Low noise surfaces have been increasingly considered as a viable and cost-effective alternative to acoustical barriers. However, road planners and administrators frequently lack information on the correlation between the type of road surface and the resulting noise emission profile. To address this problem, a method to identify and classify different types of road pavements was developed, whereby near field road noise is analyzed using statistical learning methods. The vehicle rolling sound signal near the tires and close to the road surface was acquired by two microphones in a special arrangement which implements the Close-Proximity method. A set of features, characterizing the properties of the road pavement, was extracted from the corresponding sound profiles. A feature selection method was used to automatically select those that are most relevant in predicting the type of pavement, while reducing the computational cost. A set of different types of road pavement segments were tested and the performance of the classifier was evaluated. Results of pavement classification performed during a road journey are presented on a map, together with geographical data. This procedure leads to a considerable improvement in the quality of road pavement noise data, thereby increasing the accuracy of road traffic noise prediction models. (C)
A new method to classify and identify different types of road pavements by analysing the near field sound profile and texture using statistical learning methods is proposed. A set of characteristics were extracted from the noise profile and from the road surface texture. Sound measurements were carried out following the close-proximity method with the texture descriptors being provided by a high speed profilometer system. As a first approach, it is assumed that the features extracted from the noise and texture characteristics follow normal distributions. However, this assumption is not completely verified for all types of road surfaces. The method presented herein exploits the use of Bayesian analysis complemented by a neural network in order to improve the classification results.
The measurement procedure to evaluate the influence of road surface characteristics on vehicle and traffic noise is designated by Close-Proximity (CPX) method, as described in the ISO 11819-2 draft. This procedure consists on acquiring the vehicle rolling noise signal near the tires and close to the surface by means of at least two microphones, in a special arrangement for the determination of the Close-Proximity Sound Index (CPXI). Roadtraffic noise is estimated by taking into account the absorption characteristics of road surface on the propagation of sound and the speed and type of vehicles. However, the particular characteristics of the different pavement types, which may influence the sound radiation, are not considered. The main goal of this research is to identify and classify different types of road pavements, for different stress conditions, using the CPX method. Such information can be used as a guideline for calibrating noise mapping models in order to achieve more realistic and accurate results. The classification of the different road surfaces consists on a supervised learning technique based on the Support Vector Machine, SVM, algorithms. Results based on error analysis are presented and discussed.
Measures aiming environmental noise abatement usually consider acoustic barriers alongside the road. However, the cost associated with these measures is usually considerably high and its performance in urban areas is reduced. The problem of the visual impact is another issue affecting the communities. Nowadays, road planners have started to consider silent surfaces as an alternative. These types of surfaces are constituted basically by changing the texture and/or porosity of the mixtures. In some conditions, noise level abatements up to 15 dB can be achieved. Therefore, a considerable variety of different surfaces are available. The main goal of this research is to identify and classify different types of road pavements by analyzing the noise profile, using the close proximity method. Feature extraction and selection is one of the first procedures on a classifier algorithm. Moreover, the accuracy of the results is strongly dependent on the right choice of the selected feature vector. Standard classifiers are being tested in order to establish guidelines for future developments of this research. In situations of net road surveillance, searching for inhomogeneities on the surface and the presentation of the results in a geographic map, showing the locations of the surface types and the noise levels, can improve the accuracy of the noise mapping models.
The Swept Sine and the MLS techniques are very popular in room acoustic measurement set-ups. Advantages and disadvantages of both methods have been well investigated and can be found in the literature. However, information regarding the performance of these techniques in the presence of high background music levels is scarce. Since the estimation of the room impulse response is based on the correlation between signals, the likelihood between the test signal and the music contents plays an important role on the results’ accuracy. This paper explores these issues by taking into account the semantic information of the music signals when used as disturbance. The method used for the assessment of the gain between the two techniques consists of splitting each frame into segments and applying a weighting function depending on a likelihood function. The features used for the likelihood function are the rms value of each segment, spectral energy envelope relation, bandwidth and harmonic structure. Several examples are presented for comparison of the performance of the Swept Sine and the MLS techniques. Advantages and disadvantages of each technique are discussed for music signals as noise.
The accurate estimation of the acoustical parameters of a space to be used by people, such as theaters, concert halls, conference rooms, sport stadiums, and other public areas, implies that the measurements should be evaluated in the presence of an audience. However, for reasons of annoyance, people are usually avoided and a correction factor related to the effective absorption of the audience area is applied to the results only. This procedure does not take into account the variability of some parameters such as the relative humidity during the event, which influences considerably the magnitude frequency response. The swept sine technique is very attractive in acoustical measurements due to the high signal-to-noise ratios (SNR) and robustness against nonlinearity of the measurement chain and time variance. The use of some convenient music tracks in agreement with the perceptual masking effect minimizes the annoyance and increases the SNR simultaneously. The sinusoidal synthesis algorithm is applied to some parts of the music. After questioning a set of persons, some results based on an annoyance indicator are presented giving advantages and disadvantages of this method.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.