A Hybrid Deep Learning Model for Early Forest Fire Detection
Guardat en:
| Publicat a: | Forests vol. 16, no. 5 (2025), p. 863 |
|---|---|
| Autor principal: | |
| Altres autors: | , , , , , , , |
| Publicat: |
MDPI AG
|
| Matèries: | |
| Accés en línia: | Citation/Abstract Full Text + Graphics Full Text - PDF |
| Etiquetes: |
Sense etiquetes, Sigues el primer a etiquetar aquest registre!
|
MARC
| LEADER | 00000nab a2200000uu 4500 | ||
|---|---|---|---|
| 001 | 3211971391 | ||
| 003 | UK-CbPIL | ||
| 022 | |a 1999-4907 | ||
| 024 | 7 | |a 10.3390/f16050863 |2 doi | |
| 035 | |a 3211971391 | ||
| 045 | 2 | |b d20250501 |b d20250531 | |
| 084 | |a 231463 |2 nlm | ||
| 100 | 1 | |a Akhror, Mamadmurodov |u Department of Computer Engineering, Gachon University, Seongnam-si 13120, Republic of Korea; akhror1999@gachon.ac.kr (A.M.); sabinatuit@gachon.ac.kr (S.U.); akmaljon@gachon.ac.kr (A.A.) | |
| 245 | 1 | |a A Hybrid Deep Learning Model for Early Forest Fire Detection | |
| 260 | |b MDPI AG |c 2025 | ||
| 513 | |a Journal Article | ||
| 520 | 3 | |a Forest fires pose an escalating global threat, severely impacting ecosystems, public health, and economies. Timely detection, especially during early stages, is critical for effective intervention. In this study, we propose a novel deep learning-based framework that augments the YOLOv4 object detection architecture with a modified EfficientNetV2 backbone and Efficient Channel Attention (ECA) modules. The backbone substitution leverages compound scaling and Fused-MBConv/MBConv blocks to improve representational efficiency, while the lightweight ECA blocks enhance inter-channel dependency modeling without incurring significant computational overhead. Additionally, we introduce a domain-specific preprocessing pipeline employing Canny edge detection, CLAHE + Jet transformation, and pseudo-NDVI mapping to enhance fire-specific visual cues in complex natural environments. Experimental evaluation on a hybrid dataset of forest fire images and video frames demonstrates substantial performance gains over baseline YOLOv4 and contemporary YOLO variants (YOLOv5–YOLOv9), with the proposed model achieving 97.01% precision, 95.14% recall, 93.13% mAP, and 92.78% F1-score. Furthermore, our model outperforms fourteen state-of-the-art approaches across standard metrics, confirming its efficacy, generalizability, and suitability for real-time deployment in UAV-based and edge computing platforms. These findings highlight the synergy between architectural optimization and domain-aware preprocessing for high-accuracy, low-latency wildfire detection systems. | |
| 653 | |a Forest fires | ||
| 653 | |a Accuracy | ||
| 653 | |a Public health | ||
| 653 | |a Deep learning | ||
| 653 | |a Forest fire detection | ||
| 653 | |a Edge computing | ||
| 653 | |a Biodiversity | ||
| 653 | |a Architecture | ||
| 653 | |a Visual stimuli | ||
| 653 | |a Climate change | ||
| 653 | |a Efficiency | ||
| 653 | |a Wildfires | ||
| 653 | |a Vegetation | ||
| 653 | |a Preprocessing | ||
| 653 | |a Environmental impact | ||
| 653 | |a Sensors | ||
| 653 | |a Effectiveness | ||
| 653 | |a Natural environment | ||
| 653 | |a Drones | ||
| 653 | |a Forest & brush fires | ||
| 653 | |a Surveillance | ||
| 653 | |a Latency | ||
| 653 | |a Object recognition | ||
| 653 | |a Real time | ||
| 653 | |a Semantics | ||
| 653 | |a Edge detection | ||
| 653 | |a Environmental | ||
| 700 | 1 | |a Umirzakova Sabina |u Department of Computer Engineering, Gachon University, Seongnam-si 13120, Republic of Korea; akhror1999@gachon.ac.kr (A.M.); sabinatuit@gachon.ac.kr (S.U.); akmaljon@gachon.ac.kr (A.A.) | |
| 700 | 1 | |a Mekhriddin, Rakhimov |u Department of Computer Systems, Tashkent University of Information Technologies Named After Muhammad Al-Khwarizmi, Tashkent 100200, Uzbekistan; raximov022@gmail.com | |
| 700 | 1 | |a Alpamis, Kutlimuratov |u Department of Applied Informatics, Kimyo International University in Tashkent, Toshkent 100121, Uzbekistan; kutlimuratov.aj@kiut.uz | |
| 700 | 1 | |a Zavqiddin, Temirov |u Department of Digital Technologies, Alfraganus University, Yukori Karakamish Street 2a, Tashkent 100190, Uzbekistan; temirov@afu.uz | |
| 700 | 1 | |a Nasimov Rashid |u Department of Artificial Intelligence, Tashkent State University of Economics, Tashkent 100066, Uzbekistan; rashid.nasimov@tsue.uz | |
| 700 | 1 | |a Azizjon, Meliboev |u Department of Digital Technologies and Mathematics, Kokand University, Kokand 150700, Uzbekistan; a.meliboyev@kokanduni.uz | |
| 700 | 1 | |a Akmalbek, Abdusalomov |u Department of Computer Engineering, Gachon University, Seongnam-si 13120, Republic of Korea; akhror1999@gachon.ac.kr (A.M.); sabinatuit@gachon.ac.kr (S.U.); akmaljon@gachon.ac.kr (A.A.) | |
| 700 | 1 | |a Im Cho Young |u Department of Computer Engineering, Gachon University, Seongnam-si 13120, Republic of Korea; akhror1999@gachon.ac.kr (A.M.); sabinatuit@gachon.ac.kr (S.U.); akmaljon@gachon.ac.kr (A.A.) | |
| 773 | 0 | |t Forests |g vol. 16, no. 5 (2025), p. 863 | |
| 786 | 0 | |d ProQuest |t Agriculture Science Database | |
| 856 | 4 | 1 | |3 Citation/Abstract |u https://www.proquest.com/docview/3211971391/abstract/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch |
| 856 | 4 | 0 | |3 Full Text + Graphics |u https://www.proquest.com/docview/3211971391/fulltextwithgraphics/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch |
| 856 | 4 | 0 | |3 Full Text - PDF |u https://www.proquest.com/docview/3211971391/fulltextPDF/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch |