ABSTRACT
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.
Subject(s)
Algorithms , Artificial Intelligence , Infant, Newborn , Humans , Female , Pregnancy , Bayes Theorem , Machine Learning , Health StatusABSTRACT
Polymer membrane electrolyzers are a useful tool for producing hydrogen, which is a renewable energy source. Unmanned aerial vehicle (UAV) fuel cells can be powered by the hydrogen and oxygen produced by the electrolyzer. The primary losses of polymer membrane electrolyzers must therefore be identified in order to maximize their performance. A renewable-based multi-energy system considers power, cooling, heating, and hydrogen energy as utility systems for integrated sport buildings. In this study, we investigate the effect of radiation intensity, current density, and other performance factors on the rate of hydrogen production in water electrolysis using a polymer membrane electrolyzer in combination with a solar concentrator. The findings showed that a rise in hydrogen generation led to an increase in current density, which increased the electrolyzer's voltage and decreased its energy and exergy efficiencies. The voltage was also increased, and the electrolyzer's efficiency was enhanced by a rise in temperature, a decrease in pressure, and a reduction in the thickness of the nafion membrane. Additionally, with a 145% increase in radiation intensity, hydrogen production increased by 110% while the electrolyzer's energy and exergy efficiencies decreased by 13.8% as a result of the electrolyzer's high input electric current to hydrogen output ratio.
ABSTRACT
In this article, in order to achieve a sustainable environment, the optimization of a GT equipped with intercooling of the compression process is discussed. To limit the exergy destruction in intercooling cooling process and also to reduce the heat dissipation in the environment, an ORC system is applied for heat recovery and more power generation. Decision variables include CPR, first stage CPR, TIT, intercooler effectiveness, HRVG pressure, and superheating degree. During a parametric study, the effect of decision variables on operating factors including exergy efficiency, TCR, and the normalized emission rate of environmental pollutants are investigated. Finally, by performing bi-objective optimization and considering exergy efficiency and TCR as OFs, optimal performance conditions are determined. Finally, it is observed that in optimum conditions, exergy efficiency is 33% and TCR is 0.9 $/s.
