检索结果-内蒙古大学图书馆

International conference of Electronics, Communication and Aerospace Technology (ICECA)

作者： Shallu Duggal Shivani Sood Amanpreet Singh Harjeet Singh Muthukumaran Malarvel School of Computer Applications Lovely Professional University Phagwara India Chitkara Institute of Engineering and Technology Chitkara University Punjab India Department of Computer Science and Engineering Aarupadai Veedu Institute of Technology Vinayaga Mission’s Research Foundation (Deemed to be University)

ISBN: (数字)9798350367904

ISBN: (纸本)9798350367911

Predicting hypertension, or high blood pressure, is crucial because it’s a risky condition that frequently doesn’t exhibit any obvious symptoms or indicators until major problems arise. By using predictive models for early identification, the risk of uncontrolled hypertension-related cardiovascular events, strokes, and organ damage can be decreased to take quick action. The study aims to predict the diagnosis of hypertension using three machine learning techniques: Logistic Regression, Gaussian Naive Bayes, and Support Vector machine(SVM). With the focus on improving accuracy and reliability, the various hyperparameters of each individual algorithm are tuned using the cross validation and grid search approaches. After extensive testing and parameter modification, the SVM algorithm was found to be the most accurate predictor, which achieved a significant accuracy of ${9 7. 0 0 \%}$. The best hyper-parameters achieved for SVM are c value 4 and kernel as ‘rbf’. The models’ performance is evaluated using accuracy, specificity, sensitivity, F1-score, or AUC (Area Under the Curve). This study facilitates proactive healthcare measures by offering insightful information to determine the best algorithms for the early prediction of hypertension.

关键词： Support vector machines Hypertension Logistic regression Accuracy Sensitivity machine learning algorithms Prediction algorithms Data models Bayes methods Reliability

来源：评论

学校读者我要写书评

暂无评论

Performance Comparison of machine learning algorithms for Chhattisgarh State

Performance Comparison of Machine Learning Algorithms for Ch...

引用

National Power Systems Conference (NPSC)

作者： Suruchi Shrivastava Anamika Yadav Shubhrata Gupta Department of Electrical Engineering National Institute of Technology Raipur India

ISBN: (数字)9798331519568

ISBN: (纸本)9798331519575

The process of predicting future load patterns based on historical data and probabilities is commonly known as load forecasting. Different assessment can be used depending on the model and time scale such as short-term load forecasting (STLF), medium term load forecasting, long term load forecasting. This paper incorporates STLF approach to forecast the upcoming (i.e. next day) load demand values, specifically for Chhattisgarh State. STLF approach involves machine learning models like Regression Tree, Linear Regression, Kernel Approximation Regression, Ensembles of tree, SVM (Support vector machines) and ANN (Artificial neural network). The prediction process involves historical data along with its temperature and wind speed. Historical data (last 7 days of load values) along with current load demand and generation data of 25 Dec 2021 TO 31 Mar 2024 are collected from Chhattisgarh State Load Dispatch Centre, whereas temperature and wind speed data are collected from NASA Power prediction of worldwide energy resources. After prediction, the results are evaluated through statistical matrices i.e. MAPE, MAE, and overall performance of all models are compared.

关键词： Support vector machines Temperature distribution machine learning algorithms Load forecasting Linear regression Artificial neural networks Prediction algorithms Kernel Regression tree analysis Load modeling

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Python-Based machine learning algorithms for Stock Market Prediction: A Case Study on Forecast Accuracy and Methodological Insights

Comparative Analysis of Python-Based Machine Learning Algori...

引用

Advances in Computing, Communication and Networking (ICAC2N), International Conference on

作者： Rachna Rathore Swetha B Saritha Ps Ajay Kumar Vijay Vir Singh Shyamu Dept. of Mathematics Jiwaji University Gwalior India Dept. of Mathematics Meenakshi A.H. Edu. & Research Chennai India Dept. of AI & Data Science Dhanalakshmi Srinivasan College Coimbatore India Dept. of Computing & IT Manglayatan University Aligarh India Dept. of Mathematics Lingayas Vidyapeeth Faridabad India Dept. of Computer Science J.S. University Shikohabad India

ISBN: (数字)9798350356816

ISBN: (纸本)9798350356823

Predicting stock market movements is a complex task due to the high volatility and unpredictability of stock prices. In recent years, machine learning algorithms have proven to be effective tools for addressing this challenge. This study presents a detailed analysis of various Python-based machine learning techniques applied to stock market prediction. It examines the effectiveness of several algorithms in forecasting stock prices and evaluates their comparative performance. The findings reveal that utilizing machine learning methods can significantly improve the accuracy of stock market predictions. This research offers valuable insights for both researchers and practitioners aiming to leverage machine learning for stock market forecasting. By providing a comprehensive overview of different techniques and their applications, the study serves as a critical resource for those seeking to enhance predictive capabilities and make informed decisions in the dynamic and unpredictable environment of stock market analysis.

关键词： Support vector machines machine learning algorithms Accuracy Neural networks machine learning Predictive models Prediction algorithms Stock markets Forecasting Optimization

来源：评论

学校读者我要写书评

暂无评论

Leveraging machine learning algorithms for Effective Android Ransomware Detection

Leveraging Machine Learning Algorithms for Effective Android...

引用

Advancement in Electronics & Communication Engineering (AECE), International Conference on

作者： Atul Kumar Kalpna Guleria Chitkara University Institute of Engineering and Technology Chitkara University Punjab India

ISBN: (数字)9798350364729

ISBN: (纸本)9798350364736

The rising wave of Android ransomware attacks calls for sophisticated detection mechanisms to save its users from significant security threats. In this paper, the authors present an approach based on machine learning algorithms to identify Android ransomware, focusing on three: Random Forest, SVM, and Decision Tree. In this paper, three machine learning algorithms are trained with vast datasets of benign and malicious apps to learn patterns of behaviours that characterize ransomware. It was found that the Support Vector machine was the best performer among them, showing the best accuracy, precision, recall, and F1 score; hence, it can minimize false positives and negatives effectively. Random Forest was close to SVM, followed by the Decision Tree, whose metrics were relatively lower. It calls attention to the potential of machine learning and, more specifically, SVM in remarkably enhancing the detection of Android ransomware, hence providing a more reliable and efficient security solution.

关键词： Support vector machines Measurement machine learning algorithms Data security Focusing Critical infrastructure Ransomware Decision trees Reliability Random forests

来源：评论

学校读者我要写书评

暂无评论

Arrhythmia Classification using Supervised machine learning algorithms

Arrhythmia Classification using Supervised Machine Learning ...

引用

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

作者： Suthir Sriram Vyshnavi P Nivethitha V Thangavel M S. Ravikumar Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai India College of Information and Technology United Arab Emirates University Al Ain United Arab Emirates Department of Computer Science and Engineering Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Chennai India

ISBN: (数字)9798331522988

ISBN: (纸本)9798331522995

Heart related disorders remain as one of the most chronic health issues in the world; generally, cardiovascular diseases are rated as a prime factor for morbidity and mortality worldwide. The early diagnosis and detection of such conditions may lead to imperative treatment measures and prevent unpleasant complications. This would considerably reduce the risk of serious health complications. One of the diagnostic tools for cardiac abnormalities is an electrocardiogram, a noninvasive, more generally adopted clinical investigative tool that captures over a period of time the heart’s electrical function. Due to the fact that it is very accessible and easy to use, an ECG would normally be done first in diagnosing many cardiac conditions, including arrhythmias. The paper represents the detailed classification of arrhythmia, which is an irregularity in heart rhythm and can be a symptom of severe underlying cardiac problems based on ECG data. We have explored the efficacy of machine learning algorithms and Ensemble Method that combined the former for better predictions. Our results indicate that this ensemble learning approach performs better compared to all of the other individual algorithms used in this study, with an accuracy of 72.15%. The present study not only endorses the effort being made in better cardiac diagnostic tools but also calls for further attention toward advanced computational methods in health care to resolve some of the pivotal, complex challenges in medicine.

关键词： Heart machine learning algorithms Heart beat Arrhythmia Mortality Medical services Electrocardiography Prediction algorithms Ensemble learning Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Enhancing Cardiovascular Risk Prediction Using Support Vector machines and Advanced machine learning algorithms

Enhancing Cardiovascular Risk Prediction Using Support Vecto...

引用

Computing, Applications and Systems (COMPAS), IEEE International Conference on

作者： Abhijit Pathak Touhidul Alam Seyam Arnab Chakraborty Nurjahan Kamal Santa Eftakar Uddin Tasmim Akther Mim Department of Computer Science and Engineering BGC Trust University Bangladesh Chattogram Bangladesh

ISBN: (数字)9798331529765

ISBN: (纸本)9798331529772

A major cause of illness and mortality on a global scale is Cardiovascular Disease (CVD). Ensuring timely response and efficient management requires precise risk prediction. This study rigorously examines the use of support vector machines (SVM) and other advanced machine learning algorithms to opti-mize cardiovascular risk prediction. The authors have obtained a comprehensive dataset comprising patient gender analysis, patient behavior, and medical history parameters from a diverse patient cohort. The dataset has been meticulously preprocessed to impute missing values and accurately welcome and encode attributes. There were multiple machine learning models that were utilized, including SVM, random forest, and XG boosting, to forecast the likelihood of future cardiovascular events. This study’s key contributions include: (1) developing an optimized SVM model for cardiovascular risk prediction that outperforms traditional methods, (2) comprehensively comparing multiple advanced machine learning algorithms, and (3) introducing a novel approach to handling imbalanced data in cardiovascular risk assessment. The results unequivocally demonstrate that SVM, with its kernel technique and margin optimization, delivers superior performance in accuracy, precision, and recall compared to traditional logistic regression models. Ensemble methods such as Random Forest and XG Boosting are essential for managing imbalanced data and performing thorough feature importance analysis in data science and machine learning. This will enable doctors to easily understand each feature in predicting risk. In conclusion, the integration of machine learning algorithms, especially SVMs, into cardiovascular risk prediction frameworks can significantly enhance their predictive power. These advances have the potential to revolutionize CVD risk stratification and pave the way for personalized medicine, ultimately improving patient outcomes.

关键词： Support vector machines Analytical models machine learning algorithms Precision medicine Predictive models Boosting Data models Vectors Risk management Random forests

来源：评论

学校读者我要写书评

暂无评论

Competition Score Prediction and Analysis Based on machine learning algorithms

Competition Score Prediction and Analysis Based on Machine L...

引用

Image Processing and Computer Applications (ICIPCA), IEEE International Conference on

作者： Caojia Xia Dingming Shi Kunhong Li School of Information and Communication Engineering Southeast University Cheng Xian College Nanjing China School of Economics and Management North China University of Science and Technology Tangshan China School of Electronic Information Engineering North China Institute of Science and Technology Langfang China

ISBN: (数字)9798350360240

ISBN: (纸本)9798350384161

This study delves into the elusive yet palpable concept of momentum within professional tennis matches. Through rigorous statistical analysis, including correlation and regression techniques, a robust correlation (Pearson's r = 0.8274) was established between the momentum score (MS) and the likelihood of winning subsequent points. Visualization of match flow was achieved through a combination of stream graphs and scatter plots, offering a comprehensive display of the normalized MS. Addressing skepticism about momentum's influence, the relationship between momentum and sequences of consecutive success within a match was explored, revealing a substantial average correlation (0.7877) across all players. Moreover, factors precipitating shifts in match dynamics were investigated, highlighting key predictors of momentum changes using advanced machine learning algorithms. This study solidifies the significance of momentum in shaping match outcomes and offers a novel approach to quantifying and visualizing this critical determinant of success in professional tennis.

关键词： Visualization Correlation machine learning algorithms Statistical analysis Image processing Heuristic algorithms Computer applications Forecasting Sports

来源：评论

学校读者我要写书评

暂无评论

Rainfall Prediction Enhancement Using SMOTE and machine learning algorithms

Rainfall Prediction Enhancement Using SMOTE and Machine Lear...

引用

International Conference on Computing and Networking Technology (ICCNT)

作者： R Hemanth Kumar B Vishnu Prasad Himanshu Yadav Manju Venugopalan Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

Rainfall prediction is not an easy task when utilizing conventional approaches. For many stakeholders, including people planning their daily lives, farmers caring their crop, and fishermen who depend on the weather for their livelihood, accurate rainfall forecast is essential. Predicting rainfall more accurately has been a promising use of machine learning (ML) models in recent years. Our proposed framework suggests using classification techniques like Random Forest, K-Nearest Neighbors (KNN) classifier, and Decision Tree to construct and implement an ML model for rainfall prediction. SMOTE, an efficient data-balancing technique is used for balancing the minority and majority classes of the data, as rainfall is not a uniformly distributed event, leading to an imbalanced dataset. With an astounding F1-score of around 0.91, a precision of about 0.89, a recall of about 0.94, and an accuracy of roughly 0.91, the Random Forest classifier outperformed the others. These results demonstrate how machine learning (ML) models could possibly be used in producing accurate and depewhich are effective forndable rainfall forecasts, showing significant improvements over conventional prediction techniques.

关键词： Rain Accuracy machine learning algorithms Weather forecasting Livelihood Predictive models Nearest neighbor methods Planning Stakeholders Random forests

来源：评论

学校读者我要写书评

暂无评论

A comparative study of the performances of joint RFE with machine learning algorithms for extracting Moso bamboo (Phyllostachys pubescens) forest based on UAV hyperspectral images

引用

GEOCARTO INTERNATIONAL 2023年第1期38卷

作者： Li, Yi-fan Xu, Zhang-hua Hao, Zhen-bang Yao, Xiong Zhang, Qi Huang, Xu-ying Li, Bin He, An-qi Li, Zeng-lu Guo, Xiao-yu Fuzhou Univ Acad Geog & Ecol Environm Coll Environm & Safety Engn Fuzhou Peoples R China Fujian Prov Key Lab Resources & Environm Monitorin Sanming Peoples R China Fujian Agr & Forestry Univ Coll Forestry Fuzhou Peoples R China Fujian Univ Technol Coll Architecture & Planning Fuzhou Peoples R China Fuzhou Univ Acad Digital China Minist Educ Key Lab Spatial Data Min & Informat Sharing Fuzhou Peoples R China Nanjing Univ Int Inst Earth Syst Sci Nanjing Peoples R China SEGi Univ Kota Damansara Malaysia

Unmanned aerial vehicle (UAV) hyperspectral remote sensing technology has developed rapidly in recent years, providing a new scheme for intelligent monitoring of forest resources. This study aims to deeply mining the UAV hyperspectral information, and construct the best model for extracting Moso bamboo (Phyllostachys pubescens) forest information. Firstly, the spectral information features of Moso bamboo, broadleaf, bare area and shadow were obtained and their spectral anisotropies were analyzed. Secondly, multiple machine learning algorithms were combined with the recursive feature elimination (RFE) to obtain three sets of optimized feature subsets. Eventually, three sets of optimization features were substituted into multiple machine learning algorithms to build nine models of Moso bamboo information extraction, comparing their classification effects and generalization capabilities. The results showed that: (1) The subset of features optimized by different base classifiers in combination with RFE and the ranking results of optimized features' importance were different, but all the three sets of optimized feature subsets showed relatively obvious feature difference patterns;(2) The nine models based on SVM-RFE, RF-RFE and XGBoost-RFE were all capable of extracting Moso bamboo information, among which, the classification effect of the XGBoost-RFE-XGBoost model was the best and had significant advantages, with the overall classification accuracy OA, Kappa coefficient and R (2) of 98.75%, 0.983 and 0.980, respectively, and the classification accuracy for Moso bamboo was 98.34%. Thus, XGBoost was the most applicable algorithm for feature optimization in combination with RFE, and the most effective algorithm with a better generalization ability for extracting Moso bamboo information from UAV hyperspectral images. This study is crucial for Moso bamboo's large area monitoring and fine identification, providing a technical reference for obtaining information about the spat

关键词： Recursive feature elimination (RFE) machine learning algorithms Moso bamboo forest UAV hyperspectral remote sensing feature optimization

来源：评论

学校读者我要写书评

暂无评论

Application of machine learning algorithms for Customer Segmentation in E-Commerce Management

Application of Machine Learning Algorithms for Customer Segm...

引用

Science, Technology, Engineering and Management (ICSTEM), International Conference on

作者： Rajyalaxmi M C. Vijai Kingshuk Srivastava NallaBala Kalyan B Pravallika Amit Dutt School of Business SR University Warangal Telangana India Department of Commerce and Business Administration Vel Tech Rangarajan Dr.SagunthalaR&amp D Institute of Science and Technology Chennai - 62 India Department of Data Science UPES Dehradun Uttarakhand India Department of Management Studies Sri Venkateswara College of Engineering (Autonomous) Tirupati Andhra Pradesh India Institute of Aeronautical Engineering Hyderabad Telangana India Lovely Professional University Phagwara Punjab India

ISBN: (数字)9798350376913

ISBN: (纸本)9798350388473

Client segmentation is an essential component of e-commerce operations since it enables more effective marketing and a more satisfying experience for customers. Within the context of e-commerce platforms, this research investigates the functioning of machine literacy algorithms for effective client segmentation. Through the utilization of clustering methods and predictive models, such as k-means clustering, hierarchical clustering, and decision trees, our objective is to categorize guests according to their shopping behavior, demographics, and preferences. In addition, we investigate the incorporation of sophisticated machine literacy methods, such as ensemble styles and deep literacy infrastructures, to improve the delicateness and resilience of client segmentation models. We illustrate the efficacy of machine learningusing empirical evaluation and case studies. This enables us to relate different client components and adapt marketing strategies to fit the individual requirements of each client. In the context of e-commerce enterprises, our findings highlight the value of machine literacy-driven client segmentation in terms of optimizing marketing sweats, enhancing client retention, and maximizing profit.

关键词： Adaptation models machine learning algorithms Clustering methods Clustering algorithms Predictive models Prediction algorithms Electronic commerce

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：