Acoustic lung signals analysis based on Mel frequency cepstral coefficients and self-organizing maps
This study analyzes acoustic lung signals with different abnormalities, using Mel Frequency Cepstral Coefficients (MFCC), Self-Organizing Maps (SOM), and K-means clustering algorithm. SOM models are known as artificial neural networks than can be trained in an unsupervised or supervised manner. Both...
| Main Authors: | , |
|---|---|
| Format: | Online |
| Language: | eng |
| Published: |
Universidad Pedagógica y Tecnológica de Colombia
2016
|
| Subjects: | |
| Online Access: | https://revistas.uptc.edu.co/index.php/ingenieria/article/view/5300 |
| _version_ | 1801706075264647168 |
|---|---|
| author | Orjuela-Cañón, Álvaro David Posada-Quintero, Hugo Fernando |
| author_facet | Orjuela-Cañón, Álvaro David Posada-Quintero, Hugo Fernando |
| author_sort | Orjuela-Cañón, Álvaro David |
| collection | OJS |
| description | This study analyzes acoustic lung signals with different abnormalities, using Mel Frequency Cepstral Coefficients (MFCC), Self-Organizing Maps (SOM), and K-means clustering algorithm. SOM models are known as artificial neural networks than can be trained in an unsupervised or supervised manner. Both approaches were used in this work to compare the utility of this tool in lung signals studies. Results showed that with a supervised training, the classification reached rates of 85 % in accuracy. Unsupervised training was used for clustering tasks, and three clusters was the most adequate number for both supervised and unsupervised training. In general, SOM models can be used in lung signals as a strategy to diagnose systems, finding number of clusters in data, and making classifications for computer-aided decision making systems. |
| format | Online |
| id | oai:oai.revistas.uptc.edu.co:article-5300 |
| institution | Revista Facultad de Ingeniería |
| language | eng |
| publishDate | 2016 |
| publisher | Universidad Pedagógica y Tecnológica de Colombia |
| record_format | ojs |
| spelling | oai:oai.revistas.uptc.edu.co:article-53002022-06-15T16:21:44Z Acoustic lung signals analysis based on Mel frequency cepstral coefficients and self-organizing maps Análisis de señales acústicas de pulmón basado en coeficientes cepstrales de la escala Mel y mapas auto-organizados Orjuela-Cañón, Álvaro David Posada-Quintero, Hugo Fernando acoustic lung signals computer-aided decision making self-organizing maps mapas auto-organizados señales acústicas de pulmón sistemas de apoyo a decisión This study analyzes acoustic lung signals with different abnormalities, using Mel Frequency Cepstral Coefficients (MFCC), Self-Organizing Maps (SOM), and K-means clustering algorithm. SOM models are known as artificial neural networks than can be trained in an unsupervised or supervised manner. Both approaches were used in this work to compare the utility of this tool in lung signals studies. Results showed that with a supervised training, the classification reached rates of 85 % in accuracy. Unsupervised training was used for clustering tasks, and three clusters was the most adequate number for both supervised and unsupervised training. In general, SOM models can be used in lung signals as a strategy to diagnose systems, finding number of clusters in data, and making classifications for computer-aided decision making systems. En este trabajo se realizó un análisis de anormalidades en señales acústicas de pulmón. La metodología incluyó el uso de coeficientes cepstrales de la escala Mel (MFCC), Mapas Auto-Organizados (SOM) y el algoritmo de agrupamiento K-means. Los modelos obtenidos con los mapas son conocidos como redes neuronales artificiales, que pueden ser entrenados en una forma supervisada o no supervisada. Ambos tipos de entrenamiento fueron usados para comparar el uso de este tipo de herramientas computacionales en estudios de señales respiratorias. Los resultados mostraron un 85 % de acierto en la clasificación, cuando fue implementado un entrenamiento supervisado. Al realizar tareas de agrupamiento con entrenamiento no supervisado fue encontrado que el número de grupos más adecuado es de tres. En general, los modelos SOM pueden ser usados en este tipo de señales como una estrategia útil en sistemas de diagnóstico, encontrando información en los datos y realizando clasificación para sistemas de apoyo a decisión. Universidad Pedagógica y Tecnológica de Colombia 2016-09-01 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion investigation investigación application/pdf text/html https://revistas.uptc.edu.co/index.php/ingenieria/article/view/5300 10.19053/01211129.v25.n43.2016.5300 Revista Facultad de Ingeniería; Vol. 25 No. 43 (2016); 73-82 Revista Facultad de Ingeniería; Vol. 25 Núm. 43 (2016); 73-82 2357-5328 0121-1129 eng https://revistas.uptc.edu.co/index.php/ingenieria/article/view/5300/4428 https://revistas.uptc.edu.co/index.php/ingenieria/article/view/5300/5063 |
| spellingShingle | acoustic lung signals computer-aided decision making self-organizing maps mapas auto-organizados señales acústicas de pulmón sistemas de apoyo a decisión Orjuela-Cañón, Álvaro David Posada-Quintero, Hugo Fernando Acoustic lung signals analysis based on Mel frequency cepstral coefficients and self-organizing maps |
| title | Acoustic lung signals analysis based on Mel frequency cepstral coefficients and self-organizing maps |
| title_alt | Análisis de señales acústicas de pulmón basado en coeficientes cepstrales de la escala Mel y mapas auto-organizados |
| title_full | Acoustic lung signals analysis based on Mel frequency cepstral coefficients and self-organizing maps |
| title_fullStr | Acoustic lung signals analysis based on Mel frequency cepstral coefficients and self-organizing maps |
| title_full_unstemmed | Acoustic lung signals analysis based on Mel frequency cepstral coefficients and self-organizing maps |
| title_short | Acoustic lung signals analysis based on Mel frequency cepstral coefficients and self-organizing maps |
| title_sort | acoustic lung signals analysis based on mel frequency cepstral coefficients and self organizing maps |
| topic | acoustic lung signals computer-aided decision making self-organizing maps mapas auto-organizados señales acústicas de pulmón sistemas de apoyo a decisión |
| topic_facet | acoustic lung signals computer-aided decision making self-organizing maps mapas auto-organizados señales acústicas de pulmón sistemas de apoyo a decisión |
| url | https://revistas.uptc.edu.co/index.php/ingenieria/article/view/5300 |
| work_keys_str_mv | AT orjuelacanonalvarodavid acousticlungsignalsanalysisbasedonmelfrequencycepstralcoefficientsandselforganizingmaps AT posadaquinterohugofernando acousticlungsignalsanalysisbasedonmelfrequencycepstralcoefficientsandselforganizingmaps AT orjuelacanonalvarodavid analisisdesenalesacusticasdepulmonbasadoencoeficientescepstralesdelaescalamelymapasautoorganizados AT posadaquinterohugofernando analisisdesenalesacusticasdepulmonbasadoencoeficientescepstralesdelaescalamelymapasautoorganizados |
