Abstract
In recent years, the development of fire detectors has attracted the attention of researchers for the purpose of protecting human lives and properties from catastrophic fire disasters. However, monitoring fires is challenging due to several unique characteristics of fire sensor signals, such as the existence of temporal dependency and diverse signal patterns for different fire types, including flaming, heating, and smoldering fires. In this study, we propose a new approach for fire detection based on machine learning and optimization techniques, to monitor various types of fire by utilizing information obtained via multichannel fire sensor signals. The contribution of this study is to improve an existing fire detector by developing a new fire monitoring framework to identify fire based on support vector machine with dynamic time warping kernel function (SVM-DTWK), which considers the temporal dynamics existing in the sensor signals of different fire types. In addition, multichannel sensor signals are further considered by the SVM-DTWK with a multi-modeling framework that constructs multiple classifiers for each sensor type and effectively utilizes sensor information that is critical for the detection of fires without prior knowledge of the fire type. Using real-life fire data, the proposed approach is compared with existing fire monitoring methods and achieves superior performance in terms of both fire detection time and false alarm rate.
Similar content being viewed by others
References
Fonollosa J, Solórzano A, Marco S (2018) Chemical sensor systems and associated algorithms for fire detection: a review. Sensors 18(2):1–39
Gaur A, Singh A, Kumar A, Kulkarni KS, Lala S, Kapoor K, Srivastava V, Kumar A, Mukhopadhyay SC (2019) Fire sensing technologies: a review. IEEE Sens J 19(9):3191–3202
Ahrens M (2017) Trends and patterns of US fire loss. National Fire Protection Association (NFPA) report Google Scholar
Li P, Zhao W (2020) Image fire detection algorithms based on convolutional neural networks. Case Stud Therm Eng 19:100625
Zhou K, Zhang X (2020) Design of outdoor fire intelligent alarm system based on image recognition. Int J Pattern Recognit Artif Intell 34(07):2050018
Dung NM, Ro S (2018) Algorithm for fire detection using a camera surveillance system. In: Proceedings of the 2018 international conference on image and graphics processing, pp 38–42
Halle W, Fischer C, Terzibaschian T, Zell A, Reulke R (2019) Infrared-image processing for the DLR FireBIRD mission. In: Asian conference on pattern recognition, Springer, pp 235–252
Milke JA, Hulcher ME, Worrell CL, Gottuk DT, Williams FW (2003) Investigation of multi-sensor algorithms for fire detection. Fire Technol 39(4):363–382
Cestari LA, Worrell C, Milke JA (2005) Advanced fire detection algorithms using data from the home smoke detector project. Fire Saf J 40(1):1–28
Chen S-J, Hovde DC, Peterson KA, Marshall AW (2007) Fire detection using smoke and gas sensors. Fire Saf J 42(8):507–515
Muduli L, Mishra DP, Jana PK (2019) Optimized fuzzy logic-based fire monitoring in underground coal mines: binary particle swarm optimization approach. IEEE Syst J 14(2):3039–3046
Li J, Yan B, Zhang M, Zhang J, Jin B, Wang Y, Wang D (2019) Long-range raman distributed fiber temperature sensor with early warning model for fire detection and prevention. IEEE Sens J 19(10):3711–3717
Sivathanu YR, Tseng L (1997) Fire detection using time series analysis of source temperatures. Fire Saf J 29(4):301–315
Luo RC, Su KL (2007) Autonomous fire-detection system using adaptive sensory fusion for intelligent security robot. IEEE/ASME Trans Mechatron 12(3):274–281
Kumar A, Singh A, Kumar A, Singh MK, Mahanta P, Mukhopadhyay SC (2018) Sensing technologies for monitoring intelligent buildings: a review. IEEE Sens J 18(12):4847–4860
Bukowski RW, Peacock RD, Averill JD, Cleary TG, Bryner NP, Walton WD, Reneke PA (2008) Performance of home smoke alarms. NIST Technical Note 1455
Gottuk DT, Peatross MJ, Roby RJ, Beyler CL (2002) Advanced fire detection using multi-signature alarm algorithms. Fire Saf J 37(4):381–394
McAvoy TJ, Milke J, Kunt TA (1996) Using multivariate statistical methods to detect fires. Fire Technol 32(1):6–24
JiJi RD, Hammond MH, Williams FW, Rose-Pehrsson SL (2003) Multivariate statistical process control for continuous monitoring of networked early warning fire detection (EWFD) systems. Sens Actuators B Chem 93(1–3):107–116
Croux C, Ruiz-Gazen A (2005) High breakdown estimators for principal components: the projection-pursuit approach revisited. J Multivar Anal 95(1):206–226
Ferraty F, Vieu P (2006) Nonparametric functional data analysis: theory and practice. Springer, New York
Wang X-G, Lo S-M, Zhang H-P (2013) Influence of feature extraction duration and step size on ANN based multisensor fire detection performance. Procedia Eng 52:413–421
Zheng D, Wang Y, Wang Y (2015) Intelligent monitoring system for home based on FRBF neural network. Int J Smart Home 9(2):207–218
Andrew AM, Zakaria A, Mad Saad S, Md Shakaff AY (2016) Multi-stage feature selection based intelligent classifier for classification of incipient stage fire in building. Sensors, 16(1):31
Duda RO, Hart PE, Stork DG (2012) Pattern classification. Wiley, New Jersey
Folgado D, Barandas M, Matias R, Martins R, Carvalho M, Gamboa H (2018) Time alignment measurement for time series. Pattern Recogn 81:268–279
Keogh E, Ratanamahatana CA (2005) Exact indexing of dynamic time warping. Knowl Inf Syst 7(3):358–386
Petitjean F, Inglada J, Gançarski P (2012) Satellite image time series analysis under time warping. IEEE Trans Geosci Remote Sens 50(8):3081–3095
Shorten G, Burke M (2014) Use of dynamic time warping for accurate ECG signal timing characterization. J Med Eng Technol 38(4):188–201
Li Y, Xue D, Forrister E, Lee G, Garner B, Kim Y (2016) Human activity classification based on dynamic time warping of an on-body creeping wave signal. IEEE Trans Antennas Propag 64(11):4901–4905
Zhang Z, Zhao T, Ao X, Yuan H (2017) A vehicle speed estimation algorithm based on dynamic time warping approach. IEEE Sens J 17(8):2456–2463
Sakoe H, Chiba S (1978) Dynamic programming algorithm optimization for spoken word recognition. IEEE Trans Acoust Speech Signal Process 26(1):43–49
Keogh EJ, Pazzani MJ (2001) Derivative dynamic time warping. In: Proceedings of the 2001 SIAM international conference on data mining, SIAM, pp 1–11
Schölkopf B, Tsuda K, Vert J-P (2004) Support vector machine applications in computational biology. MIT Press, Cambridge
Durgesh KS, Lekha B (2010) Data classification using support vector machine. J Theor Appl Inf Technol 12(1):1–7
Vapnik V (2013) The nature of statistical learning theory. Springer, New York
Tian Y, Shi Y, Liu X (2012) Recent advances on support vector machines research. Technol Econ Dev Econ 18(1):5–33
Schölkopf B (2001) The kernel trick for distances. In: Advances in neural information processing systems, pp 301–307
Bahlmann C, Haasdonk B, Burkhardt H (2002) Online handwriting recognition with support vector machines-a kernel approach. In: Proceedings eighth international workshop on frontiers in handwriting recognition, IEEE, pp 49–54
Lei H, Sun B (2007) A study on the dynamic time warping in kernel machines. In: 2007 third international IEEE conference on signal-image technologies and internet-based system, IEEE, pp 839–845
Kate RJ (2016) Using dynamic time warping distances as features for improved time series classification. Data Min Knowl Disc 30(2):283–312
Murphy KP (2012) Machine learning: a probabilistic perspective. MIT Press, Cambridge
Turkoz M, Kim S, Son Y, Jeong MK, Elsayed EA (2020) Generalized support vector data description for anomaly detection. Pattern Recogn 100:107119
Specht DF (1990) Probabilistic neural networks. Neural Netw 3(1):109–118
Mao KZ, Tan K-C, Ser W (2000) Probabilistic neural-network structure determination for pattern classification. IEEE Trans Neural Netw 11(4):1009–1016
Zhu X, Wu X (2004) Class noise vs. attribute noise: a quantitative study. Artif Intell Rev 2(3):177–210
Acknowledgements
The authors are grateful for the valuable comments from anonymous reviewers. This work was supported in part by the Safety Technology Commercialization Platform Construction Project (No. P0003951) with fund of the South Korean Ministry of Trade, Industry and Energy, National Research Foundation of Korea grant (No. NRF-2019R1F1A1042307) and BK21 FOUR (Brain Korea 21 Fostering Outstanding Universities for Research).
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
Conflict of Interest
The authors declare that they have no conflict of interest.
Code Availability
The code for the experiment is available upon request.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Baek, J., Alhindi, T.J., Jeong, YS. et al. Real-Time Fire Detection Algorithm Based on Support Vector Machine with Dynamic Time Warping Kernel Function. Fire Technol 57, 2929–2953 (2021). https://doi.org/10.1007/s10694-020-01062-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10694-020-01062-1