Acoustic Fingerprint Recognition Using Artificial Neural Networks

 

Eduardo Zurek^1*, Margarita R. Gamarra², José R. Escorcia³, Carlos Gutierrez⁴, Henry Bayona⁵, Roxana P. Pérez⁶, and Xavier García⁷

 

¹ Universidad del Norte, Department of Systems Engineering, Barranquilla, Colombia. *Corresponding autor (e-mail: ezurek@uninorte.edu.co).

² Universidad Autónoma del Caribe, Department of Electronic and Telecommunication Engineering, IET group, Barranquilla, Colombia. (e-mail: margarita.gamarra@uac.edu.co).

³ Universidad Autónoma del Caribe, Department of Electronic and Telecommunication Engineering, IET group, Barranquilla, Colombia, and with the Escuela Naval de Suboficiales A.R.C. Barranquilla, Colombia. (e-mail: jescorcia@uac.edu.co).

⁴ Escuela Naval de Suboficiales A.R.C. Barranquilla, GITIN group, Barranquilla, Colombia. (e-mail: ing.cagm@gmail.com).

⁵ Escuela Naval de Suboficiales A.R.C. Barranquilla, GITIN group, Barranquilla, Colombia. (e-mail: elektronikesub@gmail.com).

⁶ Escuela Naval de Suboficiales A.R.C. Barranquilla, GITIN group, Barranquilla, Colombia. (e-mail: roxp64@gmail.com).

⁷ Escuela Naval de Suboficiales A.R.C. Barranquilla, GITIN group, Barranquilla, Colombia. (e-mail: xavier.garciah@gmail.com).

 

Manuscript received on August 6, 2014
Accepted for publication on October 2, 2014
Published on November 15, 2014.

 

Abstract

This paper presents an implementation of Artificial Neural Networks (ANN) for acoustic fingerprints recognition, applied to the identification of marine vessels. In many cases, the vessel recognition process from an audible signal is performed by human operators, which could lead to failures in the identification process. Before entering the ANN classification process, the signal is filtered and its spectral characteristics are extracted. A comparison of the classification process between three types of neural networks is presented.

Key words: Acoustic fingerprint, FFT, PCA, ANN, feedforward backpropagation, RBF, PNN.

 

DESCARGAR ARTÍCULO EN FORMATO PDF

 

References

[1] R. J. Urick, Principles of Underwater Sound. New York: McGraw-Hill, 1983.         [ Links ]

[2] C. Regazonni, A. Tesei, and G. Tacconi, "A Comparison Between Spectral and Bispectral Analysis for Ship Detection From Acoustical Tímese R. R. Raories," in IEEE International Conference on Acoustics, Speech and Signl Processing, Adelaide, 1994.         [ Links ]

[3] L. A. Pfiug; G. E. Loup, and P. Jackson, "Variability in Higher Order Statistics of Measured Shallow-water Shippin Noise," in IEEE Signal Processing Workshop on Higher-Order Statistics, Banff, 1997.         [ Links ]

[4] R. H. Baran and J. P. Coughlin, "A Neural Network for Target Classificacion Using Passive Sonar," in Proceedings of the Conf. on Analysis of Neural Networks Application, Assoc. Comput. Mach., 1991.         [ Links ]

[5] A. Hernandez, Implementation de un Algoritmo de Generación de Huella Digital Acústica para el Reconocimeinto de Sonidos, Universidad de la Sierra Juarez, 2013.         [ Links ]

[6] L. Fillinger, A. Hunter, M. Zampolli and M. Clarijs, "Passive acoustic detection of closed-circuit underwater breathing apparatus in an operational port environment," J. Acoust. Soc. Am., 2012.         [ Links ]

[7] W. Soares-Filho, J. M. Seixas, and L. P. Caloba, "Enlarging Neural Class Deetection Capacity in Passive Sonar Systems," in IEEE Int. Symp. on Circuits ans Systems, Scottsdale, 2002.         [ Links ]

[8] K. Eom, M. Wellman, N. Srour, D. Hillis, and R. Chellappa, "Acoustic Target Calssification Using Multscale Methods," in Sensors and Electron Devices Symp., 1997'.         [ Links ]

[9] G. Ogden, M. Zurk, M. Jones, M. Peterson, "Extraction of Small Boat Harmonic Signatures from Passive Sonar," J. Acoust. Soc. Am., 2011.         [ Links ]

[10] J. Meister, "A Neural Network Harmonic Family Classifier," J. Acoust. Soc Am, vol. 93, no. 3, pp. 1488-1495, 1993.         [ Links ]

[11] W. Streilein, P. Gaudiano, and G. Carpenter, "A neural network for object recognition through sonar on a mobile robot," in Proceedings of Intelligent Control (ISIC), held jointly with IEEE International Symposium on Computational Intelligence in Robotics and Automation (CIRA), Intelligent Systems and Semiotics (ISAS), 1998.         [ Links ]

[12] S. Geethalakshmi, P. Subashini, and S. Ramya, "A Study on Detection and Classification of Underwater Mines Using Neural Networks," Int. J. Soft Comput. Eng. IJSCE, vol. 1, no. 5, pp. 150-157, 2006.         [ Links ]

[13] B. Howell, S. Wood, and S. Koksal, "Passive sonar Recognition and analysis using hubrid neural networks," IEEE Oceans, vol. 4, pp. 1917-1924, 2003.         [ Links ]

[14] "Lecture 8. DT Filter Design: IIR Filters," in Discrete-Time Signal Processing, Massachusetts Institute of Technology, 2006.         [ Links ]

[15] E. Zurek, M. Gamarra, J. Escorcia, C. Gutierrez, R. Pérez, X. García, H. Bayona, "Spectral Analysis Techniques for Acoustic Fingerprints Recognition," in 2014 XIX Symposium on Image, Signal Processing and Artificial Vision (STSIVA), IEEE, 2014.         [ Links ]

[16] A. C. Sanabria, C. Predraza, J. Vitola, "Quick Algorithm for Searching Audio by Content on GPUs," Intekhnia, vol. 6, no. 1, pp. 35-13, 2011.         [ Links ]

[17] D. Mitrovic, M. Zeppelzauer, C. Breiteneder, "Features for Contet-Based Audio Retrieval," Adv. Comput, vol. 78, pp. 71-150, 2010.         [ Links ]

[18] Z. Burka, Perceptual Audio Calssification Using Principal Component Analysis, Golisano College of Computing and Information Sciences, Rochester, 2010.         [ Links ]

[19] M. R. Gamarra, C. Quintero, "Using genetic algorithm feature selection in neural classification systems for image pattern recognition,"Ing. EInvestig., vol. 33, no. l, pp. 52-58, 2013.         [ Links ]

[20] "Neural Networks Toolbox," Czech Technical University. [Online]. Available: http://radio.feld.cvut.cz/matlab/toolbox/nnet/backpr52.html.         [ Links ]

[21] T. Sitamahalakshmi, A. Vinay, M. Jagadeesh, and K. Chandra, "Performance Comparison of Radial Basis Function Networks and Probabilistic Neural Networks for Telugu Character Recognition," Glob. J. Comput. Sci. Technol, vol. 11, no. 4, 2011.         [ Links ]

[22] Radial Basis Networks. [Online]. Available: http://www.inf.ufrgs.br/~engel/data/media/file/cmpl21/rbf-matlab.pdf.         [ Links ]

[23] R. C. Prati, G. Batista, M. C. Monard, "Evaluating Classifier Using ROC Curves," IEEE Latin America Transactions, vol. 6, no. 2, pp. 215-222, 2008.         [ Links ]