Search

Ischemic Cardiovascular diseases are one of the deadliest diseases in the world. However, the mortality rate can be significantly reduced if we can detect the disease precisely and effectively. Machine Learning (ML) models offer substantial assistance to individuals requiring early treatment and disease detection in the realm of cardiovascular health. In response to this critical need, this study developed a robust system to predict ischemic disease accurately using ML-based algorithms. The dataset obtained from Kaggle encompasses a comprehensive collection of over 918 observations, encompassing 12 essential features crucial for predicting ischemic disease. In contrast, much-existing research relies primarily on datasets comprising only 303 instances from the UCI repository. Six ML-based algorithms, including K Nearest Neighbors (KNN), Random Forest (RF), Logistic Regression (LR), Support Vector Machine (SVM), Gaussian Naïve Bayes (GNB), and Decision Trees (DT), are trained on the ischemic heart data. The effectiveness of the proposed methodologies is meticulously evaluated and benchmarked against cutting-edge techniques, employing a range of performance criteria. The empirical findings manifest that the KNN classifier produced optimized results with 91.8% accuracy, 91.4% recall, 91.9% F1 score, 92.5% precision, and AUC of 90.27%.

Fast-response communication is crucial for Vehicular Ad Hoc Network (VANET). In practice, the conventional VANETs, suffering from the high mobility of the vehicles and the ever-growing data to percept and process, cannot meet the demand of fast response currently. In this paper, we study the Dimensioning and Layout Planning (DLP) problem under 5G-based Vehicular Edge Computing Network (VECN) architecture which integrates the 5G Micro Base Station (gNB) and Edge Computing (EC) to reduce the response time. The DLP problem aims to minimize the total placement cost under the constraint of the full coverage. This paper formulates the DLP problem as an integer linear program (ILP) and then proposes a Greedy Algorithm (GA) and a Cost-Effective Heuristic Algorithm (CEHA) toimprove the computation efficiency. The case studies have verified the feasibility and scalability of the DLP formulation and showed that the proposed CEHA is fairly effective and efficient to solve the DLP problem.