Encoder-decoder based convolutional neural network (EDCNN) for video classification of smoke and fire image
Authors:
- Wahyu Caesarendra,
- Vigneashwara Pandiyan,
- Mohammed Umar Malik,
- Daniel Sutopo Pamungkas,
- Maciej Sulowicz,
- Hayati Yassin
Abstract
An increase in fire accident rate has been reported to be growing recently due to a lack of advanced technology for detecting the presence of smoke and fire at the initial stage. To date, electronic sensor-based monitoring methods are the most common technique that has been widely practiced. However, the existing methods are not securely proven to detect the presence of smoke and fire at an initial stage with higher accuracy. This study presents a preliminary method for the initial stage detection of smoke and fire using the Deep Learning method. One of the DL methods namely Encoder-decoder-based convolutional neural network (EDCNN) is used to classify both smoke and fire density levels. In this study, the image data are extracted from a sample video sequence, and it is further divided into three different classes such as background or negative, smoke, and fire. An EDCNN with VGG-16 architecture is used to train and test the 3 classes of image data. The global accuracy of the proposed classification method reaches up to 95%. The classification model of EDCNN is then applied to the simulated fault electronic circuit video due to loose wires. According to the video application result, the proposed method has the potential for further real-time application where the existence of smoke and fire can be distinguished by the EDCNN classification model.
- Record ID
- CUT997472aec73841ce89c0a6aca926e160
- Publication categories
- ; ;
- Author
- Pages
- 040012-1 – 040012-9
- Other elements of collation
- fot.; rys.; tab.; wykr.; Bibliografia (na s.) - 040012-9; Bibliografia (liczba pozycji) - 15; Oznaczenie streszczenia - Abstr.
- Substantive notes
- Tyt. źródła wg okł.
- Book
- Puspita Widya Rika Widya Rika Puspita (eds.): The 4th International Conference on Applied Engineering (ICAE 2021), Batam, Indonesia, 13 October 2021, AIP Conference Proceedings, no. Vol. 2665, Iss. 1, 2023, [Maryland], American Institute of Physics, AIP Publishing, ISBN 978-0-7354-4669-4
- Keywords in English
- electronic circuits, convolutional neural network, learning and learning models, regression analysis
- DOI
- DOI:10.1063/5.0127353 Opening in a new tab
- URL
- https://pubs.aip.org/aip/acp/article-abstract/2665/1/040012/2912652/Encoder-decoder-based-convolutional-neural-network Opening in a new tab
- Language
- eng (en) English
- Score (nominal)
- 20
- Score source
- publisherList
- Score
- Publication indicators
- = 0
- Uniform Resource Identifier
- https://cris.pk.edu.pl/info/article/CUT997472aec73841ce89c0a6aca926e160/
- URN
urn:pkr-prod:CUT997472aec73841ce89c0a6aca926e160
* presented citation count is obtained through Internet information analysis, and it is close to the number calculated by the Publish or PerishOpening in a new tab system.