Examinando por Materia "Deep Learning"
Mostrando 1 - 4 de 4
Resultados por página
Opciones de ordenación
Ítem Deep Learning como alternativa en la predicción del precio de las acciones del mercado de valores colombiano(Universidad EAFIT, 2021) Uribe Ramírez, Sebastián; Almonacid Hurtado, Paula MaríaÍtem Development of a machine learning-based methodology for an automatic control model in a Kaolin washing process(Universidad EAFIT, 2023) Contreras Buitrago, Oscar Javier; Martínez Vargas, Juan DavidÍtem Diagnosis evaluation of the coffee leaf rust development stage in the colombian Caturra variety integrating remote sensing, wireless sensor networks and deep learning(Universidad EAFIT, 2019) Sánchez Aristizábal, Alejandro; Sarmiento Garavito, Sebastián; Velásquez Rendón, DavidÍtem FocusNET : an autofocusing learning‐based model for digital lensless holographic microscopy(Universidad EAFIT, 2023) Montoya Zuluaga, Manuel; Trujillo Anaya, Carlos Alejandro; Lopera Acosta, María JosefThis paper reports on a convolutional neural network (CNN) – based regression model, called FocusNET, to predict the accurate reconstruction distance of raw holograms in Digital Lensless Holographic Microscopy (DLHM). This proposal provides a physical-mathematical formulation to extend its use to different DLHM setups than the optical and geometrical conditions utilized for recording the training dataset; this unique feature is tested by applying the proposal to holograms of diverse samples recorded with different DLHM setups. Additionally, a comparison between FocusNET and conventional autofocusing methods in terms of processing times and accuracy is provided. Although the proposed method predicts reconstruction distances with approximately 54 µm standard deviation, accurate information about the samples in the validation dataset is still retrieved. When compared to a method that utilizes a stack of reconstructions to find the best focal plane, FocusNET performs 600 times faster, as no hologram reconstruction is needed. When implemented in batches, the network can achieve up to a 1200-fold reduction in processing time, depending on the number of holograms to be processed. The training and validation datasets, and the code implementations, are hosted on a public GitHub repository that can be freely accessed.