Artificial neural networks for modeling and optimization of phenol and nitrophenols adsorption onto natural activated carbon

Modelado De Partículas Pm10 Y PM2.5 Mediante Redes Neuronales Artificiales Sobre Clima Tropical De San Francisco De Campeche, México

“…Para llevar acabo esto, en el transcurso del entrenamiento se generan lo que se denominan matrices de pesos y bias, las cuales se van modificando en cada iteración hasta obtener el modelo matemático óptimo. 25 En el presente trabajo la arquitectura de red utilizada es la conocida como PMC la cual usualmente se encuentra divida en tres partes: capa de entrada, capa oculta y capa de salida (Figura 3). Por otra parte, las funciones de transferencia empleadas para la solución del problema no lineal son la función logística sigmoidal (Logsig, Ec.…”

Predicting the oxidant demand in full-scale drinking water treatment using an artificial neural network: Uncertainty and sensitivity analysis

“…ANN have been broadly investigated and applied in forecasting operational parameters in the drinking water treatment field, focusing mainly in the coagulation process (Baxter et al, 1999;Gagnon et al, 1997;Griffiths and Andrews, 2011;Juntunen et al, 2012;Maier et al, 2004) and on evaluating filter performance (Baxter et al, 2002;Hawari and Alnahhal, 2016). Other applications of ANN in similar environmental processes can be found in the literature regarding optimisation of metals and organic compounds sorption processes in the industrial water treatment field (Hamzaoui et al, 2017; Mazaheri et al, 2017). The great diversity of ANN that exists in the literature has led to the need of establishing frameworks and protocols in the last decade (Baxter et al, 2002;Humphrey et al, 2017;Maier et al, 2010;Wu et al, 2014) to homogenize criteria, avoid over-parametrization of ANN models and guarantee the reproducibility and scientific reporting of these models.…”