Fire monitoring process.
<div><p>Ensuring safety and safeguarding indoor properties require reliable fire detection methods. Traditional detection techniques that use smoke, heat, or fire sensors often fail due to false positives and slow response time. Existing deep learning-based object detectors fall short of...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | , |
| Published: |
2025
|
| Subjects: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1852020934057132032 |
|---|---|
| author | Md. Shafak Shahriar Sozol (21212880) |
| author2 | M. Rubaiyat Hossain Mondal (8415447) Achmad Husni Thamrin (21212883) |
| author2_role | author author |
| author_facet | Md. Shafak Shahriar Sozol (21212880) M. Rubaiyat Hossain Mondal (8415447) Achmad Husni Thamrin (21212883) |
| author_role | author |
| dc.creator.none.fl_str_mv | Md. Shafak Shahriar Sozol (21212880) M. Rubaiyat Hossain Mondal (8415447) Achmad Husni Thamrin (21212883) |
| dc.date.none.fl_str_mv | 2025-04-29T17:47:28Z |
| dc.identifier.none.fl_str_mv | 10.1371/journal.pone.0322052.g004 |
| dc.relation.none.fl_str_mv | https://figshare.com/articles/figure/Fire_monitoring_process_/28895766 |
| dc.rights.none.fl_str_mv | CC BY 4.0 info:eu-repo/semantics/openAccess |
| dc.subject.none.fl_str_mv | Medicine Space Science Biological Sciences not elsewhere classified Information Systems not elsewhere classified including faster r href =" mailto existing deep learning traditional detection techniques provide visual explanations proposed model achieved slow response time div >< p actual fire hazards smoke detection based research combined yolov5 smoke detection model predictions model optimized use smoke time monitoring testing samples study aimed smoke images provide real prospective scenarios optimized yolov5 indoor settings indoor fire improved accuracy genetic algorithm future developments fire progression false positives ensuring safety ensuring interpretability dynamic nature cam technique art models also used 1 %, 000 images |
| dc.title.none.fl_str_mv | Fire monitoring process. |
| dc.type.none.fl_str_mv | Image Figure info:eu-repo/semantics/publishedVersion image |
| description | <div><p>Ensuring safety and safeguarding indoor properties require reliable fire detection methods. Traditional detection techniques that use smoke, heat, or fire sensors often fail due to false positives and slow response time. Existing deep learning-based object detectors fall short of improved accuracy in indoor settings and real-time tracking, considering the dynamic nature of fire and smoke. This study aimed to address these challenges in fire and smoke detection in indoor settings. It presents a hyperparameter-optimized YOLOv5 (HPO-YOLOv5) model optimized by a genetic algorithm. To cover all prospective scenarios, we created a novel dataset comprising indoor fire and smoke images. There are 5,000 images in the dataset, split into training, validation, and testing samples at a ratio of 80:10:10. It also used the Grad-CAM technique to provide visual explanations for model predictions, ensuring interpretability and transparency. This research combined YOLOv5 with DeepSORT (which uses deep learning features to improve the tracking of objects over time) to provide real-time monitoring of fire progression. Thus, it allows for the notification of actual fire hazards. With a mean average precision (<a href="mailto:mAP@0.5" target="_blank">mAP@0.5</a>) of 92.1%, the HPO-YOLOv5 model outperformed state-of-the-art models, including Faster R-CNN, YOLOv5, YOLOv7 and YOLOv8. The proposed model achieved a 2.4% improvement in mAP@0.5 over the original YOLOv5 baseline model. The research has laid the foundation for future developments in fire hazard detection technology, a system that is dependable and effective in indoor scenarios.</p></div> |
| eu_rights_str_mv | openAccess |
| id | Manara_5b3e1e7db7f1069d466fa9be1ab9fd5a |
| identifier_str_mv | 10.1371/journal.pone.0322052.g004 |
| network_acronym_str | Manara |
| network_name_str | ManaraRepo |
| oai_identifier_str | oai:figshare.com:article/28895766 |
| publishDate | 2025 |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| rights_invalid_str_mv | CC BY 4.0 |
| spelling | Fire monitoring process.Md. Shafak Shahriar Sozol (21212880)M. Rubaiyat Hossain Mondal (8415447)Achmad Husni Thamrin (21212883)MedicineSpace ScienceBiological Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedincluding faster rhref =" mailtoexisting deep learningtraditional detection techniquesprovide visual explanationsproposed model achievedslow response timediv >< pactual fire hazardssmoke detection basedresearch combined yolov5smoke detectionmodel predictionsmodel optimizeduse smoketime monitoringtesting samplesstudy aimedsmoke imagesprovide realprospective scenariosoptimized yolov5indoor settingsindoor fireimproved accuracygenetic algorithmfuture developmentsfire progressionfalse positivesensuring safetyensuring interpretabilitydynamic naturecam techniqueart modelsalso used1 %,000 images<div><p>Ensuring safety and safeguarding indoor properties require reliable fire detection methods. Traditional detection techniques that use smoke, heat, or fire sensors often fail due to false positives and slow response time. Existing deep learning-based object detectors fall short of improved accuracy in indoor settings and real-time tracking, considering the dynamic nature of fire and smoke. This study aimed to address these challenges in fire and smoke detection in indoor settings. It presents a hyperparameter-optimized YOLOv5 (HPO-YOLOv5) model optimized by a genetic algorithm. To cover all prospective scenarios, we created a novel dataset comprising indoor fire and smoke images. There are 5,000 images in the dataset, split into training, validation, and testing samples at a ratio of 80:10:10. It also used the Grad-CAM technique to provide visual explanations for model predictions, ensuring interpretability and transparency. This research combined YOLOv5 with DeepSORT (which uses deep learning features to improve the tracking of objects over time) to provide real-time monitoring of fire progression. Thus, it allows for the notification of actual fire hazards. With a mean average precision (<a href="mailto:mAP@0.5" target="_blank">mAP@0.5</a>) of 92.1%, the HPO-YOLOv5 model outperformed state-of-the-art models, including Faster R-CNN, YOLOv5, YOLOv7 and YOLOv8. The proposed model achieved a 2.4% improvement in mAP@0.5 over the original YOLOv5 baseline model. The research has laid the foundation for future developments in fire hazard detection technology, a system that is dependable and effective in indoor scenarios.</p></div>2025-04-29T17:47:28ZImageFigureinfo:eu-repo/semantics/publishedVersionimage10.1371/journal.pone.0322052.g004https://figshare.com/articles/figure/Fire_monitoring_process_/28895766CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/288957662025-04-29T17:47:28Z |
| spellingShingle | Fire monitoring process. Md. Shafak Shahriar Sozol (21212880) Medicine Space Science Biological Sciences not elsewhere classified Information Systems not elsewhere classified including faster r href =" mailto existing deep learning traditional detection techniques provide visual explanations proposed model achieved slow response time div >< p actual fire hazards smoke detection based research combined yolov5 smoke detection model predictions model optimized use smoke time monitoring testing samples study aimed smoke images provide real prospective scenarios optimized yolov5 indoor settings indoor fire improved accuracy genetic algorithm future developments fire progression false positives ensuring safety ensuring interpretability dynamic nature cam technique art models also used 1 %, 000 images |
| status_str | publishedVersion |
| title | Fire monitoring process. |
| title_full | Fire monitoring process. |
| title_fullStr | Fire monitoring process. |
| title_full_unstemmed | Fire monitoring process. |
| title_short | Fire monitoring process. |
| title_sort | Fire monitoring process. |
| topic | Medicine Space Science Biological Sciences not elsewhere classified Information Systems not elsewhere classified including faster r href =" mailto existing deep learning traditional detection techniques provide visual explanations proposed model achieved slow response time div >< p actual fire hazards smoke detection based research combined yolov5 smoke detection model predictions model optimized use smoke time monitoring testing samples study aimed smoke images provide real prospective scenarios optimized yolov5 indoor settings indoor fire improved accuracy genetic algorithm future developments fire progression false positives ensuring safety ensuring interpretability dynamic nature cam technique art models also used 1 %, 000 images |