Adaptive Hierarchical Multi-Headed Convolutional Neural Network With Modified Convolutional Block Attention for Aerial Forest Fire Detection
Effective detection and classification of forest fire imagery are critical for timely and efficient wildfire management. Convolutional Neural Networks (CNNs) have demonstrated potential in this domain but encounter limitations when addressing varying scales, resolutions, and complex spatial dependen...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10818623/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841554075771994112 |
|---|---|
| author | Md. Najmul Mowla Davood Asadi Shamsul Masum Khaled Rabie |
| author_facet | Md. Najmul Mowla Davood Asadi Shamsul Masum Khaled Rabie |
| author_sort | Md. Najmul Mowla |
| collection | DOAJ |
| description | Effective detection and classification of forest fire imagery are critical for timely and efficient wildfire management. Convolutional Neural Networks (CNNs) have demonstrated potential in this domain but encounter limitations when addressing varying scales, resolutions, and complex spatial dependencies inherent in wildfire datasets. Building upon our prior work on the Unmanned Aerial Vehicle-based Forest Fire Database (UAVs-FFDB) and the multi-headed CNN (MHCNN), this study introduces a novel architecture, namely, the Adaptive Hierarchical Multi-Headed Convolutional Neural Network with Modified Convolutional Block Attention Module (AHMHCNN-mCBAM). This enhanced framework addresses prior challenges by integrating adaptive pooling, concatenated convolutions for multi-scale feature extraction, and an improved attention mechanism incorporating shared fully connected layers, Glorot initialization, rectified linear units (ReLU), layer normalization, and attention-gating. AHMHCNN-mCBAM incorporates Gated Recurrent Unit (GRU) and Bidirectional Long Short-Term Memory (BiLSTM) networks for temporal context modeling to further refine classification accuracy. Experiments conducted on the UAVs-FFDB dataset achieved outstanding results, including 100% accuracy, a 100% Cohen’s kappa coefficient (cKappa), and compact model parameter sizes of 1.49 million (M), 0.25 M, and 0.12 M. On the Fire Luminosity Airborne-based Machine Learning Evaluation (FLAME) dataset, the model attained accuracy rates of 99.83%, 99.10%, and 99.32%, with corresponding cKappa values of 99.66%, 98.20%, and 98.65%. Compared to the baseline hierarchical MHCNN with CBAM (HMHCNN-CBAM), AHMHCNN-mCBAM demonstrated significant performance gains, including a 6.80% and 6.59% increase in accuracy, a 9.26% and 14.11% improvement in cKappa, and a 13.87% and 13.76% reduction in parameter size on the UAVs-FFDB and FLAME datasets, respectively. Additionally, AHMHCNN-mCBAM outperformed HMHCNN-CBAM in recall (25% improvement), precision (21.95%), F1-score (14.94%), and fire detection rate (FDR) reduction (25.01%), while achieving a 100% reduction in error warning rate (EWR). Leveraging Explainable Artificial Intelligence (XAI) techniques, the model provides interpretable insights into decision-making processes. |
| format | Article |
| id | doaj-art-ec2c1fe5a5a940bfa42aadcf48d92c8f |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-ec2c1fe5a5a940bfa42aadcf48d92c8f2025-01-09T00:01:33ZengIEEEIEEE Access2169-35362025-01-01133412343310.1109/ACCESS.2024.352432010818623Adaptive Hierarchical Multi-Headed Convolutional Neural Network With Modified Convolutional Block Attention for Aerial Forest Fire DetectionMd. Najmul Mowla0https://orcid.org/0000-0003-0613-9858Davood Asadi1https://orcid.org/0000-0002-2066-6016Shamsul Masum2https://orcid.org/0000-0001-8489-9356Khaled Rabie3https://orcid.org/0000-0003-0043-2025Department of Aerospace Engineering, Adana Alparslan Türkeş Science and Technology University, Adana, TürkiyeDepartment of Aerospace Engineering, Adana Alparslan Türkeş Science and Technology University, Adana, TürkiyeSchool of Electrical and Mechanical Engineering, University of Portsmouth, Portsmouth, U.K.Department of Computer Engineering and Center for Communication Systems and Sensing, King Fahd University of Petroleum and Minerals, Dhahran, Saudi ArabiaEffective detection and classification of forest fire imagery are critical for timely and efficient wildfire management. Convolutional Neural Networks (CNNs) have demonstrated potential in this domain but encounter limitations when addressing varying scales, resolutions, and complex spatial dependencies inherent in wildfire datasets. Building upon our prior work on the Unmanned Aerial Vehicle-based Forest Fire Database (UAVs-FFDB) and the multi-headed CNN (MHCNN), this study introduces a novel architecture, namely, the Adaptive Hierarchical Multi-Headed Convolutional Neural Network with Modified Convolutional Block Attention Module (AHMHCNN-mCBAM). This enhanced framework addresses prior challenges by integrating adaptive pooling, concatenated convolutions for multi-scale feature extraction, and an improved attention mechanism incorporating shared fully connected layers, Glorot initialization, rectified linear units (ReLU), layer normalization, and attention-gating. AHMHCNN-mCBAM incorporates Gated Recurrent Unit (GRU) and Bidirectional Long Short-Term Memory (BiLSTM) networks for temporal context modeling to further refine classification accuracy. Experiments conducted on the UAVs-FFDB dataset achieved outstanding results, including 100% accuracy, a 100% Cohen’s kappa coefficient (cKappa), and compact model parameter sizes of 1.49 million (M), 0.25 M, and 0.12 M. On the Fire Luminosity Airborne-based Machine Learning Evaluation (FLAME) dataset, the model attained accuracy rates of 99.83%, 99.10%, and 99.32%, with corresponding cKappa values of 99.66%, 98.20%, and 98.65%. Compared to the baseline hierarchical MHCNN with CBAM (HMHCNN-CBAM), AHMHCNN-mCBAM demonstrated significant performance gains, including a 6.80% and 6.59% increase in accuracy, a 9.26% and 14.11% improvement in cKappa, and a 13.87% and 13.76% reduction in parameter size on the UAVs-FFDB and FLAME datasets, respectively. Additionally, AHMHCNN-mCBAM outperformed HMHCNN-CBAM in recall (25% improvement), precision (21.95%), F1-score (14.94%), and fire detection rate (FDR) reduction (25.01%), while achieving a 100% reduction in error warning rate (EWR). Leveraging Explainable Artificial Intelligence (XAI) techniques, the model provides interpretable insights into decision-making processes.https://ieeexplore.ieee.org/document/10818623/Adaptive hierarchical convolutional networkmodified convolutional block attention moduleunmanned aerial vehicleforest fire detection |
| spellingShingle | Md. Najmul Mowla Davood Asadi Shamsul Masum Khaled Rabie Adaptive Hierarchical Multi-Headed Convolutional Neural Network With Modified Convolutional Block Attention for Aerial Forest Fire Detection IEEE Access Adaptive hierarchical convolutional network modified convolutional block attention module unmanned aerial vehicle forest fire detection |
| title | Adaptive Hierarchical Multi-Headed Convolutional Neural Network With Modified Convolutional Block Attention for Aerial Forest Fire Detection |
| title_full | Adaptive Hierarchical Multi-Headed Convolutional Neural Network With Modified Convolutional Block Attention for Aerial Forest Fire Detection |
| title_fullStr | Adaptive Hierarchical Multi-Headed Convolutional Neural Network With Modified Convolutional Block Attention for Aerial Forest Fire Detection |
| title_full_unstemmed | Adaptive Hierarchical Multi-Headed Convolutional Neural Network With Modified Convolutional Block Attention for Aerial Forest Fire Detection |
| title_short | Adaptive Hierarchical Multi-Headed Convolutional Neural Network With Modified Convolutional Block Attention for Aerial Forest Fire Detection |
| title_sort | adaptive hierarchical multi headed convolutional neural network with modified convolutional block attention for aerial forest fire detection |
| topic | Adaptive hierarchical convolutional network modified convolutional block attention module unmanned aerial vehicle forest fire detection |
| url | https://ieeexplore.ieee.org/document/10818623/ |
| work_keys_str_mv | AT mdnajmulmowla adaptivehierarchicalmultiheadedconvolutionalneuralnetworkwithmodifiedconvolutionalblockattentionforaerialforestfiredetection AT davoodasadi adaptivehierarchicalmultiheadedconvolutionalneuralnetworkwithmodifiedconvolutionalblockattentionforaerialforestfiredetection AT shamsulmasum adaptivehierarchicalmultiheadedconvolutionalneuralnetworkwithmodifiedconvolutionalblockattentionforaerialforestfiredetection AT khaledrabie adaptivehierarchicalmultiheadedconvolutionalneuralnetworkwithmodifiedconvolutionalblockattentionforaerialforestfiredetection |