International journal of

ADVANCED AND APPLIED SCIENCES

EISSN: 2313-3724, Print ISSN:2313-626X

Frequency: 12

line decor
  
line decor

 Volume 6, Issue 3 (March 2019), Pages: 56-61

----------------------------------------------

 Original Research Paper

 Title: Real time end-to-end glass break detection system using LSTM deep recurrent neural network

 Author(s): Wai Yan Nyein Naing *, Zaw Zaw Htike, Amir Akramin Shafie

 Affiliation(s):

 Mechatronic Engineering Department, International Islamic University Malaysia (IIUM), Gombak, Malaysia

  Full Text - PDF          XML

 * Corresponding Author. 

  Corresponding author's ORCID profile: https://orcid.org/0000-0001-5639-9899

 Digital Object Identifier: 

 https://doi.org/10.21833/ijaas.2019.03.009

 Abstract:

The aim of this paper is to propose a new design for a glass break detection system using LSTM deep recurrent neural networks at an end-to-end approach to reduce false positive alarm of state of the art glass break detectors. We utilized raw wave audio data to detect a glass break detection event in End-to-End learning approach. The key benefit of End-to-End learning is avoiding the need for hand-crafted audio features. To address the issue of a vanishing gradient and exploding gradient problem in conventional recurrent neural networks, this paper proposed deep long short term memory (LSTM) recurrent neural network to handle the sequence of the input audio data.  As a real-time detection result, the proposed glass break detection approach has a clear advantage over the conventional glass break detection system, as it yields significantly higher precision accuracy (99.999988 %) and suffers less from environmental noise that might cause a false alarm. 

 © 2019 The Authors. Published by IASE.

 This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).

 Keywords: Glass break detection system, Deep learning, Long-short term memory, Deep recurrent neural network

 Article History: Received 15 May 2018, Received in revised form 12 January 2019, Accepted 18 January 2019

 Acknowledgement:

This work was supported by the Ministry of Higher Education Malaysia under PRGS17-002-0042 and International Islamic University Malaysia under RIGS16-350-0514. 

 Compliance with ethical standards

 Conflict of interest:  The authors declare that they have no conflict of interest.

 Citation:

 Naing WYN, Htike ZZ, and Shafie AA (2019). Real time end-to-end glass break detection system using LSTM deep recurrent neural network. International Journal of Advanced and Applied Sciences, 6(3): 56-61

 Permanent Link to this page

 Figures

 Fig. 1 Fig. 2 Fig. 3 Fig. 4 Fig. 5 Fig. 6 Fig. 7 Fig. 8 

 Tables

 Table 1

----------------------------------------------

 References (19) 

  1. Aurino F, Folla M, Gargiulo F, Moscato V, Picariello A, and Sansone C (2014). One-class SVM based approach for detecting anomalous audio events. In the International Conference on Intelligent Networking and Collaborative Systems, IEEE, Salerno, Italy: 145-151. https://doi.org/10.1109/INCoS.2014.59   [Google Scholar]
  2. Cecic D and Fong HUS (1997). Glass break detector (U.S. Patent No. 5,675,320A). Patent and Trademark Office, Washington, DC, USA.   [Google Scholar]
  3. Clark FB and Lewis KT (1996). Glass break detector and a method therefor (U.S. Patent No. 5,543,783A). Patent and Trademark Office, Washington, DC, USA.   [Google Scholar]
  4. Clavel C, Ehrette T, and Richard G (2005). Events detection for an audio-based surveillance system. In the IEEE International Conference on Multimedia and Expo, IEEE, Amsterdam, Netherlands: 1306-1309.  https://doi.org/10.1109/ICME.2005.1521669   [Google Scholar]
  5. Conte D, Foggia P, Percannella G, Saggese A, and Vento M (2012). An ensemble of rejecting classifiers for anomaly detection of audio events. In the IEEE Ninth International Conference on Advanced Video and Signal-Based Surveillance, IEEE, Beijing, China: 76-81. https://doi.org/10.1109/AVSS.2012.9   [Google Scholar]
  6. Dufaux A, Besacier L, Ansorge M, and Pellandini F (2000). Automatic sound detection and recognition for noisy environment. In the 10th European Signal Processing Conference, IEEE, Tampere, Finland: 1-4.   [Google Scholar]
  7. Gers F, Schmidhuber JA, and Cummins F (2000). Learning to forget: Continual prediction with LSTM. Neural Computation, 12(10): 2451–2471. https://doi.org/10.1162/089976600300015015   [Google Scholar] PMid:11032042
  8. Gestner B, Tanner J, and Anderson D (2007). Glass break detector analog front-end using novel classifier circuit. In the IEEE International Symposium on Circuits and Systems, IEEE, New Orleans, USA: 3586-3589.  https://doi.org/10.1109/ISCAS.2007.378528   [Google Scholar]
  9. Graves A, Mohamed AR, and Hinton G (2013). Speech recognition with deep recurrent neural networks. In the IEEE International Conference on Acoustics, Speech and Signal Processing, IEEE: 6645-6649. https://doi.org/10.1109/ICASSP.2013.6638947   [Google Scholar]
  10. Kiktova E, Lojka M, Pleva M, Juhar J, and Cizmar A (2015). Gun type recognition from gunshot audio recordings. In the International Workshop on Biometrics and Forensics, IEEE, Gjovik, Norway: 1-6. https://doi.org/10.1109/IWBF.2015.7110240   [Google Scholar]
  11. Li X and Wu X (2015). Constructing long short-term memory based deep recurrent neural networks for large vocabulary speech recognition. In the IEEE International Conference on Acoustics, Speech and Signal Processing, IEEE, Brisbane, Australia: 4520-4524.     https://doi.org/10.1109/ICASSP.2015.7178826   [Google Scholar]
  12. Mahler MA, Li Q, and Li A (2017). Secure house: A home security system based on smartphone sensors. In the 2017 IEEE International Conference on Pervasive Computing and Communications (PerCom), IEEE, Kona, HI, USA: 11-20. https://doi.org/10.1109/PERCOM.2017.7917846   [Google Scholar]
  13. Matesa JM (2015). Alarm detection device and method (U.S. Patent No. 9,191,762B1). Patent and Trademark Office, Washington, DC, USA.   [Google Scholar]
  14. Pascanu R, Mikolov T, and Bengio Y (2013). On the difficulty of training recurrent neural networks. In the 30th International Conference on Machine Learning, Atlanta, Georgia, USA, 28: 1310-1318.   [Google Scholar] PMCid:PMC4517175
  15. Peng L, Yang D, and Chen X (2014). Multi frame size feature extraction for acoustic event detection. In the 2014 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, IEEE, Chiang Mai, Thailand: 1-4. https://doi.org/10.1109/APSIPA.2014.7041574   [Google Scholar]
  16. Rickman SA (1995). Direction-sensing acoustic glass break detecting system (U.S. Patent No. 5,471,195A). Patent and Trademark Office, Washington, DC, USA.   [Google Scholar]
  17. Sak H, Senior A, and Beaufays F (2014). Long short-term memory recurrent neural network architectures for large scale acoustic modeling. In the Fifteenth Annual Conference of the International Speech Communication Association, Singapore: 338-342.   [Google Scholar]
  18. Sharapov V (2011). General information about piezoelectric sensors. In: Sharapov V (Ed.), Piezoceramic Sensors: 1-24. Springer, Berlin, Heidelberg, Germany. https://doi.org/10.1007/978-3-642-15311-2_1   [Google Scholar]
  19. Zidan WI (2015). Estimation of cluster sensors’ probability of detection for physical protection systems evaluation. Journal of Physical Security 8(1): 40-54.   [Google Scholar]