Search
Abstract
The aim of an autoencoder neural network is to transform the input data into a lower-dimensional code and then to reconstruct the output from this code representation. Applications of autoencoders to classifying sound events in the road traffic have not been found in the literature. The presented research aims to determine whether such an unsupervised learning method may be used for deploying classification algorithms applied to the automatic annotation of road traffic-related events based on noise analysis. Two-dimensional representation of traffic sounds based on Mel Frequency Cepstral Coefficients (MFCC) was fed the autoencoder neural network, and after that classified with k-nearest neighbors algorithm, Support Vector Machines, and random forests. Obtained results show that sound recordings can help determine the number of vehicles passing on the road. However, instead of being treated as independent, this method output should be combined with another source of data, e.g., video processing results or microwave radar data readings. Comparative results of vehicle counting obtained with the use of autoencoder and different classifiers are shown in the paper. [The Polish National Centre finances the project for Research and Development (NCBR) from the European Regional Development Fund No. POIR.04.01.04-00-0089/16 entitled: "INZNAK: Intelligent Road Signs with V2X Interface for Adaptive Traffic Controlling."]
Citations
-
1
CrossRef
-
0
Web of Science
-
0
Scopus
Authors (3)
Cite as
Full text
- Publication version
- Accepted or Published Version
- License
- Copyright (2019 Acoustical Society of America)
Keywords
Details
- Category:
- Articles
- Type:
- artykuły w czasopismach
- Published in:
-
Journal of the Acoustical Society of America
no. 146,
pages 2958 - 2958,
ISSN: 0001-4966 - Language:
- English
- Publication year:
- 2019
- Bibliographic description:
- Czyżewski A., Kurowski A., Zaporowski S.: Application of autoencoder to traffic noise analysis// Journal of the Acoustical Society of America -Vol. 146,iss. 4 (2019), s.2958-2958
- DOI:
- Digital Object Identifier (open in new tab) 10.1121/1.5137275
- Bibliography: test
-
show (15) hide
- X. V. Gonzalez and F. Alías, "Automatic classification of road vehicles considering their pass-by acoustic signature," Proc. Meet. Acoust., vol. 19, 2013.
- K. Marciniuk, B. Kostek, and A. Czyżewski, "Traffic Noise Analysis Applied to Automatic Vehicle Counting and Classification," 2017, pp. 110-123. open in new tab
- M. A. Sobreira-Seoane, A. Rodríguez Molares, and J. L. Alba Castro, "Automatic classification of traffic noise," Proc. -Eur. Conf. Noise Control, no. June, pp. 6221-6226, 2008. open in new tab
- M. A. D, B. S. A, and M. M. H, "Classification of Vehicles Based on Audio Signals using Quadratic Discriminant Analysis and High Energy Feature Vectors," Int. J. Soft Comput., vol. 6, no. 1, pp. 53-64, 2015.
- M. Freitag, S. Amiriparian, S. Pugachevskiy, N. Cummins, and B. Schuller, "auDeep: Unsupervised Learning of Representations from Audio with Deep Recurrent Neural Networks," J. Mach. Learn. Res., vol. 18, 2017.
- J. Chorowski, R. Weiss, S. Bengio, and A. Oord, "Unsupervised Speech Representation Learning Using WaveNet Autoencoders," IEEE/ACM Trans. Audio, Speech, Lang. Process., vol. PP, p. 1, 2019. open in new tab
- F. Li et al., "Feature extraction and classification of heart sound using 1D convolutional neural networks," EURASIP J. Adv. Signal Process., vol. 2019, p. 59, 2019. open in new tab
- J. Kotus and G. Szwoch, "Calibration of acoustic vector sensor based on MEMS microphones for DOA estimation," Appl. Acoust., vol. 141, no. July, pp. 307-321, 2018. open in new tab
- A. Kurowski, K. Marciniuk, and B. Kostek, "Separability Assessment of Selected Types of Vehicle- Associated Noise," in Multimedia and Network Information Systems, 2017, pp. 113-121. open in new tab
- K. Marciniuk, M. Szczodrak, and A. Czyzewski, "An application of acoustic sensors for the monitoring of road traffic," 2018 Signal Process. Algorithms, Archit. Arrange. Appl., pp. 208-212, 2018. open in new tab
- J. Kotus, "Determination of the Vehicles Speed Using Acoustic Vector Sensor," in 2018 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA), 2018, pp. 64-69. open in new tab
- A. Kurowski, A. Czyżewski, and S. Zaporowski, "SPA 2019 Automatic labeling of traffic sound recordings using autoencoder-derived features," pp. 38-43, 2019. open in new tab
- A. Czyżewski, "Free-standing intelligent road sign," 125160, 2019 Polish patent No. W.125160,.
- A. Czyzewski, "Hanging intelligent road sign," 125159, 2019. Polish patent No. W.125159
- N. Buduma and N. Locascio, Fundamentals of Deep Learning: Designing Next-Generation Machine Intelligence Algorithms, 1st ed. O'Reilly Media, Inc., 2017.
- Sources of funding:
- Verified by:
- Gdańsk University of Technology
seen 94 times