Design of Audio-Based Accident and Crime Detection and Its Optimization

Afis Pratama - Politeknik Elektronika Negeri Surabaya, Surabaya, Indonesia
Sritrusta Sukaridhoto - Politeknik Elektronika Negeri Surabaya, Surabaya, Indonesia
Mauridhi Purnomo - Institut Teknologi Sepuluh Nopember, Surabaya, Indonesia
Vita Lystianingrum - Institut Teknologi Sepuluh Nopember, Surabaya, Indonesia
Rizqi Budiarti - Universitas Nahdlatul Ulama Surabaya, Surabaya, Indonesia


Citation Format:



DOI: http://dx.doi.org/10.30630/joiv.7.1.1643

Abstract


The development of transportation technology is increasing every day; it impacts the number of transportation and their users. The increase positively impacts the economy's growth but also has a negative impact, such as accidents and crime on the highway. In 2018, the number of accidents in Indonesia reached 109,215 cases, with a death rate of 29,472 people, which was mostly caused by the late treatment of the casualties. On the other hand, in the same year, there were 8,423 mugs, and 90,757 snitches cases in Indonesia, with only 23.99% of cases reported. This low reporting rate is mostly caused by the lack of awareness and knowledge about where to report. Therefore, a quick response surveillance system is needed. In this study, an audio-based accident and crime detection system was built using a neural network. To improve the system's robustness, we enhance our dataset by mixing it with certain noises which likely to occur on the road. The system was tested with several parameters of segment duration, bandpass filter cut-off frequency, feature extraction, architecture, and threshold values to obtain optimal accuracy and performance. Based on the test, the best accuracy was obtained by convolutional neural network architecture using 200ms segment duration, 0.5 overlap ratio, 100Hz and 12000Hz as bandpass cut-off frequency, and a threshold value of 0.9. By using mentioned parameters, our system gives 93.337% accuracy. In the future, we hope to implement this system in a real environment.


Keywords


Audio recognition; dataset manipulation; optimization; neural networks; surveillance system.

Full Text:

PDF

References


B. van de Walle and M. Turoff, “Decision Support for Emergency Situations,†Handb. Decis. Support Syst. 2, pp. 39–63, 2008, doi: 10.1007/978-3-540-48716-6_3.

J. Radianti, S. G. Martinez, B. E. Munkvold, and M. Konnestad, “Co-Designing a Virtual Training Tool for Emergency Management,†no. May, 2018.

F. L. Munthe, N. Sinaga, and B. Yunianto, “Perancangan dan Pembuatan Sistem Akuisisi Data Dinamometer Sasis Sepeda Motor Berbasis Labview serta Pengujiannya pada Sepeda Motor Honda Beat FI 110 CC,†J. Tek. MESIN, vol. 10, no. 1, pp. 69–78, 2018.

A. Mahfuzhon and G. E. Setyawan, “Rancang Bangun Alat Pendeteksi Kecelakaan Mobil Menggunakan Sensor Akselerometer dan Sensor 801s Vibration,†J. Pengemb. Teknol. Inf. dan Ilmu Komput. Univ. Brawijaya, 2018.

Y. Ryandi and N. L. P. S. E. Setyarini, “Evaluasi Ruas Jalan Gatot Subroto Menggunakan Metode Irap Untuk Mencapai Star Rating 4 Dan 5,†JMTS J. Mitra Tek. Sipil, vol. 4, no. 3, p. 777, 2021, doi: 10.24912/jmts.v0i0.12649.

N. Kattukkaran, A. George, and T. P. M. Haridas, “Intelligent accident detection and alert system for emergency medical assistance,†2017, doi: 10.1109/ICCCI.2017.8117791.

Badan Pusat Statistik, Statistik Kriminal 2019. 2019.

M. Sammarco and M. Detyniecki, “Crashzam: Sound-based car crash detection,†2018, doi: 10.5220/0006629200270035.

R. C. Gatto and C. H. Q. Forster, “Audio-Based Machine Learning Model for Traffic Congestion Detection,†IEEE Trans. Intell. Transp. Syst., pp. 1–8, 2020, doi: 10.1109/tits.2020.3003111.

R. K. Kodali and S. Sahu, “MQTT based vehicle accident detection and alert system,†Proc. 2017 3rd Int. Conf. Appl. Theor. Comput. Commun. Technol. iCATccT 2017, pp. 186–189, 2018, doi: 10.1109/ICATCCT.2017.8389130.

Y. Arslan and H. Canbolat, “Performance of deep neural networks in audio surveillance,†2018, doi: 10.1109/CEIT.2018.8751822.

P. Foggia, N. Petkov, A. Saggese, N. Strisciuglio, and M. Vento, “Audio surveillance of roads: A system for detecting anomalous sounds,†IEEE Trans. Intell. Transp. Syst., 2016, doi: 10.1109/TITS.2015.2470216.

R. Leiba, F. Ollivier, R. Marchiano, N. Misdariis, J. Marchal, and P. Challande, “Acoustical classification of the urban road traffic with large arrays of microphones,†Acta Acust. united with Acust., vol. 105, no. 6, 2019, doi: 10.3813/AAA.919387.

S. Chandrakala and S. L. Jayalakshmi, “Environmental Audio Scene and Sound Event Recognition for Autonomous Surveillance,†ACM Comput. Surv., vol. 52, no. 3, pp. 1–34, 2020, doi: 10.1145/3322240.

N. Almaadeed, M. Asim, S. Al-Maadeed, A. Bouridane, and A. Beghdadi, “Automatic detection and classification of audio events for road surveillance applications,†Sensors (Switzerland), 2018, doi: 10.3390/s18061858.

H. H. Pour et al., “A Machine Learning Framework for Automated Accident Detection Based on Multimodal Sensors in Cars,†Sensors, vol. 22, no. 10, pp. 1–21, 2022, doi: 10.3390/s22103634.

A. Bonyar et al., “A review on current eCall systems for autonomous car accident detection,†Proc. Int. Spring Semin. Electron. Technol., 2017, doi: 10.1109/ISSE.2017.8000985.

M. Muthuvel, M. Marimuthu, S. Nivetha, and K. Sirushti, “Accident Detection and Reporting System using Internet of Things Biometrics View project Internet of Things View project Accident Detection and Reporting System using Internet of Things,†Res. J. Sci. Eng. Syst., vol. 3, no. 2, pp. 121–130, 2018, [Online]. Available: www.rjsces.com.

J. Salamon, C. Jacoby, and J. P. Bello, “A dataset and taxonomy for urban sound research,†2014, doi: 10.1145/2647868.2655045.

K. J. Piczak, “ESC: Dataset for environmental sound classification,†MM 2015 - Proc. 2015 ACM Multimed. Conf., pp. 1015–1018, Oct. 2015, doi: 10.1145/2733373.2806390.

I. Trowitzsch, J. Taghia, Y. Kashef, and K. Obermayer, “The NIGENS General Sound Events Database,†Feb. 2019, doi: 10.5281/zenodo.2535878.

Q. Zhou et al., “Cough Recognition Based on Mel-Spectrogram and Convolutional Neural Network,†Front. Robot. AI, vol. 8, no. May, pp. 1–7, 2021, doi: 10.3389/frobt.2021.580080.

I. Tsiamas, G. I. Gállego, J. A. R. Fonollosa, and M. R. Costa-Jussà , “SHAS: Approaching optimal Segmentation for End-to-End Speech Translation,†Proc. Annu. Conf. Int. Speech Commun. Assoc. INTERSPEECH, vol. 2022-September, pp. 106–110, 2022, doi: 10.21437/Interspeech.2022-59.

S. Sahoo, P. Kumar, B. Raman, and P. P. Roy, “A Segment Level Approach to Speech Emotion Recognition Using Transfer Learning,†2020, doi: 10.1007/978-3-030-41299-9_34.

H. Yakura and J. Sakuma, “Robust audio adversarial example for a physical attack,†IJCAI Int. Jt. Conf. Artif. Intell., vol. 2019-August, pp. 5334–5341, 2019, doi: 10.24963/ijcai.2019/741.

J. B. Allen, “Short Term Spectral Analysis, Synthesis, and Modification by Discrete Fourier Transform,†IEEE Trans. Acoust., vol. 25, no. 3, pp. 235–238, 1977, doi: 10.1109/TASSP.1977.1162950.

G. Rybak and K. Strzecha, “Shortâ€time fourier transform based on metaprogramming and the stockham optimization method,†Sensors, vol. 21, no. 12, 2021, doi: 10.3390/s21124123.

T. Tran and J. Lundgren, “Drill fault diagnosis based on the scalogram and MEL spectrogram of sound signals using artificial intelligence,†IEEE Access, vol. 8, pp. 203655–203666, 2020, doi: 10.1109/ACCESS.2020.3036769.

Y. Lecun, Y. Bengio, and G. Hinton, “Deep learning,†Nature, vol. 521, no. 7553, pp. 436–444, 2015, doi: 10.1038/nature14539.

L. H. Iksan, M. I. Awal, R. Z. Fhamy, A. A. Pratama, D. K. Basuki, and S. Sukaridhoto, “Implementation of Cloud Based Action Recognition Backend Platform,†AIMS 2021 - Int. Conf. Artif. Intell. Mechatronics Syst., 2021, doi: 10.1109/AIMS52415.2021.9466068.