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

262 篇 会议
3 册 图书

馆藏范围

265 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

185 篇 工学
- 171 篇 计算机科学与技术...
- 148 篇 软件工程
- 46 篇 信息与通信工程
- 35 篇 生物工程
- 24 篇 生物医学工程（可授...
- 21 篇 控制科学与工程
- 18 篇 安全科学与工程
- 14 篇 交通运输工程
- 12 篇 网络空间安全
- 10 篇 电气工程
- 8 篇 机械工程
- 8 篇 电子科学与技术（可...
- 7 篇 农业工程
95 篇 理学
- 57 篇 数学
- 37 篇 生物学
- 29 篇 系统科学
- 27 篇 统计学（可授理学、...
- 12 篇 物理学
71 篇 管理学
- 45 篇 图书情报与档案管...
- 43 篇 管理科学与工程(可...
- 28 篇 工商管理
33 篇 医学
- 24 篇 基础医学(可授医学...
- 24 篇 临床医学
- 17 篇 药学(可授医学、理...
- 11 篇 公共卫生与预防医...
- 9 篇 特种医学
12 篇 经济学
- 12 篇 应用经济学
12 篇 法学
- 11 篇 社会学
9 篇 教育学
- 9 篇 教育学
9 篇 农学
- 9 篇 作物学

主题

44 篇 machine learning
14 篇 deep learning
9 篇 machine learning...
9 篇 forecasting
8 篇 support vector m...
8 篇 predictive model...
8 篇 artificial intel...
7 篇 big data
7 篇 decision trees
6 篇 sentiment analys...
5 篇 random forest
5 篇 predictive analy...
5 篇 data analytics
5 篇 data science
4 篇 internet of thin...
4 篇 visual analytics
4 篇 data mining
4 篇 adversarial mach...
4 篇 computational mo...
4 篇 time series anal...

机构

6 篇 national univers...
6 篇 the islamic univ...
6 篇 altoosi universi...
5 篇 college of mlt a...
5 篇 medical technica...
2 篇 doctoral school ...
2 篇 valdosta state u...
2 篇 waterford instit...
2 篇 karnataka bangal...
2 篇 college of scien...
2 篇 al-zahraa univer...
2 篇 hitachi asia ltd...
2 篇 wuhan business u...
2 篇 bengaluru
2 篇 vardhaman colleg...
2 篇 international sc...
2 篇 computer science...
2 篇 autonomous unive...
2 篇 st michaels hosp...
2 篇 national school ...

作者

2 篇 chen fan
2 篇 chattopadhyay su...
2 篇 cornely pierre-r...
2 篇 sumit
2 篇 kumar narendra
2 篇 kumar aman
2 篇 m. a. jabbar
2 篇 tohazen
2 篇 sanju tiwari
2 篇 fernando ortiz-r...
2 篇 khademi april
2 篇 wang jin
1 篇 banerjee anasua
1 篇 karl w. jenkins
1 篇 mahammed nadir
1 篇 yunxia feng
1 篇 harutyun s. hovh...
1 篇 chang yuan
1 篇 nguyen ngoc-nhu ...
1 篇 usmani m. ahmer

语言

259 篇 英文
6 篇 其他
6 篇 中文

检索条件"任意字段=6th International Conference on Applied Machine Learning and Data Analytics, AMLDA 2023"

共 265 条记录，以下是131-140 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：

machine learning Analysis on Predicting Credit Card Forgery 1

引用

6th international conference on Innovative Computing and Communication, ICICC 2023

作者： Janani, S. Sivarathinabala, M. Anand, Rohit Ahamad, Shahanawaj Usmani, M. Ahmer Basha, S. Mahabub Department of ECE Periyar Maniammai Institute of Science and Technology Tamil Nadu Thanjavur India Department of ECE Velammal Institute of Technology Tamil Nadu Chennai India New Delhi India College of Computer Science and Engineering University of Hail Hail City Saudi Arabia Department of CSE Department of Engineering and Technology Bharati Vidyapeeth Deemed to be University Navi Mumbai India Department of Commerce IIBS Bangalore Airport Campus Karnataka Bengaluru India

ISBN: (数字)9789819930104

ISBN: (纸本)9789819930098

Occurrences comprising of credit card fraud arise frequently and result in spending a huge amount of fund. Online credit card transactions nowadays consist of a major part of various transactions driven online, that has remarkable expansion. thus, banks and different financial institutions impart important and desirable credit card fraud detection programs. Fraudulent transactional activities can have various patterns and comprise of various types. the four major fraud schemes in real-life transactions are the subject matter of this investigation. A majority of machine learning algorithms are utilized to handle every scam, and the optimal technique is finally selected after scrutiny. this research suggests an in-depth guide for selecting the superior approach for the type of frauds, and the authors furnish a suitable performance metric to demonstrate the assessment. Real-world credit card fraud detection is a further important subject that the authors represent in this paper. To decide if a certain transaction is legal or deceitful, the authors apply predictive analytics conducted by the unified machine learning approaches and an API package. the authors assess an unparalleled technique which conveniently rectifies the skewed distribution of the data also. In accordance to a confidential declaration treaty, the bank supplied the data for this research. © 2023, the Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Predictive analytics

来源：评论

学校读者我要写书评

暂无评论

A Financial Forecast Method Based on machine learning 6

A Financial Forecast Method Based on Machine Learning

引用

6th Annual international conference on data Science and Business analytics, ICDSBA 2022

作者： Chen, Tianyao Beijing Bayi High School Beijing China

ISBN: (纸本)9781665454506

Stock forecast refers to the prediction of the future development direction and the rise and fall of the stock market by securities analysts who are familiar with the stock market according to the development of the stock market. this prediction behavior is only based on the factor assumption as a given precondition. machine learning is more popular than ever. It is widely used for data based decision-making and investment. As long as you search "machine learning"and "stock prediction"on Google at the same time, you will get rich content about time series prediction and recurrent neural network. Although stock prices are a good data choice for such algorithms, caution should be exercised, especially when funds are involved. Predicting changes in the stock market has always been one of the most challenging things. Various factors involved in this prediction. All these factors make stock prices volatile and difficult to predict accurately. the systematic risk and unsystematic risk of stock investment are complex, and it is difficult to extract and analyze the quantitative relationship between various influencing factors, which makes the prediction results of traditional methods often unsatisfactory. therefore, it is very important to find an effective inventory forecasting method. In this study, various mathematical theories and data mining techniques are applied to the stock analysis software, and through the study of historical trading data, the trend law of stocks is obtained. through machine learning, we can continuously learn and optimize the data in the process of application, and improve the prediction model to successfully predict the stock increase, and then achieve the goal of profitability. © 2022 IEEE.

关键词： Financial markets

来源：评论

学校读者我要写书评

暂无评论

Tutorial on understanding meta-learning for fast adaptation 23

Tutorial on understanding meta-learning for fast adaptation

引用

6th ACM India Joint international conference on data Science and Management of data, CODS-COMAD 2023

作者： Saxena, Kavya Ranjan Arora, Vipul Electrical Engineering Indian Institute of Technology Kanpur India

ISBN: (纸本)9781450397988

Deep learning methods provide excellent performance when sufficiently large annotated data is available. But their performance degrades when the models are applied to different target domains with very different data distributions as compared to that of the source domain. the performance of such models can be improved by domain adaptation. In this tutorial, we discuss two domain adaptation techniques, i.e. fine-tuning and meta-learning, with a methodical analysis of meta-learning based adaptation. Meta-learning works in a manner similar to how humans take in a handful of examples and learn new skills very quickly and efficiently. Generally, data-level and parameter-level approaches are considered when solving a few-shot learning problem. Meta-learning is one of the parameter-level approaches. the tutorial is targeted toward those who wish to gain comprehensive insight and practical experience in applying meta-learning for fast adaptation. We show applications of these techniques through Jupyter notebooks, demonstrating how core concepts can be translated into empirical work. For those who are new to this area, we will provide a hands-on session and online pedagogical guide that can serve as the basis for fostering future research. We hope to convey a comprehensive understanding of recent advances and current state-of-the-art approaches to those who have prior knowledge of the areas. We would expect some basic experience in the execution of Jupyter notebooks and some basic knowledge of concepts related to machine learning as a prerequisite for participation. © 2023 ACM.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Semantic Segmentation of 3D Medical Images through a Kaleidoscope: data from the Osteoarthritis Initiative 6

Semantic Segmentation of 3D Medical Images Through a Kaleido...

引用

6th international conference on Medical Imaging with Deep learning (MIDL)

作者： Woo, Boyeong Lorenzanal, Marlon Bran Engstrom, Craig Baresic, William Fripp, Jurgen Crozier, Stuart Chandra, Shekhar S. Univ Queensland Sch Informat Technol & Elect Engn Brisbane Qld 4072 Australia Univ Queensland Sch Human Movement & Nutr Sci Brisbane Qld 4072 Australia Australian EHlth Res Ctr Commonwealth Sci & Ind Res Org Brisbane Qld Australia

While there have been many studies on using deep learning for medical image analysis, the lack of manually annotated data remains a challenge in training a deep learning model for segmentation of medical images. this work shows how the kaleidoscope transform (KT) can be applied to a 3D convolutional neural network to improve its generalizability when the training set is extremely small. In this study, the KT was applied to a context aggregation network (CAN) for semantic segmentation of anatomical structures in knee MR images. In the proposed model, KAN3D, the input image is rearranged into a batch of downsampled images (KT) before the convolution operations, and then the voxels are rearranged back to their original positions (inverse KT) after the convolution operations to produce the predicted segmentation mask for the input image. Compared to the CAN3D (without the KT), the KAN3D was able to reduce overfitting without data augmentation while maintaining a fast training and inference time. the paper discusses the observed advantages and disadvantages of KAN3D.

关键词： Kaleidoscope segmentation CAN knee MRI

来源：评论

学校读者我要写书评

暂无评论

Predictive Modeling for Detection of Depression Using machine learning 6th

Predictive Modeling for Detection of Depression Using Machin...

引用

6th international conference on applied Informatics, ICAI 2023

作者： Di Felice, Martín Deroche, Ariel Trupkin, Ilan Chatterjee, Parag Pollo-Cattaneo, María F. Grupo GEMIS Facultad Regional Buenos Aires Universidad Tecnológica Nacional Buenos Aires Argentina

ISBN: (纸本)9783031468124

Predictive modeling techniques using artificial intelligence have shown promising potential in detecting and predicting depression in recent times, adding newer perspectives to mental health assessment and treatment. this paper presents a predictive modeling approach to detect the presence of depression using machine learning techniques. It presents predictive models to detect depression based on depression-related data of a student cohort containing demographic and academic data along with depression information collected through the Beck Depression Inventory questionnaire, in addition to scores such as the PHQ (Patient Health Questionnaire) score, GAD (Generalized Anxiety Disorder) score, and Epworth score, which provide insights into the severity and impact of depressive symptoms, anxiety symptoms, and daytime sleepiness, respectively. the methodology involves data collection and preparation, feature selection, model selection, and model training using machine learning techniques. the results show the performance metrics of different predictive models on various dataset versions generated through preprocessing steps such as normalization, feature encoding, and selection. the best metrics are compared and evaluated, where the Linear Discriminant Analysis model performed best in terms of AUC, F1 score, and other metrics in this specific cohort. Considering the recent advancements of machine learning, incorporating predictive modeling would be important to designing clinical decision support systems, for a comprehensive prediction and analysis of depression in different cohorts, to act as an assistive tool for mental health professionals. © 2024, the Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Decision support systems

来源：评论

学校读者我要写书评

暂无评论

Detecting Children with Autism Spectrum Disorder Based on Eye-tracking and machine learning 6

Detecting Children with Autism Spectrum Disorder Based on Ey...

引用

6th IEEE international conference on Knowledge Innovation and Invention, ICKII 2023

作者： Lu, Hsin-Yi Lin, Yang-Cheng Chen, Chia-Hsin Wang, Chih-Chung Han, Ia-Wen Liang, Wen-Lung Kaohsiung Medical University Chung-Ho Memorial Hospital Department of Rehabilitation Kaohsiung Taiwan National Cheng Kung University Department of Industrial Design Tainan Taiwan

ISBN: (纸本)9798350323535

Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder that appears in childhood with varying severity. Unfortunately, current screening methods for ASD often lack sensitivity. While clinical observation-based evaluations are more reliable, they are also time-consuming. An artificial intelligence (AI) model has the potential to analyze eye-tracking data and provide a more efficient and objective assessment of ASD, potentially reducing diagnosis time and improving accuracy. the model helps children with ASD access necessary medical resources more promptly. In the current study, 58 children aged 4 to 6 years were recruited. the children were presented with static images that were divided into five categories based on the number of individuals and interactions. Eye-tracking technology was used to record various metrics, including fixation count, duration, percentage, and time to the first fixation on areas of interest (AOI) during image viewing. Principal Component Analysis (PCA) was implemented for feature selection, and Synthetic Minority Over-sampling Technique was used to generate minority samples. Five classification algorithms (Decision Tree, Random Forest, Logistic Regression, Extreme Gradient Boosting, and Support Vector machine) were applied to classify children with ASD and TD. Both groups of children completed calibration and testing after guidance, and no adverse reactions occurred during the testing process. the results showed that the classification models achieved an SVM accuracy of 83.3%, an AUC of 0.94, an LR accuracy of 83.3%, an AUC of 0.95, a DT accuracy of 77.8%, an AUC of 0.81, an RF accuracy of 88.9%, and an AUC of 0.96, as well as an XGBoost accuracy of 94.4% and an AUC of 0.99 for selected 10 features. Using machine learning methods to analyze eye-tracking data was a useful tool for identifying children with autism and may aid in the diagnostic process. © 2023 IEEE.

关键词： Eye tracking

来源：评论

学校读者我要写书评

暂无评论

Using Sentiment Analysis to Spot Trending Products 6

Using Sentiment Analysis to Spot Trending Products

引用

6th international conference on Vocational Education and Electrical Engineering, ICVEE 2023

作者： Darraz, Nossayba Karabila, Ikram El-Ansari, Anas Alami, Nabil Lazaar, Mohamed Mallahi, Mostafa El Sidi Mohamed Ben Abdellah University High Normal School Department of Mathematics and Computer Science IPI Laboratory Fez Morocco Mohammed First University Polydisciplinary Faculty Computer Science Department MASI Laboratory Nador Morocco Mohammed First University Higher School of Technology MASI Laboratory Nador Morocco Mohamed v University ENSIAS Rabat Morocco

ISBN: (纸本)9798350326642

Trend detection refers to the process of recognizing significant patterns or trends within large datasets, including changes over time and seasonal variations. In the context of product-related data, trend product detection is a specialized tool or software that is specifically designed to identify trends in sales, customer preferences, product reviews, and other relevant data points. the study focuses on the combination of trend detection and sentiment analysis as a powerful approach for trend spotting. In this paper, we present a study that uses natural language processing (NLP) techniques and the VADER sentiment analysis tool to identify product sentiment from customer reviews. We then applied decision tree analysis to predict whether a product is likely to trend or not based on its sentiment score. Additionally, we used clustering to group the top-rated products based on their sentiment scores and applied a moving average to determine which products are currently trending. Our results show that the combination of trend detection and sentiment analysis can effectively identify trending products with an accuracy of 93%. this study demonstrates the power of NLP and sentiment analysis in detecting trends and provides valuable insights for businesses to make data-driven decisions about their product offerings. © 2023 IEEE.

关键词： machine learning

来源：评论

学校读者我要写书评

暂无评论

Occupancy Estimation in Smart Buildings: Impact of data Quality on Feature Selection 6

Occupancy Estimation in Smart Buildings: Impact of Data Qual...

引用

6th international conference on Computational Intelligence and Intelligent Systems, CIIS 2023

作者： Amayri, Manar Pawar, Yogesh Concordia Institute for Information Systems Engineering Concordia University MontrealQC Canada

ISBN: (纸本)9798400709067

Feature selection has been widely applied in machine learning applications to reduce computational time, improve learning accuracy, and better understand the data modeling process. One of the vital challenges is the correct selection of the relevant features from the available ones in the training dataset. A training dataset of poor quality may compromise the features selection step, which will decrease the generalization capability of the resulting model. Defining the essential features based on data from sensors in smart building applications can significantly reduce solution complexity and total cost. In this paper, an indicator named Qscore is proposed to assess the quality of the training data as an essential step before deploying the feature selection methods. Moreover, a high Qscore value would confirm the reliability of the selected features. To validate the proposed novel concept, the occupancy estimation problem in an office contest is investigated. the training data consist of the measurements collected from standard sensors, for instance, motion detection, power consumption, and CO2 concentration, and the label (i.e., the number of occupants). Several features selection methods along with the proposed data quality indicator and cross-validation approach are deployed to assure the best choice of features in the occupancy estimation problem. Extensive simulations and experiments show the merits of our framework. © 2023 ACM.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Optimization Technology and Application of Reinforcement Layout in Lapped Columns Based on BIM and FEM 4

Optimization Technology and Application of Reinforcement Lay...

引用

4th international conference on machine learning and Big data analytics for IoT Security and Privacy, SPIoT 2023

作者： Yang, Bing Geng, Dajiang Zhang, Baoan Guo, Xiaowei Ni, Yanming Bai, Zhicheng Long, Minjian China Construction Fourth Engineering Division Corp.Ltd Guangdong Guangzhou510510 China China Construction 4th Engineering Bureau 6th Corp. Ltd Shanghai201199 China Hangzhou Construction Engineering Quality Safety Supervision Station Zhejiang Hangzhou310000 China

Lapped column transition is a novel structural form. In lapped column transition structures, the reinforcement at the lapped column nodes is generally dense, which is highly unfavorable for construction operations. Even if construction operations are carried out, it is difficult to guarantee the construction quality and mechanical performance of the nodes. To address this issue, taking a practical engineering project as an example, a comprehensive optimization of the reinforcement layout in lapped columns is conducted using BIM (Building Information Modeling) and FEM (Finite Element Method) technologies. the research results demonstrate that BIM technology can effectively and rapidly optimize the reinforcement layout in lapped columns, resulting in a layout that is more conducive to on-site construction and can effectively ensure construction quality. FEM technology can effectively perform mechanical performance calculations on the optimized lapped columns, with the mechanical performance of the optimized lapped columns being basically unchanged and still meeting the requirements of engineering structural mechanics. © 2024 the Authors.

关键词： Lapping

来源：评论

学校读者我要写书评

暂无评论

STRESS PREDICTION USING ENHANCED FEATURE SELECTION AND KNN MODEL 6

STRESS PREDICTION USING ENHANCED FEATURE SELECTION AND KNN M...

引用

6th international conference on Advanced Computing and Communication Technologies for High Performance Applications (ACCthPA)

作者： Maria, A. S. Sunder, R. Antony, Anly M. Sahrdaya Coll Engn & Technol Dept Comp Sci & Engn Trichur India

ISBN: (纸本)9798350398441

the necessity of becoming aware of one's mental and physical well-being has been growing rapidly in light of the modern economy's enhanced conditions. Numerous significant factors contribute to mental health problems like depression and anxiety. Medical-based systems like an electroencephalogram, an electrocardiogram, and a heart rate variability analysis were utilized in the previous models. the analysis of a person's brain activities and mental state will be done by taking into account the corresponding readings and recordings of each machine used here. the results of specific approaches are gathered, which suggest different brain signal variances and nerve disorders. the implementation of this paradigm is more difficult, time-consuming, and expensive when compared to other models. the KNN (K-Nearest Neighbor) machine learning model is proposed here with an enhanced feature selection, a non-parametric technique that employs similarity to categorize or determine how each unique data point will be grouped. the enhanced feature selection model decreases the input variable and ignores the noise data. Filtering techniques like forward filtering and backward filtering are applied after preprocessing *** KNN predicts the outcome with an accuracy of 99% and is considered the best classifier.

关键词： EEG ECG HRV machine learning Model KNN classifier data Filtering Forward Filtering Backward Filtering Enhanced Feature Selection

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27页 << < 10 11 12 13 14 15 16 17 18 19 > >>

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：