Examinando por Autor "Montoya, O.L.Q."

Mostrando 1 - 3 de 3
  • No hay miniatura disponible
    Ítem
    From artificial intelligence to deep learning in bio-medical applications
    (Springer, 2020-01-01) Montoya, O.L.Q.; Paniagua, J.G.
    Since their introduction in late 80s, convolutional neural networks and auto-encoder architectures have shown to be powerful for automatic feature extraction and information simplification. Using convolution kernels from image processing in 2D and 3D spaces for the stage by stage features retrieval processes, allows the architecture to be as flexible as the designer wants, considering that this is not a lucky fact. With the recent ten years of technological progress now we can compute and train those architectures and they have faced so many challenges for applications originating the most famous CNN architectures. This chapter presents an author position related to the artificial intelligence field and machine learning/deep learning appearance in the scientific world scene describing hastily the basis for each one and later, focusing on medical applications most of the socialized on the Annual IEEE Engineering in Medicine and Biology Society conference held in Hawaii in July 2018. While addressing the medical applications from cardiovascular to cancer diagnosis, we will briefly describe the architectures and discuss some features. Finally, we will present a contribution to the deep learning by introducing a new architecture called Convolutional Laguerre-Gauss Network with a kernel based on a spiral phase function ranging from 0 to 2p and a toroidal amplitude band-pass filter, known as the Laguerre-Gauss transform. © Springer Nature Switzerland AG 2020.
  • No hay miniatura disponible
    Ítem
    Information retrieval on documents methodology based on entropy filtering methodologies
    (Inderscience Enterprises Ltd., 2015-01-01) Montoya, O.L.Q.; Villa, L.F.; Muñoz, S.; Arenas, A.C.R.; Bastidas, M.; Universidad EAFIT. Escuela de Ciencias; Modelado Matemático
    Information retrieval problem occurs when the target information is not available 'literally' into the set of documents. In problems in which the goal is to find 'hidden' information, it is important to develop hybrid methodologies or improve and design a new one. In this work the authors are dealing with identifying the most informative piece of data on a collection of documents, in order to obtain the best result on a posterior fuzzy clustering stage. The aim is to find similarities between the documents and a reference target, to establish relationships related to a non-literal feature. We propose to apply the well-known entropy term weighting scheme and then show a posterior different procedures to the right election of the interest data. This procedure brings the biggest amount of information within the smallest amount of data. Applying a specific selection procedure for a group of words, gives more information to differentiate and separate the documents after using the entropy weighting. This returns considerable results on the processing time and the right fuzzy clustering of the documents collection. Copyright © 2015 Inderscience Enterprises Ltd.
  • No hay miniatura disponible
    Ítem
    Laguerre-gauss filters in reverse time migration image reconstruction
    (Sociedade Brasileira de Geofisica, 2017-01-01) Castrillón, J.G.P.; Montoya, O.L.Q.; Sierra-Sosa, D.; Universidad EAFIT. Escuela de Ciencias; Modelado Matemático
    Reverse time migration (RTM) solves the acoustic or elastic wave equation by means of the extrapolation from source and receiver wavefield in time. A migrated image is obtained by applying a criteria known as imaging condition. The cross-correlation between source and receiver wavefields is the commonly used imaging condition. However, this imaging condition produces spatial low-frequency noise, called artifacts, due to the unwanted correlation of the diving, head and backscattered waves. Several techniques have been proposed to reduce the artifacts occurrence. Derivative operators as Laplacian are the most frequently used. In this work, we propose a technique based on a spiral phase filter ranging from 0 to 2p, and a toroidal amplitude bandpass filter, known as Laguerre-Gauss transform. Through numerical experiments we present the application of this particular filter on three synthetic data sets. In addition, we present a comparative spectral study of images obtained by the zero-lag cross-correlation imaging condition, the Laplacian filtering and the Laguerre-Gauss filtering, showing their frequency features. We also present evidences not only with simulated noisy velocity fields but also by comparison with the model velocity field gradients that this method improves the RTM images by reducing the artifacts and notably enhance the reflective events. © 2017 Sociedade Brasileira de Geofísica.