Loading...
|
Please use this identifier to cite or link to this item:
http://asiair.asia.edu.tw/ir/handle/310904400/115047
|
| Title: | Automated accurate fire detection system using ensemble pretrained residual network |
| Authors: | Dogan, Sengul;Dogan, Sengul;Datta, Prabal;Barua, Prabal Datta;Kutl, Huseyin;Kutlu, Huseyin;Baygi, Mehmet;Baygin, Mehmet;Fujit, Hamido;Fujita, Hamido;Tunce, Turker;Tuncer, Turker;Rajendra, U.;Acharya, U. Rajendra |
| Contributors: | 資訊電機學院生物資訊與醫學工程學系 |
| Keywords: | Fire detection；Ensemble ResNet；Deep feature extraction；Transfer learning；Iterative hard majority voting；NCA |
| Date: | 2022-04-01 |
| Issue Date: | 2023-03-28 02:06:37 (UTC+0) |
| Publisher: | 亞洲大學 |
| Abstract: | Nowadays, fires have been commonly seen worldwide and especially forest fires are big disasters for humanity. The prime objective of this work is to develop an accurate fire warning model by using images. In this work, two new deep feature engineering models are proposed to detect the fire accurately using images. To create deep features, residual networks (ResNet) are chosen since these networks are one of the highly accurate convolutional neural networks. In this work, four pretrained ResNets: ResNet18, ResNet50, ResNet101, and InceptionResNetV2 are used. These networks were trained using a cluster of ImageNet dataset and features were extracted using the last pooling and fully connected layers of these networks. Hence, eight feature vectors are chosen using these networks and the top 256 features of these networks are chosen using neighborhood component analysis (NCA). Support vector machine (SVM) classifier has been used for classification. Moreover, by using the eight feature vectors generated, two ensemble models have been presented. In the first ensemble model, generated all features are concatenated and the top 1000 features are chosen using a feature selector used (NCA), and these features are classified using SVM. In the second ensemble model, iterative hard majority voting (IHMV) has been applied to the generated results. The developed ensemble ResNet models attained 98.91% and 99.15% classification accuracies using an SVM classifier with a 10-fold cross-validation strategy. Our results obtained demonstrate the high classification accuracy of our presented ensemble pretrained ResNet-based deep feature extraction models. These developed models are ready to be tested with higher databases before actual real-world application. |
| Appears in Collections: | [生物資訊與醫學工程學系 ] 期刊論文
|
Files in This Item:
| File |
Description |
Size | Format | |
|---|
| index.html | | 0Kb | HTML | 78 | View/Open |
|
All items in ASIAIR are protected by copyright, with all rights reserved.
|
