Artificial Neural Network Modelling of Traffic Noise Induced Annoyance Amongst Exposed Population

IJEP 42(9): 1042-1050 : Vol. 42 Issue. 9 (September 2022)

Chidananda Prasad Das1, Smita Rath2, Bijay Kumar Swain3, Shreerup Goswami4 and Mira Das1*

1. Siksha ‘O’ Anusandhan (Deemed to be University), Environmental Science Programme, Department of Chemistry, ITER, Bhubaneswar – 751 030, Odisha, India
2. Siksha ‘O’ Anusandhan (Deemed to be University), Department of Computer Science and Engineering, ITER, Bhubaneswar – 751 030, Odisha, India
3. District Institute of Education and Training (DIET), Bhadrak, Agarpada – 756 115, Odisha, India
4. Utkal University, Department of Geology, Vanivihar, Bhubaneswar – 751 004, Odisha, India


In the current situation, traffic noise and annoyance are a matter of concern. The current study aimed to predict annoyance levels using artificial neural network (ANN) multi-layer perceptron network (MLPN) by adding five parameters, such as hours of noise exposure, qualifications, marital status and age of the respondents. This study included 60 persons (30 men and 30 women). The best ANN model was chosen by comparing the mean square error and root mean square error values of 2500 different architectures (500 architectures for each neuron, that is 1-5) with constant input, output and hidden layers with varying neurons (1-5). The architecture of the best model was ‘5 inputs®1 hidden layer (5 neurons) ® 1 output’ with minimum MSE (0.014658) and RMSE (0.12107) values. The model’s performance was determined by its relative error, which was 0.198. Hours of exposure were shown to be the most important predictor of annoyance, with a score of 0.467, followed by qualification with a score of 0.418, while age was found to be the least important predictor. According to the correlation analysis, there was a high positive link between annoyance and hours, with a Pearson correlation value of 0.758, followed by qualifications, with a Pearson correlation value of 0.669.


Annoyance, Artificial neural network, Multi-layer perceptron, Mean square error, Root mean square error


  1. Fyhri, A. and R. Klaeboe. 2009. Road traffic noise, sensitivity, annoyance and self-reported health-A structural equation model exercise. Env. Int., 35(1):91-97. DOI:10.1016/j.envint.2008.08.006.
  2. Das, P., et al. 2019. Noise mapping and assessing vulnerability in meso-level urban environment of eastern India. Sustain. Cities Soc., 46:101416. DOI:101016/j.scs.2019.01.001.
  3. Basner, M., et al. 2014. Auditory and non-auditory effects of noise on health. Lancet. 383 (9925): 1325-1332. DOI:10.1016/S0140-6736 (13)6163-X.
  4. WHO. 2011. Burden of disease from environmental noise : Quantification of healthy life years lost in Europe. World Health Organization and European Commission.
  5. Laszio, H.E., et al. 2012. Annoyance and other reaction measures to changes in noise exposure-A review. Sci. Total Env., 435-436:551-562. DOI:10. 1016/j.scitotenv.2012.06.112.
  6. Okokon, E.O., et al. 2018. Traffic noise annoyance and psychotropic medication use. Env. Int., 119 (July):287-294. DOI:10.1016/j.envint.2018.06. 034.
  7. Guski, R., D. Schrenckenberg and R. Schuemer. 2017. WHO environmental noise guidelines for the European region : A systematic review on environmental noise and annoyance. Int. J. Env. Res. Public Health. 14(12):1-39. DOI:10.3390/ijerph 14121539.
  8. Alimohammadi, I., et al. 2010. Factors affecting road traffic noise annoyance among white collar employees working in Tehran. J. Env. Health Sci. Eng., 7(1):25-34.
  9. Miedema, H.M.E. and H. Vos. 1999. Demographic and attitudinal factors that modify annoyance from transportation noise. J. Acoustical Soc. America. 105(6):3336-3344. DOI:10.1021/1.424662.
  10. Babisch, W. and K. I. Van. 2009. Exposure-response relationship of the association between aircraft noise and the risk of hypertension. Noise Health. 11(44):161-168. DOI:2009/11/44/161/53363.
  11. Kjellberg, A., et al. 1996. The effects of non-physical noise characteristics, ongoing task and noise sensitivity on annoyance and distraction due to noise at work. J. Env. Psychol., 16(2):123-136. DOI:10.1006/jevp. 1996.0010.
  12. Job, R.F.S. 1988. Community response to noise : A review of factors influencing the relationship between noise exposure and reaction. J. Acoustical Soc. America. 83(3):991-1001. DOI:10.1121/1.396524.
  13. Karandagh, S.T., et al. 2021. Association between noise annyoyance and socio-economic status of the employees in an electrical panel manufacturer. Appl. Acoustics. 176:107889. DOI:10.1016/j.apacoust.2020.107889.
  14. Jensen, H.A.R., B. Rasmussen and O. Ekholm. 2018. Neighbour and traffic noise annoyance : A nationwide study of associated mental health and perceived stress. European J. Public Health. 28(6):1050-1055. DOI:10.1093/eurpub /cky.091.
  15. Hew, J.J., et al. 2018. Mobile social tourism shopping : A dual-stage analysis of a multi-mediation model. Tourism Manage., 66:121-139. DOI: 10.1016/j.tourman. 2017.10.005.
  16. Genaro, N., et al. 2010. A neural network based model for urban noise predication. J. Acoustical Soc. America. 128(4):1738-1746. DOI: 10.1021/1.3473692.
  17. Huang, B., et al. 2017. Acoustic amenity analysis for high-rise building along urban expressway : Modelling traffic noise vertical propagation using neural networks. Transportation Res. Part D. Tan-sport Env., 53:63-77. DOI:10.1016/j.trd.2017. 04.001.
  18. Kumar, R. 2017. Padayatras and the changing nature of political communication in India. Studies Indian Politics. 5(1):32-41. DOI:10.1177/2321023017698258.
  19. Le, D.C., J. Zhang and Y. Pang. 2018. A bilinear functional link artificial neural network filter for non-linear active noise control and its stability condition. Appl. Acoustics. 132:19-25. DOI: 10.1016/j.apacoust.2017.10.023.
  20. Leong, L., et al. 2020. Predicting mobile wallet resistance : A two-staged structural equation modelling-artifical neural network approach. Int. J. Inf. Manage., 51(November):102047. DOI:10.1016/j.ijinfomgt.2019.102047.
  21. Moghadam, S.M.K., et al. 2021. Modelling effect of five big personality traits on noise sensitivity and annoyance. Appl. Acoustics. 172:107655. DOI:10.1016/j.apacoust.2020.107655.
  22. Steinbach, L. and M.E. Altinsoy. 2019. Prediction of annoyance evaluations of electric vehicle noise by using artificial neural networks. Appl. Acoustics. 145:149-158. DOI:10.1016/j.apacoust.2018. 09.024.
  23. Arora, J.K. and P.V. Mosahari. 2012. Artifical neural network modelling of traffic noise in Agra-Firozabad highway. Int. J. Computer Applications. 56(2):6-10. DOI:10.5120/8861-2824.
  24. ISO/TS 15666. 2003. Acoustics-Assessment of noise annoyance by means of social and socio-acoustic surveys (revised ISO/TS 15666:2021). International Organization for Standardization, Switzerland.
  25. Negnevitsky, M. 2011. Artificial intelligence : A guide to intelligent systems (3rd edn). Pearson Education, England.
  26. Hew, T.S. and S.L. Sharifah. 2017. Applying channel expansion and self determination theory in predicting use behaviour of cloud-based VLE. Behaviour Inf. Tech., 36(9):875-896. DOI:10.1080/0144 4929x.2017.1307450.
  27. Tian, Z., et al. 2015. Hybrid ANN-PLS approach to scroll compressor thermodynamic performance prediction. Appl. Thermal Eng., 77:113-120. DOI: 10.1016/j.applthermaleng.2014.12.023.
  28. IBM. 2012. IBM SPSS neural networks : New tools for building predictive models. IBM Software. Available at :
  29. Givargis, S. and H. Karimi. 2010. A basic neural traffic noise prediction model for Tehran’s roads. J. Env. Manage., 91(12):2529-2534. DOI:10. 1016/j.jenvman.2010.07.011.
  30. Neill, S.P. and M.R. Hashemi. 2018. Ocean modelling for resource characterization (chapter 8). In Fundamentals of ocean renewable energy. pp 193-235. DOI:10.1016/b978-0-12-810448-4.00008-2.
  31. Paunovic, K., B. Jakovljevic and G. Belojevic. 2008. The importance of non-acoustical factors on noise annoyance of urban residents. 9th International Congress on Noise as a Public health problem (ICBEN), ISO 1982. Proceedings, pp 684-687.
  32. Waye, K.P., et al. 2002. Low frequency noise enhances cortisol among noise sensitive subjects during work performance. Life Sci., 70(7):745-758. DOI:10.1016/S0024-3205(01)01450-3.
  33. Shabani, F., et al. 2020. The study of effect of educational intervention on noise annoyance among workers in a textile industry. Appl. Acoustics. 170:107515. DOI:10.1016/j.apacoust.2020. 107515.
  34. Wallenius, M.A. 2004. The interaction of noise stress and personal project stress on subjective health. J. Env. Psychol., 24(2):167-177. DOI:10. 1016/j.jenvp. 2003.12.002.
  35. El Idrissi, T., A. Idri and Z. Bakkoury. 2019. Systematic map and review of predictive techniques is diabetes self-management. Int. J. Inf. Manage., 46 (September): 263-277. DOI:10.1016/j.ijin fomgt. 2018.09.011.
  36. Ooi, K.B. and G.W.H. Tan. 2016. Mobile technology acceptance model : An investigation using mobile users to explore smartphone credit card. Expert Systems Applications. 59:33-46. DOI:10. 1016/j.eswa.2016.04.015.
  37. Nilsson, M.E. 2007. A weighted sound pressure level as an indicator of short-term loudness or annoyance of road-traffic sound. J. Sound Vibration. 302(1-2):197-207. DOI:10.1016/j.jsv. 2006.11. 010.
  38. Conger, R.D., K.J. Conger and M.J. Martin. 2010. Socio-economic status, family process and individual development. J. Marriage Family. 72(3):685-704. DOI:10.1111/j.1741-3737.2010.00725.x.
  39. Ma, J., et al. 2020. Assessing personal noise exposure and its relationship with mental health in Beijing based on individuals space-time behaviour. Env. Int., 139 (May):105737. DOI:10.1016/j.envint.2020.105737.