Traffic noise modelling on urban arterial roads using mathematical and machine-learning techniques

Simultaneous measurements of main arterial roads inside the urban perimeter of Kurukshetra City (Haryana, India) regarding noise levels, traffic flow, and vehicle composition were taken and then used to develop some Traffic Noise Models (TNMs) to predict equivalent noise levels ( <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" overflow="scroll"> <mml:mrow> <mml:msub> <mml:mi>L</mml:mi> <mml:mrow> <mml:mi>e</mml:mi> <mml:mi>q</mml:mi> </mml:mrow> </mml:msub> </mml:mrow> </mml:math> ) from traffic flow per hour. The performance of the developed mathematical model was compared with four widely used TNMs. The potential of machine-learning techniques (M5 model tree, random forest and support vector machines) was also explored and their performance was compared with the developed mathematical TNM. Finally, the versatility of the developed mathematical model was examined for predicting the standard noise descriptors ( <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" overflow="scroll"> <mml:mrow> <mml:msub> <mml:mi>L</mml:mi> <mml:mi>D</mml:mi> </mml:msub> </mml:mrow> </mml:math> , <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" overflow="scroll"> <mml:mrow> <mml:msub> <mml:mi>L</mml:mi> <mml:mi>N</mml:mi> </mml:msub> </mml:mrow> </mml:math> and <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" overflow="scroll"> <mml:mrow> <mml:msub> <mml:mi>L</mml:mi> <mml:mrow> <mml:mi>D</mml:mi> <mml:mi>N</mml:mi> </mml:mrow> </mml:msub> </mml:mrow> </mml:math> ). The model required tuning for enhanced performance in predicting <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" overflow="scroll"> <mml:mrow> <mml:msub> <mml:mi>L</mml:mi> <mml:mrow> <mml:mi>D</mml:mi> <mml:mi>N</mml:mi> </mml:mrow> </mml:msub> </mml:mrow> </mml:math> , which was achieved by introducing a model coefficient ( <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" overflow="scroll"> <mml:mrow> <mml:msub> <mml:mi>P</mml:mi> <mml:mi>n</mml:mi> </mml:msub> </mml:mrow> </mml:math> = 1.05) to compensate for the night-time penalty. The study exhibited the potential application of machine-learning techniques in developing TNMs. However, the developed mathematical TNM allows a simple representation of a mathematical formula for the determination of <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" overflow="scroll"> <mml:mrow> <mml:msub> <mml:mi>L</mml:mi> <mml:mrow> <mml:mi>e</mml:mi> <mml:mi>q</mml:mi> </mml:mrow> </mml:msub> </mml:mrow> </mml:math> for any time-duration from the corresponding traffic flow per hour.