A
Andrés Eduardo Castro-Ospina
Researcher at National University of Colombia
Publications - 50
Citations - 208
Andrés Eduardo Castro-Ospina is an academic researcher from National University of Colombia. The author has contributed to research in topics: Cluster analysis & Spectral clustering. The author has an hindex of 6, co-authored 49 publications receiving 144 citations.
Papers
More filters
Book ChapterDOI
Breast Lesion Discrimination Using Saliency Features from MRI Sequences and MKL-Based Classification
Henry Jhoán Areiza-Laverde,Carlos Andrés Duarte-Salazar,Liliana Hernández,Andrés Eduardo Castro-Ospina,Gloria M. Díaz +4 more
TL;DR: This paper presents a computational method for classifying lesions detected in breast MRI studies, which aims to reduce physician subjectivity and takes advantage of the ability of the Multiple Kernel Learning (MKL) strategy for optimally fusing the features extracted from the different image sequences that compose a breast MRI Study.
Book ChapterDOI
Multi-label Learning by Hyperparameters Calibration for Treating Class Imbalance
TL;DR: The empirical analysis shows that the proposed hyperparameter calibration method is able to improve the classification performance when it is combined with three of the most widely used strategies for treating multi-label classification problems.
Book ChapterDOI
Two Novel Clustering Performance Measures Based on Coherence and Relative Assignments of Clusters
Henry Jhoán Areiza-Laverde,Andrés Eduardo Castro-Ospina,Paul D. Rosero-Montalvo,Diego Hernán Peluffo-Ordóñez,José Luis Rodríguez-Sotelo,M. A. Becerra-Botero +5 more
TL;DR: Two novel alternatives for dealing with the highly important issue of the clustering performance estimation are proposed, one of which is the cluster coherence aimed to quantifying the normalized ratio of cuts within a graph-partitioning framework and the other is the probability-based-performance quantifier, which calculates a probability value for each cluster through relative frequencies.
Book ChapterDOI
Identification of Tropical Dry Forest Transformation from Soundscapes Using Supervised Learning
TL;DR: In this paper , the authors proposed training supervised models to identify landscape transformation from studied site soundscape at three stages: low, medium, and high, and compared the features from VGGish with 60 acoustic indices as features to train Random Forest, Neural Network, and XGBoost classifiers.
Book ChapterDOI
Characterizing ResNet Filters to Identify Positive and Negative Findings in Breast MRI Sequences.
Diana M. Marín-Castrillón,Kevin Osorno-Castillo,Liliana Hernández,Andrés Eduardo Castro-Ospina,Gloria M. Díaz +4 more
TL;DR: In this article, a new method for classification of breast lesions in magnetic resonance imaging is proposed, which uses the pre-trained ResNet-50 architecture for extracting a set of image features that are then used by an SVM model for differentiating between positive and negative findings.