Noise Prediction Using Machine Learning with Measurements Analysis

Abstract

The noise prediction using machine learning is a special study that has recently received increased attention. This is particularly true in workplaces with noise pollution, which increases noise exposure for general laborers. This study attempts to analyze the noise equivalent level (Leq) at the National Synchrotron Radiation Research Center (NSRRC) facility and establish a machine learning model for noise prediction. This study utilized the gradient boosting model (GBM) as the learning model in which past noise measurement records and many other features are integrated as the proposed model makes a prediction. This study analyzed the time duration and frequency of the collected Leq and also investigated the impact of training data selection. The results presented in this paper indicate that the proposed prediction model works well in almost noise sensors and frequencies. Moreover, the model performed especially well in sensor 8 (125 Hz), which was determined to be a serious noise zone in the past noise measurements. The results also show that the root-mean-square-error (RMSE) of the predicted harmful noise was less than 1 dBA and the coefficient of determination (R2) value was greater than 0.7. That is, the working field showed a favorable noise prediction performance using the proposed method. This positive result shows the ability of the proposed approach in noise prediction, thus providing a notification to the laborer to prevent long-term exposure. In addition, the proposed model accurately predicts noise future pollution, which is essential for laborers in high-noise environments. This would keep employees healthy in avoiding noise harmful positions to prevent people from working in that environment.

Machine Learning and Prediction of Masked Motors With Different Materials Based on Noise Analysis

“…However, few attempts have been made to use gradient boosting to predict noise. Therefore, the NSRRC designed a model based on the GBM to predict noise, which provides more accurate noise distribution prediction results than multiple linear regression (MLR) [27]. Consequently, in the present study, the GBM was selected as the machine learning model of propose approach for motor noise masking simulation, and random forests (RF), support vector machine (SVM), gaussian processes regression model (GPRM) and multiple linear regression (MLR) were very common prediction models in above literature and may performed as compare method to predict acoustic noise.…”

“…The term F(xt) represents the target prediction model. Test samples are input into this model to obtain noise prediction results [27,29,30,34,35]. Algorithm is presented in the following text.…”

“…In MLR analysis, multiple independent variables are used to predict one dependent variable. Because multidimensional data were used in the conducted experiments, we selected a compound linear regression algorithm that can handle multiple independent variables for prediction [27,31]. The selected algorithm is presented in the following text.…”

“…The motor noise in the National Synchrotron Radiation Research Center (NSRRC) facility is distributed in the lowfrequency band [27]. In the present study, three materials, namely wood, metal, and acrylic, were used to design masks for reducing motor noise.…”

ZARATAMAP: Noise Characterization in the Scope of a Smart City through a Low Cost and Mobile Electronic Embedded System

“…Among the services to be provided, it is the characterization of the possible main sources of noise in the city. Noise analysis is also an area of research in which machine learning has been shown to have a wide range of applications, being one of them, the prediction of traffic volume as a function of vehicle generated noise as in Alam et al [ 14 ] or to determine noise prediction in industrial scenarios [ 15 ]. From our point of view, we can apply this knowledge in the field of smart cities to determine the main sources of noise at specific points in the city and thus provide more detailed information to public administrations in order to take the best measures to help mitigate that source of noise.…”