Application of Machine Learning Algorithms to Classify Peruvian Pisco Varieties Using an Electronic Nose.

Pisco is an alcoholic beverage obtained from grape juice distillation. Considered the flagship drink of Peru, it is produced following strict and specific quality standards. In this work, sensing results for volatile compounds in pisco, obtained with an electronic nose, were analyzed through the application of machine learning algorithms for the differentiation of pisco varieties. This differentiation aids in verifying beverage quality, considering the parameters established in its Designation of Origin". For signal processing, neural networks, multiclass support vector machines and random forest machine learning algorithms were implemented in MATLAB. In addition, data augmentation was performed using a proposed procedure based on interpolation-extrapolation. All algorithms trained with augmented data showed an increase in performance and more reliable predictions compared to those trained with raw data. From the comparison of these results, it was found that the best performance was achieved with neural networks.

Obesidad materna como factor de riesgo de obesidad infantil / Maternal obesity as a risk factor for childhood obesity

Introducción: diversos factores ambientales se han relacionado con el incremento en la frecuencia de obesidad infantil en los últimos años. Objetivo: determinar los factores maternos, socioeconómicos y de estilo de vida asociados al sobrepeso/obesidad en niños de 5 a 10 años. Metodología: se realizó un estudio transversal analítico en 153 niños de ambos sexos a los que se les midió peso, talla, índice de masa corporal, presión arterial, glucosa capilar y la presencia de acantosis nigricans. Se compararon los factores entre niños eutróficos y niños con sobrepeso/obesidad a través de Chi cuadrada o t de Student y se realizó una regresión logística para determinar los factores asociados al sobrepeso/obesidad del niño. Resultados: el 30.7% de los niños presentó sobrepeso/obesidad, en ellos se encontró mayor frecuencia de acantosis nigricans y mayores cifras de presión arterial sistólica. El predictor de obesidad infantil fue la obesidad materna, el riesgo de obesidad entre niños de madre con obesidad fue OR: 1.261 (IC95%: 1.047-1.518). Conclusiones: la obesidad materna incrementa el riesgo de obesidad infantil.

Introduction: Several environmental factors have been related to the increase in the frequency of childhood obesity in recent years. Objective: To determine maternal, socioeconomic and lifestyle factors associated with overweight/obesity in children 5 to 10 years oíd. Methods: A cross-sectional analytical study was performed with 153 children of both sexes, measuring weight, height, body mass índex, blood pressure, casual capillary glucose and the presence of acantosis nigricans. Factors were compared between eutrophic children and those with overweight/obesity through Chi-square test or Student's t test, and logistic regression was performed to determine the factors associated with the child's overweight/obesity. Results: 30.7% of the children presented overweight/obesity. In them acantosis nigrica higher systolic blood pressure were found more frequently. The predictor of childhood was maternal obesity; the risk of obesity among children with mothers with obesity it \a 1.261 (95%CI: 1.047-1.518). Condusions: Maternal obesity increases the risk of childhood obesity.