RESUMEN
A structured approach to managing reactive power is imperative within the context of power systems. Among the restructuring initiatives in the electrical sector, power systems have undergone delineation into three principal categories: generation, transmission, and distribution entities, each of which is overseen by an independent system operator. Notably, active power emerges as the predominant commodity transacted within the electrical market, with the autonomous grid operator assuming the responsibility of ensuring conducive conditions for the execution of energy contracts across the transmission infrastructure. Ancillary services, comprising essential frameworks for energy generation and delivery to end-users, encompass reactive power services pivotal in the regulation of bus voltage. Of particular significance among the array of ancillary services requisite in a competitive market milieu is the provision of adequate reactive power to uphold grid safety and voltage stability. A salient impediment to the realization of energy contracts lies in the inadequacy of reactive power within the grid, which poses potential risks to its operational safety and voltage equilibrium. The optimal allocation of the reactive power load is predicated upon presumptions of consistent outcomes within the active power market. Under this conceptual framework, generators are afforded continual compensation for the provision of reactive power indispensable for sustaining their active energy production endeavors.
RESUMEN
BACKGROUND: Machine learning could be used for prognosis/diagnosis of maternal and neonates' diseases by analyzing the data sets and profiles obtained from a pregnant mother. PURPOSE: We aimed to develop a prediction model based on machine learning algorithms to determine important maternal characteristics and neonates' anthropometric profiles as the predictors of neonates' health status. METHODS: This study was conducted among 1280 pregnant women referred to healthcare centers to receive antenatal care. We evaluated several machine learning methods, including support vector machine (SVM), Ensemble, K-Nearest Neighbor (KNN), Naïve Bayes (NB), and Decision tree classifiers, to predict newborn health state. RESULTS: The minimum redundancy-maximum relevance (MRMR) algorithm revealed that variables, including head circumference of neonates, pregnancy intention, and drug consumption history during pregnancy, were top-scored features for classifying normal and unhealthy infants. Among the different classification methods, the SVM classifier had the best performance. The average values of accuracy, precision, recall, F1-score, and area under the receiver operating characteristic curve (AUC) in the test group were 75%, 75%, 76%, 76%, and 65%, respectively, for SVM model. CONCLUSION: Machine learning methods can efficiently forecast the neonate's health status among pregnant women. This study proposed a new approach toward the integration of maternal data and neonate profiles to facilitate the prediction of neonates' health status.