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

1,576 篇 会议
1 篇 期刊文献

馆藏范围

1,577 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

899 篇 工学
- 774 篇 计算机科学与技术...
- 533 篇 软件工程
- 253 篇 信息与通信工程
- 194 篇 控制科学与工程
- 130 篇 电气工程
- 84 篇 网络空间安全
- 78 篇 生物医学工程（可授...
- 75 篇 安全科学与工程
- 64 篇 交通运输工程
- 62 篇 生物工程
- 55 篇 电子科学与技术（可...
- 45 篇 动力工程及工程热...
- 43 篇 仪器科学与技术
- 42 篇 光学工程
- 42 篇 石油与天然气工程
306 篇 理学
- 164 篇 数学
- 83 篇 生物学
- 73 篇 统计学（可授理学、...
- 61 篇 物理学
- 37 篇 系统科学
- 33 篇 化学
267 篇 管理学
- 203 篇 管理科学与工程(可...
- 106 篇 图书情报与档案管...
- 84 篇 工商管理
- 34 篇 公共管理
114 篇 医学
- 80 篇 临床医学
- 77 篇 公共卫生与预防医...
- 64 篇 基础医学(可授医学...
51 篇 法学
- 48 篇 社会学
39 篇 经济学
- 39 篇 应用经济学
18 篇 文学
15 篇 教育学
11 篇 农学
2 篇 军事学
1 篇 艺术学

主题

193 篇 data models
157 篇 accuracy
153 篇 computational mo...
92 篇 training
86 篇 feature extracti...
86 篇 machine learning
77 篇 predictive model...
69 篇 data mining
68 篇 deep learning
63 篇 real-time system...
57 篇 big data
49 篇 adaptation model...
45 篇 security
44 篇 robustness
41 篇 decision making
40 篇 convolutional ne...
39 篇 cloud computing
36 篇 analytical model...
35 篇 neural networks
34 篇 optimization

机构

14 篇 lovely professio...
7 篇 shandong provinc...
7 篇 key laboratory o...
6 篇 college of mecha...
6 篇 institute of aer...
5 篇 lloyd institute ...
5 篇 college of intel...
5 篇 university of ch...
5 篇 national univers...
5 篇 department of co...
5 篇 shandong fundame...
5 篇 national univers...
5 篇 institute of aer...
4 篇 karnataka bangal...
4 篇 shanghai jiao to...
4 篇 school of comput...
4 篇 chitkara univers...
4 篇 new horizon coll...
4 篇 srm institute of...
4 篇 school of softwa...

作者

7 篇 nijhawan ginni
5 篇 jeanette miriam ...
5 篇 lu xiaobo
5 篇 singh navdeep
4 篇 nicola franco
4 篇 choudhry mani de...
4 篇 akhil karnam
4 篇 zhang rui
4 篇 yu zhang
4 篇 akshya j.
4 篇 lihui wang
4 篇 qu yuben
4 篇 wang lihui
4 篇 li lei
4 篇 dong chao
4 篇 dutt varun
4 篇 puri chetan
3 篇 yuangan wang
3 篇 junqi luo
3 篇 zhang lei

语言

1,273 篇 英文
303 篇 其他
4 篇 中文

检索条件"任意字段=2024 IEEE International Conference on Cognitive Computing and Complex Data"

共 1577 条记录，以下是701-710 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：

Applying Transformer-Based Neural Networks to Corpus Linguistic data for Predictive Text Generation in Multilingual Environments 6

Applying Transformer-Based Neural Networks to Corpus Linguis...

引用

6th ieee international conference on Emerging Smart computing and Informatics, ESCI 2024

作者： Taufikin Orosoo, Myagmarsuren Rengarajan, Manikandan Fatma, Gulnaz Yuldashev, Dilyorjon Raj, I Infant IAIN Kudus Indonesia Mongolian National University of Education Mongolia Vel Tech Rangarajan Dr. Sagunthala R and D Institute of Science and Technology Tamil Nadu Chennai India University College Al Ardah Jazan University Jazan Saudi Arabia Turin Polytechnic University in Tashkent Automatic Control and Computer Engineering Department Tashkent Uzbekistan K. Ramakrishnan College of Engineering Department of CSE Tamil Nadu Trichy India

ISBN: (纸本)9798350306613

In the subject of corpus linguistics, this study explores the use of transformer-based neural networks to the problems of predictive text production in multilingual contexts. The Transformer architecture presents a viable framework for natural language processing problems because of its reputation for capturing complex patterns and long-range dependencies in sequential data. The research employs a two-phase approach, whereby the Transformer is first pre-Trained using a variety of multilingual corpora. This helps the model learn representations that are independent of language, which makes it easier for it to adapt to various linguistic circumstances. The model is then fine-Tuned using language-specific datasets to improve its ability to produce linguistically nuanced and contextually appropriate text. The study looks into how different model architectures, training methods, and hyperparameters affect how well the suggested multilingual predictive text generation system performs. Evaluation measures are used to evaluate the model's performance in several languages, including linguistic diversity measurements, BLEU scores, and perplexity. The overall accuracy, calculated across all languages, stands at 80.3%, indicating the model's robust cross-lingual generalization and its effectiveness in capturing diverse linguistic nuances The efficacy and generalization of Transformer-based models are improved across a wide range of languages to handle linguistic diversity. © 2024 ieee.

关键词： Corpus Linguistics Cultural Context Integration Multilingual Text Generation Neural Language Models Transformer-Based Neural Networks

来源：评论

学校读者我要写书评

暂无评论

Experimental Analysis of Learning Based Approach to Evaluate the Integration of Social Networking Platform with Internet of Things Technology

Experimental Analysis of Learning Based Approach to Evaluate...

引用

2024 international conference on Innovative computing, Intelligent Communication and Smart Electrical Systems, ICSES 2024

作者： Karunakaran, A. Venkatraman, C.B. Suganthi, P. Santhi, G.B. Alok, Narkhede Shalout, Imad S. A. Engineering College Department of Ece Chennai India Sona College of Technology Department of Eee Salem India Sri Sai Ram Institute of Technology Department of Cse Chennai India New Prince Shri Bhavani College of Engineering and Technology Department of Computer Science and Engineering Chennai India Yeshwantrao Chavan College of Engineering Department of Mechanical Engineering Nagpur India Zarqa university Faculty of engineering Department of Civil Engineering Zarqa Jordan University of Business and Technology Jeddah21448 Saudi Arabia

ISBN: (纸本)9798331543617

Enterprising entrepreneurs are forging a new paradigm for consumer-business interactions by leveraging the convergence of social networking platforms-such as Facebook and Twitter-and the Internet of Things (IoT). This paper aims to assess an integration pipeline's performance using a learning based approach. Our aim is to understand the complex interplay between data that has been collected from IoT and how social media users act using advanced methods in data analytics. Our approach involves gathering data from both SNPs and the Internet of Things (IoT) and pre-processing it as needed before building a model that can be predicted and its performance evaluated. As opposed to the proposed method Elevated Social Networking Integration (ESNI) is a better strategy than the existing Social Networking Integration Analyzer (SNIA), which permits collecting less information through connected devices to enhance decision-making on consumer behavior and encounters. By offering a methodical approach to evaluating the value proposition of combining IoT with SNP, this study adds to the corpus of knowledge. The framework facilitates seamless interaction across diverse social media platforms, optimizing data flow and user experience. Empirical testing demonstrates ESNI's effectiveness in boosting engagement metrics and user satisfaction compared to conventional integration methods. This research highlights ESNI's potential to redefine social networking strategies, providing a robust foundation for future innovations in digital communication and marketing. © 2024 ieee.

关键词： data assimilation

来源：评论

学校读者我要写书评

暂无评论

Early Detection of Coronary Heart Disease Using Exploration data Analysis and Gradient Boosting Method

Early Detection of Coronary Heart Disease Using Exploration ...

引用

2024 international conference on Information Technology and computing, ICITCOM 2024

作者： Riyadi, Slamet Iqbal Al-Habib, Muhammad Alfiana, Fitri Damarjati, Cahya Jusman, Yessi Ramli, Suzaimah Universitas Muhammadiyah Yogyakarta Faculty of Engineering Department of Information Technology Yogyakarta Indonesia Universiti Pertahanan Nasional Malaysia Faculty of Defense Science and Technology Department of Computer Science Kuala Lumpur Malaysia

ISBN: (纸本)9798350379839

Coronary heart disease is a significant global health issue that contributes to high morbidity and mortality rates, including in Indonesia. Public awareness of risk factors for heart disease is a matter that has an impact on disease burden, prevention, and timely treatment. However, public awareness of coronary heart disease and its risk factors is still low. Many individuals continue to engage in unhealthy lifestyles, lack awareness of effective preventive actions, and neglect regular heart health check-ups. To address these challenges, one of the solutions that can be made is a valuable tool for identifying individuals at risk and enabling early intervention and preventive measures. This study proposes implementing a machine learning model for the early detection of coronary heart disease using Exploration data Analysis (EDA) and Gradient Boosting methods. Integrates EDA techniques for preprocessing data, such as finding important features and patterns, and then Gradient Boosting techniques to capture complex relationships and make accurate predictions based on a wide range of factors, such as a person's disease history, daily habits, and body characteristics. To evaluate the performance of our model, we split the dataset with an 80:20 ratio for training and testing and achieved an impressive accuracy of 91,39%. These results showed that our model could reliably predict the presence or absence of cardiac disease. With such precise forecasts, early prevention, identification, and treatment might be aided, which would ultimately reduce heart disease-related mortality and morbidity. © 2024 ieee.

关键词： Adaptive boosting

来源：评论

学校读者我要写书评

暂无评论

ScMonica: Single-cell Mosaic Omics Nonlinear Integration and Clustering Analysis

ScMonica: Single-cell Mosaic Omics Nonlinear Integration and...

引用

2024 ieee international conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Li, Xiaoli Zhang, Rui Aslam, Saba Li, Huijun Chen, Yuxi Zhang, Zequn Huang, Ruey-Song Wu, Hongyan Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China Centre for Cognitive and Brain Sciences University of Macau Taipa China Faculty of Science and Technology University of Macau Taipa China Shenzhen college of Advanced Technology University of Chinese Academy of Sciences Beijing100049 China Joint Engineering Research Center for Health Big Data Intelligent Analysis Technology Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China Faculty of Health Sciences University of Macau Taipa China

ISBN: (纸本)9798350386226

Single-cell mosaic integration has revolutionized our understanding of cellular heterogeneity, offering unprecedented resolution into cellular states and contexts. While large language models (LLMs) have achieved success in the analysis of single-cell omics data, their application specifically focused on the integration of mosaic data remains limited. Current computational approaches often fall short in addressing these challenges. They frequently depend on assumptions of data completeness and uniform quality, failing to manage the variability and noise effectively introduced by missing data. Moreover, these models might not efficiently process large, diverse datasets or account for biological heterogeneity and long-ranging dependencies across various data types. To address these shortcomings, we introduce the Single-cell Mosaic Omics Nonlinear Integration and Clustering Analysis (scMonica) framework, which employs a LSTM-transformer hybrid architecture. This innovative model combines the strengths of Long Short-Term Memory (LSTM) networks, which excel at capturing long-range dependencies within sequential gene expression patterns, with transformers, renowned for their attention mechanisms that handle the complex, non-linear interactions characteristic of multi-layered datasets. By leveraging these complementary strengths, our approach enhances the integration process significantly, allowing for nuanced management of the intrinsic heterogeneity and sparsity of mosaic datasets. Comprehensive evaluations demonstrate the robustness and effectiveness of our approach, offering unparalleled versatility and accuracy in multi-omics data analysis. These advancements underscore scMonica's potential to drive significant insights in single-cell developmental biology, oncology, and beyond. We discuss the underlying technologies, analyze their applications, and contemplate future directions that promise to extend the boundaries of both research and clinical domains. © 2024 ieee.

关键词： Gene expression

来源：评论

学校读者我要写书评

暂无评论

Two-Stage Feature Selection for PM2.5 Prediction: adjcorT-RBFNN Approach to Address Multicollinearity in Air Quality data in Urban Area

Two-Stage Feature Selection for PM2.5 Prediction: adjcorT-RB...

引用

2024 ieee international conference on computing, ICOCO 2024

作者： Arafin, Siti Khadijah Ibrahim, Nurain Rahim, Nur Azimah Abdul Mansor, Mahayaudin M. Ul-Saufie, Ahmad Zia Ghani, Nor Azura Md School of Mathematical Sciences College of Computing Informatics and Mathematics Universiti Teknologi MARA Selangor Shah Alam40450 Malaysia Kompleks Al-Khawarizmi Universiti Teknologi MARA Selangor Shah Alam40450 Malaysia

ISBN: (纸本)9798331530303

PM2.5 is a dangerous pollutant that has been shown to significantly affect human health due to its small size (≤2.5 micrometers). Urban areas often experience higher PM2.5 levels due to high traffic volume, industrial activities, and population density. Accurate prediction of PM2.5 levels not only enhances the body of knowledge on air quality modeling but also provides governments with critical insights to implement timely interventions, reduce public health risks, and guide policy-making for air quality management. Thus, this study aims to classify the next day's air quality based on PM2.5 levels in Banting, an urban area in Selangor, Malaysia, using a machine learning approach. Radial Basis Function Neural Network (RBFNN) is a neural network method widely used for prediction and classification analysis due to it can handle complex nonlinear relationship in the dataset. However, RBFNN does not address multicollinearity in air quality data. To address this, we used the adjcorT feature selection method to identify the significant features affecting next-day PM2.5 levels, while considering the multicollinearity issues in air quality data. Thus, a two-stage feature selection method, adjcorT-RBFNN, was implemented in this study to enhance the classification of next-day PM2.5 levels. The research utilized hourly secondary data from the Department of Environment Malaysia (DOE), spanning 2018 to 2022. The findings indicate that PM10, PM2.5, CO, NO2, humidity, SO2, wind speed, and wind direction are significant features for classifying next-day PM2.5 levels in Banting. Moreover, the proposed adjcorT-RBFNN technique outperformed the RBFNN method in terms of accuracy, specificity, precision, F1 score, and AUROC, with scores of 0.761, 0.752, 0.752, 0.761, and 0.761, respectively. Hence, the proposed two-stage feature selection method, adjcorT-RBFNN, can assist future researchers in improving PM2.5 level predictions in other urban areas. ©2024 ieee.

关键词： Radial basis function networks

来源：评论

学校读者我要写书评

暂无评论

Classification of Land Cover using Machine Learning Models in Landsat Satellite data 15

Classification of Land Cover using Machine Learning Models i...

引用

15th international conference on computing Communication and Networking Technologies, ICCCNT 2024

作者： Thiyagarajan, Gomathi Vijayalakshmi, V. Cmr Institute of Technology Department of Computer Applications Bengaluru India Srm Institute of Science and Technology Department of Dsbs Chennai Kattankulathur India

ISBN: (纸本)9798350370249

In this work, we examine the possibility of using cloud cover area analysis in Google Earth Engine (GEE) in conjunction with Landsat satellite data for classifying land cover in the Chennai region between 2023 and 2024. With the development of technology and the accessibility of satellite imagery, remote sensing data have provided invaluable insights into environmental dynamics and have become more important for tracking changes in land cover over time. The study area, Chennai, represents a rapidly urbanizing region where accurate land cover classification is crucial for urban planning, resource management, and environmental conservation efforts. To achieve this, we adopted a supervised classification approach, dividing the dataset into training and testing subsets with an 8 0% - 2 0% split. Three distinct classification models were developed and evaluated: Classification and Regression Trees (CART), K-Nearest Neighbors (KNN), Random Forest (RF), Support Vector Machine (SVM) and Naïve Bayes (NB). Each model leverages the spectral information from Landsat satellite imagery to classify land cover types across the study area. Our analysis revealed varying degrees of accuracy among the models. The CART model achieved a classification accuracy of 7 5%, followed by the KNN model with 77.5% accuracy, NB achieved 8 0% and SVM performed with 7 2. 5%. Notably, the Random Forest model outperformed the others significantly, achieving an impressive accuracy of 8 2. 5%. This indicates the efficacy of ensemble learning techniques, such as Random Forest, in handling complex spectral patterns and improving classification performance in urban environments like Chennai. © 2024 ieee.

关键词： GEE Land cover Landsat Satellite image

来源：评论

学校读者我要写书评

暂无评论

Experimental Analysis of Artificial Intelligence Powered Adaptive Learning Methodology Using Enhanced Deep Learning Principle

Experimental Analysis of Artificial Intelligence Powered Ada...

引用

2024 international conference on Innovative computing, Intelligent Communication and Smart Electrical Systems, ICSES 2024

作者： Rayudu, K.M. Chinnammal, V. Maria Rubiston, M. Padmaloshani, P. Singaravelu, R. Merlin, N.R Gladiss Qis College of Engineering and Technology Department of Aimlds Vengamukkapalem Andhra Pradesh Ongole India Rajalakshmi Institute of Technology Department of Ece Chennai India S.A. Engineering College Department of Ece Chennai India Selvam College of Technology Department of Ece Namakkal India Vel Tech Multi Tech Dr. Rangarajan Dr Sakunthala Engineering College Department of Ece Chennai India R.M.K. Engineering College Department of Artificial Intelligence and Data Science Chennai India

ISBN: (纸本)9798331543617

The rapid advancement of deep learning technologies and Artificial Intelligence (AI) has facilitated the development of sophisticated adaptive learning methodologies. The experimental analysis presented in this manuscript is of a novel adaptive learning methodology propelled by AI, known as the Learning Assisted Power Adaptive Strategy (LPAS). This approach optimizes the learning process in dynamic environments by combining adaptive learning techniques with sophisticated deep learning architectures. The accuracy levels of the proposed scheme are tested by cross-validating it with the traditional learning scheme called Recurrent Neural Network (RNN) so that complex and time-varying data patterns can be handled effectively. The Learning Assisted Power Adaptive Strategy is anticipated to enhance its fitness to make accurate predictions and encourage individual learning with adaptability over new and changing circumstances. The LPAS performance is assessed against a variety of benchmarks, such as precision, recall, specificity and sensitivity, through a succession of controlled experiments. The model's adaptive capabilities also enabled a more responsive response to data fluctuations, thereby improving its overall robustness. This research provides valuable insights for future advancements in the field and contributes to the continual growth of AI-driven educational resources and adaptive platforms. © 2024 ieee.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

A Feature-Based Approach for Organizing Spatial data of Digital Twin Railway 8

A Feature-Based Approach for Organizing Spatial Data of Digi...

引用

8th ieee international conference on Intelligent Transportation Engineering, ICITE 2023

作者： Cheng, Zhibo Wu, Yanhua Song, Shubao Guo, Yongxin Luan, Zhong Liu, Zheqian Institute of Computing Technologies China Academy of Railway Sciences Corporation Limited Beijing China Southwest Jiaotong University Faculty of Geosciences and Environmental Engineering Chengdu China

ISBN: (纸本)9798350314212

In response to the challenge of maintaining consistency in storing and processing geometry and semantics in the spatial data model of digital twin railway, a feature-based railway spatial data model is conducted by analyzing the establishing requirement of the railway spatial data model and combining the linear distribution characteristics of the railway. The focus was on providing a detailed discussion of the feature sets and their interrelationships within the conceptual model. Additionally, package diagrams and class diagrams using UML language to express features, which were employed to construct the logical model, and express the description of railway feature objects. Through comparative analysis, it was demonstrated that this model enables the consistent description of the geometry, location, and semantics of feature objects. It fully expresses the complex relationships present in the geographic world, more aligning with human cognitive laws regarding geographic entities. © 2023 ieee.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

Graph Convolutional Networks Approach for Alzheimer's Disease Stage Classification Using Multimodal data 13

Graph Convolutional Networks Approach for Alzheimer's Diseas...

引用

Joint 13th international conference on Soft computing and Intelligent Systems and 25th international Symposium on Advanced Intelligent Systems, SCIS and ISIS 2024

作者： Jeong, Hyujeong Kang, Do-Young Yun, Yeboon Kang, Jum-Ran Yoon, Min Lee, Gyu-Bin Pukyong National University Dept. of Applied Mathematics Busan Korea Republic of Dong-A University College of Medicine and Medical Center Institute of Convergence Bio-Health Dong-A University Dept. of Nuclear Medicine Busan Korea Republic of Kansai University Faculty of Environmental and Urban Engineering Osaka Japan Pukyong National University Dong-A University College of Medicine and Medical Center Dept. of Applied Mathematics Dept. of Nuclear Medicine Busan Korea Republic of

ISBN: (纸本)9798350373332

With the advancement of medical technology, the global population is aging and this is expected to increase the number of dementia patients. Alzheimer's disease (AD) is the most common cause of dementia and is a heterogeneous, neurodegenerative brain disorder. Due to the lack of a complete cure, early diagnosis is crucial to slow the progression of symptoms. Mild cognitive impairment (MCI), an intermediate state between normal cognition (NC) and dementia, also necessitates early diagnosis because it can progress to AD. In reality, doctors diagnose AD stage by considering multiple types of data such as brain imaging, demographic information, genetic tests, and neuropsychological tests. Therefore, AD stage classification models need to learn these multimodal data. In this study, we proposed applying the graph convolutional network (GCN) to population graphs constructed by using cosine similarity, L1-norm, and L2-norm on multimodal data for AD stage classification. The multimodal data consisted of F -18 florbetaben (FBB) amyloid brain positron emission tomography (PET) images, demographic information, and genetic test, and neuropsychological test data. Different dimensional FBB PET images and non-image data were matched by using a multimodal fusion method utilizing a 3D dense convolutional network. The proposed methods are investigated through cross-validation with support vector machine, random forest, and multilayer percep- tron models. The results suggest that the L 1 -norm leads to better performance of GCN in AD stage classification due to its better robustness against outliers and its ability to account for the heterogeneity of AD compared to cosine similarity and L2 -norm. © 2024 ieee.

关键词： Positron emission tomography

来源：评论

学校读者我要写书评

暂无评论

Self-supervised fast reconstruction method for diffusion MRI based on multi-directional assistance 17

Self-supervised fast reconstruction method for diffusion MRI...

引用

17th ieee international conference on Signal Processing, ICSP 2024

作者： Wu, Yuxin Zhang, Jian Wang, Lihui Cao, Ying Wu, Linhai Wu, Yunjia Ye, Chen Zhu, Yuemin Guizhou University Key Laboratory of Intelligent Medical Image Analysis and Precise Diagnosis of Guizhou Province Engineering Research Center of Text Computing & Cognitive Intelligence Ministry of Education State Key Laboratory of Public Big Data College of Computer Science and Technology Guiyang China Univ Lyon Insa Lyon Cnrs Inserm Creatis Umr 5220 U1206 France

ISBN: (纸本)9798350387384

Diffusion MRI (dMRI) is widely used for the detection and diagnosis of various pathologies due to its non-invasive nature. However, its signal acquisition process is relatively slow and susceptible to motions. In order to accelerate reconstruction process, many deep learning-based methods have been developed in recent years to achieve promising results, while most of them are supervised based methods and require fully sampled data which are difficult to obtain in practical applications to train the network. Self-supervised based methods were proposed to deal with this problem to a certain extent, however, they are devoted only to conventional MRI data, ignoring the correlation between the directions of dMRI data. To address this issue, we propose a self-supervised fast reconstruction method for dMRI based on multi-directional assistance. The method better utilizes the information between dMRI data directions by Partition-Replace operation, cleverly constructing data pairs and designing effective self-supervised strategy for bi-directional prediction, which can overcome the problem of data incompleteness and guide the model to reconstruct unsampled signals in spite of the difficulty of acquiring fully sampled data. Experimental results show that our method achieves better reconstruction in the absence of fully sampled data, even with an 8-fold acceleration factor. © 2024 ieee.

关键词： Self-supervised learning

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158页 << < 67 68 69 70 71 72 73 74 75 76 > >>

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：