Destek vektör makinesi ve kenar bilişim ile güçlendirilmiş gerçek zamanlı ambulans sireni algılama sistemi

Yıl 2025, Cilt: 40 Sayı: 2, 1147 - 1158

Yeliz Durgun , Mahmut Durgun

https://doi.org/10.17341/gazimmfd.1416188

Öz

Bu çalışma, trafik ortamlarında ambulans sirenlerinin tespiti için geliştirilen ve Polinom Destek Vektör Makinesi (SVM) algoritmasını temel alan bir ses sınıflandırma modelini sunmaktadır. Kenar bilişim teknolojilerini kullanarak gerçekleştirilen örnek toplama deneyleriyle desteklenen bu çalışma, gerçek zamanlı veri işleme ve gömülü sistemlerde kullanılmak üzere tasarlanmıştır. Model, trafik sesleri ve ambulans sirenleri arasında etkili bir ayrım yapabilme kapasitesine sahiptir. UMAP ve PCA analizleri, modelin yüksek boyutlu verileri düşük boyutlu uzaylarda başarılı bir şekilde işleyebildiğini ve farklı ses sınıflarını net bir şekilde ayırt edebildiğini göstermektedir. Confusion Matrix, çapraz doğrulama sonuçları ve öğrenme eğrisi, modelin hem eğitim hem de doğrulama setleri üzerinde yüksek doğruluk oranlarına ulaştığını ve tutarlı bir performans sergilediğini belirtmektedir. ROC Eğrisi ve F1 Skoru, modelin genel sınıflandırma başarısının yüksek olduğunu gösterirken, düşük bellek ve işlemci gereksinimleri modelin gömülü sistemlerde ve gerçek zamanlı uygulamalarda etkin bir şekilde çalışabileceğinin altını çizmektedir. Bu çalışmanın sonuçları, ambulans sirenlerinin tespiti ve genel trafik seslerinin sınıflandırılması alanında, kenar bilişim tabanlı gömülü sistemlerin ve gerçek zamanlı veri işlemenin önemli bir adım olduğunu göstermektedir. Modelin daha da geliştirilmesi ve çeşitli uygulama senaryolarına adapte edilmesi için gelecekteki çalışmalar büyük önem taşımaktadır.

Anahtar Kelimeler

Ambulans Siren Tespiti, Kenar Bilişim, Ses Sınıflandırma, Gömülü Sistemler, Polinom Destek Vektör Makinesi (SVM)

Support vector machine and edge computing enhanced real-time ambulance siren detection system

Öz

This study presents a sound classification model developed for the detection of ambulance sirens in traffic environments, based on the Polynomial Support Vector Machine (SVM) algorithm. Supported by sample collection experiments conducted using edge computing technologies, this work is designed for real-time data processing and use in embedded systems. The model has the capacity to effectively distinguish between traffic sounds and ambulance sirens. UMAP and PCA analyses demonstrate that the model can successfully process high-dimensional data in low-dimensional spaces and clearly differentiate between different sound classes. The Confusion Matrix, cross-validation results, and learning curve indicate that the model achieves high accuracy rates on both training and validation sets, exhibiting consistent performance. The ROC Curve and F1 Score show the model's overall high classification success, while its low memory and processor requirements underline its effectiveness in embedded systems and real-time applications. The results of this study highlight the significance of edge computing-based embedded systems and real-time data processing in the detection of ambulance sirens and the classification of general traffic sounds. Future work for further development of the model and its adaptation to various application scenarios is of great importance.

Anahtar Kelimeler

Ambulance Siren Detection, Edge Computing, Sound Classification, Embedded Systems, Polynomial Support Vector Machine (SVM)

Kaynakça

• 1. Buchanan, C.,Traffic in Towns: A study of the long term problems of traffic in urban areas, Routledge, 2015.
• 2. Ziegler, E.H.,The case for megapolitan growth management in the twenty‐first century: Regional urban planning and sustainable development in the USA, International Journal of Law in the Built Environment, 1 (2), 105–129, 2009.
• 3. Nellore, K., Hancke, G.P., A survey on urban traffic management system using wireless sensor networks, Sensors, 16 (2), 157, 2016.
• 4. Kaygisiz, Ö., Senbil, M., Yildiz, A.,Influence of urban built environment on traffic accidents: The case of Eskisehir (Turkey), Case studies on transport policy, 5 (2), 306–313, 2017.
• 5. TC Sağlık Bakanlığı,Yaşama Yol Ver, https://acilafet.saglik.gov.tr/TR-4647/yasama-yol-ver.html, Erişim: 2024.
• 6. Bhagchandani, K., Augustine, D.P.,IoT based heart monitoring and alerting system with cloud computing and managing the traffic for an ambulance in India, International Journal of Electrical and Computer Engineering, 9 (6), 5068, 2019.
• 7. Nallamothu, B.K., Bates, E.R., Wang, Y., Bradley, E.H., Krumholz, H.M.,Driving times and distances to hospitals with percutaneous coronary intervention in the United States: implications for prehospital triage of patients with ST-elevation myocardial infarction, Circulation, 113 (9), 1189–1195, 2006.
• 8. Avatefipour, O., Sadry, F.,Traffic management system using IoT technology-A comparative review, Içinde, 2018 IEEE International Conference on Electro/Information Technology (EIT), 1041–1047. IEEE, 2018.
• 9. Papageorgiou, M., Ben-Akiva, M., Bottom, J., Bovy, P.H.L., Hoogendoorn, S.P., Hounsell, N.B., Kotsialos, A., McDonald, M.,ITS and traffic management, Handbooks in operations research and management science, 14, 715-774, 2007.
• 10. Özcan Tatar C., Yılmaz E., Efe A., Sönmez B., Özdemir Y., Danışan B., Beyaz H.İ., Yegnidemir E., Mobilenet based traffic sign detection system for mobile mapping: Crowdsourced geographical data collection system, Journal of the Faculty of Engineering and Architecture of Gazi University, 39 (4), 2305–2315, 2024.
• 11. Roy, S., Bandyopadhyay, S., Das, M., Batabyal, S., Pal, S.,Real time traffic congestion detection and management using Active RFID and GSM technology, ITSC, Kyoto, Japan, 48, 2010.
• 12. Garcia Oya, J.R., Martín Clemente, R., Hidalgo Fort, E., González Carvajal, R., Muñoz Chavero, F.,Passive RFID-based inventory of traffic signs on roads and urban environments, Sensors, 18 (7), 2385, 2018.
• 13. Qin, H., Chen, W., Chen, W., Li, N., Zeng, M., Peng, Y.,A collision-aware mobile tag reading algorithm for RFID-based vehicle localization, Computer Networks, 199, 108422, 2021.
• 14. Bell, M.G.H.,Future directions in traffic signal control, Transportation Research Part A: Policy and Practice, 26 (4), 303–313, 1992.
• 15. Buchenscheit, A., Schaub, F., Kargl, F., Weber, M.,A VANET-based emergency vehicle warning system, Içinde, 2009 IEEE Vehicular Networking Conference (VNC), 1–8, IEEE, 2009.
• 16. Choudhury, K., Nandi, D.,Review of Emergency Vehicle Detection Techniques by Acoustic Signals, Transactions of the Indian National Academy of Engineering, 8 (4), 535–550, 2023.
• 17. Chandra, A., Singh, G.,Various Acoustic-Based Emergency Vehicle Detection Techniques: A Review, Içinde, 2023 2nd International Conference on Computational Modelling, Simulation and Optimization (ICCMSO), ss. 107–113. IEEE ,2023.
• 18. Chen, S., Wen, H., Wu, J.,Artificial Intelligence Based Traffic Control for Edge Computing Assisted Vehicle Networks, Journal of Internet Technology, 23 (5), 989–996, 2022.
• 19. Durgun, M.,An Acoustic Bird Repellent System Leveraging Edge Computing and Machine Learning Technologies, Içinde, 2023 Innovations in Intelligent Systems and Applications Conference (ASYU), 1–8, IEEE, 2023.
• 20. Pan, J., McElhannon, J.,Future edge cloud and edge computing for internet of things applications, IEEE Internet of Things Journal, 5 (1), 439–449, 2017.
• 21. Hong, C.-H., Varghese, B.,Resource management in fog/edge computing: a survey on architectures, infrastructure, and algorithms, ACM Computing Surveys (CSUR), 52 (5), 1–37, 2019.
• 22. Wan, S., Ding, S., Chen, C.,Edge computing enabled video segmentation for real-time traffic monitoring in internet of vehicles, Pattern Recognition, 121 108146, 2022.
• 23. Ning, Z., Huang, J., Wang, X.,Vehicular fog computing: Enabling real-time traffic management for smart cities, IEEE Wireless Communications, 26 (1), 87–93, 2019.
• 24. Gökdemr A., Çalhan A., Deep learning and machine learning based anomaly detection in internet of things environments, Journal of the Faculty of Engineering and Architecture of Gazi University, 37 (4), 1945–1956, 2022.
• 25. Durgun, Y.,Air Pollution Assessment in Turhal District: Temporal Analysis of Pollutants, International Scientific and Vocational Studies Journal, 7 (2), 161–169, 2023.
• 26. Deepa, R.,A role of an edge computing technologies for the internet of things in smart cities, Turkish Journal of Computer and Mathematics Education (TURCOMAT), 12 (9), 1321–1330, 2021.
• 27. Liu, Y., Peng, M., Shou, G., Chen, Y., Chen, S.,Toward edge intelligence: Multiaccess edge computing for 5G and Internet of Things, IEEE Internet of Things Journal, 7 (8), 6722–6747, 2020.
• 28. Meshur, H.F.A.,Understanding Smart City Solutions in Turkish Cities From the Perspective of Sustainability, Içinde, Smart Grid Analytics for Sustainability and Urbanization, 236–266. IGI Global, 2018.
• 29. Babalik-Sutcliffe, E., Cengiz, E.C.,Bus rapid transit system in Istanbul: a success story or flawed planning decision?, Transport Reviews, 35 (6), 792–813, 2015.
• 30. Nellore, K., Hancke, G.P.,Traffic management for emergency vehicle priority based on visual sensing, Sensors, 16 (11), 1892, 2016.
• 31. Carrington, A.M., Manuel, D.G., Fieguth, P.W., Ramsay, T., Osmani, V., Wernly, B., Bennett, C., Hawken, S., McInnes, M., Magwood, O.,Deep ROC analysis and AUC as balanced average accuracy to improve model selection, understanding and interpretation, arXiv preprint arXiv:2103.11357, 2021.
• 32. Chicco, D., Jurman, G.,The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation, BMC genomics, 21 (1), 1–13, 2020.
• 33. Jadhav, P., Sawarkar, S.D., Pete, D.J.,Roadside Acoustic Signals Based Road Traffic Density Estimation, Içinde, 2018 Fourth International Conference on Computing Communication Control and Automation (ICCUBEA), 1–5, 2018.
• 34. Doğan, D., Road-types classification using audio signal processing and SVM method, Içinde, 2017 25th Signal Processing and Communications Applications Conference (SIU), 1–4, 2017.
• 35. Zhongsheng, W., Jiaqiong, G.,A New Method of Improving the Traditional Traffic Identification and Accuracy, International Journal of Advanced Network, Monitoring and Controls, 3 (3), 53–60, 2018.
• 36. Jing, N., Yang, M., Cheng, S., Dong, Q., Xiong, H.,An efficient SVM-based method for multi-class network traffic classification, Içinde, 30th IEEE International Performance Computing and Communications Conference, 1–8, 2011.