AI-Empowered Software Integrated with Mobile Technology to Detect Harmful Noise
DOI:
https://doi.org/10.58197/8y8s9d32Abstract
Harmful noise is a prevalent and growing health concern worldwide, affecting millions due to prolonged exposure to excessive noise levels. Traditional hearing protection methods, such as hearing aids and cochlear implants, have limitations regarding accessibility, scalability, and effectiveness. In Rwanda, the effects of hazardous noise levels are increasingly apparent, particularly in urban areas and during musical concerts, where excessively loud environments are common. Musicians and concert attendees frequently experience high decibel levels, significantly increasing their risk of hearing impairment. This research proposes an innovative solution utilizing AI-powered software integrated with mobile technology to detect and mitigate harmful noise. The software continuously monitors environmental noise in real time, identifying hazardous sound levels and providing personalized recommendations to users to prevent hearing damage. The development process involves data collection from various audio sources, preprocessing, model training using machine learning techniques, and seamless integration into a user-friendly mobile application. Preliminary results indicate a high accuracy of the AI model in detecting dangerous noise levels and offering actionable feedback. This solution aims to enhance auditory health by making hearing protection more accessible, proactive, and effective for diverse populations. Ethical considerations, including data privacy and bias mitigation, are rigorously addressed to ensure the software's integrity and foster user trust.
References
W. H. O. (WHO), " "Deafness and hearing loss.," no. Available at: https://www.who.int/news-room/fact-sheets/detail/deafness-and-hearing-loss (Accessed: 29 May 2024).,," 2018..
W. H. O. (WHO), ""Prevention of deafness and hearing loss.," no. Available at: https://www.who.int/news-room/fact-sheets/detail/deafness-and-hearing-loss (Accessed: 29 May 2024).,," (2017) . .
W. H. O. (WHO), ""World report on hearing. Available at: https://www.who.int/publications/i/item/world-report-on-hearing (Accessed: 29 May 2024).,"," (2020) . .
M. &. S. K. Svanberg, . AI for Urban Noise Management. Journal of Environmental Management, 250, 109500. DOI: 10.1016/j.jenvman.2019.109500., (2020).
A. &. V. K. I. Brown, "The Role of Local Governments in Urban Noise Management: Case Studies from Europe. Noise & Health, 19(87), 114-122. DOI: 10.4103/nah.NAH_59_15.," (2017). .
Y. &. W. L. Zhang, "Machine Learning Techniques for Sound Classification: A Review. IEEE Access, 7, 23415-23429. DOI: 10.1109/ACCESS.2019.2892334.," (2019). .
H. &. K. S. Park, "Wearable Devices for Real-Time Noise Exposure Assessment. Sensors, 20(15), 4295. DOI: 10.3390/s20154295.," (2020). .
J. O. Smith, "Introduction to Digital Filters: With Audio Applications. 3rd edn. San Francisco: W3K Publishing,," (2018)..
I. B. Y. a. C. A. Goodfellow, " "Deep Learning. Cambridge: MIT Press.,"," (2016) .
[13] G. e. a. Pouryaghoub, "Noise-Induced hearing loss among professional musicians.," Journal of Occupational Health. [Online] 59 (1), 33–37., , (2017) ..
H. H. A. a. A. A. Hafezi, " "‘Real-time noise monitoring and hearing protection using IoT and AI’, Journal of Environmental Health Science and Engineering, 20, pp. 567-578. doi: 10.1007/s40201-022-00789-5.,"," (2022) . .
B. B. F. J. J. D. J. L. a. G. E. N. Blanchfield, "The severely to profoundly hearing-impaired population in the United States: Prevalence estimates and demographics’,," Journal of the American Academy of Audiology, 12(4), pp. 183, (2018) .
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Catholic University Multidisciplinary Journal
This work is licensed under a Creative Commons Attribution 4.0 International License.
