An Indoor Fire Detection Method Based on Multi-Sensor Fusion and a Lightweight Convolutional Neural Network
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...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/24/9689 |
| _version_ | 1797379434050748416 |
|---|---|
| author | Xinwei Deng Xuewei Shi Haosen Wang Qianli Wang Jun Bao Zhuming Chen |
| author_facet | Xinwei Deng Xuewei Shi Haosen Wang Qianli Wang Jun Bao Zhuming Chen |
| author_sort | Xinwei Deng |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-08T20:23:10Z |
| format | Article |
| id | doaj.art-8bd28e0296cc4d7593b11f5ab48071fe |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-08T20:23:10Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-8bd28e0296cc4d7593b11f5ab48071fe2023-12-22T14:40:14ZengMDPI AGSensors1424-82202023-12-012324968910.3390/s23249689An Indoor Fire Detection Method Based on Multi-Sensor Fusion and a Lightweight Convolutional Neural NetworkXinwei Deng0Xuewei Shi1Haosen Wang2Qianli Wang3Jun Bao4Zhuming Chen5Yangtze Delta Region Institute (Quzhou), University of Electronic Science and Technology of China, Quzhou 324003, ChinaYangtze Delta Region Institute (Quzhou), University of Electronic Science and Technology of China, Quzhou 324003, ChinaSchool of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Information Science and Technology, Southwest Jiaotong University, Chengdu 611756, ChinaSchool of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaYangtze Delta Region Institute (Quzhou), University of Electronic Science and Technology of China, Quzhou 324003, ChinaIndoor 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.https://www.mdpi.com/1424-8220/23/24/9689indoor fire detectionfire numerical simulationsensor data fusiontime-series imagingembedded platform |
| spellingShingle | Xinwei Deng Xuewei Shi Haosen Wang Qianli Wang Jun Bao Zhuming Chen An Indoor Fire Detection Method Based on Multi-Sensor Fusion and a Lightweight Convolutional Neural Network Sensors indoor fire detection fire numerical simulation sensor data fusion time-series imaging embedded platform |
| title | An Indoor Fire Detection Method Based on Multi-Sensor Fusion and a Lightweight Convolutional Neural Network |
| title_full | An Indoor Fire Detection Method Based on Multi-Sensor Fusion and a Lightweight Convolutional Neural Network |
| title_fullStr | An Indoor Fire Detection Method Based on Multi-Sensor Fusion and a Lightweight Convolutional Neural Network |
| title_full_unstemmed | An Indoor Fire Detection Method Based on Multi-Sensor Fusion and a Lightweight Convolutional Neural Network |
| title_short | An Indoor Fire Detection Method Based on Multi-Sensor Fusion and a Lightweight Convolutional Neural Network |
| title_sort | indoor fire detection method based on multi sensor fusion and a lightweight convolutional neural network |
| topic | indoor fire detection fire numerical simulation sensor data fusion time-series imaging embedded platform |
| url | https://www.mdpi.com/1424-8220/23/24/9689 |
| work_keys_str_mv | AT xinweideng anindoorfiredetectionmethodbasedonmultisensorfusionandalightweightconvolutionalneuralnetwork AT xueweishi anindoorfiredetectionmethodbasedonmultisensorfusionandalightweightconvolutionalneuralnetwork AT haosenwang anindoorfiredetectionmethodbasedonmultisensorfusionandalightweightconvolutionalneuralnetwork AT qianliwang anindoorfiredetectionmethodbasedonmultisensorfusionandalightweightconvolutionalneuralnetwork AT junbao anindoorfiredetectionmethodbasedonmultisensorfusionandalightweightconvolutionalneuralnetwork AT zhumingchen anindoorfiredetectionmethodbasedonmultisensorfusionandalightweightconvolutionalneuralnetwork AT xinweideng indoorfiredetectionmethodbasedonmultisensorfusionandalightweightconvolutionalneuralnetwork AT xueweishi indoorfiredetectionmethodbasedonmultisensorfusionandalightweightconvolutionalneuralnetwork AT haosenwang indoorfiredetectionmethodbasedonmultisensorfusionandalightweightconvolutionalneuralnetwork AT qianliwang indoorfiredetectionmethodbasedonmultisensorfusionandalightweightconvolutionalneuralnetwork AT junbao indoorfiredetectionmethodbasedonmultisensorfusionandalightweightconvolutionalneuralnetwork AT zhumingchen indoorfiredetectionmethodbasedonmultisensorfusionandalightweightconvolutionalneuralnetwork |