Establishment and development of infant gut microbiota

The nascent gut microbiota at birth is established in concert with numerous developmental parameters. Here, in the INFAMTET study, we chronicled the impact of some factors which are key determinants of the infant gut microbiota, namely; mode of birth, gestational age, and type of feeding. We determined that the aggregated microbiota profile of naturally delivered, initially breastfed infants are relatively stable from one week to six months of age and are not significantly altered by increased duration of breastfeeding. Contrastingly, there is significant development of the microbiota profile of C-section delivered infants, and this development is significantly influenced by breastfeeding duration. Preterm infants, born by either mode of birth, initially have a high proportion of Proteobacteria, and demonstrate significant development of the gut microbiota from week 1 to later time-points. The microbiota is still slightly, but significantly, affected by birth mode at one year of age although no specific genera were found to be significantly altered in relative abundance. By two years of age, there is no effect of either birth mode or gestational age. However this does not preclude the possibility that symptoms developed later in life, which are associated with preterm or C-section birth, are as a result of the early perturbation of the neonatal gut microbiota. It is likely that the combination of relatively low exposure (breast fed), high exposure (formula fed) or delayed exposure (C-section and preterm) to specific antigens and the resulting inflammatory responses, in this crucial window of host-microbiota interaction, influence systemic health of the individual throughout life.

Power system parameters forecasting using Hilbert-Huang transform and machine learning

A novel hybrid data-driven approach is developed for forecasting power system parameters with the goal of increasing the efficiency of short-term forecasting studies for non-stationary time-series. The proposed approach is based on mode decomposition and a feature analysis of initial retrospective data using the Hilbert-Huang transform and machine learning algorithms. The random forests and gradient boosting trees learning techniques were examined. The decision tree techniques were used to rank the importance of variables employed in the forecasting models. The Mean Decrease Gini index is employed as an impurity function. The resulting hybrid forecasting models employ the radial basis function neural network and support vector regression. A part from introduction and references the paper is organized as follows. The second section presents the background and the review of several approaches for short-term forecasting of power system parameters. In the third section a hybrid machine learningbased algorithm using Hilbert-Huang transform is developed for short-term forecasting of power system parameters. Fourth section describes the decision tree learning algorithms used for the issue of variables importance. Finally in section six the experimental results in the following electric power problems are presented: active power flow forecasting, electricity price forecasting and for the wind speed and direction forecasting.