Exploring the malicious activities in network, intrusion detection system with machine learning

AIP conference proceedings, Год журнала: 2025, Номер 3283, С. 020024 - 020024

Опубликована: Янв. 1, 2025

Язык: Английский

---

Cardiovascular Disease Prediction Using Hybrid-Random-Forest- Linear- Model (HRFLM)

2022 IEEE World Conference on Applied Intelligence and Computing (AIC), Год журнала: 2023, Номер unknown, С. 192 - 197

Опубликована: Июль 29, 2023

Heart complications has become very common disease among all the age group persons across globe. The computation techniques available in market are based different traditional machine learning models. These models successful on type of datasets they have adapted. In this work two combined to form a hybrid model (HRFLM) which is suitable for cardiovascular risk prediction. This utilized attributes like stress levels, ECG data and others ideal levels considered as key attribute vital evaluating model. results show that proposed obtained 98.36% accuracy predicting when compared with other

Язык: Английский

---

Analysis and Prediction of Liver Cirrhosis Using Machine Learning Algorithms

Опубликована: Июнь 23, 2023

Liver cirrhosis is a serious and progressive liver disease that results in the formation of scar tissue dysfunction. It one key reasons why people die morbidity worldwide, affecting millions people. The illness known as causes liver's healthy to be replaced by tissue, which impairs its ability function. crucial organ performs various purposes, including filtering toxins from bloodstream, producing bile for digestion, regulating glucose levels. When progresses, it can lead failure, life-threatening. cost complexity this disease's diagnosis are enormous. This project compare effectiveness several ML techniques lower chronic through models. We used numerous algorithms paper example LogisticRegression, KNeighbours, SVM, Naïve Bayes, RandomForest many more.The analysis result shows Random Forest achieved highest accuracy.

Язык: Английский

---

Design and Development of an Efficient Explainable AI Framework for Heart Disease Prediction

International Journal of Advanced Computer Science and Applications, Год журнала: 2024, Номер 15(6)

Опубликована: Янв. 1, 2024

Heart disease remains a global health concern, demanding early and accurate prediction for improved patient outcomes. Machine learning offers promising tools, but existing methods face accuracy, class imbalance, overfitting issues. In this work, we propose an efficient Explainable Recursive Feature Elimination with eXtreme Gradient Boosting (ERFEX) Framework heart prediction. ERFEX leverages AI techniques to identify crucial features while ad-dressing imbalance We implemented various machine algorithms within the framework, utilizing Support Vector Machine-based Synthetic Minority Over-sampling Technique (SVMSMOTE) SHapley Additive exPlanations (SHAP) imbalanced handling feature selection explainability. Among these models, Random Forest XGBoost classifiers framework achieved 100% training accuracy 98.23% testing accuracy. Furthermore, SHAP analysis provided interpretable insights into importance, improving model trustworthiness. Thus, findings of work demonstrate potential explainable prediction, paving way clinical decision-making.

Язык: Английский

---

Smart Thyroid Diagnosis: A Machine Learning Based Interactive System

Опубликована: Апрель 22, 2024

Thyroid disease is an important part of diagnosis and prognostication a strenuous problem in initiating fact-finding research. One the most vital organs our body thyroid. The thyroid glands release hormones controls metabolism. Hyperthyroidism hypothyroidism are two disorders endocrine gland which secretes hormone to regulate body's metabolic rate. A data cleaning process was used obtain sufficient raw analyze indicate patient's susceptibility conditions. significance machine learning crucial. In prediction process, this article discusses examination categorization illness models using Information gathered from UCI Machine Learning Repository file. It guarantee strong base that can be combined as hybrid model difficult tasks such prediction. piece, we'll also go over lot research protection tests. To forecast patients' risk illness, algorithms, K-NN, decision trees, support vector machines used.

Язык: Английский

---

Klasifikasi Penyakit Serangan Jantung Menggunakan Metode Machine Learning K-Nearest Neighbors (KNN) dan Support Vector Machine (SVM)

JURNAL MEDIA INFORMATIKA BUDIDARMA, Год журнала: 2024, Номер 8(3), С. 1617 - 1617

Опубликована: Июль 27, 2024

Cardiovascular disease (CVD) is a general term for disorders related to the heart, coronary arteries, and blood vessels. These diseases are most commonly caused by blocked vessels, either due fat buildup or internal bleeding. According WHO, each year, cardiovascular account 32% of all deaths, which translates about 17.9 million people annually. The numerous factors causing CVD make it challenging doctors diagnose patients who at low higher risk heart attacks. A machine learning model needed early recognition attack symptoms. Supervised models such as KNN SVM were used in previous studies without feature selection, with datasets obtained from Kaggle. PCA was applied reduce data dimensions smaller variables. With use confusion matrix ROC curve evaluations, accuracy results improved 83.6% 90.16%. also saw an increase 85.7% 86.88%. selection demonstrated improvement study. model, rate 90.16%, better classifying individuals normal diagnosed attack.

Язык: Английский

---

Revolutionizing Cardiovascular Attack Prediction: A Comprehensive Machine Learning Approach for Accurate and Timely Detection

Опубликована: Апрель 18, 2024

Язык: Английский

---

Medical Image Synthesis Using DCGAN for Chest X-Ray Images

Опубликована: Апрель 18, 2024

Язык: Английский

---

Evaluating the Performance of Clinical data using Machine learning Approach– An Ensemble Model

Опубликована: Авг. 9, 2024

Язык: Английский

---

RSVM: A Promising Approach for Early Heart Disease Prediction

Опубликована: Ноя. 24, 2023

The cardiovascular complications have rapidly increased after COVID-19 pandemic leading to various health effects, including heart disease. Irregular blood flow and inflammation harm the vessels, driving problems that require early detection prevent fatalities. A novel approach using supervised machine learning technique called Rule-based Support Vector Machine (RSVM) has been introduced in this paper, aimed at of proposed rule engine is formed K-Means clustering. Before applying computational model, data was cleaned, preprocessed outliers were removed. Stratified K-fold (K=10) cross-validation applied here due imbalance target variables. UCI based dataset disease from Kaggle are utilized analyze model's efficacy. effectiveness model assessed by computing metrics, mean accuracy (93.7%), precision (96.93%), recall (91.51%) F1-score (94.06%) clearly surpasses alternative models performance.

Язык: Английский

---