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

22,737 篇 会议
3,246 篇 期刊文献
19 篇 学位论文
7 册 图书

馆藏范围

26,008 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

5,167 篇 工学
- 3,101 篇 计算机科学与技术...
- 2,550 篇 电气工程
- 1,389 篇 信息与通信工程
- 689 篇 控制科学与工程
- 593 篇 软件工程
- 286 篇 仪器科学与技术
- 219 篇 环境科学与工程（可...
- 189 篇 机械工程
- 184 篇 生物医学工程（可授...
- 163 篇 交通运输工程
- 150 篇 测绘科学与技术
- 130 篇 生物工程
- 123 篇 石油与天然气工程
- 121 篇 电子科学与技术（可...
- 118 篇 材料科学与工程（可...
- 111 篇 网络空间安全
- 96 篇 土木工程
- 92 篇 动力工程及工程热...
- 65 篇 水利工程
944 篇 理学
- 289 篇 生物学
- 188 篇 物理学
- 157 篇 化学
- 139 篇 地球物理学
- 133 篇 数学
- 84 篇 系统科学
612 篇 管理学
- 525 篇 管理科学与工程(可...
- 69 篇 图书情报与档案管...
439 篇 医学
- 284 篇 临床医学
- 96 篇 基础医学(可授医学...
227 篇 农学
- 148 篇 作物学
53 篇 经济学
51 篇 法学
49 篇 文学
48 篇 教育学
17 篇 艺术学
3 篇 军事学
2 篇 哲学

主题

26,009 篇 machine learning...
8,393 篇 machine learning
4,275 篇 support vector m...
4,229 篇 accuracy
4,193 篇 prediction algor...
3,613 篇 predictive model...
3,490 篇 training
3,223 篇 classification a...
3,187 篇 feature extracti...
1,954 篇 data models
1,815 篇 computational mo...
1,787 篇 deep learning
1,683 篇 random forests
1,468 篇 neural networks
1,400 篇 real-time system...
1,398 篇 clustering algor...
1,276 篇 data mining
1,149 篇 optimization
1,004 篇 decision trees
977 篇 measurement

机构

120 篇 chitkara univers...
39 篇 lovely professio...
36 篇 chitkara centre ...
30 篇 computer science...
30 篇 centre of resear...
28 篇 department of co...
26 篇 school of comput...
21 篇 univ chinese aca...
21 篇 computer science...
21 篇 school of comput...
20 篇 computer science...
18 篇 school of comput...
17 篇 school of comput...
17 篇 department of co...
16 篇 brac university ...
16 篇 khulna universit...
15 篇 symbiosis instit...
14 篇 department of co...
13 篇 school of comput...
13 篇 computer science...

作者

25 篇 ashwini kodipall...
24 篇 mahendra kumar g...
15 篇 rakesh kumar
13 篇 wei liu
13 篇 atul kumar
12 篇 qiangfu zhao
12 篇 amit kumar
12 篇 surendran r
12 篇 satvik vats
11 篇 jun zhang
11 篇 li li
11 篇 liu yang
11 篇 wei li
10 篇 sudeep tanwar
10 篇 himanshu sharma
10 篇 amiya ranjan pan...
9 篇 lei wang
9 篇 tohari ahmad
9 篇 shanmugasundaram...
9 篇 rishabh sharma

语言

25,798 篇 英文
153 篇 其他
33 篇 中文
4 篇 法文
2 篇 西班牙文
2 篇 荷兰文
2 篇 土耳其文

检索条件"主题词=Machine Learning Algorithms"

共 26009 条记录，以下是4431-4440 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：

AI-Powered Cigarette Demand Forecasting: A Hybrid machine learning and Deep learning Approach

AI-Powered Cigarette Demand Forecasting: A Hybrid Machine Le...

引用

Computer Applications and Information Technology (ISCAIT), International Symposium on

作者： Jing Yang Changxian Jia Jie Liu Fang Song Langang Feng Guizhou Tobacco Company Qiannan Branch Company Duyun China

ISBN: (数字)9798331542856

ISBN: (纸本)9798331542863

This study puts forward a framework driven by AI, aimed at forecasting cigarette sales through combining various machine learning and deep learning models in a bid to enhance the precision and interpretability of forecasts. Different algorithms are evaluated, which includes models like Random Forest, Gradient Boosting Trees, XGBoost, LightGBM, Support Vector machine, and Artificial Neural Networks, to make predictions about cigarette demand. It is indicated that models such as RF, GBT, XGBoost, and LightGBM offer forecasts that are quite accurate overall, displaying low RMSE and high $\mathbf{R}^algorithms$ values, hence they become the selected models for this forecasting endeavor. Analysis surrounding feature importance indicates that economic factors, including aspects like product category, income, and GDP, are significant to consider when predicting cigarette sales. The benefits of employing an ensemble-based approach are emphasized, which combines different model strengths in pursuit of greater robustness and adaptability, particularly in rapidly changing market situations. This framework holds insights that might be of value to stakeholders involved in the tobacco industry, potentially assisting in the refinement of marketing and distribution strategies that they use. There could be future research that thinks about integrating real-time data along with enhancements in deep learning methods for better accommodating the complexities of the market.

关键词： Deep learning Industries machine learning algorithms Economic indicators Biological system modeling Demand forecasting Predictive models Boosting Stakeholders Random forests

来源：评论

学校读者我要写书评

暂无评论

Disambiguating Terminal Punctuation Identification of Elucidating Period Using machine learning Techniques in English Linguistic Processing

Disambiguating Terminal Punctuation Identification of Elucid...

引用

International Conference on Electrical, Computer and Communication Engineering (ECCE)

作者： Md. Tariqul Islam Foujia Khanam Tabia Md. Abu Saim Suraiya Islam Department of Computer Science and Engineering University of Global Village Barishal Bangladesh

ISBN: (数字)9798350357509

ISBN: (纸本)9798350357516

In natural text, a period is a punctuation, also known as a ”full stop" in British English. It appears like- "." or we can say dot or tiny circle. It is more ambiguous, meaning it is similarly most unclear or unresolved. Sentence boundary detection is the principal problem in period disambiguation. Periods are used to end sentences and for multiple other uses, including-URLs, abbreviations, and designations. Therefore, resolving period disambiguity is a crucial challenge in Natural Language Processing. In this paper, we proposed to classify the problem of disambiguity in natural texts through various supervised machine learning models. Several features were recognized between sentence-ending and nonsentence-ending periods. Features were extracted from the dataset from the different newspapers from online news web portals. The classes were labeled in that dataset. Different supervised learning algorithms were implemented in the dataset to predict the classes. This research aims to allow machines to perceive the context of periods, thereby having beneficial effects on Natural Language Processing, tests, and sentence analysis.

关键词： Solid modeling machine learning algorithms Accuracy Supervised learning Bidirectional control Feature extraction Transformers Natural language processing Encoding Vectors

来源：评论

学校读者我要写书评

暂无评论

Enhanced Diabetes Prediction Through Systematic Analysis of machine learning Techniques and Data Optimization

Enhanced Diabetes Prediction Through Systematic Analysis of ...

引用

Visual Analytics and Data Visualization (ICVADV), International Conference on

作者： Saroj Kumar Behera Kedarnath Panda M Vamsi Krishna P Ram Kishore Kumar Reddy P Lakshmi Supriya Kiran Kumar Reddy Penubaka Department of CSA Gandhi Institute of Engineering and Technology University Odisha India Department of CSE Gandhi Institute of Engineering and Technology University Odisha India Department of Computational Intelligence (CSE - AI & ML) Malla Reddy College of Engineering and Technology Hyderabad India Department of EEE Mahatma Gandhi Institute of Technology Hyderabad India Department of EEE Mahatma Gandhi Institute of Technology (A) Gandipet Hyderabad India Department of CSE-AIML MLR Institute of Technology Hyderabad India

ISBN: (数字)9798331521394

ISBN: (纸本)9798331521400

This research concentrates on applying various machine learning algorithms to develop an effective and efficient predictive model for screening for diabetes prediction. Its primary aim is to enhance the performance of the model and time to learn and generalize by performing feature engineering, feature selection, and hyperparameter tuning all apt. The strategy begins with preprocessing data, where problems of missing or incorrect values are addressed and duplicate records are eliminated on a dataset from Kaggle. SMOTE is employed in the case of class imbalance; new samples for the minority class are created, while outliers in datasets are identified using the DBSCAN algorithm. The required features are achieved through the Wolf Optimized Recursive Elimination (WORE), the union of the Grey Wolf Optimization (GWO) algorithm, and Recursive Feature Elimination (RFE). The model is constructed through the Random Forest-Enhanced Logistic Regression (RFELR) model, a hybrid of both Random Forest and Logistic Regression in which Random Forest is employed to obtain a nonlinear relationship, combined with logistic regression for a linear decision boundary. The final adjustment of the models is carried out using Grid Search as the Hyperparameter tuning method. These indicate that the overall performance reaches 91.5 % accuracy while precision, recall, and Fl were at 89.6%, 83.1 %, and 87.5% respectively. The paper has pointed out the appropriateness of the suggested approach in predictive performance improvement for diabetes detection to a significant degree beneficial to clinical use.

关键词： Logistic regression machine learning algorithms Systematics Visual analytics Forestry Predictive models Diabetes Optimization Tuning Random forests

来源：评论

学校读者我要写书评

暂无评论

A machine learning Framework for Skin Cancer Detection using Transfer learning

A Machine Learning Framework for Skin Cancer Detection using...

引用

International Image Processing, Applications and Systems Conference (IPAS)

作者： Mary Linda Panakal Augustine Sotirios Spanogianopoulos Mhd Saeed Sharif Department of Computer Science and Digital Technologies School of Architecture Computing and Engineering University of East London London UK School of Electrical and Mechanical Engineering University of Portsmouth Portsmouth UK

ISBN: (数字)9798331506520

ISBN: (纸本)9798331506537

This paper uses deep learning algorithms including InceptionV2, InceptionV3, DenseNet, MobileNet, and VGG19 to improve skin cancer detection. This research aims to improve skin cancer diagnosis. This work aims to determine the most effective evolutionary metrics-based technique to recognizing skin cancer, which is comparable to other diseases. Ultimately, our paper aims to create a realistic skin cancer detection system that uses the best deep learning algorithm. This discovery might improve medical diagnostics, leading to earlier diagnosis and improved healthcare outcomes.

关键词： Deep learning machine learning algorithms Image processing Transfer learning Medical diagnosis Reliability Skin cancer Image classification

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Stop-Loss Hedging Strategies for NSE Using machine learning Techniques

Data-Driven Stop-Loss Hedging Strategies for NSE Using Machi...

引用

Multi-Agent Systems for Collaborative Intelligence (ICMSCI), International Conference on

作者： Nagaraj P M Chaithanya Prabhu Visist T Janani D Hitesh S Saranath P Department of Computer Science and Engineering Kalasalingam Academy of Research and Education Virudhunagar India Department of Data Science and Artificial Intelligence Indian Institute of Technology Madras Chennai India

ISBN: (数字)9798331509828

ISBN: (纸本)9798331509835

The financial markets are inherently volatile, and investors constantly seek ways to mitigate risks while maximizing returns. This work aims to develop a stop-loss hedging strategy for a portfolio of stocks listed on the National Stock Exchange (Nse) to minimize losses and maximize returns. This strategy utilizes real-time market data to adjust stop-load levels dynamically by predicting future stock. This will protect against market downwards. We used long short-term memory (LSTM) neural networks to predict the next stock value. This AI-driven model allows the system to predict the next stock by using real-time market data and adjust the stoploss level accordingly. In addition, this system integrates a hedging strategy. It determines whether to hedge based on the predicted stock price compared to the current price. If the predicted price is less than the current price a hedging strategy like short selling or buying put option is suggested. This automated solution is useful for retail investors. This strategy will protect against losses and returns maximum profits. When the market is upside the stoploss position also increases and will make maximum profits. If the market is downward it will protest from losses by putting a stoploss level and it will return minimum losses. Here we use different algorithms in the work like decision tree, random forest, LSTM, and SVM. Based on the all algorithms we got the highest accuracy for the decision tree and the accuracy is 99.54%.

关键词： Support vector machines machine learning algorithms Accuracy Predictive models Real-time systems Decision trees Stock markets Long short term memory Random forests Portfolios

来源：评论

学校读者我要写书评

暂无评论

Improving Cardiovascular Disease Risk Prediction with machine learning

Improving Cardiovascular Disease Risk Prediction with Machin...

引用

Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI), IEEE Conference on

作者： Prince Rajput Shubham Sharma Rachit Jain Department of Electronics Engineering Madhav Institute of Technology & Science Deemed University Gwalior India Department of IT Prestige Institute of Management & Research Gwalior India

ISBN: (数字)9798331521691

ISBN: (纸本)9798331521707

The worldwide impact of cardiovascular diseases (CVDs) remains a critical issue, contributing to a significant number of fatalities annually. The primary challenge lies in the timely recognition and timely intervention to mitigate risks and improve outcomes. This study addresses this issue by employing machine learning methodologies to estimate the chances of CVDs, utilizing a dataset from Kaggle comprising information on 1000 patients and 14 key attributes including age, cholesterol levels, and prior heart conditions. The training and evaluation of four machine learning models—Random Forest, Logistic Regression, XGBoost, and Decision Tree—were conducted, with an emphasis on metrics including accuracy, recall, precision, and F1-score. Among these models, the Random Forest algorithm demonstrated superior performance, demonstrated an accuracy of 98.50%, a precision reaching 98.00%, and an F1-score hitting 99.00%. The findings highlight the possible use of machine learning techniques in supporting healthcare practitioners with early diagnosis and preventive care. Future enhancements could include incorporating genetic and lifestyle factors, alongside addressing class imbalance issues, to further improve the predictive accuracy of these models.

关键词： Training Radio frequency Measurement Technological innovation Accuracy machine learning algorithms Medical services Predictive models Cardiovascular diseases Random forests

来源：评论

学校读者我要写书评

暂无评论

machine learning Based Exploration of Lives of Interstate Migrant Workers

Machine Learning Based Exploration of Lives of Interstate Mi...

引用

Mobile Computing and Sustainable Informatics (ICMCSI), International Conference on

作者： U. Raga Jothi S. Selvaraju B. Lavaraju Saveetha School of Law Saveetha Institute of Medical and Technical Sciences (SIMATS) Chennai Tamilnadu

ISBN: (数字)9798331522667

ISBN: (纸本)9798331522674

Interstate migration plays a crucial role in fueling the growth of labor-intensive industries in India, particularly in the textile sector. This study explores the lives of interstate migrant workers in Kancheepuram's textile industry using a hybrid predictive model that combines machine learning and deep learning techniques. Data were collected through surveys, interviews, and focus group discussions, supplemented with secondary sources such as government labor reports and industry publications. Key factors such as socioeconomic background, working conditions, and access to welfare facilities were identified and processed for model development. The hybrid model integrates machine learning algorithms (Decision Trees, Random Forest, Gradient Boosting) and deep learning (LSTM networks), achieving high accuracy in predicting job retention, satisfaction, and well-being. The LSTM model demonstrated the highest accuracy at 91.7%, outperforming other models in recall, F1-score, and error metrics (MSE: 0.085). Correlation analysis identified strong relationships between income stability, training program participation, and worker satisfaction. Predictive insights highlighted that workers earning above INR 15,000 and attending at least two training sessions had an 85% probability of high job retention. These findings underscore the importance of targeted interventions in improving worker conditions and integration. This study contributes to understanding migration challenges and provides actionable insights for policymakers and industry stakeholders to enhance worker welfare and productivity.

关键词： Industries Training Accuracy machine learning algorithms Predictive models Stability analysis Interviews Long short term memory Thermal stability Textile industry

来源：评论

学校读者我要写书评

暂无评论

Smart Sensing of Water Quality: A Satellite-Driven machine learning Approach to Chemical Oxygen Demand Assessment

Smart Sensing of Water Quality: A Satellite-Driven Machine L...

引用

Computational Intelligence Approaches and Applications (ICCIAA), International Conference on

作者： Nidal M. Hussein Mohammed N. Assaf Tariq Jawad Al-Musawi Department of Civil Engineering University of Petra Amman Jordan Department of Civil Engineering and Architecture (DICAr) University of Pavia Pavia Italy Building and Construction Techniques Engineering Department Al-Mustaqbal University Babylon Iraq

ISBN: (数字)9798331523657

ISBN: (纸本)9798331523664

The limited availability of freshwater necessitates continuous and rigorous monitoring of its quality. In this context, remote sensing data has emerged as a vital tool for capturing detailed characteristics of water bodies and enabling effective water quality monitoring. This study systematically evaluates five machine learning (ML) algorithms for the inversion of chemical oxygen demand (COD) with Sentinel 2 data. These ML algorithms include CatBoost Regression (CB), XGBoost regression (XGB), random forest regression (RF), support vector machine regression (SVM), and artificial neural network (ANN). With regards to predicting COD, XGB shows the best performance with an R2 of 0.85, RMSE of 7.71 mg/l and a MAE of 2.82 mg/l on the training set, and a R2 of 0.84, RMSE of 4.27 mg/l and a MAE of 3.29 mg/l on the test set. From this study's findings, the potential for monitoring water quality in inland water bodies using remote sensing integrated with ML algorithms is illustrated, along with how it can improve decision-making.

关键词： Support vector machines Training Radio frequency machine learning algorithms Water quality Prediction algorithms Convolutional neural networks Monitoring Remote sensing Long short term memory

来源：评论

学校读者我要写书评

暂无评论

Using machine learning to Enhance Cybersecurity Threat Detection

Using Machine Learning to Enhance Cybersecurity Threat Detec...

引用

Pervasive Computational Technologies (ICPCT), International Conference on

作者： Nilesh Parihar Priyanka Fernandes Swati Tyagi Anuj Tyagi Mohit Tiwari Ahmad Y. A. Bani Ahmad ECE Gandhinagar University Gandhinagar Gujrat IT Finolex Academy of Management and Technology Ratnagiri Mumbai University Maharashtra University of Delaware DE USA Sr. Site Reliability Engineer AI/Cloud Ring Cental Inc. Denver Colorado USA Department of Computer Science and Engineering Bharati Vidyapeeth’s College of Engineering Delhi Department of Accounting and Finance Science Faculty of Business Middle East University Amman Jordan

ISBN: (数字)9798331508685

ISBN: (纸本)9798331519476

In cybersecurity, machine learning is becoming more and more significant. Making threat detection more actionable, scalable, and efficient than using conventional methods that call for human intervention is the main goal of using machine learning in cybersecurity. Cybersecurity machine learning issues require efficient, systematic, and theoretical solutions. The subtleties of applying machine learning algorithms to lower cybersecurity threats are examined in this study. The rapid increase of data in cyberspace and the level of precision of attacks necessitate a proactive approach to security. The adversarial nature of online attacks, data quality, and model robustness are some of the subjects covered in this paper. In the context of cybersecurity, ethical issues are also covered, as is the requirement for accountable and transparent AI systems. Through a careful examination of current research and practical implementations, this research demonstrates the vast potential of machine learning (ML) in bolstering cybersecurity defenses. It shows the importance of a well-coordinated approach that combines human expertise with machine learning capabilities. As the environment of cyber threats evolves, organisations seeking to safeguard their data and digital assets must leverage ML's capabilities.

关键词： machine learning algorithms Systematics machine learning Data breach Threat assessment Malware Stability analysis Robustness Computer security Computer crime

来源：评论

学校读者我要写书评

暂无评论

Enterprise Financial Risk Assessment and Pre-Alarm Model Based on machine learning Algorithm

Enterprise Financial Risk Assessment and Pre-Alarm Model Bas...

引用

Digital Analysis and Processing, Intelligent Computation (DAPIC), International Conference on

作者： Rui He Department of Sydney Smart Technology College Northeastern University at Qinhuangdao Qinhuangdao Hebei China

ISBN: (数字)9798331536169

ISBN: (纸本)9798331536176

The purpose of this article is to study the enterprise financial risk assessment and pre-alarm model based on machine learning (ML) algorithm, so as to improve the intelligent and refined level of enterprise risk management. An efficient enterprise financial risk assessment and pre-alarm system is constructed by comprehensively applying random forest (RF) algorithm, data preprocessing technology and feature selection method. In the process of model construction, firstly, the collected financial data of enterprises are comprehensively cleaned and standardized, and then the model is trained and optimized by RF algorithm. The results show that the model is excellent in accuracy, response time and concurrent processing ability, which can effectively identify potential risk signals in enterprise financial data and provide timely and reliable financial pre-alarm for enterprise managers. This study provides a new perspective for enterprise financial risk management and confirms the great potential of ML algorithm in the field of financial risk management. In the future, we will continue to explore more advanced algorithms and technologies to further optimize the model performance.

关键词： Radio frequency Analytical models machine learning algorithms Accuracy Computational modeling Data models Risk management Time factors Reliability Random forests

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500页 << < 440 441 442 443 444 445 446 447 448 449 > >>

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：