Sound Pressure Level at Terminals through Data Mining

Abstract

The land transportation is a cause of noise in cities, thus breaking the natural balance and bringing with it physiological and mental illnesses, as well as occupational accidents. In this sense, the objective of the research was to estimate the sound pressure in land terminals in the city of Jaen, Peru, using data mining algorithms. The methodology consisted in environmentally monitoring six terminals in the city of Jaen, during 2019, using a class 1 sound level meter; the exploratory analysis of the collected variables that influence the noise of the terminals (minimum and maximum sound pressure level, number of light and heavy vehicles, and equivalent sound pressure level) was performed, which were grouped into three groups of variables for the purpose of using data mining algorithms. Three algorithms were used, namely, artificial neural network, linear regression, and M5Rules, using the free software Weka. Considering all variables, the M5Rules method performed the best, because the value of the mean absolute error (0.7462), the root mean square error (1.0575), and uncertainty analysis (0.09) was the smallest compared to the other two methods. However, for the two remaining groups of variables, the linear regression model showed the lowest mean absolute error and mean square root of the error; in addition to presenting coefficients of determination close to one. The algorithms show good behavior when estimating the sound pressure of the terminals in the city of Jaen.