PMID- 38139534
OWN - NLM
STAT- PubMed-not-MEDLINE
LR  - 20231225
IS  - 1424-8220 (Electronic)
IS  - 1424-8220 (Linking)
VI  - 23
IP  - 24
DP  - 2023 Dec 7
TI  - An Indoor Fire Detection Method Based on Multi-Sensor Fusion and a Lightweight 
      Convolutional Neural Network.
LID - 10.3390/s23249689 [doi]
LID - 9689
AB  - Indoor fires pose significant threats in terms of casualties and economic losses 
      globally. Thus, it is vital to accurately detect indoor fires at an early stage. 
      To improve the accuracy of indoor fire detection for the resource-constrained 
      embedded platform, an indoor fire detection method based on multi-sensor fusion 
      and a lightweight convolutional neural network (CNN) is proposed. Firstly, the 
      Savitzky-Golay (SG) filter is used to clean the three types of heterogeneous 
      sensor data, then the cleaned sensor data are transformed by means of the Gramian 
      Angular Field (GAF) method into matrices, which are finally integrated into a 
      three-dimensional matrix. This preprocessing stage will preserve temporal 
      dependency and enlarge the characteristics of time-series data. Therefore, we 
      could reduce the number of blocks, channels and layers in the network, leading to 
      a lightweight CNN for indoor fire detection. Furthermore, we use the Fire Dynamic 
      Simulator (FDS) to simulate data for the training stage, enhancing the robustness 
      of the network. The fire detection performance of the proposed method is verified 
      through an experiment. It was found that the proposed method achieved an 
      impressive accuracy of 99.1%, while the number of CNN parameters and the amount 
      of computation is still small, which is more suitable for the 
      resource-constrained embedded platform of an indoor fire detection system.
FAU - Deng, Xinwei
AU  - Deng X
AD  - Yangtze Delta Region Institute (Quzhou), University of Electronic Science and 
      Technology of China, Quzhou 324003, China.
FAU - Shi, Xuewei
AU  - Shi X
AD  - Yangtze Delta Region Institute (Quzhou), University of Electronic Science and 
      Technology of China, Quzhou 324003, China.
FAU - Wang, Haosen
AU  - Wang H
AD  - School of Information and Communication Engineering, University of Electronic 
      Science and Technology of China, Chengdu 611731, China.
FAU - Wang, Qianli
AU  - Wang Q
AD  - School of Information Science and Technology, Southwest Jiaotong University, 
      Chengdu 611756, China.
FAU - Bao, Jun
AU  - Bao J
AD  - School of Information and Communication Engineering, University of Electronic 
      Science and Technology of China, Chengdu 611731, China.
FAU - Chen, Zhuming
AU  - Chen Z
AD  - Yangtze Delta Region Institute (Quzhou), University of Electronic Science and 
      Technology of China, Quzhou 324003, China.
LA  - eng
GR  - 2022D004./the Municipal Government of Quzhou/
PT  - Journal Article
DEP - 20231207
PL  - Switzerland
TA  - Sensors (Basel)
JT  - Sensors (Basel, Switzerland)
JID - 101204366
SB  - IM
PMC - PMC10747019
OTO - NOTNLM
OT  - embedded platform
OT  - fire numerical simulation
OT  - indoor fire detection
OT  - sensor data fusion
OT  - time-series imaging
COIS- The authors declare no conflict of interest.
EDAT- 2023/12/23 12:43
MHDA- 2023/12/23 12:44
PMCR- 2023/12/07
CRDT- 2023/12/23 01:23
PHST- 2023/10/08 00:00 [received]
PHST- 2023/11/28 00:00 [revised]
PHST- 2023/12/05 00:00 [accepted]
PHST- 2023/12/23 12:44 [medline]
PHST- 2023/12/23 12:43 [pubmed]
PHST- 2023/12/23 01:23 [entrez]
PHST- 2023/12/07 00:00 [pmc-release]
AID - s23249689 [pii]
AID - sensors-23-09689 [pii]
AID - 10.3390/s23249689 [doi]
PST - epublish
SO  - Sensors (Basel). 2023 Dec 7;23(24):9689. doi: 10.3390/s23249689.