Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313434480> ?p ?o ?g. }
- W4313434480 endingPage "228" @default.
- W4313434480 startingPage "228" @default.
- W4313434480 abstract "One of the most expensive and fatal natural disasters in the world is forest fires. For this reason, early discovery of forest fires helps minimize mortality and harm to ecosystems and forest life. The present research enriches the body of knowledge by evaluating the effectiveness of an efficient wildfire and smoke detection solution implementing ensembles of multiple convolutional neural network architectures tackling two different computer vision tasks in a stage format. The proposed architecture combines the YOLO architecture with two weights with a voting ensemble CNN architecture. The pipeline works in two stages. If the CNN detects the existence of abnormality in the frame, then the YOLO architecture localizes the smoke or fire. The addressed tasks are classification and detection in the presented method. The obtained model’s weights achieve very decent results during training and testing. The classification model achieves a 0.95 F1-score, 0.99 accuracy, and 0.98e sensitivity. The model uses a transfer learning strategy for the classification task. The evaluation of the detector model reveals strong results by achieving a 0.85 mean average precision with 0.5 threshold (mAP@0.5) score for the smoke detection model and 0.76 mAP for the combined model. The smoke detection model also achieves a 0.93 F1-score. Overall, the presented deep learning pipeline shows some important experimental results with potential implementation capabilities despite some issues encountered during training, such as the lack of good-quality real-world unmanned aerial vehicle (UAV)-captured fire and smoke images." @default.
- W4313434480 created "2023-01-06" @default.
- W4313434480 creator A5023889839 @default.
- W4313434480 creator A5030346209 @default.
- W4313434480 creator A5037293810 @default.
- W4313434480 creator A5051158911 @default.
- W4313434480 creator A5059829609 @default.
- W4313434480 creator A5060832078 @default.
- W4313434480 creator A5077504804 @default.
- W4313434480 date "2023-01-02" @default.
- W4313434480 modified "2023-10-18" @default.
- W4313434480 title "Wildfire and Smoke Detection Using Staged YOLO Model and Ensemble CNN" @default.
- W4313434480 cites W2194775991 @default.
- W4313434480 cites W2531409750 @default.
- W4313434480 cites W2538179893 @default.
- W4313434480 cites W2610484101 @default.
- W4313434480 cites W2791569356 @default.
- W4313434480 cites W2807862495 @default.
- W4313434480 cites W2912514498 @default.
- W4313434480 cites W2958837267 @default.
- W4313434480 cites W2963037989 @default.
- W4313434480 cites W2963163009 @default.
- W4313434480 cites W2963351448 @default.
- W4313434480 cites W2963446712 @default.
- W4313434480 cites W2978858971 @default.
- W4313434480 cites W2979526390 @default.
- W4313434480 cites W3010635215 @default.
- W4313434480 cites W3088990057 @default.
- W4313434480 cites W3090022951 @default.
- W4313434480 cites W3119629789 @default.
- W4313434480 cites W3126294508 @default.
- W4313434480 cites W3132971810 @default.
- W4313434480 cites W3136217325 @default.
- W4313434480 cites W3138239532 @default.
- W4313434480 cites W3164016092 @default.
- W4313434480 cites W3170009461 @default.
- W4313434480 cites W3196908521 @default.
- W4313434480 cites W3206280020 @default.
- W4313434480 cites W4200459315 @default.
- W4313434480 cites W4205452632 @default.
- W4313434480 cites W4205785826 @default.
- W4313434480 cites W4206054559 @default.
- W4313434480 cites W4207031702 @default.
- W4313434480 cites W4207054463 @default.
- W4313434480 cites W4213223813 @default.
- W4313434480 cites W4214663719 @default.
- W4313434480 cites W4311104091 @default.
- W4313434480 cites W618316763 @default.
- W4313434480 doi "https://doi.org/10.3390/electronics12010228" @default.
- W4313434480 hasPublicationYear "2023" @default.
- W4313434480 type Work @default.
- W4313434480 citedByCount "9" @default.
- W4313434480 countsByYear W43134344802023 @default.
- W4313434480 crossrefType "journal-article" @default.
- W4313434480 hasAuthorship W4313434480A5023889839 @default.
- W4313434480 hasAuthorship W4313434480A5030346209 @default.
- W4313434480 hasAuthorship W4313434480A5037293810 @default.
- W4313434480 hasAuthorship W4313434480A5051158911 @default.
- W4313434480 hasAuthorship W4313434480A5059829609 @default.
- W4313434480 hasAuthorship W4313434480A5060832078 @default.
- W4313434480 hasAuthorship W4313434480A5077504804 @default.
- W4313434480 hasBestOaLocation W43134344801 @default.
- W4313434480 hasConcept C108583219 @default.
- W4313434480 hasConcept C119857082 @default.
- W4313434480 hasConcept C126042441 @default.
- W4313434480 hasConcept C127413603 @default.
- W4313434480 hasConcept C148524875 @default.
- W4313434480 hasConcept C150899416 @default.
- W4313434480 hasConcept C153180895 @default.
- W4313434480 hasConcept C154945302 @default.
- W4313434480 hasConcept C199360897 @default.
- W4313434480 hasConcept C2776151529 @default.
- W4313434480 hasConcept C41008148 @default.
- W4313434480 hasConcept C43521106 @default.
- W4313434480 hasConcept C548081761 @default.
- W4313434480 hasConcept C58874564 @default.
- W4313434480 hasConcept C76155785 @default.
- W4313434480 hasConcept C81363708 @default.
- W4313434480 hasConceptScore W4313434480C108583219 @default.
- W4313434480 hasConceptScore W4313434480C119857082 @default.
- W4313434480 hasConceptScore W4313434480C126042441 @default.
- W4313434480 hasConceptScore W4313434480C127413603 @default.
- W4313434480 hasConceptScore W4313434480C148524875 @default.
- W4313434480 hasConceptScore W4313434480C150899416 @default.
- W4313434480 hasConceptScore W4313434480C153180895 @default.
- W4313434480 hasConceptScore W4313434480C154945302 @default.
- W4313434480 hasConceptScore W4313434480C199360897 @default.
- W4313434480 hasConceptScore W4313434480C2776151529 @default.
- W4313434480 hasConceptScore W4313434480C41008148 @default.
- W4313434480 hasConceptScore W4313434480C43521106 @default.
- W4313434480 hasConceptScore W4313434480C548081761 @default.
- W4313434480 hasConceptScore W4313434480C58874564 @default.
- W4313434480 hasConceptScore W4313434480C76155785 @default.
- W4313434480 hasConceptScore W4313434480C81363708 @default.
- W4313434480 hasIssue "1" @default.
- W4313434480 hasLocation W43134344801 @default.
- W4313434480 hasOpenAccess W4313434480 @default.
- W4313434480 hasPrimaryLocation W43134344801 @default.