检索结果-内蒙古大学图书馆

Artificial Intelligence, Blockchain, and Internet of Things (AIBThings), IEEE International Conference on

作者： Md Rahat Kader Khan Tamador Mohaidat Kasem Khalil Department of Electrical and Computer Engineering University of Mississippi Mississippi USA

ISBN: (数字)9798331529529

ISBN: (纸本)9798331529536

Acute myocardial infarction remains the leading cause of mortality in both developed and developing countries. This severe medical condition requires prompt hospitalization and often requires immediate diagnosis and treatment in emergency departments to prevent fatal outcomes. While numerous studies have explored the prognosis of AMI using hemogram parameters, none have employed an interpretable artificial intelligence-based clinical approach to investigate these parameters for diagnosing AMI. In this paper, we present a study that leverages potential hemogram parameters to detect acute myocardial infarction. By implementing a diverse range of machine learning algorithms, our research highlights the superior performance of boosting algorithms over classical machine learning methods. Among these, the Light Gradient Boosting machine algorithm, combined with hemogram parameters, establishes a new benchmark, achieving an accuracy of 85.31% and a score of 85.28% for the Area Under the Receiver Operating Characteristic Curve, indicating its robust capability to distinguish between AMI patients and healthy individuals.

关键词： Performance evaluation machine learning algorithms Accuracy Simulation Receivers Myocardium Benchmark testing Prediction algorithms Boosting Diseases

来源：评论

学校读者我要写书评

暂无评论

machine learning algorithms in shipping: improving engine fault detection and diagnosis via ensemble methods

引用

WMU JOURNAL OF MARITIME AFFAIRS 2020年第1期19卷 51-72页

作者： Tsaganos, G. Nikitakos, N. Dalaklis, D. Olcer, A., I Papachristos, D. Merchant Acad Athens Dept Marine Engn Athens Greece Dept Shipping Trade & Transport Chios Greece World Maritime Univ WMU Malmo Sweden Dept Ind Engn & Prod Chios Greece

Detection and diagnosis of marine engines faults are extremely important functions for the optimized voyage of any sea-going vessel, as well as the safe conduct of navigation. Early detection of these faults is a prerequisite for reliability: incidents of engine breakdowns can be avoided, since the timely resolving of these faults can ensure the non-interrupted tempo of the sail. Avoiding malfunctions could also improve the ship's overall environmental "footprint" and even ensure reduced fuel consumption. Initial results of the analysis at hand were presented during the 3rd International Symposium on Naval Architecture and Maritime (INT-NAM 2018), in Istanbul-Turkey. Further exploring the use of machine learning algorithms in shipping and by elaborating more on that effort, an evaluation of intelligent diagnostic methods applicable for a two-stroke slow-speed marine diesel engine is taking place, with the aim to facilitate effective detection and classification of occurring faults. This research was carried out via the cost-free Weka data mining tool, which was used to analyze the data of the engine's operating parameters that were found outside of the prescribed boundaries. The proposed method is based on the construction of an ensemble classification model "AdaBoost", which further improves the performance of a basic Simple Cart classifier. During the related experimental activities, the overall recorded performance was 96.5%, clearly establishing this method as a very appropriate choice.

关键词： Marine diesel engine Fault detection machine learning algorithms Ensemble methods Weka Cross-validation Confusion matrix

来源：评论

学校读者我要写书评

暂无评论

Exploring machine learning algorithms for Early Diagnosis of Plant Disease

Exploring Machine Learning Algorithms for Early Diagnosis of...

引用

Computational Intelligence, Communication Technology and Networking (CICTN), International Conference on

作者： Rev Ojha Saru Dhir Raghav Betty Paulraj Sumita Gupta Amity University Noida Uttar Pradesh

ISBN: (数字)9798331530389

ISBN: (纸本)9798331530396

Plant leaf diseases threaten agricultural productivity and food security, affecting global crop production. Traditional detection methods are often time-consuming and error-prone. This paper explores using machine learning to automate plant leaf disease detection, improving speed and accuracy. Paper elaborates the execution of a comprehensive database of plant leaf diseases, detailing symptoms, environmental conditions, and affected species, to train. The experimental results generated through the implementation were tested with the state-of-the-art methodologies and found to be over 90% accurate. The proposed method outperformed the existing methods. The performance measures like the accuracy and other evaluation metric proved the efficiency of the methodology presented with improved accuracy. The outcome of the paper served as a socio-beneficial so as the reformation of agricultural practices have been emerged out. The new revolution in the modern agricultural practices had emerged owing to the inclusion of machine learning (ML) and the Deep learning models in the early disease prediction in plant.

关键词： Support vector machines Productivity Measurement Plant diseases Accuracy machine learning algorithms Plants (biology) Food security Predictive models Nearest neighbor methods

来源：评论

学校读者我要写书评

暂无评论

Prognostic Modeling of Diabetes Mellitus in Women: A comparitive analysis of machine learning algorithms integrating Clinical and Genetic Data

Prognostic Modeling of Diabetes Mellitus in Women: A compari...

引用

Emerging Technologies in Computer Science for Interdisciplinary Applications (ICETCS), International Conference on

作者： M. Venkat Prashanth Nikhil Tom Jose Konda Hemesh Verma B. Sreevidya M. Rajesh Department of Computer Science and Engineering Amrita School of Computing Bengaluru Amrita Vishwa Vidyapeetham India

ISBN: (数字)9798350372502

ISBN: (纸本)9798350372519

Diabetes is considered as one of the most commonly observed medical condition among human beings. Millions of people worldwide are affected by a chronic condition that goes by the name of diabetes. There are 3 sorts of diabetes and they comprise of Type 1, Type 2 and Gestational diabetes. Early prediction of diabetes helps to avoid complications like diabetic retinopathy which leads to blindness. There is a 13% higher risk of death among people with diabetes, especially in women, cardiovascular disease caused by diabetes attributes to 50% higher risk of death, coronary heart disease caused by diabetes contributes to a 58% higher risk of death. The proposed research work aims in predicting diabetes from the symptoms a patient exhibit. The proposed system is a healthcare assisting system which is accessible to patients as well as medical practitioners. The system is developed as a web application using the features of Django python framework along with suitable database management system. The system is powered with gradient boosting machine learning algorithm for predictions. By using the web application along with a blood test to find out the insulin levels and glucose levels in blood, any user can predict whether he/she would be affected by diabetes in future and can avoid the complications caused by diabetes.

关键词： Heart machine learning algorithms Computational modeling Predictive models Boosting Diabetes Glucose

来源：评论

学校读者我要写书评

暂无评论

Going the distance: Application of machine learning algorithms in predicting Housing Price Dynamics

Going the distance: Application of Machine Learning Algorith...

引用

Computational Intelligence for Green and Sustainable Technologies (ICCIGST), International Conference on

作者： Babita Sonare Sudeep Thepade Pratiksha Gangane Esha Govardhan Tisha Nawani Pragati Gadkar Information Technology Pimpri Chinchwad College of Engineering Pune India Computer Engineering Pimpri Chinchwad College of Engineering Pune India

ISBN: (数字)9798350381887

ISBN: (纸本)9798350381894

In this paper, we have used various algorithms such as Gradient Boost Regression, Catboost Regression, Decision Tree Regression and K-neighbors Regression by categorizing predictions based on threshold. To address the problems of data quality and other complexities, we performed validation on all the algorithms mentioned above. Predicting house prices often involves many barriers such as taking all the important factors into account, being aware of the demand of a particular area, government policies, spatial locations and houses with different sizes. We overcame these problems with the ML models we built. Among all the algorithms, Catboost Regression gave great results with mean absolute percentage error of 0.018 and r-squared value of 0.904. This paper provides insights in more detail about the strong positive correlation between area and price.

关键词： Government policies machine learning algorithms Correlation Heuristic algorithms Data integrity Pricing Predictive models Prediction algorithms Maintenance Regression tree analysis

来源：评论

学校读者我要写书评

暂无评论

Application of machine learning algorithms in Personalized Marketing

Application of Machine Learning Algorithms in Personalized M...

引用

Recent Trends in Computer Science and Technology (ICRTCST), International Conference on

作者： P G Thirumagal Dr. Kishore Bhattacharjee Rajesh Dorbala Manesh R. Palav Viji S Vaishali Mahajan Department of MBA VISTAS Chennai Tamil Nadu Amity University Patna Bihar Mittal School of Business Lovely Professional University Phagwara Punjab India MBA Department Global Business School & Research Centre Pune Maharashtra India Department of Commerce Kalasalingam Academy of Research and Education Srivilliputtur Tamil Nadu Department of Marketing Symbiosis Centre for Management & Human Resource Development (SCMHRD) Pune Maharashtra

ISBN: (数字)9798350351378

ISBN: (纸本)9798350351385

The win-win relationship between artificial intelligence and the cutting-edge field of targeted advertising. Companies nowadays are employing machine learning algorithms to develop targeted marketing strategies because they simply cannot afford to ignore their clients. This article delves into significant machine learning approaches such collaborative filtering, content-based filtering, clustering, and predictive modelling to illuminate their roles in offering personalised experiences. Examining real-world applications across many industries, such as e-commerce, social media, email marketing, and retail, highlights successful implementations. Although the piece focuses on the positives, such increased conversion rates and satisfied consumers, it also examines the negatives, like concerns about data privacy and algorithmic biases. The discusses the ethical concerns brought up by highly personalised advertising and foresees future advances such as natural language processing and reinforcement learning. Lastly, this article provides excellent research on the ways in which machine learning algorithms have changed personalised marketing, which can help businesses adapt to the dynamic nature of customer engagement.

关键词： Industries machine learning algorithms Social networking (online) Filtering Heuristic algorithms Reinforcement learning Predictive models

来源：评论

学校读者我要写书评

暂无评论

Transformer equipment fault detection based on multiple machine learning algorithms

Transformer equipment fault detection based on multiple mach...

引用

作者： Zhongping Ning School of Mechanical and Automotive Engineering Anhui Industrial Economics Vocational and Technical College

Transformer is an indispensable equipment in the power system, and its normal operation plays a vital role in the stable operation of the power system and power ***, due to the complexity of the working environment of the transformer, its internal structure is also more complex, so the transformer failure frequency is higher. Therefore,timely detection and early warning of transformer failure is of great importance. In this paper, a machine learning algorithm is introduced to automatically discover the laws and patterns in the data by learning and analysing a large amount of data, and use these laws and patterns to make predictions and decisions. In this paper, the winding temperature indicator, oil temperature indicator alarm, oil temperature indicator trip and magnetic oil level indicator are taken as the target variables, and the current and voltage parameters are taken as the input variables, and the dataset is divided into training set, validation set and test set according to the ratio of 6:2: *** dataset is divided into training set, validation set and test set, and 12 kinds of machine learning models are introduced to predict the winding temperature indicator, the oil temperature indicator alarm, the oil temperature indicator trip, and the magnetic oil level indicator, respectively. indicator alarm, oil temperature indicator trip, and magnetic oil level indicator values, respectively, to observe the operating status of the transformer in real time by predicting the transformer state parameters. The results show that the machine learning model has high application value in transformer condition monitoring. Through the input of current and voltage parameters, the machine learning model can accurately predict and monitor the important indicators of the transformer, and discover the abnormal state of the transformer in time, so as to ensure the safe operation of the transformer. In the prediction of winding temperature, oil temperature and oil temp

关键词： Transformer equipment fault detection machine learning algorithms Prediction accuracy

来源：评论

学校读者我要写书评

暂无评论

A Screening Method for Left Ventricular Systolic Dysfunction by Single-Channel Electrocardiogram Using machine learning algorithms

A Screening Method for Left Ventricular Systolic Dysfunction...

引用

IEEE Annual International Computer Software and Applications Conference (COMPSAC)

作者： Natalia Kuznetsova Alexander Suvorov Petr Chomakhidze Philippe Kopylov I.M. Sechenov First Moscow State Medical University Moscow Russia

ISBN: (数字)9798350376968

ISBN: (纸本)9798350376975

Background. Analysis of a single-channel electrocardiogram can potentially be used as a screening method to detect systolic dysfunction of the left ventricle. The purpose of our study was to develop a new screening method for detecting a decrease in systolic function of the left ventricle based on single-channel ECG and pulse wave recording using machine learning methods. Materials and methods. The study prospectively included 1039 patients aged 18 years and above. A transthoracic echocardiographic study and 1-minute single channel electrocardiogram were performed for each patient. Spectral analysis of the electrocardiogram based on the Fourier transform. More than 200 parameters were included in machine learning algorithms. Results. For ejection fraction decrease: Lasso regression showed a sensitivity of 92,2%, specificity of 90,1% (AUC=0.920); Random Forest Classifier sensitivity - 88.2%, specificity - 83,3% (AUC=0.834). Algorithm approbation has shown diagnostic accuracy of 90,1% in left ventricular systolic dysfunction. Conclusions. machine learning models, based on the single lead ECG parameters, as well as age and gender may simplify screening diagnostics of ejection fraction decrease prior to echocardiographic study for in time heart failure diagnostics with high accuracy.

关键词： machine learning algorithms Sensitivity Accuracy Software algorithms Electrocardiography Software Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

Detection of Fake Profiles and News on Social Media Using machine learning algorithms

Detection of Fake Profiles and News on Social Media Using Ma...

引用

Computing, Sciences and Communications (ICCSC), International Conference on

作者： Sachin Saxena Archana Singh Shailesh Tiwari Amity School of Engineering and Technology Amity University Noida India KIET Group of Institutions Ghaziabad India

ISBN: (数字)9798350353648

ISBN: (纸本)9798350353655

Technology is advancing rapidly every day, becoming an integral part of our lives and helping people connect with each other through social media and online news outlets. But as everything has its own advantages and disadvantages, it has too, and this paves a way for individuals to make fake news and accounts that are posing a major threat to society. This paper tries to incorporate a strategy utilizing machine learning algorithms. Random Forest, Support Vector machines and Neural Network are some of the algorithms which are used to distinguish fake profiles on social media and for detection of fake news online Naïve Bayes' and LSTM are utilized. Hence, detection of fake profiles and fake news online is possible using the above-mentioned frameworks. The outcome illustrates the ability to distinguish between fake and real profiles using extracted features by applying trained machine learning models. Naive Bayes, k-nearest neighbor, and Poisson calculation independently give precision of 87%, 88.3.5%, and 91.2% individually. The proposed approach shows that the algorithm neural networks system has an accuracy of 94.3%. The proposed work uses the machine learning approach for detection of tampered profiles on social media platforms.

关键词： Support vector machines machine learning algorithms Social networking (online) Neural networks Nearest neighbor methods Feature extraction Bayes methods Fake news Random forests Long short term memory

来源：评论

学校读者我要写书评

暂无评论

Emboli Detection by machine learning algorithms using multi-level feature extraction

Emboli Detection by machine learning algorithms using multi-...

引用

International Conference on Image and Signal Processing and their Applications (ISPA)

作者： Ab Waheed Lone Ahmet Elbir Nizamettin Aydin Department of Computer Engineering Yildiz Technical University Istanbul Turkey Department of Computer Engineering Istanbul Technical University Istanbul Turkey

ISBN: (数字)9798350309249

ISBN: (纸本)9798350309256

In real world, data understanding involves finding relationship between dependent and independents events, and usually this data is embedded in the form of images, audio, videos, speech, text and much more and to extract useful and representative information, feature extraction and representation is a front-end step. For machine learning algorithms, feature extraction is a preprocessing technique that helps in finding the relationship between different variables. In biomedical signal analysis such as cerebral emboli signal detection, feature extraction from samples constitutes an important step. In this paper, we performed two step feature extraction procedure. First we extracted Mel Frequency Cepstral Coefficients (MFCC) and biologically inspired Gamma-tone Cepstral Coefficients from Doppler signals. Second we extracted kurtosis and skewness parameters from all the Mel-frequency cepstral coefficients and Gamma-tone Cepstral Coefficients coefficients. To gain the understanding of extracted features from Doppler signals, we trained some machine learning algorithms such as k-nearest neighbors, support vector machines and logistic regression. GTCC based kurtosis and skewness features show better classification between emboli, artifact signals and Doppler speckle signals. We present evaluation results using confusion matrix for classification between emboli signals (ES), Doppler speckle (DS) and artifact signals (AS).

关键词： Wavelet transforms machine learning algorithms Scattering Pattern classification machine learning Speckle Feature extraction

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：