Erasmo Cadenas

Wind Speed Forecasting Using a Hybrid Neural-Evolutive Approach

The design of models for time series prediction has found a solid foundation on statistics. Recently, artificial neural networks have been a good choice as approximators to model and forecast time series. Designing a neural network that provides a good approximation is an optimization problem. Given the many parameters to choose from in the design of a neural network, the search space in this design task is enormous. When designing a neural network by hand, scientists can only try a few of them, selecting the best one of the set they tested. In this paper we present a hybrid approach that uses evolutionary computation to produce a complete design of a neural network for modeling and forecasting time series. The resulting models have proven to be better than the ARIMA and the hand-made artificial neural network models.

Involvement of cyclodipeptides in the competition of bacterial communities in the oligotrophic Churince aquatic system of Cuatro Ciénegas Basin dominated by Gammaproteobacteria

The Cuatro Ciénegas Basin (CCB) within the Chihuahuan Desert in México is an extremely oligotrophic oasis with negligible phosphorous levels, described as a hot spot of biodiversity, not only in stromatolites and microbial mats, but also in living forms in general. The microorganisms possess the capability to produce a wide variety of virulence factors, antibiotics, and quorum-sensing (QS) crosstalk signals such as non-ribosomal cyclodipeptides (CDPs) which enables them to colonize diverse ecological niches. In the aquatic system of CCB known as Churince, a bacterial population was isolated from the Lagunita pond dominated by Gammaproteobacteria. In this work, we determined the relationships between the antagonism and CDPs production in this bacterial population. Results indicate that 68% of isolates showed antagonistic effects over other isolates, correlating with production of CDPs and the antibiotic 2,4-diacetylphloroglucinol (DAPG). Although a minority of the isolates were capable of inducing a QS biosensor strain, bacterial QS interference was not the main mechanism in the antagonism observed. Thus, our results indicate that CDPs primarily, and DAPG to a lesser degree, are involved with the growth-inhibition competition mechanisms of bacterial communities in the Lagunita pond and was associated with a Gammaproteobacteria dominancy phenomena.