Papers by Genaro Daza Santacoloma
Revista Ingenieria E Investigacion, Sep 1, 2009
Se presenta una metodología para el preproceso de características generadas a partir de registros... more Se presenta una metodología para el preproceso de características generadas a partir de registros electrónicos de bioseñales, particularmente se experimenta con señales de voz en la detección automática de patologías. La metodología de proceso propuesta se limita a tres fases: detección de datos atípicos, verificación de normalidad y transformación de distribuciones. La metodología conlleva al mejoramiento en la detección de las patologías de voz, además de reducir la complejidad computacional de los algoritmos de clasificación. El desempeño del clasificador indica un aumento superior a 15 puntos porcentuales en la detección de disfonías al emplear la metodología. Palabras clave: preproceso, datos atípicos, normalidad, Box-Cox, reconocimiento de patrones, clasificación, patologías de voz.
Auditio, 2006
Se presenta el análisis de las diferentes características acústicas, y su influencia en la identi... more Se presenta el análisis de las diferentes características acústicas, y su influencia en la identificación automática de hipernasalidad. La metodología de selección efectiva de características, incluye el preproceso del espacio inicial de observaciones y está basada en el análisis de independencia estadística. De forma paralela, se propone la síntesis de una característica de diagnóstico especializado, basada en el análisis de la emisión acústica de la voz hipernasal. Como resultado se obtiene que, aunque las características acústicas permiten diferenciar con la suficiente precisión la patología, la característica propuesta con un nivel de complejidad computacional menor, no requiere muestras para entrenamiento y permite diferenciar los grados de compromiso de resonancia de la patología.
Análisis acústico de voz y de posturas labiales en pacientes de5 a 15 años con Labio y/o Paladar hendido corregido en la zona centro del país
IP 1119-14-1286
Dimensionality Reduction for Automatic Pattern Recognition on Biosignals
Results for a dimension reduction methodology based on the comparison of several feature selectio... more Results for a dimension reduction methodology based on the comparison of several feature selection and feature extraction techniques are presented. The main contribution of this work is the identification of the application conditions for each technique. Experimental tests were made employing a voice disorders database. Results for reduction and classification expose better performance for feature selection than for feature extraction; nevertheless, the statistical nature of data influences the feature reduction methods.
Metodolog´õa de reduccion de dimension para sistemas de reconocimiento automatico de patrones sobre biosenales

Intell. Autom. Soft Comput., 2009
In pattern recognition, observations are often represented by the so called static features, that... more In pattern recognition, observations are often represented by the so called static features, that is, numeric values that represent some kind of attribute from observations, which are assumed constant with respect to an associated dimension or dimensions (e.g. time, space, and so on). Nevertheless, we can represent the objects to be classified by means of another kind of measurements that do change over some associated dimension: these are called dynamic features. A dynamic feature can be represented by either a vector or a matrix for each observation. The advantage of using such an extended form is the inclusion of new information that gives abetter representation of the object. The main goal in this work is to extend traditional Principal Component Analysis (normally applied on static features) to a classification task using a dynamic representation. The method was applied to detect the presence of pathology in the speech using two different voice disorders databases, obtaining hi...
Results for a dimension reduction methodology based on the comparison of several feature selectio... more Results for a dimension reduction methodology based on the comparison of several feature selection and feature extraction techniques are presented. The main contribution of this work is the identification of the application conditions for each technique. Experimental tests were made employing a voice disorders database. Results for reduction and classification expose better performance for feature selection than for feature extraction; nevertheless, the statistical nature of data influences the feature reduction methods.
This document describes a calibration protocol with the intention to introduce a guide to standar... more This document describes a calibration protocol with the intention to introduce a guide to standardize the metrological vocabulary among manufacturers of image-guided surgery systems. Two stages were developed to measure the errors and estimate the uncertainty of a neuronavigator in different situations, on the first one it was determined a mechanical error on a virtual model of an acrylic phantom, on the second it was determined a coordinate error on the computerized axial tomography scan of the same phantom. Ten standard coordinates of the phantom were compared with the coordinates generated by the NeuroCPS. After measurement model was established, there were identified the sources of uncertainty and the data was processed according the guide to the expression of uncertainty in measurement.
Relevant information undersampling to support imbalanced data classification
Neurocomputing, 2021

Scientia et technica, 2016
El registro de imágenes sobre todo en el ámbito de la medicina, han cobrado una gran importancia ... more El registro de imágenes sobre todo en el ámbito de la medicina, han cobrado una gran importancia en las últimas décadas pues esto se mejora la planeación, intervención y posterior análisis de dichos procedimientos médicos, como es el caso de las cirugías guiadas por imágenes donde se requiere una especial precisión y confiabilidad. Registrar dos o más imágenes consiste en alinearlas de tal manera que queden orientadas de la misma forma, así se puede combinar la información de ambas en un mismo espacio y en una misma representación visual. El objetivo principal de este trabajo es comparar de forma sistemática algunas metodologías para el registro de imágenes multimodales utilizando medidas de similitud basadas en información mutua (IM).Se obtuvo que el registro de imágenes basada en IM es capaz de registrar imágenes multimodales y monomodales con poca susceptibilidad a los cambios de brillo o contraste en la imagen, pero con alta sensibilidad al ruido. También se estableció que las ...

TecnoLógicas, 2010
En este trabajo se realiza una comparación de las principales técnicas de reducción de dimensión ... more En este trabajo se realiza una comparación de las principales técnicas de reducción de dimensión no lineal basadas en análisis por localidades, tales como: Locally linear embedding, Isometric feature mapping y Maximum variance unfolding. El estudio pretende determinar, bajo criterios objetivos, cuál de las técnicas consideradas conserva de mejor manera las propiedades locales de la variedad, y la estructura global de los datos de entrada al realizar un mapeo a un espacio de menor dimensión. Los métodos son especialmente analizados en aplicaciones de visualización. Las inmersiones obtenidas son evaluadas por medio de dos criterios: Error de Conservación de Vecindarios y Promedio de Vecinos Conservados. Para la validación experimental se utilizan bases de datos artificiales y reales que permiten confirmar visualmente la calidad de las inmersiones obtenidas. Con base en los resultados se observa que la técnica Maximum variance unfolding presenta inmersiones de mejor calidad, debido a q...
TecnoLógicas, 2017
Este documento describe un protocolo de calibración con el objetivo de introducir una guía que es... more Este documento describe un protocolo de calibración con el objetivo de introducir una guía que estandarice el vocabulario metrológico entre los fabricantes de sistemas de cirugía guiada por imágenes. Se desarrollaron dos etapas para medir los errores y estimar la incertidumbre de un neuronavegador en diferentes situaciones, en la primera se determinó un error mecánico en un modelo virtual de una estructura acrílica, en la segunda se determinó un error de coordenadas sobre imágenes de tomografía axial computarizada de la misma estructura. Diez coordenadas de referencia de la estructura acrílica se compararon con las coordenadas generadas por el neuronavegador. Después de establecer el modelo de medición, fueron identificadas las fuentes de incertidumbre, los datos se procesaron de acuerdo a la guía para la expresión de la incertidumbre de medida.

Automatic epileptic seizure prediction based on scalp EEG and ECG signals
2016 XXI Symposium on Signal Processing, Images and Artificial Vision (STSIVA), 2016
The epilepsy is a common neurological disease caused by a neuronal electric activity imbalance in... more The epilepsy is a common neurological disease caused by a neuronal electric activity imbalance in any side of the brain, named epileptic focus. The epilepsy is characterized by recurrent and sudden seizures. Recently, researchers found that approximately 50% of epileptic patients feel auras (subjective phenomenon which precedes and indicates an epileptic seizure onset) associated to a physiological anomaly. In this research, a non-invasive seizure prediction methodology is developed in order to improve the quality of life of the patients with epilepsy, alerting them about potential seizure and avoiding falls, injuries, wounds or even death. The research addresses the recognition of patterns in electroencephalographic (EEG) and electrocardiographic (ECG) signals taken from 7 patients with focal epilepsy whom are treated at the Instituto de Epilepsia y Parkinson del Eje Cafetero-NEUROCENTRO-. The biosignals were independently analyzed, at least 15 minutes before the seizure onset and in periods with no seizure were considered. The methodology considers the generation of features computed over the discrete wavelet transform of the EEG signal and others related to the heart rate variability in the ECG signal. Using feature selection techniques such as Sequential Forward Selection (SFS) with classification algorithms as cost functions (linear-Bayes and k-nearest neighbors classifier), we found which features have the most relevant information about pre-ictal state and which of them are the most appropriated for seizure forecasting, therefore we found that ECG signal could be a potential resource for predicting epileptic seizures, and we concluded that there are patterns in EEG and ECG signals that, via machine learning algorithms, can predict the epileptic seizure onset.

DYNA, 2016
La Estimulación Cerebral Profunda (DBS) es un tratamiento efectivo para la enfermedad de Parkinso... more La Estimulación Cerebral Profunda (DBS) es un tratamiento efectivo para la enfermedad de Parkinson. Gran variedad de modelos matemáticos y computacionales para describir la propagación eléctrica debido a la DBS han sido propuestos, desafortunadamente, no existe claridad sobre las razones que justifican el uso de un modelo específico. En el presente trabajo se presenta una formulación matemática detallada de la propagación eléctrica debido a DBS que soporta un modelo basado en la ecuación de Laplace. Se realizan simulaciones para diferentes modelos geométricos del cerebro para determinar si la geometría, el tamaño y la ubicación de la tierra del modelo afectan la predicción de la estimulación eléctrica mediante el uso del Método de Elementos Finitos (FEM). Los análisis teórico y experimental muestran en primera instancia que la ecuación de Laplace es adecuada para describir la propagación eléctrica en el cerebro, y en segunda instancia que la estructura geométrica, tamaño y ubicación...
Pattern recognition by dinamic feature analysis based on PCA

A latent force model for describing electric propagation in deep brain stimulation: A simulation study
Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference, 2014
Deep brain stimulation (DBS) is a neurosurgical method used to treat symptoms of movement disorde... more Deep brain stimulation (DBS) is a neurosurgical method used to treat symptoms of movement disorders by implanting electrodes in deep brain areas. Often, the DBS modeling approaches found in the literature assume a quasi-static approximation, and discard any dynamic behavior. Nevertheless, in a real DBS system the stimulus corresponds to a wave that changes as a function of time. It is clear that DBS demands an approach that takes into account the time-varying behavior of the input stimulus. In this work, we present a novel latent force model for describing the dynamic electric propagation occurred during DBS. The performance of the proposed model was studied by simulations under different conditions. The results show that our approach is able to take into account the time variations of the source and the produced field. Moreover, by restricting our model it is possible to obtain solutions for electrostatic formulations, here experimental results were compared with the finite element...

Lecture Notes in Computer Science, 2012
Human motion analysis has emerged as an important area of research for different fields and appli... more Human motion analysis has emerged as an important area of research for different fields and applications. However, analyzing image and video sequences to perform tasks such as action recognition, becomes a challenge due to the high dimensionality of this type of data, not mentioning the restrictions in the recording conditions (lighting, angle, distances, etc). In that sense, we propose a framework for human action recognition, which involves a preprocessing stage that decreases the influence of the record conditions in the analysis. Further, our proposal is based on a new supervised feature extraction technique that includes class label information in the mapping process, to enhance both the underlying data structure unfolding and the margin of separability among classes. Proposed methodology is tested on a benchmark dataset. Attained results show how our approach obtains a suitable performance using straightforward classifiers.

Electric propagation modeling of Deep Brain Stimulation (DBS) using the finite element method (FEM)
2014 XIX Symposium on Image, Signal Processing and Artificial Vision, 2014
Deep Brain Stimulation (DBS) is a clinical treatment for Parkinson disease and has demonstrated t... more Deep Brain Stimulation (DBS) is a clinical treatment for Parkinson disease and has demonstrated the effective control of some of the symptoms related with Parkinson. DBS consist in the implantation of a neurostimulator into a region of the brain such as the subthalamic nucleus, the internal globus pallidus, etc. The electrodes are configured with a desired electric pulse in order to achieve the neural activation of the objective regions. Parameters of the stimulation pulse are experimentally adjusted for the neurologist during several sessions. In recent years, some efforts has been realized in order to facilitate the selection of the optimal parameters for DBS therapy without the experimental process, using head models that includes the electrical properties and geometry of the different brain structures in which the electric propagation is desired. The large variety of electromagnetic phenomena can all be described by the Maxwell's equations, which are also the basis for deep brain stimulation modelling. In particular, the Laplace equation is well suited for computing the electric propagation due DBS. For solving the Laplace equation in complex geometries is used the finite element method (FEM), which allows to compute of a numerical solution of differential equations applied over several domains by the creation of a structured mesh. The state of art works presented in the context of DBS modelling such as [1] [2] commonly uses a commercial software for FEM calculation. Since there is no way to measure the potentials directly from the brain during DBS, propagation models of the brain must be builded to determine the electric propagation. Nowadays, several GNU libraries for FEM computing are available. This work addresed the use of FEnICS library for C++ and phyton for solving the electric propagation in 2D and 3D geometrical models. With this in mind, we are interested in estimating the voltage propagation, around the DBS lead, in a particular area of the brain. Results show that the GNU libraries are well suited for FEM-DBS modelling in contrast to the obtained results using commercial software found in the literature.
Image Synthesis Based on Manifold Learning
Lecture Notes in Computer Science, 2011
A new methodology for image synthesis based on manifold learning is proposed. We employ a local a... more A new methodology for image synthesis based on manifold learning is proposed. We employ a local analysis of the observations in a low-dimensional space computed by Locally Linear Embedding, and then we synthesize unknown images solving an inverse problem, ...
Neurocomputing, 2010
Locally linear embedding (LLE) is a recent unsupervised learning algorithm for non-linear dimensi... more Locally linear embedding (LLE) is a recent unsupervised learning algorithm for non-linear dimensionality reduction of high dimensional data. One advantage of this algorithm is that just two parameters are needed to be set by user: the number of nearest neighbors and a regularization parameter. The choice of the regularization parameter plays an important role in the embedding results. In this paper, an automated method for choosing this parameter is proposed. Besides, in order to objectively qualify the performance of the embedding results, a new measure of embedding quality is suggested. Our approach is experimentally verified on 9 artificial data sets and 2 real world data sets. Numerical results are compared against two methods previously found in the state of art.
Uploads
Papers by Genaro Daza Santacoloma