Scopus
🔓 Açık Erişim YÖKSİS Eşleşti
Determining the Extinguishing Status of Fuel Flames with Sound Wave by Machine Learning Methods
IEEE Access · Ocak 2021
YÖKSİS Kayıtları
Determining the Extinguishing Status of Fuel Flames With Sound Wave by Machine Learning Methods
IEEE Access · 2021 SCI-Expanded
DOÇENT MURAT KÖKLÜ →
Determining the Extinguishing Status of Fuel Flames With Sound Wave by Machine Learning Methods
IEEE Access · 2021 SCI-Expanded
DOÇENT YAVUZ SELİM TAŞPINAR →
Determining the Extinguishing Status of Fuel Flames With Sound Wave by Machine Learning Methods
IEEE Access · 2021 SCI-Expanded
DOÇENT MURAT KÖKLÜ →
Makale Bilgileri
DergiIEEE Access
Yayın TarihiOcak 2021
Cilt / Sayfa9 · 86207-86216
Scopus ID2-s2.0-85112384139
Erişim🔓 Açık Erişim
Özet
Fire is a natural disaster that can be caused by many different reasons. Recently, more environmentally friendly and innovative extinguishing methods have started to be tested, some of which are also used. For this purpose, a sound wave fire-extinguishing system was created and firefighting tests were performed. With the data obtained, as a result of 17,442 tests, a data set was created. In this study, five different machine learning methods were used by using the data set created. These are artificial neural network, k-nearest neighbor, random forest, stacking and deep neural network methods. Stacking method is an ensemble method created by using artificial neural network, k-nearest neighbor, random forest models together. Classification of extinction and non-extinction states of the flame was made with the models created with these methods. The accuracy of models in classification should be analyzed in detail in order to be used as a decision support system in the sound wave fire-extinguishing system. Hence, the classification processes were carried out through the 10-fold cross-validation method. As a result of these tests, the performance analysis of the models was carried out, and the results showed that the highest classification accuracy belongs to the stacking model with 97.06%. The classification accuracy was determined 96.58% in random forest method, 96.03% in artificial neural network model, 94.88% in deep neural network model and 92.62% in k-NN model. The performance of the methods was compared by analyzing the performance metrics of machine learning methods. Thanks to the decision support system to be obtained based on the results of the analyzes, the sound wave fire-extinguishing system can be used efficiently.
Yazarlar (2)
1
Murat Koklu
ORCID: 0000-0002-2737-2360
2
Yavuz Selim Taspinar
ORCID: 0000-0002-7278-4241
Anahtar Kelimeler
extinguishing
fire
flame
machine learning
Sound wave
Kurumlar
Selçuk Üniversitesi
Selçuklu Turkey
Metrikler
23
Atıf
2
Yazar
5
Anahtar Kelime