Ingeniería de software
Permanent URI for this community
Browse
Browsing Ingeniería de software by Author "Bergamini, María Lorena"
Results Per Page
Sort Options
-
ItemDetección de patologías en señales biomédicas mediante técnicas de machine learning(Universidad Nacional de la Patagonia Austral, 2020-6) Bergamini, María Lorena ; Liberczuk, Sergio JavierEl procesamiento de señales biomédicas tiene una importancia relevante en el diagnóstico temprano y prevención de enfermedades. El electrocardiograma (ECG) es un estudio noinvasivo, de bajo costo, que brinda información valiosa sobre la actividad eléctrica cardíaca. El análisis de esta señal estudia patrones que se asocian con condiciones anormales de funcionamiento. El objetivo principal de este proyecto es desarrollar técnicas y algoritmos para el análisis, modelado, clasificación y segmentación de señales electrocardiográficas, a fin de que puedan ser aplicados en tiempo real; y poder así dar soporte a la detección temprana de eventos patológicos. Específicamente, nos proponemos diseñar algoritmos de procesamiento de ECG con un enfoque Bayesiano, con el objetivo de sintonizar los parámetros de un modelo dinámico que permitan la síntesis de señales de ECG registrables durante procesos de isquemia e infarto. Asimismo, se aplicarán técnicas de machine learning para procesar los parámetros y configurar un sistema de asistencia al médico en el diagnóstico automático de patologías.
-
ItemHeart beat parametric modeling based on Monte Carlo fitting techniques(Sociedad Argentina de Bioingeniería, 2019-3-28) Liberczuk, Sergio Javier ; Bergamini, María Lorena ; Arini, PedroSynthesis of electrocardiogram (ECG) signals is closely linked to the modeling process since precise knowledge of the parameters of the heartbeat to be modeled is required. The knowledge of these parameters is achieved through methods of adjusting curves between simulated beats and real beats. These traditional optimization methods, such as nonlinear least squares or similar, suffer from the drawback of falling at local minima especially when the initial conditions are not given in an accurate fashion. In the present work, we have designed a novel method robust to deviations in the initial conditions based on Monte Carlo techniques derived from the ideas of the Particle Filtering. Our method allows to adjust the heart beat and to determine the parameters of a model already known in the literature that consists of the sum of five Gaussian curves. The method fits with errors very similar to the traditional method when the initial conditions are good, but better results are obtained in terms of squared error when the initial conditions are sufficiently degraded. Validation was carried out with real physiological and pathological ECG records from international databases.
-
ItemModel based feature extraction method for myocardial infarction detection(Asociación Argentina de Mecánica Computacional, 2018-11) Liberczuk, Sergio Javier ; Bergamini, María LorenaThe electrical activity of the heart represented by the electrocardiogram (ECG) has been widely used for the detection of heart diseases. Long-term records require the automatic detection of cardiac events. In this work, the detection of myocardial infarction (MI) is performed by means of novel ECG features based on a synthesis ECG model previously described in the literature. The model consists of a sum of five Gaussians centered on each wave of the ECG (P, Q, R, S and T). Each Gaussian is fully specified by three parameters; location in time, amplitude and broadness. By fitting this set of Gaussians, and performing numerical and nonlinear optimization procedures in the resulting 15-dimensional space, we get this set of 15 parameters as features for classification. Although the model was widely used previously with different purposes, its parameters had never been used as features for heartbeat classification even though they reflect the morphology of the ECG in an accurate manner. Physikalisch-Technische-Bundesanstalt (PTB) database was used to validate training and testing algorithms. Data was obtained from 48 healthy subjects (HS) and 95 patients with MI and was split into two datasets. The first dataset contains 190 beats from 26 HS, and 140 beats from 60 patients with MI and was used to train a support vector machine (SVM) classifier with linear kernel. The second dataset contains 88 beats from 22 HS, and 70 beats from 35 subjects with MI and was used to provide a detection performance assessment of the previously trained SVM. This assessment yielded an overall accuracy above 93%. The results show the feasibility of performing the separation between infarcted beats and physiological beats based on the new model-based features proposed. The simplicity of the linear kernel used in the SVM classifier shows the power of the proposed features for classification tasks.
-
ItemSemi-autonomous robot control system with an improved 3D vision scheme for search and rescue missions : a joint research collaboration between South Africa and Argentina(ASTES, 2018-12-1) Kamlofsky, Jorge Alejandro ; Bergamini, María Lorena ; Naidoo, Nicol ; Bright, Glen ; Zelasco, José ; Ansaldo, Francisco ; Stopforth, RiaanRescue operations require technology to assist the rescue process. The robotic technology in these missions is becoming very important. The important aspects investigated in this study are the integration of a mechatronic system that will allow for a robotic platform with a vision system. The research collaboration between Argentina and South Africa is discussed, with the correlating research areas that each country investigated. The study permitted the development and advancement of a search and rescue system for different robots (wayfarer and drones) with different vision capabilities. A novel and innovative vision approach is presented.