Real time end-to-end glass break detection system using LSTM deep recurrent neural network
Presently, glass windows in commercial and residential buildings are very popular. While glass has its benefits, it is also disposed to security risks. Almost all glass break detectors use a pre-determined frequency of breaking glass sound and vibration threshold signals of a pane to determine whet...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English English |
| Published: |
Institute of Advanced Science Extension
2019
|
| Subjects: | |
| Online Access: | http://irep.iium.edu.my/69671/ http://irep.iium.edu.my/69671/ http://irep.iium.edu.my/69671/ http://irep.iium.edu.my/69671/14/69671_Real%20time%20end-to-end%20glass%20break%20detection.pdf http://irep.iium.edu.my/69671/13/69671_Real%20time%20end-to-end%20glass%20break%20detection_wos.pdf |
| id |
iium-69671 |
|---|---|
| recordtype |
eprints |
| spelling |
iium-696712019-04-23T03:24:33Z http://irep.iium.edu.my/69671/ Real time end-to-end glass break detection system using LSTM deep recurrent neural network Nyein Naing, Wai Yan Htike, Zaw Zaw Shafie, Amir Akramin Q350 Information theory Presently, glass windows in commercial and residential buildings are very popular. While glass has its benefits, it is also disposed to security risks. Almost all glass break detectors use a pre-determined frequency of breaking glass sound and vibration threshold signals of a pane to determine whether or not breakage has occurred. However, sounds such as thunder sounds, shouting, gunshot, hitting objects are similar in frequency and threshold value to glass breaking sounds events, and may consequently cause false positives in detection in the alarm system. The aim of this paper is to propose a new design for a glass break detection system using LSTM deep recurrent neural networks in 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 of 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. Institute of Advanced Science Extension 2019-03 Article PeerReviewed application/pdf en http://irep.iium.edu.my/69671/14/69671_Real%20time%20end-to-end%20glass%20break%20detection.pdf application/pdf en http://irep.iium.edu.my/69671/13/69671_Real%20time%20end-to-end%20glass%20break%20detection_wos.pdf Nyein Naing, Wai Yan and Htike, Zaw Zaw and Shafie, Amir Akramin (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). pp. 56-61. ISSN 2313-626X E-ISSN 2313-3724 http://science-gate.com/IJAAS/Articles/2019/2019-6-3/1021833ijaas201903009.pdf 10.21833/ijaas.2019.03.009 |
| repository_type |
Digital Repository |
| institution_category |
Local University |
| institution |
International Islamic University Malaysia |
| building |
IIUM Repository |
| collection |
Online Access |
| language |
English English |
| topic |
Q350 Information theory |
| spellingShingle |
Q350 Information theory Nyein Naing, Wai Yan Htike, Zaw Zaw Shafie, Amir Akramin Real time end-to-end glass break detection system using LSTM deep recurrent neural network |
| description |
Presently, glass windows in commercial and residential buildings are very popular. While glass has its benefits, it is also disposed to security risks. Almost all glass break detectors use a pre-determined frequency of breaking
glass sound and vibration threshold signals of a pane to determine whether or not breakage has occurred. However, sounds such as thunder sounds, shouting, gunshot, hitting objects are similar in frequency and threshold
value to glass breaking sounds events, and may consequently cause false positives in detection in the alarm system. The aim of this paper is to propose a new design for a glass break detection system using LSTM deep recurrent
neural networks in 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 of 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. |
| format |
Article |
| author |
Nyein Naing, Wai Yan Htike, Zaw Zaw Shafie, Amir Akramin |
| author_facet |
Nyein Naing, Wai Yan Htike, Zaw Zaw Shafie, Amir Akramin |
| author_sort |
Nyein Naing, Wai Yan |
| title |
Real time end-to-end glass break detection system using LSTM deep recurrent neural network |
| title_short |
Real time end-to-end glass break detection system using LSTM deep recurrent neural network |
| title_full |
Real time end-to-end glass break detection system using LSTM deep recurrent neural network |
| title_fullStr |
Real time end-to-end glass break detection system using LSTM deep recurrent neural network |
| title_full_unstemmed |
Real time end-to-end glass break detection system using LSTM deep recurrent neural network |
| title_sort |
real time end-to-end glass break detection system using lstm deep recurrent neural network |
| publisher |
Institute of Advanced Science Extension |
| publishDate |
2019 |
| url |
http://irep.iium.edu.my/69671/ http://irep.iium.edu.my/69671/ http://irep.iium.edu.my/69671/ http://irep.iium.edu.my/69671/14/69671_Real%20time%20end-to-end%20glass%20break%20detection.pdf http://irep.iium.edu.my/69671/13/69671_Real%20time%20end-to-end%20glass%20break%20detection_wos.pdf |
| first_indexed |
2023-09-18T21:38:54Z |
| last_indexed |
2023-09-18T21:38:54Z |
| _version_ |
1777413006594932736 |