Abstract
In case of a dangerous incident, such as a fire, a collision or an earthquake, a lot of contextual data is available for the first incident responders when handling this incident. Based on this data, a commander on scene or dispatchers need to make split-second decisions to get a good overview on the situation and to avoid further injuries or risks. Therefore, we propose a decision support system that can aid incident responders on scene in prioritizing the rescue efforts that need to be addressed. The system collects relevant data from a custom designed drone by detecting objects such as firefighters, fires, victims, fuel tanks, etc. The drone autonomously observes the incident area, and based on the detected information it proposes a prioritized based action list on e.g. urgency or danger to incident responders.
This paper presents the architecture of the framework and a prototype implementation and evaluation of a decision support system, responsible for digesting and prioritizing the large amount of contextual data captured at an incident site. The evaluation of the decision support system shows that the proposed solution works accurately in supporting incident responders in providing a sorted overview of the actions needed in real-time, with an average response time of 334 ms on a less powerful device and 263 ms on a powerful device equipped with a GPU.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
FLIR Boson. http://www.flir.it/cores/boson/
Sony Semiconductor Solutions Corporation - IMX274QC. https://www.sony-semicon.co.jp/products_en/new_pro/october_2016/imx274lqc_e.html
Abadi, M., et al.: TensorFlow: a system for large-scale machine learning. In: 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 2016), pp. 265–284 (2016). https://doi.org/10.1038/nn.3331
Abu-Elkheir, M., Hassanein, H.S., Oteafy, S.M.: Enhancing emergency response systems through leveraging crowdsensing and heterogeneous data. In: 2016 International Wireless Communications and Mobile Computing Conference, IWCMC 2016, pp. 188–193 (2016). https://doi.org/10.1109/IWCMC.2016.7577055
Banerjee, A., Basak, J., Roy, S., Bandyopadhyay, S.: Towards a collaborative disaster management service framework using mobile and web applications. Int. J. Inf. Syst. Crisis Response Manag. 8(1), 65–84 (2016). https://doi.org/10.4018/IJISCRAM.2016010104
Bishop, C.M.: Pattern Recognition and Machine Learning. Springer, New York (2006). https://doi.org/10.1117/1.2819119
Burges, C.J.: A tutorial on support vector machines for pattern recognition. Data Min. Knowl. Discov. 2(2), 121–167 (1998). https://doi.org/10.1023/A:1009715923555
Chen, R., Sharman, R., Rao, H.R., Upadhyaya, S.J.: Coordination in emergency response management. Commun. ACM 51(5), 66–73 (2008). https://doi.org/10.1145/1342327.1342340
Cristianini, N., Shawe-Taylor, J.: An Introduction to Support Vector Machines: And Other Kernel-based Learning Methods. Cambridge University Press, New York (2000)
Dotson, G.S., Hudson, N.L., Maier, A.: A decision support framework for characterizing and managing dermal exposures to chemicals during Emergency Management and Operations. J. Emerg. Manag. 13(4), 359–380 (2015). https://doi.org/10.5055/jem.2015.0248
Fürnkranz, J.: Pruning algorithms for rule learning. Mach. Learn. 27(2), 139–172 (1997). https://doi.org/10.1023/A:1007329424533
Fürnkranz, J.: Separate-and-conquer rule learning. Artif. Intell. Rev. 13(1), 3–54 (1999). https://doi.org/10.1023/A:1006524209794
Fürnkranz, J.: Round robin rule learning. In: Proceedings of the Eighteenth International Conference on Machine Learning, ICML 2001, pp. 146–153. Morgan Kaufmann Publishers Inc., San Francisco (2001). http://dl.acm.org/citation.cfm?id=645530.655685
Google Research: Tensorflow Serving (2017). tensorflow.github.io/serving/
Kotsiantis, S.B.: Supervised machine learning: a review of classification techniques. Informatica 31, 249–268 (2007). https://doi.org/10.1115/1.1559160
Laskey, K.B.: Crowdsourced decision support for emergency responders 4444(703) (2013)
Lim, T.S., Loh, W.Y., Shih, Y.S.: A comparison of prediction accuracy, complexity, and training time of thirty-three old and new classification algorithms. Mach. Learn. 40(3), 203–228 (2000). https://doi.org/10.1023/A:1007608224229
Morentz, J.W., Doyle, C., Skelly, L., Adam, N.: Unified incident command and decision support (UICDS): a department of homeland security initiative in information sharing. In: 2009 IEEE Conference on Technologies for Homeland Security, HST 2009, pp. 182–187 (2009). https://doi.org/10.1109/THS.2009.5168032
Murthy, S.K.: Automatic construction of decision trees from data: a multi-disciplinary survey. Data Min. Knowl. Discov. 2(4), 345–389 (1998). https://doi.org/10.1023/A:1009744630224
Nair, V., Hinton, G.E.: Rectified linear units improve restricted boltzmann machines. In: Proceedings of the 27th International Conference on International Conference on Machine Learning, ICML 2010, Omnipress, USA, pp. 807–814 (2010). http://dl.acm.org/citation.cfm?id=3104322.3104425
Tijtgat, N., Ranst, W.V., Volckaert, B., Goedemé, T., De Turck, F.: Embedded real-time object detection for a UAV warning system. In: 2017 IEEE International Conference on Computer Vision Workshops (ICCVW), pp. 2110–2118 (2017). https://doi.org/10.1109/ICCVW.2017.247
Tijtgat, N., Volckaert, B., De Turck, F.: Real-time hazard symbol detection and localization using UAV imagery. In: 2017 IEEE 86th Vehicular Technology Conference (VTC-Fall), pp. 1–5 (2017). https://doi.org/10.1109/VTCFall.2017.8288259
Torfs, M.: 1 dead, 33 injured in Wetteren train derailment, May 2013. http://deredactie.be/cm/vrtnieuws.english/News/1.1620582
Yildiz, O.T., Dikmen, O.: Parallel univariate decision trees. Pattern Recogn. Lett. 28(7), 825–832 (2007). https://doi.org/10.1016/j.patrec.2006.11.009
Acknowledgement
The authors would like to thank all partners namely, Xtendit Solutions, Fire.BE, DroneMatrix, CityMesh, Seris Security, SAIT and KU Leuven - Eavise, in the 3DSafeGuard-VL project and the Agency for Innovation by Science and Technology (Vlaio) for funding and support.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Moeyersons, J., Maenhaut, PJ., De Turck, F., Volckaert, B. (2018). Aiding First Incident Responders Using a Decision Support System Based on Live Drone Feeds. In: Chen, J., Yamada, Y., Ryoke, M., Tang, X. (eds) Knowledge and Systems Sciences. KSS 2018. Communications in Computer and Information Science, vol 949. Springer, Singapore. https://doi.org/10.1007/978-981-13-3149-7_7
Download citation
DOI: https://doi.org/10.1007/978-981-13-3149-7_7
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-13-3148-0
Online ISBN: 978-981-13-3149-7
eBook Packages: Computer ScienceComputer Science (R0)