New results in fuzzy pattern classification of background noise

Abstract

This paper proposes a background noise classifier based on a new, computationally simple, robust set of acoustic features. Complementary to a previous work [l], reporting on the first studies carried out by the authors on background noise classification, this paper mainly presents: 1) a criterion to group a large range of environmental noise into a reduced set of classes of noise with similar acoustic characteristics; 2) a larger set of background noise together with a new multilevel classification architecture; 3) a new set of robust acoustic parameters. We have maintained the pattern recognition approach proposed in [ 13 in which the matching phase is performed using a set of trained fuzzy rules. The improved version of the Fuzzy Noise Classifier (FNC) has been assessed in terms of misclassification percentage and compared with a Quadratic Gaussian Classifier (QGC).

A neural network based model for urban noise prediction

“…Nevertheless, there are currently few studies that analyze environmental noise, even traffic flow as the most important component of urban noise, with ANNs 22-32 or other soft computing techniques. 29,[31][32][33][34][35][36][37][38][39][40][41][42][43][44][45][46][47][48][49][50] Specifically, we found only two papers ͑Refs. 22 and 25͒, describing studies in which an ANN was used for noise level prediction.…”

Automatic environmental noise source classification model using fuzzy logic

“…Fuzzy reasoning builds this understanding into the process rather than tacking it onto the end. Recently the use of fuzzy logic has been a very popular method for researchers in many fields such as control systems, robotics, image processing, and noise recognition/classification algorithms (Beritelli et al, 1999;Laboid, Boucherit, & Guerra, 2005;Mendoza, Melin, & Licea, 2007;Sun & Er, 2004).…”

“…They stated that their proposed fuzzy logic approach achieves a fairly better performance than a number of other existing methods. Another fuzzy logic approach for classification of background noise (Beritelli, Casale, & Ruggeri, 1999) proposed a background noise classifier based on fuzzy logic approach and it is compared with Quadratic Gaussian Classifier (QGC). They seperated the inputs according to parameter of being stationary and nonstationary.…”

Developing an Artificial Neural Network for Modeling and Prediction of Temporal Structure and Spectral Composition of Environmental Noise in Cities

“…Genetic Algorithms Hidden Markov Models Sound Pressure Level Prediction (Cammarata et al, 1995;Avsar et al, 2004;Genaro et al, 2010) (Aguilera de Maya, 1997;Caponetto et al, 1997) (Caponetto et al, 1997) Noise Annoyance Prediction (Zaheeruddin & Garima, 2006) (Botteldooren & Verkeyn, 2001;Botteldooren & Verkeyn, 2002a,b,c,d,e;Botteldooren et al, 2002a,b;Botteldooren et al, 2003a,b;Botteldooren & Lercher, 2004;Zaheeruddin & Garima, 2006) (Botteldooren & Verkeyn, 2001;Botteldooren et al, 2003b) Noise Classification (Berg, 2002;Couvreur & Laniray, 2004;Betkowsa et al, 2005) (Caponetto et al, 1997) (Beritelli et al, 2000) ( Ma et a., 2003a,b;Couvreur & Laniray, 2004;Betkowsa et al, 2005; Urban Traffic Flow Prediction (Fortuna et al, 2004;Dougherty & Cobbett, 1997;Ledoux, 1997;Dia, 2001;Yin et al, 2002) (Fortuna et al, 1994;Yin et al, 2002) Table 1. Taxonomy of the urban noise vs. soft-computing methods publications (Genaro et al, 2010) www.intechopen.com…”

“…The neural network is built with a backpropagation architecture with three neurons in the hidden layer. In (Beritelli et al, 2000) an urban noise classifier based on fuzzy techniques is presented. Considering a set of acoustic characteristics it tries to distinguish among seven categories: bus, car, rail, construction works, people talking, street and factory.…”