Classification of noisy vehicles from unsupervised measurements

Abstract

The NEMO-project (https://nemo-cities.eu/) aims to identify noisy and polluting road and rail vehicles, using remote sensing technology. Noise levels from individual road vehicles are measured from the roadside, in normal traffic. Road authorities may use these data to enforce noise limits, to limit access to Low Emission Zones or to influence driving behaviour. Whether a vehicle is a 'high noise emitter' is a complex question, as the noise level depends on vehicle type and condition, driving style, weather and location-specific characteristics. From a legal perspective, the question may be answered in relation to type approval noise limits, or in relation to local noise disturbance regulations. Within NEMO, a classification model is developed from a large dataset of unsupervised pass-by noise measurements, from different locations. The model labels noisy vehicles based on the noise measurements, technical vehicle data, driving conditions, and external factors. Several modeling and machine learning techniques were evaluated, to find the most accurate solution. This paper presents the results, and it looks forward to how the technological solution could be applied to enforce regulations, leading to a reduction of traffic noise annoyance.