Çankaya GCRIS Standart veritabanının içerik oluşturulması ve kurulumu Research Ecosystems (https://www.researchecosystems.com) tarafından devam etmektedir. Bu süreçte gördüğünüz verilerde eksikler olabilir.
In this thesis, accurate prediction of concrete strength was investigated by using artificial neural network hybrid algorithms. To hybridize and tune ANN models, Particle Swarm Optimization was implemented. Optimization process was conducted step by step up to reaching predictions at a high level of accuracy. Activation functions, numbers of neuron in hidden layers, initial learning rate, solver and learning rate were subjected to optimization.