Skip to main content
Erschienen in:

08.12.2022

Hybrid Ensemble Based Machine Learning for Smart Building Fire Detection Using Multi Modal Sensor Data

verfasst von: Sandip Jana, Saikat Kumar Shome

Erschienen in: Fire Technology | Ausgabe 2/2023

Einloggen

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

Fire disasters are one the most challenging accidents that can take place in any urban buildings like houses, offices, hospitals, colleges and industries. These accidents which the world faces now, have never been more frequent and fatal, leading to innumerable loses, damage of expensive equipment and unparalleled human lives. The concrete landscapes are threatened by fire disasters, which have prolifically outnumbered in the last decade, both in intensity and frequency. Thus, to minimize the impact of fire disasters, adoption of well planned, intelligent and robust fire detection technology harnessing the niches of machine learning is necessary for early warning and coordinated prevention and response approach. In this research a novel hybrid ensemble technology based machine algorithm using maximum averaging voting classifier has been designed for fire detection in buildings. The proposed model uses feature engineering pre-processing techniques followed by a synergistic integration of four classifiers namely, logistic regression, support vector machine (SVM), Decision tree and Naive Bayes classifier to yield better prediction and improved robustness. A database from NIST has been chosen to validate the research under different fire scenarios. Results indicate an improved classification accuracy of the proposed ensemble technique as compared to reported literatures. After validating the algorithm, the firmware has been implemented on a laboratory developed prototype of smart multi sensor, embedded fire detection node. The designed smart hardware is successfully able to transmit the sensed data wirelessly onto the cloud platform for further data analytics in real time with high precision and reduced root mean square error (MAE).

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Literatur
1.
Zurück zum Zitat Bu F, Gharajeh MS (2019) Intelligent and vision-based fire detection systems: a survey. Image Vis Comput 91:103803CrossRef Bu F, Gharajeh MS (2019) Intelligent and vision-based fire detection systems: a survey. Image Vis Comput 91:103803CrossRef
2.
Zurück zum Zitat Wu H, Wu D, Zhao J (2019) An intelligent fire detection approach through cameras based on computer vision methods. Process Saf Environ Prot 127:245–256CrossRef Wu H, Wu D, Zhao J (2019) An intelligent fire detection approach through cameras based on computer vision methods. Process Saf Environ Prot 127:245–256CrossRef
3.
Zurück zum Zitat Meacham BJ (1994) The use of artificial intelligence techniques for signal discrimination in fire detection systems. J Fire Prot Eng 6:125–136CrossRef Meacham BJ (1994) The use of artificial intelligence techniques for signal discrimination in fire detection systems. J Fire Prot Eng 6:125–136CrossRef
4.
Zurück zum Zitat Ko B, Cheong K, Nam J (2009) Fire detection based on vision sensor and support vector machines. Fire Safety J 44:322–329CrossRef Ko B, Cheong K, Nam J (2009) Fire detection based on vision sensor and support vector machines. Fire Safety J 44:322–329CrossRef
5.
Zurück zum Zitat Olivas JA (2003) Forest fire prediction and management using soft computing Proceedings of the International Conference on Industrial Informatics (INDIN), pp. 338–344 Olivas JA (2003) Forest fire prediction and management using soft computing Proceedings of the International Conference on Industrial Informatics (INDIN), pp. 338–344
6.
Zurück zum Zitat Mahdipour E, Dadkhah C (2010) Automatic fire detection based on soft computing techniques: review from 2000 to Artif. Intell Rev 42(4):895–934CrossRef Mahdipour E, Dadkhah C (2010) Automatic fire detection based on soft computing techniques: review from 2000 to Artif. Intell Rev 42(4):895–934CrossRef
7.
Zurück zum Zitat Anezakis VD, Demertzis K, Iliadis L, Spartalis S (2016) A hybrid soft computing approach producing robust forest fire risk indices. In: IFIP International Conference on Artificial Intelligence Applications and Innovations, Springer International Publishing, pp. 191–203. Anezakis VD, Demertzis K, Iliadis L, Spartalis S (2016) A hybrid soft computing approach producing robust forest fire risk indices. In: IFIP International Conference on Artificial Intelligence Applications and Innovations, Springer International Publishing, pp. 191–203.
8.
Zurück zum Zitat Aertsen W, Kint V, Van J, Orshoven K., Ozkan, Muys B (2009) Performance of modelling techniques for the prediction of forest site index: a case study for pine and cedar in the Taurus mountains. Turkey XIII World Forestry Congress, pp. 18–23 Aertsen W, Kint V, Van J, Orshoven K., Ozkan, Muys B (2009) Performance of modelling techniques for the prediction of forest site index: a case study for pine and cedar in the Taurus mountains. Turkey XIII World Forestry Congress, pp. 18–23
9.
Zurück zum Zitat Angelis AD, Ricotta C, Conedera M, Pezzatti GB (2015) Modelling the meteorological forest fire niche in heterogeneous pyrologic conditions. PLoS ONE 10(2):0116875CrossRef Angelis AD, Ricotta C, Conedera M, Pezzatti GB (2015) Modelling the meteorological forest fire niche in heterogeneous pyrologic conditions. PLoS ONE 10(2):0116875CrossRef
10.
Zurück zum Zitat Oliveira S, Oehler F, San-Miguel-Ayanz J, Camia A, Pereira JM (2012) Modeling spatial patterns of fire occurrence in Mediterranean Europe using Multiple Regression and Random Forest Ecol. Manage 275:117–212 Oliveira S, Oehler F, San-Miguel-Ayanz J, Camia A, Pereira JM (2012) Modeling spatial patterns of fire occurrence in Mediterranean Europe using Multiple Regression and Random Forest Ecol. Manage 275:117–212
11.
Zurück zum Zitat West AM, Kumar S, Jarnevich CS (2016) Regional modeling of large wildfires under current and potential future climates in Colorado and Wyoming USA. Clim Change 134(4):565–577CrossRef West AM, Kumar S, Jarnevich CS (2016) Regional modeling of large wildfires under current and potential future climates in Colorado and Wyoming USA. Clim Change 134(4):565–577CrossRef
12.
Zurück zum Zitat Bedia J, Herrera S, Camia A, Moreno JM, Gutiérrez JM (2014) Forest fire danger projections in the Mediterranean using ENSEMBLES regional climate change scenarios. Clim Change 122(1–2):185–199CrossRef Bedia J, Herrera S, Camia A, Moreno JM, Gutiérrez JM (2014) Forest fire danger projections in the Mediterranean using ENSEMBLES regional climate change scenarios. Clim Change 122(1–2):185–199CrossRef
13.
Zurück zum Zitat Amatulli G, Camia A, San-Miguel-Ayanz J (2013) Estimating future burned areas under changing climate in the EU-Mediterranean countries Sci. Total Environ 450:209–222CrossRef Amatulli G, Camia A, San-Miguel-Ayanz J (2013) Estimating future burned areas under changing climate in the EU-Mediterranean countries Sci. Total Environ 450:209–222CrossRef
15.
Zurück zum Zitat Özbayoğlu AM, Bozer R (2012) Estimation of the burned area in forest fires using computational intelligence techniques. Proc Comput Sci 12:282–287CrossRef Özbayoğlu AM, Bozer R (2012) Estimation of the burned area in forest fires using computational intelligence techniques. Proc Comput Sci 12:282–287CrossRef
16.
Zurück zum Zitat Yuan C, Zhang Y, Liu Z (2015) A survey on technologies for automatic forest fire monitoring detection and fighting using unmanned aerial vehicles and remote sensing techniques. Can J Forest Res 45(7):783–792CrossRef Yuan C, Zhang Y, Liu Z (2015) A survey on technologies for automatic forest fire monitoring detection and fighting using unmanned aerial vehicles and remote sensing techniques. Can J Forest Res 45(7):783–792CrossRef
17.
Zurück zum Zitat Denham M, Cortés AT , Margalef E (2008) Applying a dynamic data driven genetic algorithm to improve forest fire spread prediction International Conference on Computational Science. Springer Berlin Heidelberg, pp. 36–45 Denham M, Cortés AT , Margalef E (2008) Applying a dynamic data driven genetic algorithm to improve forest fire spread prediction International Conference on Computational Science. Springer Berlin Heidelberg, pp. 36–45
18.
Zurück zum Zitat Bui DT, Bui QT, Nguyen QP, Pradhan B, Nampak H, Trinh PT (2017) A hybrid artificial intelligence approach using GIS-based neural-fuzzy inference system and particle swarm optimization for forest fire susceptibility modeling at a tropical area. Agric For Meteorol 233:32–44CrossRef Bui DT, Bui QT, Nguyen QP, Pradhan B, Nampak H, Trinh PT (2017) A hybrid artificial intelligence approach using GIS-based neural-fuzzy inference system and particle swarm optimization for forest fire susceptibility modeling at a tropical area. Agric For Meteorol 233:32–44CrossRef
20.
Zurück zum Zitat Hong H, Naghibi SA, Dashtpagerdi MM, Pourghasemi HR, Chen W (2017) A comparative assessment between linear and quadratic discriminant analyses (LDA-QDA) with frequency ratio and weights-of-evidence models for forest fire susceptibility mapping in China. Arab J Geosci 10:167CrossRef Hong H, Naghibi SA, Dashtpagerdi MM, Pourghasemi HR, Chen W (2017) A comparative assessment between linear and quadratic discriminant analyses (LDA-QDA) with frequency ratio and weights-of-evidence models for forest fire susceptibility mapping in China. Arab J Geosci 10:167CrossRef
21.
Zurück zum Zitat Bisquert M, Caselles E, Sánchez JM, Caselles V (2012) Application of artificial neural networks and logistic regression to the prediction of forest fire danger in Galicia using MODIS data. Int J Wildland Fire 21:1025–1029CrossRef Bisquert M, Caselles E, Sánchez JM, Caselles V (2012) Application of artificial neural networks and logistic regression to the prediction of forest fire danger in Galicia using MODIS data. Int J Wildland Fire 21:1025–1029CrossRef
23.
Zurück zum Zitat Maeda EE, Formaggio AR, Shimabukuro YE, Arcoverde GFB, Hansen MC (2009) Predicting forest fire in the Brazilian Amazon using MODIS imagery and artificial neural networks. Int J Appl Earth Obs Geoinf 11:265–272 Maeda EE, Formaggio AR, Shimabukuro YE, Arcoverde GFB, Hansen MC (2009) Predicting forest fire in the Brazilian Amazon using MODIS imagery and artificial neural networks. Int J Appl Earth Obs Geoinf 11:265–272
24.
Zurück zum Zitat Safi Y, Bouroumi A (2013) Prediction of forest fires using artificial neural networksAppl. Math Sci 7:271–286 Safi Y, Bouroumi A (2013) Prediction of forest fires using artificial neural networksAppl. Math Sci 7:271–286
25.
Zurück zum Zitat Basheer I, Hajmeer AM (2000) Artificial neural networks: fundamentals computing design and application. J Microbiol Methods 43:3–31CrossRef Basheer I, Hajmeer AM (2000) Artificial neural networks: fundamentals computing design and application. J Microbiol Methods 43:3–31CrossRef
26.
Zurück zum Zitat Sakr GE, Elhajj IH, Mitri G (2011) Efficient forest fire occurrence prediction for developing countries using two weather parametersEng. Appl Artif Intell 24:888–894CrossRef Sakr GE, Elhajj IH, Mitri G (2011) Efficient forest fire occurrence prediction for developing countries using two weather parametersEng. Appl Artif Intell 24:888–894CrossRef
27.
Zurück zum Zitat Xie DW, Shi SL (2014) Prediction for burned area of forest fires based on SVM model. Appl Mech Mater 513:4084–4089CrossRef Xie DW, Shi SL (2014) Prediction for burned area of forest fires based on SVM model. Appl Mech Mater 513:4084–4089CrossRef
28.
Zurück zum Zitat Ko BC, Cheong KH, Nam JY (2009) Fire detection based on vision sensor and support vector machines. Fire Saf J 44:322–329CrossRef Ko BC, Cheong KH, Nam JY (2009) Fire detection based on vision sensor and support vector machines. Fire Saf J 44:322–329CrossRef
29.
Zurück zum Zitat Zhao J, Zhang Z, Han S, Qu C, Yuan Z, Zhang D (2011) SVM based forest fire detection using static and dynamic features. Computer Sci Inform Syst 8:821–841CrossRef Zhao J, Zhang Z, Han S, Qu C, Yuan Z, Zhang D (2011) SVM based forest fire detection using static and dynamic features. Computer Sci Inform Syst 8:821–841CrossRef
30.
Zurück zum Zitat Wen T, Zhang B, University LT (2014) Prediction model for open-pit coal mine slope stability based on random forest. Sci Technol Rev 32:105–109 Wen T, Zhang B, University LT (2014) Prediction model for open-pit coal mine slope stability based on random forest. Sci Technol Rev 32:105–109
35.
Zurück zum Zitat Zhao H, Yin S, Ru Z (2012) Relevance vector machine applied to slope stability analysis. Int J Numer Anal Meth Geomech 36:643–652CrossRef Zhao H, Yin S, Ru Z (2012) Relevance vector machine applied to slope stability analysis. Int J Numer Anal Meth Geomech 36:643–652CrossRef
38.
Zurück zum Zitat Chok YH, Jaksa MB, Kaggwa WS, Griffiths DV, Fenton GA (2016) Neural network prediction of the reliability of heterogeneous cohesive slopes. Int J Numer Anal Meth Geomech 40:1556–1569CrossRef Chok YH, Jaksa MB, Kaggwa WS, Griffiths DV, Fenton GA (2016) Neural network prediction of the reliability of heterogeneous cohesive slopes. Int J Numer Anal Meth Geomech 40:1556–1569CrossRef
40.
Zurück zum Zitat Dietterich TG (1997) Machine-learning research. AI Mag 18:97 Dietterich TG (1997) Machine-learning research. AI Mag 18:97
41.
Zurück zum Zitat Cho SB, Ryu J (2002) Classifying gene expression data of cancer using classifier ensemble with mutually exclusive features. Proc IEEE 90:1744–1753CrossRef Cho SB, Ryu J (2002) Classifying gene expression data of cancer using classifier ensemble with mutually exclusive features. Proc IEEE 90:1744–1753CrossRef
44.
Zurück zum Zitat Jiakun Z, Ju J, Si C, Ruifeng Z, Bilin Y, Qingfang L (2020) A weighted hybrid ensemble method for classifying imbalanced data” Knowledge-Based Systems. ISSN 203:106087 Jiakun Z, Ju J, Si C, Ruifeng Z, Bilin Y, Qingfang L (2020) A weighted hybrid ensemble method for classifying imbalanced data” Knowledge-Based Systems. ISSN 203:106087
45.
Zurück zum Zitat He H, Garcia EA (2009) Learning from imbalanced data. IEEE Trans Knowl Data Eng 21:1263–1284CrossRef He H, Garcia EA (2009) Learning from imbalanced data. IEEE Trans Knowl Data Eng 21:1263–1284CrossRef
49.
Zurück zum Zitat Liu H, Gegov A, Cocea M (2015) Hybrid ensemble learning approach for generation of classification rules. International Conference on Machine Learning and Cybernetics (ICMLC) . pp. 377–382 Liu H, Gegov A, Cocea M (2015) Hybrid ensemble learning approach for generation of classification rules. International Conference on Machine Learning and Cybernetics (ICMLC) . pp. 377–382
51.
Zurück zum Zitat Yang S, Chen L, Yan T, Zhao Y, Fan Y (2017) An ensemble classification algorithm for convolutional neural network based on AdaBoost. IEEE/ACIS 16th International Conference on Computer and Information Science (ICIS). pp. 401–406 Yang S, Chen L, Yan T, Zhao Y, Fan Y (2017) An ensemble classification algorithm for convolutional neural network based on AdaBoost. IEEE/ACIS 16th International Conference on Computer and Information Science (ICIS). pp. 401–406
52.
Zurück zum Zitat Lu H, Gao H, Ye M, Wang X (2019) A Hybrid ensemble algorithm combining adaboost and genetic algorithm for cancer classification with gene expression data. IEEE/ACM Trans Comput Biol Bioinf 01:1–1 Lu H, Gao H, Ye M, Wang X (2019) A Hybrid ensemble algorithm combining adaboost and genetic algorithm for cancer classification with gene expression data. IEEE/ACM Trans Comput Biol Bioinf 01:1–1
54.
Zurück zum Zitat Vahini Ezhilraman S, Srinivasan S et al (2019) Breast cancer detection using gradient boost ensemble decision tree classifier. Int J Eng Adv Technol 9:2249–8958 Vahini Ezhilraman S, Srinivasan S et al (2019) Breast cancer detection using gradient boost ensemble decision tree classifier. Int J Eng Adv Technol 9:2249–8958
62.
Zurück zum Zitat Rosadi D, Andriyani W (2021) Prediction of forest fire using ensemble method. J Phys: Conf Ser 1918:042043 Rosadi D, Andriyani W (2021) Prediction of forest fire using ensemble method. J Phys: Conf Ser 1918:042043
63.
Zurück zum Zitat Xie Y, Peng M (2018) Forest fire forecasting using ensemble learning approaches. Neural Comput Appl 31:4541–4550CrossRef Xie Y, Peng M (2018) Forest fire forecasting using ensemble learning approaches. Neural Comput Appl 31:4541–4550CrossRef
64.
Zurück zum Zitat Stracher GB et al (2019) Gases generated during the low-temperature oxidation and pyrolysis of coal and the effects on methane-air flammable limits. In: Stracher GB (ed) Coal and peat fires: a global perspective. Elsevier, Amsterdam, pp 157–171CrossRef Stracher GB et al (2019) Gases generated during the low-temperature oxidation and pyrolysis of coal and the effects on methane-air flammable limits. In: Stracher GB (ed) Coal and peat fires: a global perspective. Elsevier, Amsterdam, pp 157–171CrossRef
65.
Zurück zum Zitat Nikunj C et al (2004) Ensemble Data Mining Methods NASA Ames Research Centre, USA Nikunj C et al (2004) Ensemble Data Mining Methods NASA Ames Research Centre, USA
66.
Zurück zum Zitat Kohavi R ( 2001) A study of cross‐validation and bootstrap for accuracy estimation and model selection. In International Joint Conference on ArtificialIntelligence, pp. 1137‐1143 Kohavi R ( 2001) A study of cross‐validation and bootstrap for accuracy estimation and model selection. In International Joint Conference on ArtificialIntelligence, pp. 1137‐1143
67.
Zurück zum Zitat Jiao Z, Zhang Y, Xin J et al (2019) A deep learning based forest fire detection approach using uav and yolov3. In 2019 1st International Conference on Industrial Artificial Intelligence (IAI), Shenyang, China, 2019, pp. 1–5 Jiao Z, Zhang Y, Xin J et al (2019) A deep learning based forest fire detection approach using uav and yolov3. In 2019 1st International Conference on Industrial Artificial Intelligence (IAI), Shenyang, China, 2019, pp. 1–5
68.
Zurück zum Zitat Lin Z, Chen F, Li B et al (2019) A contextual and multitemporal active-fire detection algorithm based on FengYun-2G SVISSR data. IEEE Trans Geosci Remote Sens 57(11):8840–8852CrossRef Lin Z, Chen F, Li B et al (2019) A contextual and multitemporal active-fire detection algorithm based on FengYun-2G SVISSR data. IEEE Trans Geosci Remote Sens 57(11):8840–8852CrossRef
69.
Zurück zum Zitat Jang E, Kang Y, Im J, Lee DW, Yoon J, Kim SK (2019) Detection and monitoring of forest fires using Himawari-8 geostationary satellite data in South Korea. Remote Sensing 11(3):271CrossRef Jang E, Kang Y, Im J, Lee DW, Yoon J, Kim SK (2019) Detection and monitoring of forest fires using Himawari-8 geostationary satellite data in South Korea. Remote Sensing 11(3):271CrossRef
70.
Zurück zum Zitat Shi F, Qian H, Chen W, Huang M, Wan Z (2020) A fire monitoring and alarm system based on YOLOv3 with OHEM. In: Proceedings of the 2020 39th Chinese Control Conference (CCC), Shenyang, China, 27–29 July 2020, pp. 7322–7327 Shi F, Qian H, Chen W, Huang M, Wan Z (2020) A fire monitoring and alarm system based on YOLOv3 with OHEM. In: Proceedings of the 2020 39th Chinese Control Conference (CCC), Shenyang, China, 27–29 July 2020, pp. 7322–7327
71.
Zurück zum Zitat Kim B, Lee J (2019) A video-based fire detection using deep learning models. Appl Sci 9:2862CrossRef Kim B, Lee J (2019) A video-based fire detection using deep learning models. Appl Sci 9:2862CrossRef
Metadaten
Titel
Hybrid Ensemble Based Machine Learning for Smart Building Fire Detection Using Multi Modal Sensor Data
verfasst von
Sandip Jana
Saikat Kumar Shome
Publikationsdatum
08.12.2022
Verlag
Springer US
Erschienen in
Fire Technology / Ausgabe 2/2023
Print ISSN: 0015-2684
Elektronische ISSN: 1572-8099
DOI
https://doi.org/10.1007/s10694-022-01347-7

Weitere Artikel der Ausgabe 2/2023

Fire Technology 2/2023 Zur Ausgabe