ALGORITMOS DE PROCESADO DE SEÑAL BASADOS EN NON-NEGATIVE MATRIX FACTORIZATION APLICADOS A LA SEPARACIÓN, DETECCIÓN Y CLASIFICACIÓN DE SIBILANCIAS EN SEÑALES DE AUDIO RESPIRATORIAS MONOCANAL
Fecha
2021-03-24
Autores
Título de la revista
ISSN de la revista
Título del volumen
Editor
Jaén : Universidad de Jaén
Resumen
La auscultación es el primer examen clínico que un médico lleva a cabo para evaluar el estado del sistema respiratorio, debido a que es un método no invasivo, de bajo coste, fácil de realizar y seguro para el paciente. Sin embargo, el diagnóstico que se deriva de la auscultación sigue siendo un diagnóstico subjetivo que se encuentra condicionado a la habilidad, experiencia y entrenamiento de cada médico en la escucha e interpretación de las señales de audio respiratorias. En consecuencia, se producen un alto porcentaje de diagnósticos erróneos que ponen en riesgo la salud de los pacientes e incrementan el coste asociado a los centros de salud. Esta Tesis propone nuevos métodos basados en Non-negative Matrix Factorization aplicados a la separación, detección y clasificación de sonidos sibilantes para proporcionar una vía de información complementaria al médico que ayude a mejorar la fiabilidad del diagnóstico emitido por el especialista.
Auscultation is the first clinical examination that a physician performs to evaluate the condition of the respiratory system, because it is a non-invasive, low-cost, easy-to-perform and safe method for the patient. However, the diagnosis derived from auscultation remains a subjective diagnosis that is conditioned by the ability, experience and training of each physician in the listening and interpretation of respiratory audio signals. As a result, a high percentage of misdiagnoses are produced that endanger the health of patients and increase the cost associated with health centres. This Thesis proposes new methods based on Non-negative Matrix Factorization applied to separation, detection and classification of wheezing sounds in order to provide a complementary information pathway to the physician that helps to improve the reliability of the diagnosis made by the doctor.
Auscultation is the first clinical examination that a physician performs to evaluate the condition of the respiratory system, because it is a non-invasive, low-cost, easy-to-perform and safe method for the patient. However, the diagnosis derived from auscultation remains a subjective diagnosis that is conditioned by the ability, experience and training of each physician in the listening and interpretation of respiratory audio signals. As a result, a high percentage of misdiagnoses are produced that endanger the health of patients and increase the cost associated with health centres. This Thesis proposes new methods based on Non-negative Matrix Factorization applied to separation, detection and classification of wheezing sounds in order to provide a complementary information pathway to the physician that helps to improve the reliability of the diagnosis made by the doctor.
Descripción
Palabras clave
Non-negative Matrix Factorization (NMF), Procesado de señal biomédica, Auscultación, Sibilancias, Sonidos respiratorios normales
Citación
p.[http://hdl.handle.net/10953/]