“…Yao et al [15] used a case study to show that a combined forecasting model based on a combination of neural networks and a few other methods is promising for predicting the hourly loads in buildings. Solmaz et al [16] used the same concept of neural networks to predict the hourly cooling load for vehicle cabins.…”
“…Yao et al [15] used a case study to show that a combined forecasting model based on a combination of neural networks and a few other methods is promising for predicting the hourly loads in buildings. Solmaz et al [16] used the same concept of neural networks to predict the hourly cooling load for vehicle cabins.…”
“…The activation function j is generally the sigmoid or hyperbolic tangent function in the hidden layers, whereas the linear function is also utilized in the output layer [44]. It is vital to normalize the input and output data for the ANN training so as to prevent saturation of the activation function of neurons [44,45]. A suitable number of representative examples of the relevant phenomenon must be selected in order to train the ANN so that it can learn the system behavior with the adaptive modification of its weights [42,44].…”
Section: Ann (Artificial Neural Network)mentioning
“…Several studies (Li et al, Jan. 2009;Kashiwagi and Tobi, 1993;BenNakhi and Mahmoud, 2004;Sousa et al, 1997;Yao et al, 2004;Solmaz et al, 2014;Fayazbakhsh et al, 2015;Liang and Du, 2005) show that artificial intelligence algorithms such as neural networks, genetic algorithm, and fuzzy logic can help estimate the thermal loads in HVAC-R systems. Such models focus on relating the thermal load to parameters such as the ambient temperature by learning from real-time measurements rather than explicitly using the heat transfer equations.…”
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.