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 article proposes a predictive maintenance algorithm based on machine learning to predict the remaining useful life of industrial assets. The synthetic dataset N-CMAPSS was used, which contains a performance degradation dataset until the presence of failure of an aircraft fleet under real flight conditions is detected. The principal element of maintenance focuses on the predictability of the remaining useful life; predictive models need performance information of an asset from the beginning to failure. [1]. The approach considers the data analysis to understand the data behavior. Monotonicity and principal component analysis are applied in the variable selection. Furthermore, convolutional neural networks are integrated to predict the remaining useful life, resulting in a 10.91 mean of RSME. The “DS01” dataset was used for training; six engines were used for the training dataset and the remaining four for the test dataset.

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.

Abstract Stereo matching obtains a depth map called a disparity map that indicates or shows the positions of the objects in a scene. To estimate a disparity map, the most popular trend consists of comparing two images (left‐right) from two different points from the same scene. Unfortunately, small window sizes are suitable to preserve the edges, while large window sizes are required in homogeneous areas. To solve this problem, in this article, a novel real‐time stereo matching algorithm embedded in an FPGA is proposed. The approach consists of estimating disparity maps with different window sizes by using the sum of absolute differences (SAD) as a local correlation metric. Once the disparity maps are obtained, the left‐right consistency for each window size is computed. At the end of this stage, the centre pixel deviation is estimated through a 5 × 5 window and the Sobel gradient is extracted from the left image. Finally, both parameters are processed by a Fuzzy Inference System (FIS), which combines the calculated disparities and generates a final disparity map. An architecture embedded in FPGA is established and hardware acceleration strategies are discussed. Experimental results demonstrated that this algorithmic formulation provides promising results compared with the current state of the art.