Integración de indicadores borrosos en redes de sensores inalámbricos. Aplicación para la monitorización acústica
Archivos
Fecha
2017-09-25
Autores
Título de la revista
ISSN de la revista
Título del volumen
Editor
Resumen
En los últimos años, hay un gran interés en la monitorización de la contaminación acústica, existiendo estudios recientes que proponen el uso de redes de sensores inalámbricos. Aunque los indicadores de ruido definidos en la directiva 2002/49/EC pueden ser calculados por nodos sensores, la percepción del ruido se ve afectada por factores subjetivos y no existe una correlación directa entre los indicadores y la percepción subjetiva de ruido. En este sentido, esta tesis doctoral presenta un nuevo Indicador de Ruido Borroso (FNI) para inferir el grado de molestia subjetiva de ruido, utilizando un nuevo algoritmo de dominio de frecuencia adaptado para su uso en dispositivos con recursos muy limitados. Cada nodo ejecuta un Sistema Basado en Reglas Borrosas especialmente adaptado, que dispone de dos entradas: a) el nivel de presión sonora equivalente ponderado (Tipo A) y b) su persistencia en el tiempo. Los resultados muestran, que el indicador borroso puede ser utilizado para distinguir situaciones de más o menos nivel de molestia subjetiva.
Over the last few years, there is a growing interest in monitoring noise pollution and some recent studies have proposed the deployment of Wireless Sensor Networks for this task. Although the noise indicators defined by European Union directive 2002/49/EC can be calculated by sensor nodes, the noise perception is affected by subjective factors and there is not a direct correlation between the indicators and the subjective perception of noise. Accordingly, this Ph. P. Thesis presents a new Fuzzy Noise Indicator (FNI) to infer the degree of subjective noise annoyance, using a new frequency domain algorithm adapted for use in resource-constrained devices. Each device executes an adapted Fuzzy Rule-Based System which has two inputs: a) the A-weighting equivalent noise level value and b) its persistence in time. The results show that the use of this Fuzzy Indicator helps to distinguish between situations with noise annoyance and other situations less annoying.
Over the last few years, there is a growing interest in monitoring noise pollution and some recent studies have proposed the deployment of Wireless Sensor Networks for this task. Although the noise indicators defined by European Union directive 2002/49/EC can be calculated by sensor nodes, the noise perception is affected by subjective factors and there is not a direct correlation between the indicators and the subjective perception of noise. Accordingly, this Ph. P. Thesis presents a new Fuzzy Noise Indicator (FNI) to infer the degree of subjective noise annoyance, using a new frequency domain algorithm adapted for use in resource-constrained devices. Each device executes an adapted Fuzzy Rule-Based System which has two inputs: a) the A-weighting equivalent noise level value and b) its persistence in time. The results show that the use of this Fuzzy Indicator helps to distinguish between situations with noise annoyance and other situations less annoying.
Descripción
Palabras clave
Redes de sensores inalámbricos, contaminación acústica, sistemas borrosos basados en reglas, Wireless sensor networks, noise pollution, fuzzy rule-based system