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

554 篇 会议
8 册 图书
2 篇 期刊文献

馆藏范围

564 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

386 篇 工学
- 370 篇 计算机科学与技术...
- 246 篇 软件工程
- 61 篇 信息与通信工程
- 58 篇 生物工程
- 43 篇 生物医学工程（可授...
- 28 篇 电气工程
- 25 篇 控制科学与工程
- 18 篇 化学工程与技术
- 13 篇 机械工程
- 13 篇 光学工程
- 13 篇 农业工程
- 13 篇 安全科学与工程
161 篇 理学
- 106 篇 数学
- 61 篇 生物学
- 57 篇 系统科学
- 39 篇 统计学（可授理学、...
- 20 篇 物理学
- 13 篇 化学
- 9 篇 大气科学
95 篇 管理学
- 52 篇 图书情报与档案管...
- 47 篇 管理科学与工程(可...
- 24 篇 工商管理
42 篇 医学
- 42 篇 临床医学
- 41 篇 基础医学(可授医学...
- 29 篇 药学(可授医学、理...
- 15 篇 公共卫生与预防医...
18 篇 农学
- 18 篇 作物学
15 篇 法学
- 11 篇 社会学
10 篇 教育学
- 10 篇 教育学
9 篇 经济学
- 9 篇 应用经济学

主题

116 篇 machine learning
50 篇 deep learning
44 篇 machine learning...
38 篇 accuracy
35 篇 support vector m...
21 篇 predictive model...
20 篇 security
18 篇 data models
15 篇 adversarial mach...
15 篇 feature extracti...
15 篇 random forests
15 篇 prediction algor...
15 篇 training
14 篇 decision trees
14 篇 classification a...
14 篇 forecasting
13 篇 computational mo...
12 篇 internet of thin...
12 篇 information tech...
11 篇 real-time system...

机构

3 篇 faculty of compu...
2 篇 faculty of compu...
2 篇 infologia techno...
2 篇 kindi center for...
2 篇 centre of resear...
2 篇 department of co...
2 篇 graphic era hill...
2 篇 greater bay area...
2 篇 vellore institut...
2 篇 department of ar...
2 篇 school of comput...
2 篇 department of ma...
2 篇 chitkara centre ...
2 篇 fraunhofer cente...
2 篇 department of co...
2 篇 sreyas institute...
2 篇 school of comput...
2 篇 ipmi internation...
2 篇 al-farabi kazakh...
2 篇 department of ma...

作者

6 篇 azar ahmad taher
3 篇 bhatnagar roheet
3 篇 foozy cik feresa...
3 篇 ammar hossam has...
2 篇 valeeva elvira
2 篇 khan ayub
2 篇 santos igor
2 篇 varun ojha
2 篇 shreya
2 篇 bringas pablo ga...
2 篇 kurniawan r.
2 篇 maragatharajan m...
2 篇 usha g.
2 篇 singh shikha
2 篇 xiao kai
2 篇 cao peng
2 篇 shyamala devi m.
2 篇 nazri m.z.a.
2 篇 m. maragatharaja...
2 篇 swathi p.

语言

544 篇 英文
18 篇 其他
2 篇 中文

检索条件"任意字段=4th International Conference on Machine Learning and Soft Computing, ICMLSC 2020"

共 564 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：

Performance optimization algorithm for CRF layer of Chinese sequence labeling model based on deep learning 4

Performance optimization algorithm for CRF layer of Chinese ...

引用

4th international conference on machine learning, Big Data and Business Intelligence, MLBDBI 2022

作者： Zhu, Li Zhang, Yue Dong, Yu Cui, Chengyu Engineering University of Pap Xi'an China Shijiazhuang Division of Plaa Infantry College Shijiazhuang China National Defense University Joint Operations College Shijiazhuang China China Mobile Chengdu Institute of Research and Development Chengdu China

ISBN: (纸本)9798350333947

the 'deep learning model + CRF' model architecture such as Bi-LSTM-CRF has outstanding performance| in the tasks of part-of-speech tagging, named entity recognition, and semantic role tagging in the field of natural language processing, and has become the most popular algorithm for sequence tagging tasks. However, in practical applications, due to the strong fitting ability of the feature extractor in the deep learning model, the use efficiency of the CRF layer is relatively low;at the same time, the calculation cost of the CRF layer is relatively large. this paper proposes a performance optimization algorithm for the CRF layer in the sequence annotation task based on the deep learning model. the algorithm introduces five rules. First of all, the tag result of the feature extractor is checked by the five rules, if the adjacent tag is found to be logically incorrect, then use the CRF layer for logic correction. the experimental results show that the algorithm shows great advantages in the process of word segmentation, part-of-speech tagging and named entity recognition, a lot of computing time has been saved. © 2022 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Federated learning for Low-Latency IoT Communications

Federated Learning for Low-Latency IoT Communications

引用

computing and Information Technology (ICCIT-1441), 2020 international conference on

作者： Mohammed M Alenazi Computer Engineering Faculty of Computers and Information Technology University Of Tabuk

ISBN: (数字)9798350353839

ISBN: (纸本)9798350353846

Many sectors have been transformed by the growth of the Internet of things devices, but it also presents difficulties, particularly in the latency of data exchange. In this research, I suggest a unique distributed federated learning architecture for low-latency Internet of things communications. I empower IoT devices to jointly train machine learning models without compromising data privacy by utilizing federated learning techniques. To accomplish low-latency IoT communications, the architecture prioritizes communication efficiency optimization. Use Python to create this design and provide experimental data to show how successful.

关键词： Data privacy Federated learning Computational modeling Computer architecture Data models Internet of things Data communication Low latency communication Information technology Optimization

来源：评论

学校读者我要写书评

暂无评论

Predictive Analysis of machine learning Frameworks in the review of Multivariate datasets for Crop Yield Prediction

Predictive Analysis of Machine Learning Frameworks in the re...

引用

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

作者： Kutlwano Sedimo Venumadhav Kuthadi Othapile Dinakenyane Rajalakshmi Selvaraj Department of Computing and Informatics Botswana International University of Science and Technology Palapye Botswana

ISBN: (数字)9798331518981

ISBN: (纸本)9798331518998

Crop Yield Prediction (CYP) is crucial for optimizing agricultural practices globally. this study conducts an in-depth review of machine learning (ML) techniques applied to multivariate datasets for crop yield forecasting. We examine the performance of models including deep learning, ensemble classifiers, and hybrid approaches, emphasizing their ability to integrate diverse data sources and adapt to varying climatic conditions. Despite significant progress, challenges such as sparse data handling and generalization across regions persist. this paper not only identifies these challenges but also proposes advanced solutions for improving prediction accuracy, offering a roadmap for future research in agricultural ML frameworks.

关键词： Deep learning Adaptation models Technological innovation Accuracy Reviews soft sensors Data models Reliability Predictive analytics Crop yield

来源：评论

学校读者我要写书评

暂无评论

Improved Alzheimer's Disease Early Prediction using machine learning Method : A Comprehensive Diagnostic Approach with Random Forest Classifier

Improved Alzheimer's Disease Early Prediction using Machine ...

引用

soft computing for Security Applications (ICSCSA), international conference on

作者： Madiha Munawar Monika Singh T Kishor Kumar Reddy C Marlia Mohd Hanafiah Department of Computer Science and Engineering Stanley College of Engineering and Technology for Women Hyderabad India Faculty of Science and Technology Universiti Kebangsaan Malaysia Malaysia

ISBN: (数字)9798331515720

ISBN: (纸本)9798331515737

Alzheimer's Disease (AD) often affects the elder persons and is the prevalent kind of Dementia. AD has a huge expense, especially when it comes to the treatment. AD is a main reason the older generations die whereas when Alzheimer Disease is detected early there will be minimal deaths and accurate diagnosing likely occurs in most cases. Using anonymized Oasis longitudinal MRI data, the study trains several machine learning algorithms to identify AD patients. Analyzing the test result includes utilizing different learning strategies or algorithms e.g., Ensemble Random Forest (RF), Hierarchical Decision Tree (DT), Logistic Regression (LR), Convolutional Neural Network (CNN), Deep Neural Network binary classifier (DNN), soft voting classifier (SVC), transfer learning approaches (TLA), Support Vector machine (SVM) and boosting AdaBoost in reference of their Accuracy, Error Rate, AUC (area under the curve), Time Taken and Recall for each method. the obtained results concluded that the proposed Random Forest classifier achieves higher accuracy (92.84%), Error Rate (7.16%), AUC (95%) (Area Under Curve) and Recall (89%). the Random Forest classifier also achieves higher Time Taken that is 483.654 sec.

关键词： Support vector machines Deep learning machine learning algorithms Accuracy Error analysis Magnetic resonance imaging Prediction algorithms Classification algorithms Alzheimer's disease Random forests

来源：评论

学校读者我要写书评

暂无评论

Towards Early Stroke Prediction: Detecting Hidden Patterns with Data Analytics

Towards Early Stroke Prediction: Detecting Hidden Patterns w...

引用

Sentiment Analysis and Deep learning (ICSADL), international conference on

作者： Priyanka P. Shinde Varsha P. Desai Gayatri S. Mirajkar Kavita S. Oza Department of MCA Government College of Engineering Karad Karad Maharashtra India Computer Science and Engineering D Y Patil Agriculture and Technical University Kolhapur Maharashtra India Arvind Gavali College of Engineering Satara Maharashtra India Computer Science Department Shivaji University Kolhapur Maharashtra India

ISBN: (数字)9798331523923

ISBN: (纸本)9798331523930

soft computing has found wide-ranging applications in diverse fields, including agriculture, finance, commerce, retail, education, healthcare, genetics, and genomics. Among these areas, healthcare is a critical domain that soft computing techniques can profoundly impact. the adoption of machine learning methods in the healthcare industry has steadily increased due to their potential to improve decision-making and uncover valuable patterns. the healthcare sector presents an ideal platform for implementing soft computing techniques, given the massive amounts of data generated daily in health records. machine learning has demonstrated remarkable effectiveness in manually identifying hidden patterns that are difficult to discern. this capability of machine learning can lead to significant improvements in diagnosis, the development of innovative treatments, cost reduction, and enhanced patient care, making it a compelling choice for integration in the healthcare industry-diseases like heart disease, stroke, lung cancer, and diabetes demand intensive research and investigation. Brain stroke stands out as a severe and potentially fatal condition arising from interrupted blood supply to a portion of the brain. the lack of oxygen and glucose supply leads to the deterioration and eventual death of brain cells. As the second most common disease worldwide, early diagnosis and prediction become paramount for the survival of patients suffering from brain strokes. this research paper delves into utilizing machine learning techniques for early illness identification, primarily focusing on predicting the likelihood of strokes before they occur. the stroke probability dataset, encompassing input variables such as gender, the number of diseases, age, and smoking habits, was sourced from the kaggle database. Various machine learning algorithms were employed to construct prediction models, including Random Forest, KNN, Logistic Regression, SVM, and Decision Trees. through this work, the

关键词： Support vector machines Sentiment analysis machine learning algorithms Medical services machine learning Stroke (medical condition) Predictive models Nearest neighbor methods Brain modeling Stress

来源：评论

学校读者我要写书评

暂无评论

Enhancing Bone Fracture Detection in Radiology: A machine learning and Explainable AI Approach

Enhancing Bone Fracture Detection in Radiology: A Machine Le...

引用

soft computing for Security Applications (ICSCSA), international conference on

作者： Krishnav Deka Madhurjya Rabha Deepratim Saikia Junali Jasmine Jena Mahendra Kumar Gourisaria Dayal Kumar Behera School of Computer Engineering KIIT Deemed to be University Bhubaneswar Odisha India

ISBN: (数字)9798331515720

ISBN: (纸本)9798331515737

Bone fractures, caused by impacts, trauma or conditions such as osteoporosis, require timely and precise detection for effective medical care. Traditional approaches rely on radiologists' interpretations of X-rays, which are labor-intensive and prone to errors. machine learning (ML) presents a promising solution for enhancing fracture identification. However, the opacity of ML models presents challenges in their integration into healthcare, necessitating transparency and interpretability. this work examines the use of ML in fracture detection and incorporates Explainable AI (XAI) techniques to clarify decision-making processes and bolster model reliability. Here, Local Directional Pattern (LDP) and Local Binary Pattern (LBP) have been used for extracting the features and it is found that the Random Forest Classifier achieved the highest accuracy of 95 %. By assessing both the accuracy and interpretability of ML models in identifying fractures, this study aims to promote wider acceptance and application of AI-driven diagnostic tools in medical settings.

关键词： Osteoporosis Accuracy Explainable AI X-rays Radiology Bones Feature extraction Security Reliability Random forests

来源：评论

学校读者我要写书评

暂无评论

Data Analysis for Predicting Attacks in Smart Systems Using AI Techniques

Data Analysis for Predicting Attacks in Smart Systems Using ...

引用

computing and Information Technology (ICCIT-1441), 2020 international conference on

作者： Reem Mushari Albalawi Shrouq Khalaf Alaazi thuraya Saeed Alshahrani Wejdan ALomrani Tahani Mohammed Alanazi Faculty of Computers & Information Technology University of Tabuk Tabuk Saudi Arabia

ISBN: (数字)9798350353839

ISBN: (纸本)9798350353846

this paper presents an AI-driven framework to predict and mitigate DDoS attacks in smart cities using softwareDefined Networking (SDN), federated learning, and advanced machine learning algorithms. Parameter optimization significantly enhanced model performance. the Decision Tree algorithm, optimized via Research, achieved an accuracy of 0.9236 and an F1-Score of 0.929, outperforming Logistic Regression. Deep learning models also improved with strategies like Early Stopping and ReduceLROnPlateau, with SimpleRNN showing the highest improvement, followed by GRU, LSTM, and CNN models. these results surpass previous research, demonstrating the effectiveness of the applied techniques and model preparation.

关键词： Deep learning machine learning algorithms Accuracy Smart cities Federated learning Denial-of-service attack Internet of things Decision trees Computer crime Optimization

来源：评论

学校读者我要写书评

暂无评论

Sequence Labeling Approach to the Task of Sentence Boundary Detection 2020

Sequence Labeling Approach to the Task of Sentence Boundary ...

引用

4th international conference on machine learning and soft computing (icmlsc)

作者： the Anh Le Moscow Inst Phys & Technol Neural Networks & Deep Learning Lab Moscow Russia Vietnam Maritime Univ Fac Informat Technol Hai Phong Vietnam

ISBN: (纸本)9781450376310

One of the keys to enable chatbots to communicate with human in a more natural way is the ability to handle long and complex user's utterances. In order to achieve this goal, we propose to integrate the Sentence Boundary Detection (SBD) module into the chatbot architecture, whose role is to take as input a user's utterance from an automatic speech recognition device, in which sentence boundaries are not available, and output the corresponding list of punctuated sentences for downstream modules such as Intent Detection, Topic Classification, Sentiment Analysis, Named Entity Recognition, as well as Coreference Recognition. To address the SBD task, we reformulate it as a sequence labeling task. In this way, both deep neural network models (e.g., Bi-directional Long Short-Term Memory, Convolutional Neural Network) and structured prediction models (e.g., Hidden Markov Model, Maximum Entropy Model, Conditional Random Field) can be leveraged. After reformulating the SBD task, we built a hybrid deep neural network model and achieved good performance on both CornellMovie-Dialog and DailyDialog datasets.

关键词： Sentence boundary detection sequence labeling voice-enabled chatbot

来源：评论

学校读者我要写书评

暂无评论

Morphology-Based soft Label Smoothing Strategy for Fine-Grained Domain Adaptationming 4th

Morphology-Based Soft Label Smoothing Strategy for Fine-Grai...

引用

4th international conference on machine learning for Cyber Security, ML4CS 2022

作者： Li, Kangshun Wang, Yi Feng, Tian Jalil, Hassan Nie, Huabei College of Computer Science Guangdong University of Science and Technology Guangdong Dongguan523000 China School of Mathematics and Information South China Agricultural University Guangdong Guangzhou510642 China School of Computer and Informatics Dongguan City University Guangdong Dongguan523808 China

ISBN: (纸本)9783031201011

Semantic segmentation algorithms are the cornerstone of the autonomous driving algorithm. the implementation of these algorithms requires a lot of data. However, due to the complex and changeable production environment, the differences in image style, illumination and weather conditions not only significantly degrade the performance of network models under development environment data, but also cause costly data annotation. this paper proposes a dilation-corrosion soft label smoothing strategy. this strategy utilizes the existing self-supervised learning soft label generation strategy and overcomes the premise assumption defect of the fine-grained adversarial model on the target domain model. Our strategy evaluates its effectiveness on the domain adaptation task of GTA5 → Cityscapes. At the same time, we reduce the amount of source domain data by half and the number of domain classification training iterations by half, the resulting in the comprehensive evaluation index is 1.5% higher, and the individual category is 10 percentage points higher. Our strategy shortens the time and improves the efficiency of segmentation. © 2023, the Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Integrating Deep learning, machine learning, AI, IoT and Data Science for Future Innovations

Integrating Deep Learning, Machine Learning, AI, IoT and Dat...

引用

soft computing for Security Applications (ICSCSA), international conference on

作者： Shipra Gupta Vijay Kumar Graphic Era Hill University Dehradun Uttarakhand India Department of Physics Graphic Era Hill University Dehradun Uttarakhand India

ISBN: (数字)9798331515720

ISBN: (纸本)9798331515737

machine learning (ML), Deep learning (DL), Internet of things (IoT), Artificial Intelligence (AI) and Data Science are integrated to create innovative solutions that are powering industries today like never before. this paper reviews these technologies and how they can work together to transform industries like healthcare, finance, and manufacturing, as well as the immensely important space of smart cities. With ML and DL-driven analytics for predictions, IoT-based real-time data capture mechanisms, AI making informed decisions along data science generating insights from the data makes organizations efficient in every aspect as well as reliable and innovative. Some example applications are predictive maintenance in manufacturing, personalized medicine in healthcare, algorithmic trading in finance and the development of smart/sustainable urban environments. While these potboilers offer a hopeful advantage, they also come with some hurdles, data privacy/security, integration complexity and the need for high-end technical skills being the topmost. In this manuscript, some case studies of success are highlighted in the belonging field and discuss the challenges for incorporation today along with future directions for seamless integration aimed at promoting even greater innovation.

关键词： Industries Deep learning Technological innovation Finance Medical services Data science Real-time systems Manufacturing Internet of things Security

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57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：