Ambulance Siren Detection using Artificial Intelligence in Urban Scenarios

Muhammad Usaid; Muhammad Asif; Tabarka Rajab; Munaf Rashid; Syeda Iqra Hassan

Authors

Muhammad Usaid Data Acquisition, Processing & Predictive Analytics Lab, NCBC
Muhammad Asif
Tabarka Rajab
Munaf Rashid
Syeda Iqra Hassan

Keywords:

Artificial Intelligence, Acoustic Monitoring, Deep Learning, Emergency Vehicle Siren, Multilayer Perceptron,

Abstract

Traffic density is growing day by day due to the increasing population and affordable prices of cars. It created a void for traffic management systems to cope with traffic congestion and prioritize ambulances. The consequences can be a terrible situation. Emergency vehicles are the most affected in these situations, and inadequate traffic control can put many lives at stake. Ambulances on the road are detected using an acoustic-based Artificial Intelligence system in this article. Emergency vehicle siren and road noise datasets have been developed for ambulance acoustic monitoring. The dataset is developed along with a deep learning (MLP-based) model and trained to use audio monitoring to predict the ambulance presence on the roads. This model achieved 90% accuracy when trained and validated against a developed dataset of only 300 files. With this validated algorithm, researchers can develop a real-time hardware-based model to detect emergency vehicles and make them arrive at the hospital as soon as possible.

References

Becker, L. R., Zaloshnja, E., Levick, N., Li, G., & Miller, T. R. (2003). The relative risk of injury and death in ambulances and other emergency vehicles. Accident Analysis & Prevention, 35(6), 941948.

Foggia, P., Petkov, N., Saggese, A., Strisciuglio, N., & Vento, M. (2015). Audio surveillance of roads: A system for detecting abnormal sounds. IEEE transactions on intelligent transportation systems, 17(1), 279-288.

World Health Organization. (2018). World health statistics 2018: monitoring health for the SDGs, sustainable development goals. World Health Organization.

Liaw, J. J., Wang, W. S., Chu, H. C., Huang, M. S., & Lu, C. P. (2013, October). Recognition of the ambulance siren sound in Taiwan by the longest common subsequence. In 2013 IEEE International Conference on Systems, Man, and Cybernetics (pp. 3825-3828). IEEE.

Beritelli, F., Casale, S., Russo, A., & Serrano, S. (2006, September). An automatic emergency signal recognition system for the hearing impaired. In 2006 IEEE 12th Digital Signal Processing Workshop & 4th IEEE Signal Processing Education Workshop (pp. 179-182). IEEE.

Milner, B., & Shao, X. (2006). Clean speech reconstruction from MFCC vectors and fundamental frequency using an integrated front-end. Speech Communication, 48(6), 697-715.

Rabiner, L., & Juang, B. H. (1993). Fundamentals of speech recognition. Prentice-Hall, Inc...

Jain, A. K., Mao, J., & Mohiuddin, K. M. (1996). Artificial neural networks: A tutorial. Computer, 29(3), 31-44.

Li, F. F., & Cox, T. J. (2003). Speech transmission index from running speech: A neural network approach. The Journal of the Acoustical Society of America, 113(4), 1999-2008.

Vapnik, V. N. (1999). An overview of statistical learning theory. IEEE transactions on neural networks, 10(5), 988-999.

Dobre, R. A., Negrescu, C., & Stanomir, D. (2017, October). An improved low computational method for siren detection. In 2017 IEEE 23rd International Symposium for Design and Technology in Electronic Packaging (SIITME) (pp. 318-323). IEEE.

Fatimah, B., Preethi, A., Hrushikesh, V., Singh, A., & Kotion, H. R. (2020, July). An automatic siren detection algorithm using Fourier Decomposition Method and MFCC. In 2020 11th International Conference on Computing, Communication and Networking Technologies (ICCCNT) (pp. 1-6). IEEE.

Alibaba.com .(2022). ISO 9001 CE ECE IP68 certificated! P8 S 300W Wireless remote control federal Signal siren ambulance siren for sale. Retrieved From: https://www.alibaba.com/productdetail/ISO-9001-CE-ECE-IP68-certificated_60718161325.html [15] etsnm.com. (2022). Etsnm ML-1 Microphone. Retrieved From:

https://www.etsnm.com/ML1-DOCS/ml1-ws.pdf.