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

2,973 篇 会议
176 册 图书
24 篇 期刊文献

馆藏范围

3,172 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

2,043 篇 工学
- 1,825 篇 计算机科学与技术...
- 960 篇 软件工程
- 329 篇 电气工程
- 313 篇 信息与通信工程
- 214 篇 控制科学与工程
- 207 篇 生物工程
- 149 篇 生物医学工程（可授...
- 71 篇 光学工程
- 64 篇 机械工程
- 62 篇 化学工程与技术
- 51 篇 电子科学与技术（可...
- 47 篇 仪器科学与技术
- 46 篇 安全科学与工程
- 36 篇 交通运输工程
648 篇 理学
- 352 篇 数学
- 244 篇 生物学
- 140 篇 物理学
- 135 篇 统计学（可授理学、...
- 95 篇 系统科学
- 62 篇 化学
408 篇 管理学
- 244 篇 图书情报与档案管...
- 182 篇 管理科学与工程(可...
- 83 篇 工商管理
262 篇 医学
- 241 篇 临床医学
- 123 篇 基础医学(可授医学...
- 74 篇 药学(可授医学、理...
- 40 篇 公共卫生与预防医...
46 篇 法学
- 42 篇 社会学
38 篇 教育学
- 32 篇 教育学
33 篇 经济学
- 31 篇 应用经济学
23 篇 农学
6 篇 艺术学
4 篇 文学

主题

575 篇 machine learning
564 篇 data mining
323 篇 pattern recognit...
212 篇 deep learning
201 篇 feature extracti...
154 篇 support vector m...
145 篇 artificial intel...
129 篇 machine learning...
120 篇 accuracy
120 篇 training
91 篇 data mining and ...
90 篇 data models
72 篇 neural networks
71 篇 classification
69 篇 predictive model...
66 篇 face recognition
61 篇 learning systems
52 篇 computer imaging...
50 篇 convolutional ne...
48 篇 classification a...

机构

9 篇 school of comput...
9 篇 chinese academy ...
8 篇 zhejiang univers...
8 篇 chitkara univers...
7 篇 guangdong univer...
7 篇 school of inform...
6 篇 xi'an university...
6 篇 indian statistic...
6 篇 central south un...
6 篇 department of co...
6 篇 unsw sydney
6 篇 xi'an university...
6 篇 southern univers...
5 篇 indian institute...
5 篇 study group aust...
5 篇 peking universit...
4 篇 centre for patte...
4 篇 chongqing univer...
4 篇 national laborat...
4 篇 sun yat sen univ...

作者

11 篇 de-shuang huang
8 篇 petra perner
7 篇 krasotkina olga
7 篇 mottl vadim
7 篇 ying tan
6 篇 zheng-guang wu
6 篇 ryszard tadeusie...
6 篇 marcin korytkows...
6 篇 phung dinh
6 篇 venkatesh svetha
6 篇 hongyi li
6 篇 jacek m. zurada
6 篇 chaojie li
6 篇 biao luo
6 篇 ilias maglogiann...
6 篇 lotfi a. zadeh
6 篇 leszek rutkowski
6 篇 lazaros iliadis
6 篇 long cheng
5 篇 vitoantonio bevi...

语言

2,869 篇 英文
290 篇 其他
34 篇 中文
1 篇 土耳其文

检索条件"任意字段=5th International Conference on Machine Learning and Data Mining in Pattern Recognition"

共 3173 条记录，以下是1091-1100 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：

Classifying Eye-Tracking data Using Saliency Maps 25

Classifying Eye-Tracking Data Using Saliency Maps

引用

25th international conference on pattern recognition (ICPR)

作者： Rahman, Shafin Rahman, Sejuti Shahid, Omar Abdullah, Md Tahmeed Sourov, Jubair Ahmed North South Univ Elect & Comp Engn Dhaka Bangladesh Univ Dhaka Robot & Mechatron Engn Dhaka Bangladesh

ISBN: (纸本)9781728188089

A plethora of research in the literature shows how human eye fixation pattern varies depending on different factors, including genetics, age, social functioning, cognitive functioning, and so on. Analysis of these variations in visual attention has already elicited two potential research avenues: 1) determining the physiological or psychological state of the subject and 2) predicting the tasks associated with the act of viewing from the recorded eye-Iixation data. To this end, this paper proposes a visual saliency based novel feature extraction method for automatic and quantitative classification of eye-tracking data, which is applicable to both of the research directions. Instead of directly extracting features from the fixation data, this method employs several well-known computational models of visual attention to predict eye fixation locations as saliency maps. Comparing the saliency amplitudes, similarity and dissimilarity of saliency maps with the corresponding eye fixations maps gives an extra dimension of information which is effectively utilized to generate discriminative features to classify the eye-tracking data. Extensive experimentation using Saliency4ASD [1], Age Prediction [2], and Visual Perceptual Task [3] dataset show that our saliency-based feature can achieve superior performance, outperforming the previous state-of-the-art methods [2], [4], 5] by a considerable margin. Moreover, unlike the existing application-specific solutions, our method demonstrates performance improvement across three distinct problems from the real-life domain: Autism Spectrum Disorder screening, toddler age prediction, and human visual perceptual task classification, providing a general paradigm that utilizes the extra-information inherent in saliency maps for a more accurate classification.

关键词： Eye-tracking Visual Saliency Autism Spectrum Disorder Toddler Age Prediction Visual Perceptual Task

来源：评论

学校读者我要写书评

暂无评论

Fluorescence Microscopy Images Segmentation Based on Prototypical Networks with a Few Annotations 5th

Fluorescence Microscopy Images Segmentation Based on Prototy...

引用

5th Chinese conference on pattern recognition and Computer Vision (PRCV)

作者： Guo, Yuanhao Lu, Yaoru Li, Wenjing Yang, Ge Chinese Acad Sci Inst Automat Computat Biol & Machine Intelligence Lab Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100049 Peoples R China

ISBN: (纸本)9783031189098;9783031189104

the objects in fluorescence microscopy images (FMIs) are rather densely populated, and often have complex structures as well as large color variations. these issues result in time-consuming manual annotations for training a segmentation model. Few-shot segmentation (FSS) models reduce the requirements of annotations by using prototypical networks to generalize the object regions given only a few annotation masks. these methods, however, often fail to generalize to FMIs due to the domain shift from the images of source class to those of target class. To tackle these challenges, we adapt the prototypical networks from the few-shot learning scheme as our base model architecture to learn a compact feature representation of the object, with only a few annotated masks. then, to solve the domain shift problem, we propose a resampling strategy to regularize the model training. Specifically, we construct the training set using not only the images form the source class, but also the support set from the target class by resampling the latter for regularizing the training. To distinguish our FMIs segmentation method from the conventional FSS models, we define it as a training regularization strategy based on the prototypical networks (TRPN). Experimental results on three public datasets, *** ER, MITO and NUC, have confirmed the advantages of our method, which provides robust and accurate segmentation performance on FMIs only with a few annotation masks. Source code and data of this work are made publicly available at: https://***/cbmi-group/TRPN-model.

关键词： Fluorescence microscopy images segmentation A few annotations Prototypical feature learning Training regularizationstrategy

来源：评论

学校读者我要写书评

暂无评论

machine learning solutions for securing IoT-based healthcare: A Review

Machine learning solutions for securing IoT-based healthcare...

引用

international conference on pattern Analysis and Intelligent Systems (PAIS)

作者： Kharoubi Kamir Cherbal Sarra LRSD Laboratory Faculty of Sciences Ferhat Abbas University of Setif-1 Setif Algeria

the Internet of things (IoT) has become a powerful force that is revolutionizing various fields to improve human life, including healthcare. By establishing interconnectedness among devices through network connectivity, IoT facilitates real-time data exchange, enables remote patient diagnosis, and ensures ubiquitous access. However, the exchange of sensitive patient data within healthcare IoT systems presents significant security and privacy challenges that must be addressed to achieve a secure Healthcare IoT (H-IoT) ecosystem, resilient to attacks and threats. Among these issues, there are integrity, privacy and availability of data. It highlights the pressing need for robust security measures to safeguard patient information and explores the promising role of the ML techniques in addressing these challenges. ML algorithms offer the ability to detect and prevent both known and unknown attacks at an early stage, enhancing the security of H-IoT systems. this paper provides an overview about H-IoT, its requirements in security and some existing attacks. then, it presents ML techniques and their utilization for security. Finally, it conducts an extensive review of the contemporary solutions employed for enhancing the security of H-IoT systems during the period spanning from 2020 to 2023.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Detection and Classification of Bipolar Disorder Syndrome using Deep learning

Detection and Classification of Bipolar Disorder Syndrome us...

引用

Smart Electronics and Communication (ICOSEC), international conference on

作者： R.M. Dilip Charaan J Vimala Ithayan M Sankar R Chithambaramani P Sivaprakash D Marichamy Department of Computer Science & Engineering Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Chennai India Department of CSE Vel Tech Rangarajan Dr. Sagunthala Institute of Science and Technology Chennai India Department of ECE Vel Tech Rangarajan Dr. Sagunthala Institute of Science and Technology Chennai India

ISBN: (数字)9798331504403

ISBN: (纸本)9798331504410

Neural networks that are inspired by the way a human brain is structured, are known as artificial neural networks represent a unique class of machine learning algorithms. these algorithms allow artificial neural networks to acquire from data, and make resolutions based on the outcome, just like humans do. Non-linear data models, which have a whole load of variables and inputs, can predict new patterns. Artificial neural networks are already leveraged in everything from medical diagnoses to speech recognition as well as the ever-growing field of machine translation. there are multiple processes involved in the deep learning methodology that the method suggests for classifying bipolar disease. First, clinical and demographic data such as the sample’s age, gender, symptom severity, and medication history would be included in the dataset of bipolar disorder patient samples and control samples. the dataset would next undergo preprocessing to remove any outliers or missing values. In the meantime, standardization and normalization would be applied to the data to ensure that each variable is on a consistent scale. data scientists may also decide to use feature selection to determine which variables are most useful for overall optimization for classification goals. In this proposed system accuracy is better as compared to the remaining conventional models. this makes it easier for us to select the elements that are most crucial to making our part a real feature. the two models ANN are the final features. Findings demonstrate that deep learning models, like as artificial neural networks (ANNs), are effective in treating neuroinformatics illnesses since datasets are readily available. When it comes to public relations, moods, and the dataset, the deep learning model predicts the correct classes with more precision. A popular application of ANN involves approximating a random function, thereby providing an inexpensive way to get to various statistics characterizing its distrib

关键词： Deep learning machine learning algorithms Public relations Artificial neural networks Standardization Speech recognition Predictive models Prediction algorithms Medical diagnostic imaging Biological neural networks

来源：评论

学校读者我要写书评

暂无评论

Breast Cancer Detection using machine learning

Breast Cancer Detection using Machine Learning

引用

Advances in Computing, Communication Control and Networking (ICAC3N), international conference on

作者： Bipul Raj Kishlay Raj L. Vetrivendan M. Arvindhan School Of Computer Science & Engineering Galgotias University Greater Noida Uttar Pradesh

ISBN: (数字)9798350330861

ISBN: (纸本)9798350330878

Breast Cancer is the major cancer among all other type of cancer in women around the world and it is increasing day by day in most of the developing countries and the cases are diagnosed in the last stage in most cases. Some of the project that have been already proposed shows a comparison with the help of machine learning algorithms like data mining techniques or blood analysis, ensemble methods and diagnostics etc. In this paper we will make a comparison of six machine learning (ML) algorithms: random forest (RT), Naive Bayes (NB), nearest neighbor (KNN), artificial neural networks (ANN), support vector machines (SVM) and Wisconsin Decision Tree (DT) on Diagnostic Breast Cancer (WDBC) dataset which is extracted from a digitized image of an MRI. Some data from the international agencies shows that breast cancer generally occurs in the middle-aged women and there are very few cases where it is seen in the women under the age of 25.

关键词： Support vector machines Surveys machine learning algorithms Artificial neural networks Prediction algorithms Breast cancer Vectors

来源：评论

学校读者我要写书评

暂无评论

Innovation of Multimodal learning Paths Based on learning Behavior and Sentiment Analysis in AI Digital Intelligence Platform

Innovation of Multimodal Learning Paths Based on Learning Be...

引用

5th international conference on machine learning and Big data Analytics for IoT Security and Privacy, SPIoT 2024

作者： Wang, Lei Peng, Nan Liu, Lu Wei, Sheng Basic Education Department East University of Heilongjiang Harbin150066 China Teaching Affairs Department East University of Heilongjiang Harbin150066 China School of Management Harbin University of Commerce Harbin150028 China

this study develops an intelligent multimodal learning path recommendation system to address the problems of lack of personalized learning paths and insufficient attention to students' emotional impact in traditional digital education models. By integrating learning behavior analysis and sentiment analysis, the Random Forest (RF) model is used to deeply mine students' learning behavior data, such as analyzing learning time, resource access frequency, etc., to precisely understand students' learning patterns. At the same time, with the help of sentiment analysis technology based on BERT (Bidirectional Encoder Representations from Transformers), students' emotional states during the learning process are monitored in real-time, including positive, negative, neutral, and other emotions. the experimental results show that by dynamically adjusting the learning path and monitoring students' emotional states, students' average scores increase by 6.0%, and homework completion rate increases by 4.4%. this study not only improves the overall quality of education, but also provides educators with more scientific decision-making support tools. © 2025 the Authors. Published by Elsevier B.V.

关键词： Emotion recognition

来源：评论

学校读者我要写书评

暂无评论

A Concept Drift Detection Approach Based on Jensen-Shannon Divergence for Network Traffic Classification 22

A Concept Drift Detection Approach Based on Jensen-Shannon D...

引用

Proceedings of the 2022 5th international conference on Artificial Intelligence and pattern recognition

作者： Wujun Yang Rui Su Yuanzheng Cheng Juan Guo School of Communications and Information Engineering Xi'an University of Posts & Telecommunications China

ISBN: (纸本)9781450396899

Network traffic features change with time and network environment, creating a concept drift problem that leads to a decrease in the accuracy of machine learning-based network traffic classification methods. this is because the traditional network traffic classifiers are static models that cannot adapt to the changes in data distribution. therefore, we proposed a concept drift detection approach based on Jensen–Shannon divergence, named CDJD. the method uses a double-layer window mechanism to detect changes in data distribution based on the Jensen-Shannon divergence, and thus detects concept drift. After detecting concept drift, the Jensen-Shannon divergence is used to check whether the current concept is a recurrence of the past concept and thus decide whether to reuse the old classifier. the method is experimentally compared with common concept drift detection methods, and the experimental results show that the method can effectively detect concept drift and showing better classification performance.

关键词： Concept drift Jensen–Shannon divergence machine learning Network traffic classification

来源：评论

学校读者我要写书评

暂无评论

Personalized and Interactive Demented Care and learning Mate with a Virtual System Using Emotion recognition

Personalized and Interactive Demented Care and Learning Mate...

引用

Advancements in Computing (ICAC), international conference on

作者： Nipuna Kaushan Devshan Fernando Chamod Gayashan Sachitha Udayakantha Hansi De Silva Sanduni Perera Department of Information Technology Sri Lanka Institute of Information Technology Malabe Sri Lanka Department of Computer Science and Software Engineering Sri Lanka Institute of Information Technology Malabe Sri Lanka

this study investigates the development and application of a personalized, interactive virtual system to enhance dementia care and protect people with dementia. A significant challenge in providing care for individuals with dementia is the propensity to wander and become lost, which can lead to anxiety and distress for both the patient and the carers as well as safety concerns. the system combines cutting-edge emotion recognition technology and healthcare IOT technology to effectively identify and provide real-time solutions in response to users' emotional states. this initiative combines dementia care, educational support, and patient security to establish a comprehensive strategy for maintaining well-being and managing the disease in dementia patients. this project has experimentally designed a security system to enhance the safety of dementia patients, a Health Checker system aimed at maintaining their health stability, and a virtual assistant that offers guidance by identifying real-time emotions and providing activities to improve cognitive function and promote relaxation Given a vast amount of patient data, the AI model has been able to identify 98% of patients' illnesses early. security software successfully detected patients with 99% accuracy using GPS technology and machine learning algorithms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Communication with Real-Time Tamil Subtitled Sign Language

Enhancing Communication with Real-Time Tamil Subtitled Sign ...

引用

Innovative Trends in Information Technology (ICITIIT), international conference on

作者： S Shoba R Krithiga A V J Dhanushvardan K Gowtham Balaaji S Krithika S Pranaav Centre for Advanced Data Science (CADS) Vellore Institute of Technology Chennai Tamil Nadu India School of Computer Science and Engineering (SCOPE) Vellore Institute of Technology Chennai Tamil Nadu India School of Electronics Engineering (SENSE) Vellore Institute of Technology Chennai Tamil Nadu India

ISBN: (数字)9798350386813

ISBN: (纸本)9798350386820

Communicating with hearing impaired people through sign language is challenging since Indian Sign Language (ISL) differs from each state. this acts as a solution to the dearth of resources for studying ISL in Tamil, addressing the issues faced by the 1.6 million disabled people in Tamil Nadu. this innovative software prototype offers real-time subtitles for Indian Sign Language (ISL), empowering the deaf and dumb communities. A painstakingly trained machine learning model, an easy-to-use web application made using Streamlit, a smooth integration of the ML model for real-time sign recognition, and cloud deployment for public accessibility are the main elements of the project. the project’s potential to improve comprehension and communication within the deaf and dumb community is what makes it significant.

关键词： Sign language Prototypes machine learning Auditory system People with disabilities Market research Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Predicting Environmental, Social, and Governance Scores with machine learning: A Systematic Literature Review

Predicting Environmental, Social, and Governance Scores with...

引用

data Analytics for Business and Industry: Way Towards a Sustainable Economy (ICDABI), international conference on

作者： Fatima Binzaiman Kubra Maki Edhrabooh Muna Alromaihi Minwir AlShammari Economic and Finance Department University of Bahrain Sakhir Bahrain Business and Logistics Faculty Bahrain Polytechnic Isa Town Bahrain Management & Marketing Department University of Bahrain Sakhir Bahrain

ISBN: (数字)9798350368710

ISBN: (纸本)9798350368727

the paramount factors in assessing sustainability and the social responsibility of business are environmental, social, and governance (ESG). Over the last few years, leveraging machine learning (ML) methods in predicting ESG scores has preserved significant recognition due to its possibility of enhancing prediction accuracy, investment practices, and decision-making processes by stakeholders, policymakers, and investors. Our research uses ML methods to synthesize recent findings from scholarly articles on ESG score prediction. the systematic literature review (SLR) elucidates diverse areas of previous literature, such as datasets, methodology, metrics, and findings. the finding of SLR illustrates the significant application of ML to predict ESG scores, especially by Random Forest. the research paves the way for practical implications for stakeholders seeking long-term investment practices. However, it also underscores the pressing need for further studies to explore the capabilities of other ML models and enhance their capabilities through integrating hybrid models or feature engineering, thereby ensuring the continued improvement and relevance of ESG score prediction.

关键词： Measurement Industries Pressing Predictive models Stakeholders Sustainable development Random forests Systematic literature review Investment Business

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318页 << < 106 107 108 109 110 111 112 113 114 115 > >>

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：