KutralNet: A Portable Deep Learning Model for Fire Recognition. Ayala, A., Fernandes, B., Cruz, F., MacEdo, D., Oliveira, A., & Zanchettin, C. In Proceedings of the International Joint Conference on Neural Networks, 2020. doi abstract bibtex © 2020 IEEE. Most of the automatic fire alarm systems detect the fire presence through sensors like thermal, smoke, or flame. One of the new approaches to the problem is the use of images to perform the detection. The image approach is promising since it does not need specific sensors and can be easily embedded in different devices. However, besides the high performance, the computational cost of the used deep learning methods is a challenge to their deployment in portable devices. In this work, we propose a new deep learning architecture that requires fewer floating-point operations (flops) for fire recognition. Additionally, we propose a portable approach for fire recognition and the use of modern techniques such as inverted residual block, convolutions like depth-wise, and octave, to reduce the model's computational cost. The experiments show that our model keeps high accuracy while substantially reducing the number of parameters and flops. One of our models presents 71% fewer parameters than FireNet, while still presenting competitive accuracy and AUROC performance. The proposed methods are evaluated on FireNet and FiSmo datasets. The obtained results are promising for the implementation of the model in a mobile device, considering the reduced number of flops and parameters acquired.
@inproceedings{
title = {KutralNet: A Portable Deep Learning Model for Fire Recognition},
type = {inproceedings},
year = {2020},
keywords = {deep learning,fire recognition,portable models},
id = {0cbf3327-68bb-3de0-a2f1-eebec883a99e},
created = {2020-10-30T23:59:00.000Z},
file_attached = {false},
profile_id = {74e7d4ea-3dac-3118-aab9-511a5b337e8f},
last_modified = {2020-11-04T08:26:12.683Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {false},
hidden = {false},
private_publication = {false},
abstract = {© 2020 IEEE. Most of the automatic fire alarm systems detect the fire presence through sensors like thermal, smoke, or flame. One of the new approaches to the problem is the use of images to perform the detection. The image approach is promising since it does not need specific sensors and can be easily embedded in different devices. However, besides the high performance, the computational cost of the used deep learning methods is a challenge to their deployment in portable devices. In this work, we propose a new deep learning architecture that requires fewer floating-point operations (flops) for fire recognition. Additionally, we propose a portable approach for fire recognition and the use of modern techniques such as inverted residual block, convolutions like depth-wise, and octave, to reduce the model's computational cost. The experiments show that our model keeps high accuracy while substantially reducing the number of parameters and flops. One of our models presents 71% fewer parameters than FireNet, while still presenting competitive accuracy and AUROC performance. The proposed methods are evaluated on FireNet and FiSmo datasets. The obtained results are promising for the implementation of the model in a mobile device, considering the reduced number of flops and parameters acquired.},
bibtype = {inproceedings},
author = {Ayala, A. and Fernandes, B. and Cruz, F. and MacEdo, D. and Oliveira, A.L.I. and Zanchettin, C.},
doi = {10.1109/IJCNN48605.2020.9207202},
booktitle = {Proceedings of the International Joint Conference on Neural Networks}
}
Downloads: 0
{"_id":"zB5Rw29DyrZyodzGT","bibbaseid":"ayala-fernandes-cruz-macedo-oliveira-zanchettin-kutralnetaportabledeeplearningmodelforfirerecognition-2020","authorIDs":["PtDsdiZ3iPSFZKH6J"],"author_short":["Ayala, A.","Fernandes, B.","Cruz, F.","MacEdo, D.","Oliveira, A.","Zanchettin, C."],"bibdata":{"title":"KutralNet: A Portable Deep Learning Model for Fire Recognition","type":"inproceedings","year":"2020","keywords":"deep learning,fire recognition,portable models","id":"0cbf3327-68bb-3de0-a2f1-eebec883a99e","created":"2020-10-30T23:59:00.000Z","file_attached":false,"profile_id":"74e7d4ea-3dac-3118-aab9-511a5b337e8f","last_modified":"2020-11-04T08:26:12.683Z","read":false,"starred":false,"authored":"true","confirmed":false,"hidden":false,"private_publication":false,"abstract":"© 2020 IEEE. Most of the automatic fire alarm systems detect the fire presence through sensors like thermal, smoke, or flame. One of the new approaches to the problem is the use of images to perform the detection. The image approach is promising since it does not need specific sensors and can be easily embedded in different devices. However, besides the high performance, the computational cost of the used deep learning methods is a challenge to their deployment in portable devices. In this work, we propose a new deep learning architecture that requires fewer floating-point operations (flops) for fire recognition. Additionally, we propose a portable approach for fire recognition and the use of modern techniques such as inverted residual block, convolutions like depth-wise, and octave, to reduce the model's computational cost. The experiments show that our model keeps high accuracy while substantially reducing the number of parameters and flops. One of our models presents 71% fewer parameters than FireNet, while still presenting competitive accuracy and AUROC performance. The proposed methods are evaluated on FireNet and FiSmo datasets. The obtained results are promising for the implementation of the model in a mobile device, considering the reduced number of flops and parameters acquired.","bibtype":"inproceedings","author":"Ayala, A. and Fernandes, B. and Cruz, F. and MacEdo, D. and Oliveira, A.L.I. and Zanchettin, C.","doi":"10.1109/IJCNN48605.2020.9207202","booktitle":"Proceedings of the International Joint Conference on Neural Networks","bibtex":"@inproceedings{\n title = {KutralNet: A Portable Deep Learning Model for Fire Recognition},\n type = {inproceedings},\n year = {2020},\n keywords = {deep learning,fire recognition,portable models},\n id = {0cbf3327-68bb-3de0-a2f1-eebec883a99e},\n created = {2020-10-30T23:59:00.000Z},\n file_attached = {false},\n profile_id = {74e7d4ea-3dac-3118-aab9-511a5b337e8f},\n last_modified = {2020-11-04T08:26:12.683Z},\n read = {false},\n starred = {false},\n authored = {true},\n confirmed = {false},\n hidden = {false},\n private_publication = {false},\n abstract = {© 2020 IEEE. Most of the automatic fire alarm systems detect the fire presence through sensors like thermal, smoke, or flame. One of the new approaches to the problem is the use of images to perform the detection. The image approach is promising since it does not need specific sensors and can be easily embedded in different devices. However, besides the high performance, the computational cost of the used deep learning methods is a challenge to their deployment in portable devices. In this work, we propose a new deep learning architecture that requires fewer floating-point operations (flops) for fire recognition. Additionally, we propose a portable approach for fire recognition and the use of modern techniques such as inverted residual block, convolutions like depth-wise, and octave, to reduce the model's computational cost. The experiments show that our model keeps high accuracy while substantially reducing the number of parameters and flops. One of our models presents 71% fewer parameters than FireNet, while still presenting competitive accuracy and AUROC performance. The proposed methods are evaluated on FireNet and FiSmo datasets. The obtained results are promising for the implementation of the model in a mobile device, considering the reduced number of flops and parameters acquired.},\n bibtype = {inproceedings},\n author = {Ayala, A. and Fernandes, B. and Cruz, F. and MacEdo, D. and Oliveira, A.L.I. and Zanchettin, C.},\n doi = {10.1109/IJCNN48605.2020.9207202},\n booktitle = {Proceedings of the International Joint Conference on Neural Networks}\n}","author_short":["Ayala, A.","Fernandes, B.","Cruz, F.","MacEdo, D.","Oliveira, A.","Zanchettin, C."],"biburl":"https://bibbase.org/service/mendeley/74e7d4ea-3dac-3118-aab9-511a5b337e8f","bibbaseid":"ayala-fernandes-cruz-macedo-oliveira-zanchettin-kutralnetaportabledeeplearningmodelforfirerecognition-2020","role":"author","urls":{},"keyword":["deep learning","fire recognition","portable models"],"metadata":{"authorlinks":{"zanchettin, c":"https://zanche.github.io/publications/"}},"downloads":0},"bibtype":"inproceedings","biburl":"https://bibbase.org/service/mendeley/74e7d4ea-3dac-3118-aab9-511a5b337e8f","creationDate":"2020-12-26T17:53:36.591Z","downloads":0,"keywords":["deep learning","fire recognition","portable models"],"search_terms":["kutralnet","portable","deep","learning","model","fire","recognition","ayala","fernandes","cruz","macedo","oliveira","zanchettin"],"title":"KutralNet: A Portable Deep Learning Model for Fire Recognition","year":2020,"dataSources":["fvRdkx56Jpp5ebtSw"]}