Smoke and Fire Detection Base on Convolutional Neural Network

ELVIRA SUKMA WAHYUNI, MUHAMMAD HENDRI

Sari


ABSTRAK

Deteksi api dan asap adalah langkah pertama sebagai deteksi dini kebakaran. Deteksi dini kebakaran berdasarkan pemrosesan gambar dianggap mampu memberikan hasil yang efektif. Pilihan metode deteksi adalah kunci penting. Metode ekstraksi fitur berdasarkan analisis statistik dan analisis dinamis kadang-kadang memberikan akurasi kurang akurat dalam mendeteksi asap dan api, terutama pada deteksi asap, hal ini disebabkan oleh karakteristik objek asap yang transparan dan bergerak. Dalam penelitian ini, metode Convolutional Neural Network (CNN) diterapkan untuk deteksi asap dan api. Dari penelitian ini, diketahui bahwa CNN memberikan kinerja yang baik dalam deteksi kebakaran dan asap. Akurasi deteksi tertinggi diperoleh dengan menggunakan 144 data pelatihan, 20.000 iterasi dengan dropout.

Kata kunci: Deteksi asap, deteksi kebakaran, Jaringan Syaraf Konvolusional

 

ABSTRACT

Fire and smoke detection is the first step as early detection of fires. Early detection of fire based on image processing is considered capable of providing effective results. The choice of detection method is an important key. Feature extraction methods based on statistical analysis and dynamic analysis sometimes provide less accurate accuracy in detecting smoke and fire, especially on smoke detection, this is due to the characteristics of transparent and moving smoke objects. In this study, the Convolutional Neural Network (CNN) method was applied for smoke and fire detection. From this study, it is known that CNN provides good performance in fire and smoke detection. The highest detection accuracy is obtained by using 144 training data, 20,000 iterations and dropout is true.

Keywords: Smoke detection, Fire detection, Convolutional Neural Network


Kata Kunci


Deteksi asap; deteksi kebakaran; Convulutional Neural Network

Teks Lengkap:

PDF (English)

Referensi


Dileep, K. A., Rashedul I., Sheraz, A. K., & Jong, M. K. (2017). A video-based smoke detection using smoke flow pattern and spatial-temporal energy analyses for alarm systems. Inf. Sci. (Ny). , 418–419 (32), 91–101.

Jasmin, Ć., Miroslav, B., & Domagoj, K. (2016). Computer Vision Application for Early Stage Smoke Detection on Ships. Maritime & Transportation Science, 52 (1), 63–80.

Jiuxiang, G., et al. (2018). Recent advances in convolutional neural networks. Pattern Recognit. , 77 (5), 354–377.

Luyang, J., Ming, Z., Pin L., & Xiaoqiang, X. (2017). A convolutional neural network based feature learning and fault diagnosis method for the condition monitoring of gearbox. Meas. J. Int. Meas. Confed. , 111 (18), 1–10.

Neha, S., Vibhor, J., & Anju, M. (2018). An Analysis of Convolutional Neural Networks for Image Classification. Procedia Comput. Sci. , 132 (38), 377–384.

Sipongi. (2018). Data Matrik Titik Panas TERRA/AQUA (LAPAN) ≥ 80%. Retrieved from sipongi.menlhk.go.id.

Sheng, L., Changwei, Y., Kelu, W., & Jiangyu, Z. (2015). Smoke detection based on condensed image. Fire Saf. J., 75 (5), 23–35.

Turgay, Ç., Huseyin, Ö., & Hasan, D. (2007). Fire and smoke detection without sensors. 15th European Signal Processing Conference, (pp. 1794–1798).




DOI: https://doi.org/10.26760/elkomika.v7i3.455

Refbacks

  • Saat ini tidak ada refbacks.


_______________________________________________________________________________________________________________________

ISSN (cetak) : 2338-8323   |  ISSN (elektronik) : 2459-9638    

diterbitkan oleh :

Teknik Elektro Institut Teknologi Nasional Bandung

Alamat : Gedung 20 Jl. PHH. Mustofa 23 Bandung 40124

Kontak : Tel. 7272215 (ext. 206)  Fax. 7202892

Surat Elektronik jte.itenas@itenas.ac.id

_________________________________________________________________________________________________________________________

Terindeks 

index copernicus

________________________________________________________________________________________________________________________

Statistik Pengunjung 

Free counters!

 Web
Analytics Made Easy - StatCounter

Lihat Statistik Jurnal

Jurnal ini terlisensi oleh Creative Commons Attribution-ShareAlike 4.0 International License.

Creative Commons License