This article presents a machine learning approach to assess the risk level of developing cardiovascular disease. We employed various machine learning algorithms, like random forest, decision tree, MLP, CNN, and SVM, to improve the accuracy of risk assessment. Utilizing a dataset consisting of 12 features, including the target variable, sourced from IEEE, we aimed to surpass the 73% accuracy reported in state-of-the-art. To achieve this, we applied a Variational Autoencoder-Generative Adversarial Network (VAE-GAN) to generate additional synthetic data, which underwent rigorous validation procedures to ensure coherence and reliability. Our results demonstrate a significant improvement in precision and reliability in cardiovascular risk assessment, with an accuracy of 90.50% achieved thus far.

This paper proposes to solve the problem of the simple Traveler Agent by applying combined heuristic methods of local search. The proposed method evaluates a random initial route, using a modified simulated annealing algorithm that seeks to improve the route's cost globally, and finally, using a 2-opt local search technique that improves the cost. Different instances of TSPLIB data are evaluated and compared with other methods. The proposed method is compared with other techniques such as Ant Colony Optimization algorithm (ACO), Neural Networks (NN), Particle Swarm Optimization (PSO), and Genetics Algorithm (GA), where results are obtained sub-optimal solution, but in shorter computational time; Validation is obtained by applying two types of statistical indices, the relative percentage error and the coefficient of variation, as well as the execution times in seconds. Finally, using the instances, a MAPE equal to 3.0353% is obtained.