检索结果-内蒙古大学图书馆

Health Data-Driven machine learning algorithms Applied to Risk Indicators Assessment for Chronic Kidney Disease

RISK MANAGEMENT AND HEALTHCARE POLICY 2021年 14卷 4401-4412页

作者： Chiu, Yen-Ling Jhou, Mao-Jhen Lee, Tian-Shyug Lu, Chi-Jie Chen, Ming-Shu Yuan Ze Univ Grad Inst Med Taoyuan 32003 Taiwan Yuan Ze Univ Grad Sch Biomed Informat Taoyuan 32003 Taiwan Natl Taiwan Univ Coll Med Grad Inst Clin Med Taipei 10002 Taiwan Far Eastern Mem Hosp Dept Med Res Dept Med New Taipei 22056 Taiwan Fu Jen Catholic Univ Grad Inst Business Adm New Taipei 242062 Taiwan Fu Jen Catholic Univ Artificial Intelligence Dev Ctr New Taipei 242062 Taiwan Fu Jen Catholic Univ Dept Informat Management New Taipei 242062 Taiwan Asia Eastern Univ Sci & Technol Coll Healthcare & Management Dept Healthcare Adm New Taipei 22061 Taiwan

Purpose: As global aging progresses, the health management of chronic diseases has become an important issue of concern to governments. Influenced by the aging of its population and improvements in the medical system and healthcare in general, Taiwan's population of patients with chronic kidney disease (CKD) has tended to grow year by year, including the incidence of high-risk cases that pose major health hazards to the elderly and middle-aged populations. Methods: This study analyzed the annual health screening data for 65,394 people from 2010 to 2015 sourced from the MJ Group - a major health screening center in Taiwan - including data for 18 risk indicators. We used five prediction model analysis methods, namely, logistic regression (LR) analysis, C5.0 decision tree (C5.0) analysis, stochastic gradient boosting (SGB) analysis, multivariate adaptive regression splines (MARS), and eXtreme gradient boosting (XGboost), with estimated glomerular filtration rate (e-GFR) data to determine G3a, G3b & G4 stage CKD risk factors. Results: The LR analysis (AUC=0.848), SGB analysis (AUC=0.855), and XGboost (AUC=0.858) generated similar classification performance levels and all outperformed the C5.0 and MARS methods. The study results showed that in terms of CKD risk factors, blood urea nitrogen (BUN) and uric acid (UA) were identified as the first and second most important indicators in the models of all five analysis methods, and they were also clinically recognized as the major risk factors. The results for systolic blood pressure (SBP), SGPT, SGOT, and LDL were similar to those of a related study. Interestingly, however, socio-economic status-related education was found to be the third important indicator in all three of the better performing analysis methods, indicating that it is more important than the other risk indicators of this study, which had different levels of importance according to the different methods. Conclusion: The five prediction model methods can provid

关键词： chronic kidney disease health screening machine learning algorithms risk indicators assessment education

来源：评论

学校读者我要写书评

暂无评论

Cervical Cancer Diagnostics Using machine learning algorithms

Cervical Cancer Diagnostics Using Machine Learning Algorithm...

引用

Emerging Technology (INCET), International Conference for

作者： Ashok K Chikaraddi Suvarna Kanakaraddi Priyadarshini Kalwad Atharv Kadole Shashikala Budni Computer Applications K L E Technological University Hubli Karnataka India School of Computer Science and Engineering K L E Technological University Hubli Karnataka India

ISBN: (数字)9798350361155

ISBN: (纸本)9798350361162

A rising number of people and businesses are using Deep learning (DL) and machine learning (ML) to analyze vast volumes of data and provide insights that can be put to use. In medical practice, it is becoming more and more usual to use machine learning methods to predict major illnesses such as cancer, kidney failure, and heart attacks in their early stages. One of the most common illnesses affecting for women is cervical cancer, which may be prevented with an early diagnosis. As a result, this work considers suitable ML algorithms to detect cervical cancer. Predictive Model Selection (PMS), data preprocessing, are performed for the chosen dataset. A variety of traditional machine learning techniques, such as Decision Trees (DT), Logistic Regression (LR), Support Vector machines (SVM), adaptive boosting, gradient boosting, random forest, K-Nearest Neighbors algorithm (KNN), and XG-Boost, are tested and reported in the PMS section. Regarding the prognosis of cervical cancer. In this work trained the dataset on three models, VGG16, Inception-v3, ResNet-50, and also developed and analyzed the performance of Ensemble model.

关键词： Support vector machines Analytical models Adaptation models machine learning algorithms Accuracy Nearest neighbor methods Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

Ransomware Detection Using machine learning algorithms

Ransomware Detection Using Machine Learning Algorithms

引用

Intelligent Methods, Systems, and Applications (IMSA)

作者： Wael Farouk Elsersy Ahmed ElShamy Moataz Samy Faculty of Computer Science October University for Modern Sciences and Arts (MSA) Giza Egypt

ISBN: (数字)9798350362633

ISBN: (纸本)9798350362640

This research paper delves into the realm of cybersecurity, exploring the synergy between machine learning algorithms and malware detection. The primary objective is to enhance the detection of ransomware cyber attacks through a meticulous analysis of binary file attributes. Leveraging a diverse dataset comprising legitimate binaries and malware files, we employ a comprehensive methodology that spans dataset selection, exploration, segmentation, visualization, cleaning, feature selection, and model building. The study uses three machine learning models; Random Forest Classifier, Logistic Regression, and a Neural Network to analyze and categorize binary files. The Random Forest Classifier shows strong performance with the highest accuracy, indicating its effectiveness with tangled datasets. Logistic Regression, acting as a baseline, demonstrates moderate effectiveness, offering insights into the dataset's complexity. The Neural Network, built with TensorFlow and Keras showcased its ability to understand complicated *** paper provides valuable insights into the capacities of different machine learning models for malware detection, emphasizing the critical role of model selection in addressing the challenges posed by ransomware cyberattacks.

关键词： Logistic regression Analytical models Visualization machine learning algorithms Neural networks Feature extraction Complexity theory

来源：评论

学校读者我要写书评

暂无评论

Enhanced machine learning algorithms for Classification in Agricultural Advisory Systems and Agricultural Data Analysis

Enhanced Machine Learning Algorithms for Classification in A...

引用

Electronic Systems and Intelligent Computing (ICESIC), International Conference on

作者： Logesh M Domnic S J. Nelson Raja Electrical & Electronics Engineering (SG & EV) Sastra Deemed University Thanjavur Tamil Nadu India Department of Computer Application National Institute of Technonology Tiruchirappalli Tamil Nadu India Department of Computer Science Thiagarajar College Madurai Tamil Nadu India

ISBN: (数字)9798331522988

ISBN: (纸本)9798331522995

Agricultural technology, ensuring reliability, and optimizing processes are paramount. This work explores the application of machine learning algorithms (ML) to two critical areas: agricultural advisory systems (AAS) and agricultural data analysis (ADA). By leveraging historical data and advanced algorithms, this work aims to enhance predictive accuracy and operational efficiency in ADA and AAS. The proposed work focuses on various ML models for classification tasks, comparing their performance metrics, and discussing their applicability in agricultural sector. The findings highlight the ML model to significantly improve outcomes in agricultural management.

关键词： Measurement machine learning algorithms Data analysis Accuracy Computational modeling Prediction algorithms Classification algorithms Reliability

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Software Reliability Prediction and Optimization using machine learning algorithms

Comparative Analysis of Software Reliability Prediction and ...

引用

Intelligent Systems and Computational Networks (ICISCN), International Conference on

作者： Prashanth Kumar Bolisetty Midhunchakkaravarthy Faculty of AI AI Computing and Multimedia Lincoln University College Selangor Darul Eshan Malaysia Faculty of AI Computing and Multimedia Lincoln University College Selangor Darul Eshan Malaysia

ISBN: (数字)9798331529246

ISBN: (纸本)9798331529253

Software reliability plays a crucial role in assessing the overall quality of software systems. Developing highly reliable software presents challenges, including ensuring usability, maintaining consistent performance, offering reliable service, and facilitating smooth maintenance. To overcome these limitations, researchers have turned to intelligent prediction and optimization algorithms. This paper presents a comprehensive review of software reliability prediction, emphasizing the application of machine learning techniques. It also provides an analytical evaluation of existing methods to identify areas for improvement and future research opportunities in software reliability prediction.

关键词： machine learning algorithms Reviews Software algorithms machine learning Software systems Prediction algorithms Software reliability Maintenance Usability Optimization

来源：评论

学校读者我要写书评

暂无评论

Enhancing Phishing Detection using machine learning algorithms

Enhancing Phishing Detection using Machine Learning Algorith...

引用

International Conference on Inventive Computation Technologies (ICICT)

作者： Jeswin K S Shubhank Gupta Rajashree Santhanakrishnan Jemshia Miriam Nafees Muneera Sathyabama Institute of Science and Technology Chennai India CMR University Bangalore

ISBN: (数字)9798331512248

ISBN: (纸本)9798331512255

The current article introduces the application of machine learning algorithms to aid phishing, i.e., the application of these algorithms to prepare well-fitting, realistic phishing attacks. Due to the nature of ML in having attributes, including natural language comprehension and pattern recognition ability, phishing attacks have the potential to evade the current traditional security tactic and execute real-time. As per the paper, the supervised learning is being trained for phishing email crafting and the unsupervised learning training for phishing victim behavioral pattern exploitation, illustrating how ML can be effectively utilized to automate and escalate phishing attacks. The findings showcase the need for adaptive ML-based security solutions to detect and counter such emerging threats.

关键词： Training Support vector machines machine learning algorithms Accuracy Phishing Unsolicited e-mail Feature extraction Ensemble learning Security Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Integrating Multiple machine learning algorithms for Bankruptcy Prediction: The Role of Voting Classifiers in Enhancing Predictive Performance

Integrating Multiple Machine Learning Algorithms for Bankrup...

引用

Advances in Computation, Communication and Information Technology (ICAICCIT), International Conference on

作者： Ashima Arya Tanishq Soni Deepali Gupta Mudita Uppal Shilpa Saini KIET Group of Institutions Delhi NCR Ghaziabad India Chitkara University Institute of Engg. And Technology Punjab India Chandigarh University Mohali India

ISBN: (数字)9798331541217

ISBN: (纸本)9798331541224

In financial management, it is an important chore to find businesses that might go bankrupt and so enable preventative measures to avert a financial crisis. In this work, the authors build an innovative model for bankruptcy prediction using a voting classifier, one of the ensemble learning techniques combining traits of several machine learning algorithms for superior predictive performance. Combining logistic regression, decision trees, and support vector machines in the approach generates a more robust prediction. The authors obtained an accuracy of $\mathbf{9 7 \%}$ with the voting classifier after rigorous training and testing on dataset having multiple financial variables. This tremendous degree of accuracy is meant to show how well ensemble methods capture complex patterns and connections inside financial data. The results reveal that the voting classifier not only raises the accuracy in prediction but also offers a dependable method through which likely bankruptcy may be found at an early stage, thereby enabling rapid and smart actions on the part of financial stakeholders.

关键词： Training Support vector machines Accuracy machine learning algorithms Predictive models Ensemble learning Stakeholders Bankruptcy Bagging Testing

来源：评论

学校读者我要写书评

暂无评论

Multi-Layer Soil Moisture Estimation Using Combined L-and P-Band Radiometry: an Application of machine learning algorithms

Multi-Layer Soil Moisture Estimation Using Combined L-and P-...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Foad Brakhasi Jeffrey P. Walker Jasmeet Judge Pang-Wei Liu Xiaoji Shen Nan Ye Xiaoling Wu In-Young Yeo Richa Prajapati Edward Kim Yann Kerr Thomas Jackson Department of Civil Engineering Monash University Clayton Australia Department of Agricultural and Biological Engineering University of Florida Gainesville USA Hydrological Sciences Laboratory NASA Goddard Space Flight Center Greenbelt USA Yangtze Institute for Conservation and Development Hohai University Nanjing China School of Engineering The University of Newcastle Callaghan Australia Centre d'Etudes Spatiales de la Biosphère Toulouse France USDA ARS Hydrology and Remote Sensing Laboratory (Retired) Beltsville USA

ISBN: (数字)9798350360325

ISBN: (纸本)9798350360332

Understanding the vertical distribution of soil moisture is crucial for making informed decisions in various applications, ranging from precision agriculture to hydrological modeling. Four machine learning algorithms, including random forest, extreme gradient boosting, deep learning, and support vector regression were employed to estimate the soil moisture profile from collected tower-based L-band and P-band brightness temperature observations in Victoria, Australia. The results showed that random forest outperformed the other algorithms, with root mean square error (RMSE) values of 0.03, 0.04, and 0.06 m 3 /m 3 for depths of 0-5 cm, 0-30 cm, and 0-60 cm, respectively

关键词： Radio frequency Support vector machines Deep learning machine learning algorithms Soil moisture Estimation Boosting

来源：评论

学校读者我要写书评

暂无评论

Microfluidic Lab-on-a-Chip Design and Analysis for GFAP Biomarker Detection Using machine learning algorithms

Microfluidic Lab-on-a-Chip Design and Analysis for GFAP Biom...

引用

Communication, Control and Intelligent Systems (CCIS)

作者： P. Balaji D. Devasena P. Rithick T. Karthi K. Rishmitha R. Roopa Dept. of. Electronics and Instrumentation Engineering Sri Ramakrishna Engineering College Coimbatore Tamilnadu Dept. of Robotics and Automation Engineering Sri Ramakrishna Engineering College Coimbatore Tamilnadu Dept. of Automobile Engineering Kongu Engineering College Erode India Dept. of Artificial Intelligence and Data Science Arjun College of Technology Coimbatore Tamilnadu

ISBN: (数字)9798331528201

ISBN: (纸本)9798331528218

The detection of Glial Fibrillary Acidic Protein (GFAP) is a crucial biomarker for diagnosing neurological conditions such as traumatic brain injuries (TBI) and astrocytoma. This paper presents the design and analysis of a novel microfluidic Lab-on-a-Chip (LoC) platform for GFAP biomarker detection. The system integrates microfluidic channels with embedded gold nanoparticle-functionalized electrochemical sensors for high-sensitivity biomarker capture. The microfluidic chip is designed using soft lithography and PDMS (Polydimethylsiloxane), allowing for precise fluid handling and minimal sample consumption. The electrochemical sensors generate voltage signals corresponding to GFAP concentration levels, which are processed using digital filtering techniques to mitigate noise and improve signal quality. For accurate biomarker quantification, machine learning algorithms, including Random Forest ,KNN and Support Vector machine (SVM), are employed to classify sensor output data into clinically significant concentration ranges. The model is trained on both simulated and experimentally collected sensor data, achieving an accuracy of over 93 percent in distinguishing low (below 50 ng/mL) and high (above 50 ng/mL) GFAP concentrations. The combination of microfluidic precision, sensitive electrochemical detection, and data analysis enables rapid and reliable detection of GFAP , providing a scalable and portable solution for early diagnosis of brain injuries and neurodegenerative diseases. This system highlights the potential of integrating microfluidics and machine learning in next-generation point-of-care diagnostic devices.

关键词： Support vector machines Soft lithography machine learning algorithms Accuracy Data analysis Lab-on-a-chip Sensor systems Biosensors Microfluidics Brain injuries

来源：评论

学校读者我要写书评

暂无评论

Analyzing Inconsistencies Across Financial Services machine learning algorithms and Implementations

Analyzing Inconsistencies Across Financial Services Machine ...

引用

International Conference on machine learning and Applications (ICMLA)

作者： Syed Muhammad Ammar Haider Raina Samuel Department of Computer Science Colgate University Hamilton New York USA School of Computing Montclair State University Montclair New Jersey USA

ISBN: (数字)9798350374889

ISBN: (纸本)9798350374896

Various machine learning algorithms are being used for financial valuation and classification tasks. However, incon-sistency, which refers to the difference in output behaviors, has yet to be investigated across algorithms used for a particular financial task and across different implementations. We analyze inconsistencies across Multivariate Linear Regression and Feed-forward Neural Networks for financial valuation tasks on 11 datasets, and inconsistencies across Gradient Boosted Decision Trees and Random Forests for financial classification tasks on 12 datasets. We also analyze inconsistencies across two toolkits used to implement each algorithm and find statistically significant evidence for inconsistency across the algorithms and their imple-mentations. Our findings suggest that inconsistencies can vary based on the training dataset. Overall, training datasets should be analyzed for inconsistency during the selection process, especially in situations where multiple algorithms and implementations may be used for a particular task and agreement in output data is desired.

关键词： Training machine learning algorithms Linear regression Forestry Classification algorithms Decision trees Reliability Cost accounting Random forests Financial services

来源：评论

学校读者我要写书评

暂无评论

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：

请选择收藏分类：

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

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：