Capsule neural network and adapted golden search optimizer based forest fire and smoke detection
Abstract Forest fires represent a major risk to both ecosystems and human health that rising frequency of it exacerbates global warming. This study introduces an innovative methodology for detecting forest fires and smoke using an enhanced capsule neural network (CNN) together with an adapted golden...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-02-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-81742-y |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823862493152280576 |
|---|---|
| author | Luling Liu Li Chen Mehdi Asadi |
| author_facet | Luling Liu Li Chen Mehdi Asadi |
| author_sort | Luling Liu |
| collection | DOAJ |
| description | Abstract Forest fires represent a major risk to both ecosystems and human health that rising frequency of it exacerbates global warming. This study introduces an innovative methodology for detecting forest fires and smoke using an enhanced capsule neural network (CNN) together with an adapted golden search optimizer (AGSO). By using advanced deep learning and optimization strategies, the method effectively identifies complex patterns linked to wildfires. Testing this model on wildfire smoke imagery and the BowFire dataset reveals that the proposed methodology outperformed traditional feature selection and classification methods. The integration of the modified CNN and AGSO facilitated rapid response and mitigation efforts, enhancing the accuracy and dependability of forest fire identification. This research highlights the importance of advanced computational techniques in reducing risks, ensuring safety, and progressing automatic forest fire detection systems. The combination of capsule neural networks with the golden search optimizer illustrates the potential of merging cutting-edge technologies to tackle intricate environmental issues efficiently. |
| format | Article |
| id | doaj-art-86c5f063a5e34426a7ddb87e8ec0d6b4 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-86c5f063a5e34426a7ddb87e8ec0d6b42025-02-09T12:31:54ZengNature PortfolioScientific Reports2045-23222025-02-0115112010.1038/s41598-024-81742-yCapsule neural network and adapted golden search optimizer based forest fire and smoke detectionLuling Liu0Li Chen1Mehdi Asadi2College of Mechanical and Electrical Engineering, The College of Post and Telecommunication of WITCollege of Mechanical and Electrical Engineering, The College of Post and Telecommunication of WITDepartment of Energy Systems Engineering, University of TehranAbstract Forest fires represent a major risk to both ecosystems and human health that rising frequency of it exacerbates global warming. This study introduces an innovative methodology for detecting forest fires and smoke using an enhanced capsule neural network (CNN) together with an adapted golden search optimizer (AGSO). By using advanced deep learning and optimization strategies, the method effectively identifies complex patterns linked to wildfires. Testing this model on wildfire smoke imagery and the BowFire dataset reveals that the proposed methodology outperformed traditional feature selection and classification methods. The integration of the modified CNN and AGSO facilitated rapid response and mitigation efforts, enhancing the accuracy and dependability of forest fire identification. This research highlights the importance of advanced computational techniques in reducing risks, ensuring safety, and progressing automatic forest fire detection systems. The combination of capsule neural networks with the golden search optimizer illustrates the potential of merging cutting-edge technologies to tackle intricate environmental issues efficiently.https://doi.org/10.1038/s41598-024-81742-yCapsule neural networksGolden search optimizerSmoke detectionForest fireEarly identificationSwift response |
| spellingShingle | Luling Liu Li Chen Mehdi Asadi Capsule neural network and adapted golden search optimizer based forest fire and smoke detection Scientific Reports Capsule neural networks Golden search optimizer Smoke detection Forest fire Early identification Swift response |
| title | Capsule neural network and adapted golden search optimizer based forest fire and smoke detection |
| title_full | Capsule neural network and adapted golden search optimizer based forest fire and smoke detection |
| title_fullStr | Capsule neural network and adapted golden search optimizer based forest fire and smoke detection |
| title_full_unstemmed | Capsule neural network and adapted golden search optimizer based forest fire and smoke detection |
| title_short | Capsule neural network and adapted golden search optimizer based forest fire and smoke detection |
| title_sort | capsule neural network and adapted golden search optimizer based forest fire and smoke detection |
| topic | Capsule neural networks Golden search optimizer Smoke detection Forest fire Early identification Swift response |
| url | https://doi.org/10.1038/s41598-024-81742-y |
| work_keys_str_mv | AT lulingliu capsuleneuralnetworkandadaptedgoldensearchoptimizerbasedforestfireandsmokedetection AT lichen capsuleneuralnetworkandadaptedgoldensearchoptimizerbasedforestfireandsmokedetection AT mehdiasadi capsuleneuralnetworkandadaptedgoldensearchoptimizerbasedforestfireandsmokedetection |