Cited by A System for Diagnosing and Classifying Heart Diseases: A Comparison of Classification Techniques (Preprint)

Enhanced Cardiovascular Disease Prediction Modelling using Machine Learning Techniques: A Focus on CardioVitalnet DOI

Chukwuebuka Joseph Ejiyi, Zhen Qin, Grace Ugochi Nneji

et al.

Network Computation in Neural Systems, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 33

Published: April 16, 2024

Aiming at early detection and accurate prediction of cardiovascular disease (CVD) to reduce mortality rates, this study focuses on the development an intelligent predictive system identify individuals risk CVD. The primary objective proposed is combine deep learning models with advanced data mining techniques facilitate informed decision-making precise CVD prediction. This approach involves several essential steps, including preprocessing acquired data, optimized feature selection, classification, all aimed enhancing effectiveness system. chosen optimal features are fed as input classification into some Machine Learning (ML) algorithms for improved performance in classification. experiment was simulated Python platform evaluation metrics such accuracy, sensitivity, F1_score were employed assess models' performances. ML (Extra Trees (ET), Random Forest (RF), AdaBoost, XG-Boost) classifiers achieved high accuracies 94.35%, 97.87%, 96.44%, 99.00%, respectively, test set, while CardioVitalNet (CVN) 87.45% accuracy. These results offer valuable insights process selecting medical analysis, ultimately ability make more diagnoses predictions.

Language: Английский

Citations

Optimizing the light gradient-boosting machine algorithm for an efficient early detection of coronary heart disease DOI

Temidayo Oluwatosin Omotehinwa, David Opeoluwa Oyewola,

Ervin Gubin Moung

et al.

Informatics and Health, Journal Year: 2024, Volume and Issue: 1(2), P. 70 - 81

Published: July 2, 2024

Coronary heart disease (CHD) remains a prominent cause of mortality globally, necessitating early and accurate detection methods. Traditional diagnostic approaches can be invasive, costly, time-consuming, the need for more efficient alternatives. This aimed to optimize Light Gradient-Boosting Machine (LightGBM) algorithm enhance its performance accuracy in CHD, providing reliable, cost-effective, non-invasive tool. The Framingham Heart Study (FHS) dataset publicly available on Kaggle was used this study. Multiple Imputations by Chained Equations (MICE) were applied separately training testing sets handle missing data. Borderline-SMOTE (Synthetic Minority Over-sampling Technique) set balance dataset. LightGBM selected efficiency classification tasks, Bayesian Optimization with Tree-structured Parzen Estimator (TPE) employed fine-tune hyperparameters. optimized model trained evaluated using metrics such as accuracy, precision, AUC-ROC test set, cross-validation ensure robustness generalizability. showed significant improvement CHD detection. baseline dropped values had an 0.8333, sensitivity 0.1081, precision 0.3429, F1 score 0.1644, AUC 0.6875. With MICE imputation, improved 0.9399, 0.6693, 0.9043, 0.7692, 0.9457. combined approach Borderline-SMOTE, TPE achieved 0.9882, 0.9370, 0.9835, 0.9597, 0.9963, indicating highly effective robust model. demonstrated outstanding study's strengths include comprehensive addressing data class imbalance fine-tuning hyperparameters through Optimization. However, there is other datasets generalizability well-established. study provides strong framework detection, improving clinical practice allowing precise dependable diagnostics interventions.

Language: Английский

Citations

Using skeleton model to recognize human gait gender DOI

Omar Ibrahim Alsaif,

Saba Qasim Hasan,

Abdulrafa Hussain Maray

et al.

IAES International Journal of Artificial Intelligence, Journal Year: 2022, Volume and Issue: 12(2), P. 974 - 974

Published: Dec. 12, 2022

Biometrics became fairly important to help people identifications persons by their individualities or features. In this paper, gait recognition has been based on a skeleton model as an indicator in prevalent activities. Using the reliable dataset for Chinese Academy of Sciences (CASIA) silhouettes class C database. Each video discredited 75 frames each (20 (10 males and 10 females)) (1.0), result will be 1,500 frames. After Pre-processing images, many features are extracted from human silhouette images. For gender classification, walking used study. The proposed is morphological processes common angle computed two legs. Later, principal components analysis (PCA) was applied to reduce data using feature selection technology get the most useful information gait analysis. Applying classifiers artificial neural network (ANN) Gaussian Bayes distinguish male female classifier. experimental results suggested method provided significant accomplishing about (95.5%), accuracy (75%). Gender classification using ANN more efficient technique (20%), where given superior performance recognition.

Language: Английский

Citations

Heart Attack Prediction Using Ensemble Learning DOI

Saurabh Mali,

Karthika Veeramani

Published: July 4, 2024

Language: Английский

Citations

Develop Approach to Predicate Software Reliability Growth Model Parameters Based on Machine learning DOI

Anfal A. Fadhil,

Asmaa Hadi Al bayati,

Ibrahim A. Hameed

et al.

Iraqi Journal for Computers and Informatics, Journal Year: 2024, Volume and Issue: 50(2), P. 110 - 121

Published: Dec. 30, 2024

One of the most important aspects in determining quality a software product before placing it on market is its reliability. The main problem creating effective that satisfies user preferences must be highly reliable. factor has remarkable influence overall reliability system software. Reliability critical aspect quality, and industry faces many challenges quest to produce reliable at scale. models are basic method for quantitatively calculating Thus, this paper inspects applications as substantial feature application helps determine extent performing specialized functions. This goal accomplished by parameters growth (SRGMs). evaluated using three algorithms: machine learning decision tree (DT), support vector (SVM), K-nearest neighbors (K-NN). Results show SVM model achieves best mean square error.

Language: Английский

Citations

Devising a method for predicting a blood pressure level based on electrocardiogram and photoplethysmogram signals DOI

Alexey Savostin, Аmandyk Tuleshov, Kayrat Koshekov

et al.

Eastern-European Journal of Enterprise Technologies, Journal Year: 2022, Volume and Issue: 5(2(119)), P. 62 - 74

Published: Oct. 30, 2022

Determining the level of blood pressure (BP) in a non-invasive way and without sphygmomanometer cuff is great relevance when conducting continuous monitoring or screening studies. In this regard, method for predicting BP parameters based on signals photoplethysmogram (PPG) electrocardiogram (ECG) has been developed. It proposed to use, as informative features, time pulse wave propagation (PTT) set calculated PPG. PTT defined intervals between R-wave ECG corresponding characteristic points PPG acquired optically from finger. As pulse, known characteristics signal described literature are used, well additional features selected during study. accordance with above, tools machine learning theory were used construct classifier model regression models. The approach paper determine makes it possible use 10-second any 12 common leads optical type sensor. built detects three levels BP: low, normal, high, at accuracy metric=0.8494. models predict systolic, diastolic, mean requirements British Hypertension Society (BHS) standard by magnitude absolute error. assessing involves real-time measurements can be design measuring equipment studies, tasks within framework BHS requirements.

Language: Английский

Citations

A System for Diagnosing and Classifying Heart Diseases: A Comparison of Classification Techniques (Preprint) DOI

Ayedh Ayedh,

Naoufel Kharroubi,

Tahar Alroshahy

et al.

Published: Sept. 20, 2022

UNSTRUCTURED Heart disease is one of the leading causes death around world. Because its great impact on life, so early classification, diagnosis and prediction it essential. This paper attempts to diagnose classify common heart diseases using various classification techniques be able show symptoms that affect functioning heart. Some algorithms are used in order reduce costs medical errors. Six were with a data set, evaluate analyze risk factors associated compare performance implemented classifiers. The Weka tool set for diseases. amount distortion was calculated entropy. Provided methodology designing web-based system ASPX language help based best algorithm training results, enable user enter patient's condition into predict condition. helps doctors diagnostic process. results showed all predictive give relatively correct answer. It found Random Frist outperforms an accuracy rate 92, followed by ID3.

Language: Английский

Citations