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

14,303 篇 会议
98 册 图书
66 篇 期刊文献
1 篇 资讯

馆藏范围

14,468 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

9,574 篇 工学
- 8,758 篇 计算机科学与技术...
- 6,972 篇 软件工程
- 2,028 篇 信息与通信工程
- 1,454 篇 控制科学与工程
- 1,256 篇 电气工程
- 907 篇 生物工程
- 473 篇 网络空间安全
- 436 篇 电子科学与技术（可...
- 421 篇 生物医学工程（可授...
- 313 篇 化学工程与技术
- 307 篇 仪器科学与技术
- 294 篇 机械工程
- 268 篇 光学工程
- 256 篇 安全科学与工程
- 240 篇 交通运输工程
- 182 篇 动力工程及工程热...
3,191 篇 理学
- 1,265 篇 数学
- 932 篇 生物学
- 900 篇 物理学
- 503 篇 统计学（可授理学、...
- 462 篇 系统科学
- 378 篇 化学
2,915 篇 管理学
- 1,865 篇 图书情报与档案管...
- 1,281 篇 管理科学与工程(可...
- 472 篇 工商管理
613 篇 医学
- 418 篇 临床医学
- 369 篇 基础医学(可授医学...
- 353 篇 公共卫生与预防医...
470 篇 法学
- 438 篇 社会学
229 篇 教育学
- 225 篇 教育学
207 篇 文学
159 篇 经济学
98 篇 农学
11 篇 艺术学
9 篇 军事学
1 篇 哲学

主题

2,963 篇 natural language...
874 篇 natural language...
839 篇 natural language...
817 篇 semantics
577 篇 deep learning
554 篇 machine learning
533 篇 sentiment analys...
507 篇 data mining
395 篇 knowledge engine...
368 篇 large language m...
362 篇 training
355 篇 computational mo...
312 篇 feature extracti...
309 篇 speech recogniti...
304 篇 speech processin...
275 篇 signal processin...
272 篇 accuracy
241 篇 neural networks
239 篇 transformers
237 篇 knowledge based ...

机构

57 篇 institute of inf...
52 篇 school of cyber ...
49 篇 school of commun...
40 篇 chitkara univers...
40 篇 maharishi school...
35 篇 lovely professio...
34 篇 university of ch...
34 篇 school of comput...
33 篇 school of comput...
31 篇 xi'an university...
30 篇 faculty of engin...
27 篇 department of el...
23 篇 school of inform...
22 篇 school of comput...
22 篇 department of co...
20 篇 centre of interd...
19 篇 beijing universi...
18 篇 pune
17 篇 zhejiang univers...
17 篇 college of compu...

作者

38 篇 ren fuji
27 篇 wan wanggen
17 篇 liu yang
16 篇 yixin zhong
14 篇 wu jin
14 篇 lei li
14 篇 shingo kuroiwa
13 篇 zhang tao
13 篇 wang lei
13 篇 sabetzadeh mehrd...
13 篇 zheng dequan
13 篇 liu jie
12 篇 tiejun zhao
12 篇 f. ren
12 篇 li ying
11 篇 li sheng
11 篇 yang yang
11 篇 tao zhang
11 篇 arora chetan
11 篇 wang wei

语言

10,918 篇 英文
3,521 篇 其他
53 篇 中文
1 篇 土耳其文

检索条件"任意字段=IEEE International Conference on Natural Language Processing and Knowledge Engineering"

共 14468 条记录，以下是4871-4880 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：

A Two-stage Algorithm for Automatic Diagnosis of Keratitis 4

A Two-stage Algorithm for Automatic Diagnosis of Keratitis

引用

4th international conference on natural language processing, ICNLP 2022

作者： Jiang, Jiewei Liu, Wei Gong, Jiamin Pei, Mengjie Xi'an University of Posts & Telecommunications School of Electronics Engineering Xi'an China Xi'an University of Posts & Telecommunications School of Communication and Information Engineering Xi'an China Xi'an University of Posts & Telecommunications School of Computer Science and Technology Xi'an China

ISBN: (数字)9781665495448

ISBN: (纸本)9781665495448

Keratitis, as a corneal disease, is an important factor resulting in corneal blindness. Therefore, the key to prevent corneal blindness is how to diagnose keratitis with high accuracy. Hence, in this paper, a two-stage deep learning algorithm for automatic diagnosis of keratitis is proposed based on automatic localization of ocular surface. Firstly, the target detection algorithm, Single Shot MultiBox Detector (SSD) is used to automatically locate the conjunctival and corneal regions on the slit-lamp images, and remove the eyelid and surrounding noise area. Then, DenseNetl21 is applied to automatically classify the located conjunctival and corneal regions, so as to realize the diagnosis of keratitis, other corneal abnormalities, and normal cornea. Based on the dataset of 6,567 slit-lamp images, the accuracy of the proposed method improves by 0.8% compared to categorizing raw images directly, and also improves by 2.1% and 2% respectively on external test sets from two other hospitals. This study provides an effective artificial intelligence algorithm for assisting doctors in the early diagnosis of keratitis, and has great significance for the treatment of keratitis. © 2022 ieee.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Exploring knowledge Landscapes: Clustering and Topic Modeling of Sebha University Scientific Publications

Exploring Knowledge Landscapes: Clustering and Topic Modelin...

引用

Sciences and Techniques of Automatic Control and Computer engineering MI-STA, ieee international Maghreb Meeting of the conference on

作者： Roqyia Abdelhamed Mansour Essgaer Department of Computer Sciences Faculty of Science Sebha University Sebha Libya Department of Information Technology Faculty of information Technology Sebha University Sebha Libya

ISBN: (数字)9798350372632

ISBN: (纸本)9798350372649

The continuous and exponential growth in scientific publications poses a challenge in manually sorting and searching for specific topics within a university's publications. Recent advancements in artificial intelligence, natural language processing, and clustering methods, particularly the K-Means, have shown satisfactory performance in handling large volumes of textual data. Furthermore, topic modeling methods, notably praised for their effectiveness in organizing textual documents. This study focuses on evaluating the performance of the K-Means and Latent Dirichlet Allocation in clustering Sebha University scientific publications. Different term weighting is employed namely term frequency inverse document frequency, and Word2Vec to represent the tokens. K-Means demonstrated notable performance when coupled with Word2vec, as indicated by metrics such as the Davies-Bouldin Index, Silhouette Score, Calinski-Harabasz Index, and Inertia. The best performance was observed when using term frequency inverse document frequency with the Entropy metric. The evaluation metrics for K-Means did not unanimously agree on the optimal number of clusters. In contrast, Latent Dirichlet Allocation consistently performed well, with all measurements agreeing on the best results with the smallest number of clusters. Among the various combinations tested, Latent Dirichlet Allocation paired with Word2vec produced the best results across metrics, demonstrating superior cohesion strength through the topic coherence metric and minimizing noise aggregates based on the entropy metric.

关键词： Measurement Automatic frequency control Refining Noise Entropy natural language processing Resource management

来源：评论

学校读者我要写书评

暂无评论

Global Multi-scale Fog Salient Object Detection Based on Local Attention Feature 4

Global Multi-scale Fog Salient Object Detection Based on Loc...

引用

4th international conference on natural language processing, ICNLP 2022

作者： Lin, Zhenxian Yan, Shuai Wu, Chengmao Xi'an University of Posts and Telecommunications School of Science Xi'an China Xi'an University of Posts and Telecommunications School of Communications and Information Engineering Xi'an China Xi'an University of Posts and Telecommunications School of Electronic Engineering Xi'an China

ISBN: (数字)9781665495448

ISBN: (纸本)9781665495448

In foggy conditions, the target in the image is affected by fuzzy edge and low resolution, which limits the accuracy of target detection. In order to improve the detection accuracy of salient targets in foggy conditions, a detection algorithm with two-path global multi-scale and local attention features was proposed. Firstly, the image is defogged. Then the network model is divided into two branches after passing through the backbone network to extract the local and global features of the image respectively. At the same time, attention mechanism is introduced to enhance local features. Finally, local and global features at different scales are integrated to obtain more expressive output features. The proposed algorithm is tested on three data sets of PASCAL-S, DUT-OMRON and SOD. It was found that the maximum values of F-measure were 0.901, 0.832 and 0.896, and MAE were 0.061, 0.043 and 0.073, respectively. The results show that the proposed algorithm performs well in foggy weather compared with existing algorithms, which verifies the effectiveness of the proposed algorithm. © 2022 ieee.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Integrating Embedded Systems with natural language processing: Innovations and Applications in Intelligent Systems

Integrating Embedded Systems with Natural Language Processin...

引用

international conference on ICT in Business Industry & Government (ICTBIG)

作者： Anurag Shrivastava Ruchira Rawat Ramy Riad Al-Fatlawy Saloni Bansal Archana Sehgal Priyanka Gupta Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai Tamilnadu Department of Computer Science & Engineering Graphic Era Deemed to be University Dehradun Department of Computers Techniques Engineering College of Technical Engineering The Islamic University Najaf Iraq Department of Computer Engineering and Applications GLA University Mathura Lovely Professional University Phagwara India Department of Computer Science and Engineering Institute of Aeronautical Engineering Hyderabad Telangana

ISBN: (数字)9798331518981

ISBN: (纸本)9798331518998

The amalgamation of natural language processing (NLP) with Embedded Systems signifies a revolutionary progression in the creation of intelligent systems, permitting them to participate in interactions that are akin to those of humans. This study looks into the creative ways that NLP and embedded technology can be used in a variety of industries, such as healthcare, automotive, and smart homes. The paper illustrates how NLP enables embedded devices to comprehend, interpret, and react to human commands, improving user experience and operational efficiency, by looking at the underlying principles. The main obstacles to this integration are thoroughly examined, including resource shortages, the need for real-time processing, and environmental restrictions. The study emphasises how important it is to use low-power, compact NLP models that enable real-time language processing without sacrificing system efficiency. Additionally, the research discusses the fundamental approaches for improving these models’ using methods like transfer learning, quantisation, and model reduction. In the end, this work seeks to shed light on the enormous potential of voice-enabled intelligence in embedded systems, opening the door to more interactive, intuitive, and adaptable technologies that can easily adjust to changing human needs. This study advances the continuous development of smart gadgets by bridging the linguistic and technological divide, increasing their usability and accessibility in daily life.

关键词： Support vector machines Embedded systems Computational modeling Hidden Markov models Smart homes Medical services Transformers natural language processing Real-time systems Long short term memory

来源：评论

学校读者我要写书评

暂无评论

Creating An Artificial Intelligence-Powered Image Classification Model For Specially Abled Persons 9

Creating An Artificial Intelligence-Powered Image Classifica...

引用

9th international conference on Advanced Computing and Communication Systems, ICACCS 2023

作者： Srikanth, Kandula Venuthurumilli, Munni Manaswini, Nune Vl Somayajulu, M.V.N.N.S.S.R.K.S. Seshadri Rao Gudlavalleru Engineering College Department of Information Technology Andhra Pradesh India PB Siddhartha College of Arts and Science Department of Computer Science Andhra Pradesh Vijayawada India Nalanda Degree College Department of Computer Science Andhra Pradesh Vijayawada India Krishna University Machilipatnam Department of Computer Science and Engineering Andhra Pradesh India

ISBN: (纸本)9798350397376

This article describes how to use Python's Keras deep learning package to build an Artificial Intelligence-powered image classification model. Speech, text, and other types of input are transformed into machine-readable form by the system using natural language processing (NLP) and speech recognition technology. Other assistive technologies can be adapted to and used with the system. The purpose of this study is to show how straightforward and simple it is to use Keras to create an accurate picture categorization model. Convolutional neural network (CNN) architecture, a kind of deep learning model best suited for image classification tasks, is built first in the procedure. Following that, the model is assembled and trained on a sizable dataset, where it discovers patterns and features in the photos. The model is tested and evaluated on fresh data after training to ensure accuracy. The outcomes demonstrate that Keras can efficiently and accurately construct an AI-powered picture classification model, making it a useful tool for resolving practical computer vision issues. This demonstrates the capabilities of AI in this area and offers a thorough manual for people wishing to create their own picture classification models using Keras. © 2023 ieee.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Improvement of Deep Learning Models by Excluding Inappropriate Data Based on Interpretability

Improvement of Deep Learning Models by Excluding Inappropria...

引用

ieee Annual international Computer Software and Applications conference (COMPSAC)

作者： Saneyasu Yamaguchi Fuma Hirabayashi Atsuki Tamekuri Department of Information and Communications Engineering Kogakuin University Tokyo Japan Electrical Engineering and Electronics Kogakuin University Graduate School Tokyo Japan

ISBN: (数字)9798350376968

ISBN: (纸本)9798350376975

Deep learning and large scale language models have significantly advanced data engineering, particularly in natural language processing. However, it has been pointed out that deep learning is a black box, raising concerns about its interpretability. To address this, methods for extracting decision bases and training data that influence the decision have been proposed. This paper focuses on a method for extracting training data that have a large impact on the decision, and proposes a method for improving training data by identifying and excluding training data that lead to incorrect decisions. The method divides the training data into subsets-the training data in the training data, the verification data in the training data, and the test data in the training data-and uses them to train and test the task. It then identifies and excludes training data that cause incorrect classifications. We evaluate this approach on document classification tasks using BERT, which is a large scale language model, demonstrating its effectiveness. We also evaluate our method on popular corpora, highlighting both its strengths and limitations.

关键词： Deep learning Training Accuracy Training data Data engineering natural language processing Data models

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Predictive Skin Disease Diagnosis and Analysis

Deep Learning-Based Predictive Skin Disease Diagnosis and An...

引用

knowledge engineering and Communication Systems (ICKECS), international conference on

作者： Manikundan Karnati Pavan Sai Rohith Kumar Pittala K. Radhika K. Sugamya Department Of Artificial Intelligence and Data Science Chaitanya Bharathi Institute of Technology Hyderabad India Department Of Information technology Chaitanya Bharathi Institute of Technology Hyderabad India

ISBN: (数字)9798350359688

ISBN: (纸本)9798350359695

In modern medical diagnostics, AI integration is crucial for enhancing the prediction or classification of diseases. The primary goal of this project is to develop a multimodal deeplearning system capable of diagnosing skin diseases. The project integrates image analysis for skin conditions and the interpretation of textual descriptions of symptoms, ultimately providing an accurate diagnosis for users. It integrates deep learning and natural language processing to diagnose skin diseases. It Enhances healthcare by providing accurate diagnoses, and remedies and improving accessibility for self-diagnostics.

关键词： knowledge engineering Deep learning Accuracy Image analysis Communication systems Predictive models Skin

来源：评论

学校读者我要写书评

暂无评论

Context-aware DL-based Approach Combining GNN and Attention for CSI-based Indoor Localization 4

Context-aware DL-based Approach Combining GNN and Attention ...

引用

4th international conference on Computer, Big Data and Artificial Intelligence, ICCBD+AI 2023

作者： Sun, Daobo Yu, Haohao Dong, Tao Meng, Xiangxu Tang, Bin Harbin Engineering University College of Computer Science and Technology Harbin150000 China Harbin Engineering University Innovation and Development Base Qingdao266000 China

ISBN: (纸本)9798350373233

In recent years, due to the limitations of GPS in indoor environments, where signals may be obstructed or reflected, significant advancements have been made in indoor localization technologies to address this gap. Among these, fingerprinting localization based on Channel State Information (CSI) has garnered widespread attention owing to its robustness and cost-effectiveness. The inherent nature of deep learning (DL), with its offline training and online positioning capabilities, aligns seamlessly with CSI fingerprinting localization. With the emergence of deep learning techniques, fingerprinting localization has undergone transformative changes. However, most of the current DL-based approaches are inspired by computer vision and natural language processing, implying that they do not fully account for the physical characteristics of CSI. In this paper, we thoroughly consider the physical properties of CSI and design a context-aware approach to embed CSI into a non-Euclidean space for graph-structured learning. Moreover, in feature learning, we separately contemplate the spatial and frequency dimensions, engaging in graph-structured feature learning from distinct physical dimensions. Results on real-world datasets demonstrate that our methodology significantly outperforms state-of-the-art DL-based and meachine learning (ML)-based approaches. © 2023 ieee.

关键词： Cost effectiveness

来源：评论

学校读者我要写书评

暂无评论

Enhancing Cross-Domain Slot Filling with Joint LLM Data Generation and Data Curation

Enhancing Cross-Domain Slot Filling with Joint LLM Data Gene...

引用

international conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Peijie Huang Weizhen Li Yuhong Xu Junbao Huang College of Mathematics and Informatics South China Agricultural University Guangzhou China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

In real-world scenarios, due to data scarcity, cross-domain slot filling in spoken language understanding remains a significant challenge. Previous works focus on supplementing sequence labeling models with slot meta-information or metric learning. They have poor generalization capabilities lacking specific domain knowledge. To enhance generalization, recent studies introduce implicit general knowledge to enhance the performance of slots lacking domain-specific knowledge by further pretraining or larger-parameter generative models. However, this knowledge is domain-agnostic and difficult to provide comprehensive knowledge for target domain. Therefore, we propose a two-stage data generation strategy, utilizing powerful LLMs to synthesize samples to introduce knowledge for each slot of the data-scarce target domain. More importantly, we employ a data curation mechanism based on confidence and uncertainty to identify and filter out low-quality samples to obtain a high-quality synthetic dataset. Extensive experimental results demonstrate the effectiveness and generality of our approach.

关键词： Measurement Uncertainty Pipelines Data collection Signal processing Filling Acoustics Labeling Speech processing Synthetic data

来源：评论

学校读者我要写书评

暂无评论

NLP and Deep Learning for Fake News Classification

NLP and Deep Learning for Fake News Classification

引用

2023 international conference on New Frontiers in Communication, Automation, Management and Security, ICCAMS 2023

作者： Vimal, S.P. Abishek, V. Akash, S. Deepak Kumar, B. Sri Ramakrishna Engineering College Department of Electronics and Communication Engineering Coimbatore India

ISBN: (纸本)9798350317060

The prevalence of social media and online news sources, which enable the quick dissemination of false information, has contributed significantly to the problem of fake news in recent years. To solve this issue, natural language processing (NLP) and deep learning techniques have been deployed to automatically identify and classify fake news articles. In this study, we applied four popular machine learning algorithms, namely Support Vector Machine (SVM), Decision Tree, Random Forest, and Logistic Regression, to classify fake news articles. The results showed that all four algorithms were capable of achieving high accuracy in classifying fake news articles, with Random Forest performing the best with an accuracy of 96.7%. To make the classification process more accessible to users, we developed a web interface using HTML, CSS, and Flask. The interface allows users to input news articles and receive a classification of whether the article is real or fake. The Flask server uses the machine learning models to classify the article and returns the result to the web application, which displays the classification result on the page using HTML and CSS. Furthermore, a comparative analysis of the four algorithms was conducted to determine which algorithm performed the best in terms of accuracy and computational efficiency. The results indicated that Random Forest outperformed the other algorithms in both accuracy and computational efficiency, Overall, the combination of NLP techniques, machine learning algorithms, and web technologies can provide a powerful tool for combating fake news and promoting more accurate information dissemination. © 2023 ieee.

关键词： Python

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 << < 484 485 486 487 488 489 490 491 492 493 > >>

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：