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171-180 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：

Combining Dynamic Programming and GPU to accelerate k-Distance Discord Detection in Time Series data 6

Combining Dynamic Programming and GPU to accelerate k-Distan...

引用

6th international conference on machine learning and machine Intelligence, MLMI 2023

作者： Nhan, Nguyen Trong Anh, Duong Tuan Dvorsky, Jiri Center for Applied Information Technology Ton Duc Thang University Ho Chi Minh City Viet Nam Faculty of Information Technology Ton Duc Thang University Ho Chi Minh City Viet Nam Department of Computer Science Faculty of Electrical Engineering and Computer Science VSB Technical University of Ostrava Czech Republic Department of IT Ho Chi Minh City University of Foreign Languages and Information Technology Ho Chi Minh City Viet Nam

ISBN: (纸本)9798400709456

Detecting anomalous subsequences plays a vital role in time series analysis. Traditional approaches often rely on sliding windows to extract subsequences and identify anomalies. However, these methods encounter two difficulties: i) they are unable to address the "twin freak"problem and ii) they incur high computational costs when dealing with large time series datasets. We introduce a new method called DP_KBF_GPU to address the aforementioned challenge. Our method is designed for identifying K-Distance discords and effectively handle the "twin freak"problem commonly encountered. this method combines Dynamic Programming technique and Graphics Processing Units (GPUs) parallelization to enhance its performance. By employing Dynamic Programming with the Euclidean distance metric and leveraging the parallel processing capabilities of GPUs, our method achieves efficient computations. Experimental results on six benchmark time series datasets have demonstrated the high efficiency of our approach in timely detecting the most anomalous subsequences while maintaining high accuracy. © 2023 ACM.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Domain Adaptation using Silver Standard Labels for Ki-67 Scoring in Digital Pathology: A Step Closer to Widescale Deployment 6

Domain Adaptation using Silver Standard Labels for Ki-67 Sco...

引用

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

作者： Dy, Amanda Nguyen, Ngoc-Nhu Jennifer Mirjahanmardir, Seyed Hossein Dawe, Melanie Fyles, Anthony Shi, Wei Liu, Fei-Fei Androutsos, Dimitrios Done, Susan Khademi, April Toronto Metropolitan Univ Elect Comp & Biomed Engn Toronto ON Canada Univ Toronto Dept Lab Med & Pathobiol Toronto ON Canada Univ Hlth Network Princess Margaret Canc Ctr Toronto ON Canada St Michaels Hosp Keenan Res Ctr Toronto ON Canada Inst Biomed Engn Sci & Technol iBEST Toronto ON Canada

Deep learning systems have been proposed to improve the objectivity and efficiency of Ki-67 PI scoring. the challenge is that while very accurate, deep learning techniques suffer from reduced performance when applied to out-of-domain data. this is a critical challenge for clinical translation, as models are typically trained using data available to the vendor, which is not from the target domain. To address this challenge, this study proposes a domain adaptation pipeline that employs an unsupervised framework to generate silver standard (pseudo) labels in the target domain, which is used to augment the gold standard (GS) source domain data. Five training regimes were tested on two validated Ki-67 scoring architectures (UV-Net and piNET), (1) SS Only: trained on target silver standard (SS) labels, (2) GS Only: trained on source GS labels, (3) Mixed: trained on target SS and source GS labels, (4) GS+SS: trained on source GS labels and fine-tuned on target SS labels, and our proposed method (5) SS+GS: trained on source SS labels and fine-tuned on source GS labels. the SS+GS method yielded significantly (p < 0.05) higher PI accuracy (95.9%) and more consistent results compared to the GS Only model on target data. Analysis of t-SNE plots showed features learned by the SS+GS models are more aligned for source and target data, resulting in improved generalization. the proposed pipeline provides an efficient method for learning the target distribution without manual annotations, which are time-consuming and costly to generate for medical images. this framework can be applied to any target site as a per-laboratory calibration method, for widescale deployment.

关键词： Ki-67 proliferation index domain adaptation self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Multi-objective Optimization of Adhesive Bonding Process in Constrained and Noisy Settings 6th

Multi-objective Optimization of Adhesive Bonding Process in...

引用

6th international conference on Optimization and learning, OLA 2023

作者： Morales-Hernández, Alejandro Van Nieuwenhuyse, Inneke Rojas Gonzalez, Sebastian Jordens, Jeroen Witters, Maarten Van Doninck, Bart Flanders Make@UHasselt Faculty of Science Hasselt University Diepenbeek3590 Belgium Data Science Institute Hasselt University Diepenbeek3590 Belgium Surrogate Modeling Lab Ghent University Ghent9000 Belgium CoDesignS Flanders Make Lommel3920 Belgium

ISBN: (纸本)9783031340192

Finding the optimal process parameters for an adhesive bonding process is challenging: the optimization is inherently multi-objective (aiming to maximize break strength while minimizing cost), constrained (the process should not result in any visual damage to the materials, and stress tests should not result in adhesive failures), and uncertain (measuring the same process parameters several times lead to different break strength). Real-life physical experiments in the lab are expensive to perform (∼ 6 h of experimentation and subsequent production costs);traditional evolutionary approaches are then ill-suited to solve the problem, due to the prohibitive amount of experiments required for evaluation. In this research, we successfully applied specific machine learning techniques (Gaussian Process Regression and Logistic Regression) to emulate the objective and constraint functions based on a limited amount of experimental data. the techniques are embedded in a Bayesian optimization algorithm, which succeeds in detecting Pareto-optimal process settings in a highly efficient way (i.e., requiring a limited number of experiments). © 2023, the Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Investigation of Air Effluence Using IoT and machine learning 6th

Investigation of Air Effluence Using IoT and Machine Learn...

引用

6th international conference on Emerging Technologies in Computing, iCETiC 2023

作者： Shakil, Shalah Uddin Perbhez Kashem, Mohammod Abul Islam, Md. Monirul Nayan, Nasim Mahmud Uddin, Jia Department of Computer Science and Engineering Dhaka University of Engineering and Technology Gazipur1707 Bangladesh Birulia Savar Dhaka1216 Bangladesh Dhaka1212 Bangladesh AI and Big Data Department Endicott College Woosong University Daejeon Korea Republic of

ISBN: (纸本)9783031502149

Air pollution poses a significant issue in numerous cities worldwide, impacting public health and the environment. We study three significant cities under the Dhaka division, including Kuril Bishow Road, Uttara, and Tongi. Traditional air quality monitoring methods often need more coverage and accuracy. Leveraging Internet of things (IoT) technology as well as machine learning (ML) algorithms, this study deploys an IoT-based sensor network using Arduino boards and various devices, including MQ135, DHT22, PM2.5, MQ9, and dust sensors to gather real-time values on air pollutants. the gathered data, including sulfur dioxide, ozone, particulate matter 2.5, nitrogen dioxide, particulate matter 10, as well as carbon monoxide, provides a comprehensive view of city pollution levels. ML models such as linear regression, decision trees, K-Nearest Neighbors (KNN), Naive Bayes (NB), Gradient Boosting (GB), and Random Forest classifiers are applied to predict pollution levels using environmental parameters. the Random Forest classifier achieves an impressive prediction accuracy of 97.2 %. Evaluation metrics, including precision, recall, F1 score, Kappa score, mean square error (MSE), root mean square error(RMSE), along mean absolute error (MAE), are used to assess the performance of the models. this study demonstrates the potential of IoT technology along with ML algorithms in accurately predicting air pollution levels, aiding in environmental management and public health efforts in urban areas. © 2024, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Enhancing Service Classification for Network Slicing in 5G Using machine learning Algorithms 6th

Enhancing Service Classification for Network Slicing in 5G U...

引用

6th international conference on New Trends in Information and Communications Technology Applications, NTICT 2022

作者： Mohammedali, Noor Abdalkarem Kanakis, Triantafyllos Al-Sherbaz, Ali Agyeman, Michael Opoku Hasson, Saad Talib University of Northampton Northampton United Kingdom School of Computing and Engineering University of Gloucestershire Gloucestershire United Kingdom College of Information Technology University of Babylon Babylon Iraq

ISBN: (纸本)9783031354410

In a virtualization aspect, Network Function Virtualization (NFV) has a role in implementing network slicing. Using NFV to slice the network, make the network more flexible, but very complicated in term of management. A slice is a set of services that the network needs based on the user requirements. Moreover, each slice has a set of services called sub-slice, or one type of service. this research aims to improve the availability and scalability of the services in network slicing by managing the performance of the inter/intra slice in real-time. Also, this research will enhance the Quality of Service (QoS) for the network resources and services and the Quality of Experience (QoE) for the users within the slice when we applied machine learning algorithms to classify and predicate accurate service to the user. With this research, we implemented the slices based on the principles of NFV to deliver flexibility in the 5G network by creating multiple slices on top of the physical network. When the implementation of the prototype is completed, traffic generated tool was used to send traffic over the slices. After data collection, we classified different services using machine learning algorithms. the optimizable tree model had almost high accuracy among other algorithms which was 99.3%. © 2023, the Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Network function virtualization

来源：评论

学校读者我要写书评

暂无评论

Athlete Performance Analysis: machine learning for Predicting Tennis Player Scores

Athlete Performance Analysis: Machine Learning for Predictin...

引用

international conference on Communications, Information System and Computer Engineering (CISCE)

作者： Peizhe Zhao Tianyu Luo Pengfei Bi Waterford Institute Nanjing University of Information Science and Technology Nanjing China

ISBN: (数字)9798350353174

ISBN: (纸本)9798350353181

In recent years, machine learning and deep learning have become increasingly prevalent in the field of data classification and regression, with applications in a diverse range of disciplines. Furthermore, the field of sports analytics is also gradually becoming one of the topics of machine learning research. the application of machine learning and deep learning technologies to the analysis of real-time data from sporting events enables a more accurate understanding of the performance and status of athletes. Coaches can then combine these results to determine the current state of the athlete, which allows them to adjust the game strategy accordingly and increase the probability of winning. this study employs the example of tennis, utilising detailed data from the game “the Championships Wimbledon 2023”. the data was subjected to preliminary processing in order to identify the key factors that influence the players' scores. the data was then subjected to regression and prediction using a variety of machine learning algorithms and multilayer perceptron machines in deep learning. the results demonstrate that LightGBM and NLP are the most effective algorithms for accurately evaluating the current state of athletes with the available data.

关键词： Deep learning machine learning algorithms Accuracy Games Multilayer perceptrons Prediction algorithms Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Understanding and Managing Employee Attrition: Strategies for Retaining Talent

Understanding and Managing Employee Attrition: Strategies fo...

引用

Advances in Science and Technology (ICAST), international conference on

作者： Ghanashyam Phadke Aryan Chadha Haider Bharmal Sahil Pathare Department of Artificial Intelligence and Data Science K.J. Somaiya Institute of Technology Mumbai India

In this study, we address the issue of employee attrition by employing a synergistic approach that amalgamates Power BI analytics and advanced machine learning techniques. Our methodology includes a meticulous analysis of historical employee data using Power BI, uncovering subtle attrition trends, influential variables, and pertinent demographic insights. Subsequently, we engineer a predictive machine learning model that forecasts forthcoming attrition patterns and proficiently classifies employees at high risk of departure. the model’s precision is meticulously refined through rigorous feature engineering and judicious algorithm selection like Decision Trees, Gaussian NB, Random Forest, XGBoost. To actualize these insights, we develop a user-friendly Flask web application that seamlessly integrates the analytical and predictive processes. this intuitive application empowers users to input employee details and promptly receive accurate attrition predictions. Our innovative amalgamation of analytics, machine learning, and user-centric web deployment establishes a comprehensive and efficient solution. By arming organizations with actionable insights and preemptive strategies, we significantly contribute to ameliorating employee retention, fostering engagement, and augmenting overall organizational efficacy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Tomato Leaf Disease Detection Using machine learning

Comparative Analysis of Tomato Leaf Disease Detection Using ...

引用

international conference on Information Systems and Computer Networks (ISCON)

作者： Shruti Agnihotri Jaydeep Gupta Neha Garg Pallavi Khatri Department of CSA ITM University Gwalior India

Disease transmission from affected crops to unaffected crops is getting the most dangerous things to agriculture. Epidemics spread like wildfire can affect entire farms if not spotted early. the plant disease detection method helps to identify infected plants at a very early stage and also helps users to extend plant disease identification for a variety of plants in an efficient manner. the purpose for work is to test the data using different machine learning models, Convolutional Neural Networks (CNN), K Nearest Neighbors (KNN), Visual Geometry Group (VGG-19), and apply them to plant disease detection on tomato leaves. the results on the implementation of machine learning models show that the KNN model performs better on every evaluation indicator.

关键词： Plant diseases Visual analytics Image processing Crops Imaging machine learning Software

来源：评论

学校读者我要写书评

暂无评论

Development of Smart Tongue using Ionic Polymer Metal Composite for Robotic Applications 23

Development of Smart Tongue using Ionic Polymer Metal Compos...

引用

6th international conference on Advances in Robotics, AIR 2023

作者： Das, Suman Bhadra, Subir Bhattacharya, Srijan Chattopadhyay, Subrata Department of Electrical Engineering Mckv Institute of Engineering Howrah India Department of Computer Science and Engineering Mckv Institute of Engineering India Applied Electronics and Instrumentation Engineering Department Rcc Institute of Information Technology Kolkata India Electrical Engineering Department National Institute of Technical Teachers Training and Research Kolkata India

ISBN: (纸本)9781450399807

this paper focus on the development Ionic Polymer Metal Composite (IPMC) based robotic tongue as artificial taste sensor to identify and discriminate between different taste senses. In this study, taste samples are used which denotes five taste senses- Salty, Sweetness, Spicy, Bitterness and Sourness. NafionTM-117 (DuPont) substrate based IPMC due to its hydrophilic nature allow cations like Li+, Na+, K+ etc. diffuse through its perfluorinated polymer membrane penetrating Platinum (Pt)-surface electrode layer on both side of the membrane. Cations of different concentration present in natural and artificial food products. Based on the amount of diffused cations inside the polymer matrix of IPMC, various taste samples are identified. While bending force applied on IPMC strip, mobile cations and fixed anions get polarized inside IPMC polymer membrane and create potential difference in millivolts (mV). the potential difference measured across the Pt-surface electrode of IPMC. Magnitude of the developed emf depends on cationic concentration for different taste samples. Considering taste sense as identification index, bending deformation of IPMC strip has clear correlation with magnitude of emf developed across the Pt-surface electrode. K-nearest neighbor (KNN) based Classification technique is applied in developing the machine learning (ML) Model for prediction of different taste senses. the model is trained with real-time dataset having information about output voltage developed across IPMC' vs. taste samples of variable concentration'. Training is done in two phases where the ratio of training data: test data was 70%: 30% and 80%: 20% respectively. It is observed that Prediction accuracy of the learned model increases if the volume of training dataset increases. High prediction accuracy of the developed ML model confirms the competence IPMC based e-tongue technology, applicable for robotic system as artificial taste sensor. © 2023 ACM.

关键词： machine learning

来源：评论

学校读者我要写书评

暂无评论

data Mining Approach in Predicting House Price for Automated Property Appraiser Systems 6th

Data Mining Approach in Predicting House Price for Automated...

引用

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

作者： Yousir, Naeem th. Abdulameer, Shaymaa Mohammed Mostafa, Salama A. College of Information Engineering Al-Nahrain University Baghdad10072 Iraq Faculty of Computer Science and Information Technology Universiti Tun Hussein Onn Malaysia Batu Pahat Johor86400 Malaysia

ISBN: (纸本)9789819930098

the house price prediction model can be a logistic tool in assisting individuals and companies to determine the cost of a property or a house on sale and the best time to acquire a house. With the ever-increasing in house price rates, data mining approaches have been used as a property appraiser system to predict a house price based on house features before making a deal. Existing research in house prediction involves collecting a number of house price estimation attributes into a dataset of house price features. this study is aimed at building a model for predicting house price based on the house price features dataset. then dataset is run through machine learning (ML) algorithms to learn the pattern and predict new house price cases. the cross-industry standard process for data mining (CRISP-DM) method is used for this research. Decision tree regression (DTR), linear regression (LR), multiple linear regression (MLR), and random forest regression (RFR) are the ML algorithms applied in this research. the results have shown that RFR is the most suitable algorithm for this dataset, with an average coefficient of determination (R square) of 82.09%, followed by the DTR with an R square score of 73.32% when using different training and learning splitting ratios. An application of the RFR model can be used in real estate companies for estimating the prices of properties. © 2023, the Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Multiple linear regression

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 << < 14 15 16 17 18 19 20 21 22 23 > >>

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：