Analysis of artificial intelligence methods for rail transport traffic noise detection

: pp. 107 - 116
Lviv Polytechnic National University
AGH University of Science and Technology in Kraków
Lviv Polytechnic National University, Ukraine
Lviv Polytechnic National University, Ukraine
Lviv Polytechnic National University, Ukraine

Nowadays, many cities all over the world suffer from noise pollution. Noise is an invisible danger that can cause health problems for both people and wildlife. Therefore, it is essential to estimate the environmental noise level and implement corrective measures. There are a number of noise identification techniques, and the choice of the most appropriate technique depends upon the information required and its application. Analyzing audio data requires three key aspects to be considered such as time period, amplitude, and frequency. Based on the above parameters, the source of noise can be identified.

This research paper suggests the utilization of artificial intelligence and machine learning algorithms for the traffic noise detection process. Computational methods are the fastest and most innovative way to analyze raw data sets and predict results. Identifying patterns in these methods requires a large amount of data and computing power. Machine learning models can be trained using three types of data: experimental sound libraries, audio datasets purchased from data providers, and data collected by domain experts. In the scope of the study, an experimental dataset was used to train a model that predicts the correct outcomes based on the inputs, using supervised learning. Developing an accurate model requires high-quality data input. However, incorrect data collection can cause noise in feature sets, as can human error or instrument error. Traffic sound events in the real environment do not usually occur in isolation but tend to have a significant overlap with other sound events. A part of this paper is dedicated to the problems that may arise during traffic noise detection, like incorrect data processing and data collection. It also discusses the ways to improve the quality of the input data. The study also states that the field of transport noise detection would greatly benefit from the development of a centralized railway database based on constructive railroad data, and from a centralized database with railway-specific datasets. Based on preliminary results of traffic noise analysis, modernization of the tram lines was proposed to reduce the environmental noise.

  1. Roberts L. Understanding the Mel Spectrogram [Електронний ресурс] / Leland Roberts // Medium. – 2020. – Режим доступу до ресурсу: mel-spectrogram-fca2afa2ce53.
  2. Audio Analysis With Machine Learning: Building AI-Fueled Sound Detection App [Електронний ресурс] // Altexsoft. – 2022. – Режим доступу до ресурсу:
  3. Déborah M. Python AI: How to Build a Neural Network & Make Predictions [Електронний ресурс] / Mesquita Déborah // Realpython. – 2020. – Режим доступу до ресурсу:
  4. Overlap-Add (OLA) STFT Processing [Електронний ресурс] // Center for Computer Research in Music and Acoustics (CCRMA). – 2022. – Режим доступу до ресурсу:
  5. Zuzana Papánová, Daniel Papán, Libor Ižvolt, Peter Dobeš, Modernization of Heavy Loaded Tram Radial Effect on Noise and Vibration, Appl. Sci. 2022, 12(14), 6947; Received: 21 March 2022 / Revised: 27 June 2022 / Accepted: 5 July 2022 / Published: 8 July 2022
  6. Special Issue "Design of Track System and Railway Vehicle Dynamics Analysis" [Електронний ресурс] // MDPI. – 2022. – Режим доступу до ресурсу:
  7. Morihara, T.; Yokoshima, S.; Matsumoto, Y. Effects of Noise and Vibration Due to the Hokuriku Shinkansen Railway on the Living Environment: A Socio-Acoustic Survey One Year after the Opening. Int. J. Environ. Res. Public Health 2021, 18, 7794. [Google Scholar] [CrossRef] [PubMed]
  8. Maclachlan, L.; Ögren, M.; Van Kempen, E.; Hussain-Alkhateeb, L.; Persson Waye, K. Annoyance in Response to Vibrations from Railways. Int. J. Environ. Res. Public Health 2018, 15, 1887. [Google Scholar] [CrossRef] [PubMed][Green Version]
  9. Lercher, P.; De Coensel, B.; Dekonink, L.; Botteldooren, D. Community Response to Multiple Sound Sources: Integrating Acoustic and Contextual Approaches in the Analysis. Int. J. Environ. Res. Public Health 2017, 14, 663. [Google Scholar] [CrossRef] [PubMed][Green Version]
  10. Bao, Y.; Li, Y.; Ding, J. A Case Study of Dynamic Response Analysis and Safety Assessment for a Suspended Monorail System. Int. J. Environ. Res. Public Health 2016, 13, 1121. [Google Scholar] [CrossRef] [PubMed]
  11. A Systematic Review of Artificial Intelligence Public Datasets for Railway Applications, September 2021, DOI:10.3390/infrastructures6100136, RAILS - Roadmaps for A.I. integration in the rail Sector (EU Horizon 2020 - Shift2Rail JU)
  12. Understanding Spectrograms [Електронний ресурс] // iZotope. – 2020. – Режим доступу до ресурсу:
  13. Fast Fourier Transformation FFT - Basics [Електронний ресурс] // NTi-audio. – 2020. – Режим доступу до ресурсу:
  14. Audio Feature Extraction [Електронний ресурс] // Devopedia. – 2021. – Режим доступу до ресурсу:
  15. Schutz, Michael, and Jonathan M. Vaisberg. 2012. "Surveying the temporal structure of sounds used in Music Perception." Music Perception: An Interdisciplinary Journal, vol. 31, no. 3, pp. 288-296. doi: 10.1525/mp.2014.31.3.288. Accessed 2021-05-23.