Center Div. Of General Internal Medicine MemphisTN United States

ISBN: (纸本)9798350388572

Over 70% Americans experience daily stress, making real-time, accurate stress detection crucial for timely intervention, and promoting physical and mental well-being. In this study, we detect stress using machine learning from publicly available wrist-worn sensor data. We examined both population and individual levels, focusing on simple, computation friendly statistical features for reduced processing to facilitate adoptions in real-life mHealth applications. Our framework demonstrates that stress detection achieves over 96% accuracy at both the population and individual levels, with the Extreme Gradient Boosting classifier achieving the highest predictive accuracy. We found significant variability between individuals and achieved an average accuracy of 99.63% with area under the curve (AUC) 99.23%, F1-score 99.00%, precision, and recall 99.22%. This approach offers a promising solution for real-life stress detection due to its high accuracy and simplicity. © 2024 IEEE.

关键词： LightGBM Machine learning Personalization Stress detection Wrist-band sensors

来源：评论

学校读者我要写书评

暂无评论

Multi-Language Medical Symptoms Analyzer and Hospital Locator Chatbot 4

Multi-Language Medical Symptoms Analyzer and Hospital Locato...

引用

4th International Conference on Expert Clouds and Applications, ICOECA 2024

作者： Ramani, Kasarapu Deepthi, Malepati Sai Naveen, N. Raju, Chintala Jeevan Krishna, Kandati Mohan Babu University Erstwhile Sree Vidyanikethan Engineering College Dept. of Data Science Tirupati India Sree Vidyanikethan Engineering College Department of IT Tirupati India

ISBN: (纸本)9798350385793

Not every hospital may have a help desk to respond to patient queries regarding the disease prediction based on their symptoms and suggesting appropriate department or medicine, providing precautions for that disease in multiple languages. An automated system, such as a chatbot, can effectively address this issue. The medical chatbot is trained using Hybrid Deep Neural Network-Recurrent Neural Networks (DNN-RNN). The user's query accepted through user interface is pre-processed using Natural Language Processing (NLP) and based on the symptoms disease is predicted using wikipedia summary dynamically. The chatbot is user-friendly, and allows the users to interact in three different languages-English, Hindi and Telugu. It also enables users to enter the location in text, and it using Geopy library, Google Places API, and Folium library hospitals' location information is displayed in the user-specified area. The performance of the proposed method is evaluated using accuracy and loss function. This proposed method is a highly effective learning process, making the chatbot a reliable tool for medical queries and disease prediction based on symptoms. © 2024 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Precise Diagnosis of Heart Disease with Stacking Classifier 5

Precise Diagnosis of Heart Disease with Stacking Classifier

引用

5th IEEE International Conference for Emerging Technology, INCET 2024

作者： Jyothsna, V. Poojitha, B. Divya, A. Sai Ganesh, B. Srinija, D. Department of Data Science Mohan Babu University Tirupati India Dept. of information technology Sree Vidyanikethan Engineering College Tirupati India

ISBN: (纸本)9798350361155

Heart disease stands as a significant global health challenge, marked by a worrying rise in prevalence and substantial mortality rates. Despite the wealth of healthcare data, early detection of heart conditions remains elusive. This endeavor aims to address this issue by crafting a predictive model that integrates individual medical histories and lifestyle factors. The proposed methodology centers on the use of a Stacking classifier for heart disease prediction. To gauge the model's efficacy, the Framingham Heart Disease dataset is employed, sourced from the widely recognized Kaggle repository, endorsed by numerous researchers. Evaluation encompasses ensemble model assessments, incorporating critical metrics such as sensitivity, specificity, accuracy, and f-measure. Furthermore, the investigation delves into the application of ensemble methods for forecasting heart disease incidence over a decade, aiming to contribute to more effective strategies for early detection and management. Through the fusion of advanced modeling techniques and comprehensive datasets. © 2024 IEEE.

关键词： Diagnosis

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163页 << < 8 9 10 11 12 13 14 15 16 17 > >>

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：