TY - GEN
T1 - Machine Learning Applications for Fire Detection in a Residential Building
AU - Mwedzi, Ngonidzashe A.
AU - Nwulu, Nnamdi I.
AU - Gbadamosi, Saheed Lekan
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/12
Y1 - 2019/12
N2 - Fire is one of the most serious accidents that can occur in houses, schools, offices and companies. This can lead to several losses, causalities and serious equipment damages. It is highly essential to put in place advanced disaster response mechanisms in order to safeguard against fire disaster in our environment. Recently, modern buildings possess surveillance cameras for security purpose, such cameras can be utilized for fire detection in buildings. In this paper, deep learning and computer vision are applied for detecting fire incident in different systems. The proposed model utilizes an advanced image processing and classification algorithms via deep learning and convolutional neural networks (CNN) to improve the performance of residential fire alarms and eradicate nuisance alarm scenarios.
AB - Fire is one of the most serious accidents that can occur in houses, schools, offices and companies. This can lead to several losses, causalities and serious equipment damages. It is highly essential to put in place advanced disaster response mechanisms in order to safeguard against fire disaster in our environment. Recently, modern buildings possess surveillance cameras for security purpose, such cameras can be utilized for fire detection in buildings. In this paper, deep learning and computer vision are applied for detecting fire incident in different systems. The proposed model utilizes an advanced image processing and classification algorithms via deep learning and convolutional neural networks (CNN) to improve the performance of residential fire alarms and eradicate nuisance alarm scenarios.
KW - Deep Learning
KW - false alarm
KW - fire detection
UR - http://www.scopus.com/inward/record.url?scp=85090247578&partnerID=8YFLogxK
U2 - 10.1109/ICETAS48360.2019.9117318
DO - 10.1109/ICETAS48360.2019.9117318
M3 - Conference contribution
AN - SCOPUS:85090247578
T3 - ICETAS 2019 - 2019 6th IEEE International Conference on Engineering, Technologies and Applied Sciences
BT - ICETAS 2019 - 2019 6th IEEE International Conference on Engineering, Technologies and Applied Sciences
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 6th IEEE International Conference on Engineering, Technologies and Applied Sciences, ICETAS 2019
Y2 - 20 December 2019 through 21 December 2019
ER -