Diabetic retinopathy is an eye complication of a widespread disease named diabetes mellitus. The most widely used method for diagnosing diabetic retinopathy is the analysis of retinal fundus images obtained by retinography. Deep Learning-based methods have shown promising results as a diagnostic tool for diabetic retinopathy, achieving, in some cases, performance close to the human inspection of images. However, the performance of these methods relies heavily on fine-tuning the algorithm hyperparameters and big data sets. In this work, we propose training a Deep Learning network with evolutionary algorithms to classify three stages of Diabetic Retinopathy: i) no sign of diabetic retinopathy, ii) Non-proliferative dia-betic retinopathy, and iii) proliferative diabetic retinopathy. We propose a neuroevolution methodology for selecting the most efficient Deep Learning model. The results of the neuroevolution methodology were improved by including Simulated Annealing strategies, Population Reinitialization, and ensembles. With high accuracy, sensitivity, specificity, and kappa index rates of 0.889, 0.889, 0.951, and 0.822, respectively, in the best case found, the experiments show that our neuroevolution methodology for selecting the Deep Learning model hyperparameters is a competitive alternative for training deep neural networks to classify three stages of diabetic retinopathy even with a small data set.

For the training of blood pressure predictive models, it is necessary to determine the optimal number of predictors when the data set is of high dimensionality. Applying the appropriate dimensionality reduction technique according to the dataset will reduce the number of components and improve the performance of the predictive models. This work proposes the dimensionality reduction of the data set through the explorations of linear and nonlinear relationships of photoplethysmography signals by applying principal component analysis through the decomposition of Pearson and Spearman correlation matrices. The differences between the explained and cumulative variances of the principal components are minimal by applying Pearson and Spearman correlations. The predictive models trained with the first 5 principal components obtained better results for the estimation of blood pressure, with minimal loss of information with respect to the original data set.

Dengue fever represents a public health problem and accurate forecasts can help governments take the best preventive actions. As the volume of data provided continuously increases, machine learning and deep learning (DL) models have become an attractive approach. However, it is difficult to perform accurate predictions in areas with fewer cases. In this work, we compare traditional approaches such as LASSO Regression (LR), Random Forest (RF), Support Vector Regression (SVR) vs DL models based on long short-term memory (LSTM), considering weekly dengue incidence and climate, in 217 cities in Paraguay. Several city models may present heterogeneous behaviors and poor accuracy. To mitigate this problem, a clustering analysis between time series is performed based on silhouette scores and measuring how well an observation is clustered. Our results indicate the hierarchical clustering combined with Spearman correlation is the most appropriate approach. Then several LSTM models are compared on subgroups of similar time series. The root mean squared error (RMSE) confirms that the LSTM clustered models improve the accuracy by 31.6% approximately. The main contribution of this work is that LSTM clustered models can perform predictions in cities with low incidence by combining information from similar time-series and weather data.

This paper defines new constructs to support aggregation in the temporal query language TQuel and presents their formal semantics in the tuple relational calculus. A formal semantics for Quel aggregates is defined in the process. Multiple aggregates; aggregates appearing in the where, when, and valid clauses; nested aggregation; and instantaneous, cumulative, moving window, and unique variants are supported. These aggregates provide a rich set of statistical functions that range over time, while requiring minimal additions to TQuel and its semantics. We show how the aggregates may be supported in an historical algebra, both in a batch and in an incremental fashion, demonstrating that implementation is straightforward and efficient.>