Abstract
The growing population in the metropolises is influencing the need to plan cities to be safer for people. Several Smart Cities initiatives are being implemented in the cities to achieve this goal. A network of acoustic sensors has been deployed in New York City thanks to the SONYC project. Sounds of the city are being collected and analyzed. In this research work, acoustic signal data are represented with Mel-spectrogram images with mel-scale frequency versus time on a decibel scale. Traditional autoencoders and variational autoencoder models are deployed to detect anomalies in the mel-spectrogram images. The obtained results demonstrate that the variational autoencoder model finds anomalies accurately in the acoustic records.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Abri, F., Gutiérrez, L.F., Siami Namin, A., Sears, D.R.W., Jones, K.S.: Predicting emotions perceived from sounds. In: 2020 IEEE International Conference on Big Data (Big Data), pp. 2057–2064 (2020)
Agency, E.E.: Noise pollution is a major environmental health concern in Europe (2022). https://www.eea.europa.eu/themes/human/noise. Accessed 30 Apr 2023
Altan, G., Kutlu, Y.: Chapter three - generalization performance of deep autoencoder kernels for identification of abnormalities on electrocardiograms. In: Das, H., Pradhan, C., Dey, N. (eds.) Deep Learning for Data Analytics, pp. 37–62. Academic Press (2020)
Bello, J.P., et al.: SONYC: a system for monitoring, analyzing, and mitigating urban noise pollution. Commun. ACM 62(2), 68–77 (2019)
Camero, A., Alba, E.: Smart city and information technology: a review. Cities 93, 84–94 (2019)
Chandola, V., Banerjee, A., Kumar, V.: Anomaly detection: a survey. ACM Comput. Surv. 41(3), 1–58 (2009)
Ciaburro, G., Iannace, G.: Improving smart cities safety using sound events detection based on deep neural network algorithms. In: Informatics, vol. 7, no. 3 (2020)
Dua, S., et al.: Developing a speech recognition system for recognizing tonal speech signals using a convolutional neural network. Appl. Sci. 12, 6223 (2022)
Ehsani, N., Aminifar, F., Mohsenian-Rad, H.: Convolutional autoencoder anomaly detection and classification based on distribution PMU measurements. IET Gener. Transm. Distrib. 16(14), 2816–2828 (2022)
Kunapuli, S.S., Bhallamudi, P.C.: Chapter 22 - a review of deep learning models for medical diagnosis. In: Machine Learning. Big Data, and IoT for Medical Informatics, pp. 389–404. Academic Press, Intelligent Data-Centric Systems (2021)
Lebrusán, I., Toutouh, J.: Using smart city tools to evaluate the effectiveness of a low emissions zone in Spain: Madrid central. Smart Cities 3(2), 456–478 (2020)
Lerch, A., Knees, P.: Machine learning applied to music/audio signal processing. Electronics 10(24), 3077 (2021)
Librosa: Documentation (2023). https://librosa.org/doc/latest/index.html. Accessed 20 Apr 2023
Murphree, J.: Machine learning anomaly detection in large systems. In: 2016 IEEE AUTOTESTCON, pp. 1–9. IEEE (2016)
Müller, R., Illium, S., Ritz, F., Schmid, K.: Analysis of feature representations for anomalous sound detection. In: Proceedings of the 13th International Conference on Agents and Artificial Intelligence. Science and Technology Publications (2021)
Natsiou, A., O’Leary, S.: Audio representations for deep learning in sound synthesis: a review. 2021 IEEE/ACS 18th International Conference on Computer Systems and Applications (AICCSA), pp. 1–8 (2021)
Pita, A., Rodriguez, F.J., Navarro, J.M.: Cluster analysis of urban acoustic environments on Barcelona sensor network data. Int. J. Environ. Res. Public Health 18(16), 8271 (2021)
Ren, Z., Chang, Y., Bartl-Pokorny, K.D., Pokorny, F.B., Schuller, B.W.: The acoustic dissection of cough: diving into machine listening-based COVID-19 analysis and detection. J. Voice 22 (2022)
Rovetta, S., Mnasri, Z., Masulli, F., Cabri, A.: Anomaly detection based on interval-valued fuzzy sets: application to rare sound event detection. In: WILF. CEUR Workshop Proceedings (2021)
Singh, K.: Anomaly detection and diagnosis in manufacturing systems: a comparative study of statistical, machine learning and deep learning techniques. In: PHM Society, vol. 11 (2019)
(SONYC-UST), S.U.S.T.: A multilabel dataset from an urban acoustic sensor network (2020). https://zenodo.org/record/3966543#.YznJ93ZByUk
Venkatesh, S., Moffat, D., Miranda, E.R.: You only hear once: a YOLO-like algorithm for audio segmentation and sound event detection. Appl. Sci. 12(7), 3293 (2022)
Wang, Y., et al.: Unsupervised anomalous sound detection for machine condition monitoring using classification-based methods. Appl. Sci. 11(23), 11128 (2021)
Wei, Y., Jang-Jaccard, J., Xu, W., Sabrina, F., Camtepe, S., Boulic, M.: LSTM-autoencoder based anomaly detection for indoor air quality time series data (2022)
Zhao, F., Fashola, O.I., Olarewaju, T.I., Onwumere, I.: Smart city research: a holistic and state-of-the-art literature review. Cities 119, 103406 (2021)
Acknowledgements
The authors would like to thank the Spanish Ministry of Science and Innovation for the support under projects PID2020-117954RB-C2 and TED2021-131311B-C22, the European Regional Development Fund and Junta de Andalucía for PY20-00870, P18-RT-2778 and UPO-138516 and the US-Spain Fulbright grant.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Melgar-García, L., Hosseini, M., Troncoso, A. (2023). Identification of Anomalies in Urban Sound Data with Autoencoders. In: García Bringas, P., et al. Hybrid Artificial Intelligent Systems. HAIS 2023. Lecture Notes in Computer Science(), vol 14001. Springer, Cham. https://doi.org/10.1007/978-3-031-40725-3_3
Download citation
DOI: https://doi.org/10.1007/978-3-031-40725-3_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-40724-6
Online ISBN: 978-3-031-40725-3
eBook Packages: Computer ScienceComputer Science (R0)