ABSTRACT
In our current world of increasingly common natural disasters, new technologies need to be developed to bolster our society's infrastructure during disaster-relief scenarios. Among these services, our communication networks currently serve to be particularly vulnerable, requiring both a constantly operational power grid and a fully functional network to connect residents. This paper aims to design two low cost, low maintenance wireless Free Space Optical Communications (FSOC) designs and connections that are able to function under most points of weather. The devices should sustain a high uptime, have a low Bit Error Rate (BER), and use inexpensive materials and devices to maintain their connection. This system was developed to help reduce this vulnerability of communication infrastructure during disaster relief scenarios. In this paper, we will test two devices' ability to collect data under different weather conditions. First, Arduino Unos sent information by flashing handheld laser diodes and received information by decoding light levels from an array of photodiodes. Second, each device was then upgraded by changing to Arduino Dues and redesigning the Printed Circuit Board, gear mechanism, and enclosure. A Machine Learning-based error correction system was then designed and implemented, using Manchester Encoding and a restricted character set to detect and automatically correct trivial errors. After sending the information to a connected computer, messages with erroneous characters were pushed through a Java-based Machine Learning algorithm to further reduce errors before being displayed. Testing has shown this system to be highly effective in correcting errors within messages that used words trained with the algorithm. With further development, this system aims to be rapidly deployed directly after natural disasters, providing emergency communications until the primary power grid and network infrastructure can be fully repaired.
- Asad Ali, Fatima Hussain, Rasheed Hussain, Adil Mehmood Khan, and Alexander Ferworn. 2020. Multi-band Multi-hop WLANs for Disaster Relief and Public Safety Applications. In 2020 IEEE Wireless Communications and Networking Conference Workshops (WCNCW). IEEE, Seoul, Korea, 1--6.Google Scholar
- Arduino. 2017. Arduino Due. https://docs.arduino.cc/hardware/dueGoogle Scholar
- Arduino. 2017. Arduino Uno. https://docs.arduino.cc/hardware/uno-rev3Google Scholar
- Sandra Banholzer, James Kossin, and Simon Donner. 2014. The Impact of Climate Change on Natural Disasters. In Reducing Disaster: Early Warning Systems for Climate Change. Springer, 21--49.Google Scholar
- Leah Platt Boustan, Matthew E. Kahn, Paul W. Rhode, and Maria Lucia Yanguas. 2017. The Effect of Natural Disasters on Economic Activity in U.S. Counties: A Century of Data. Technical Report. National Bureau of Economic Research.Google Scholar
- Vincent W.S. Chan. 2006. Free-space Optical Communications. Journal of Lightwave Technology 24, 12 (2006), 4750--4762.Google ScholarCross Ref
- Olivier Chapelle, Patrick Haffner, and Vladimir N. Vapnik. 1999. Support Vector Machines for Histogram-based Image Classification. IEEE Transactions on Neural Networks 10, 5 (1999), 1055--1064.Google ScholarDigital Library
- Frank Eibe, Mark A. Hall, and Ian H. Witten. 2016. The WEKA Workbench. Online Appendix for Data Mining: Practical Machine Learning Tools and Techniques. In Morgan Kaufmann. Elsevier Amsterdam, The Netherlands.Google Scholar
- NOAA National Centers for Environmental Information (NCEI). 2021. U.S. Billion-dollar Weather and Climate Disasters. (2021). Google ScholarCross Ref
- Will Hedgecock. 2018. jSerialComm: Platform-independent Serial Port Access for Java. jSerialComm. https://fazecast.github.io/jSerialComm/Google Scholar
- Witten Ian, Frank Eibe, Hall Mark, and Pal Christopher. 2016. Practical Machine Learning Tools and Techniques. In DATA MINING.Google Scholar
- Mohammadreza A. Kashani, Murat Uysal, and Mohsen Kavehrad. 2015. A Novel Statistical Channel Model for Turbulence-induced Fading in Free-space Optical Systems. Journal of Lightwave Technology 33, 11 (2015), 2303--2312.Google ScholarCross Ref
- Thaddeus R. Miller, Mikhail Chester, and Tischa A. Muñoz-Erickson. 2018. Rethinking Infrastructure in an Era of Unprecedented Weather Events. Issues in Science and Technology (2018), 47--58.Google Scholar
- World Health Organization et al. 2018. Chemical Releases Caused by Natural Hazard Events and Disasters: Information for Public Health Authorities. (2018).Google Scholar
- Charles A. Thompson, Michael W. Kartz, Laurence M. Flath, Scott C. Wilks, Richard A. Young, Gary W. Johnson, and Anthony J. Ruggiero. 2002. Free-space Optical Communications Utilizing MEMS Adaptive Optics Correction. In Free-space Laser Communication and Laser Imaging II, Vol. 4821. International Society for Optics and Photonics, 129--138.Google Scholar
- Pascaline Wallemacq. 2018. Economic Losses, Poverty & Disasters: 1998-2017. Centre for Research on the Epidemiology of Disasters, CRED.Google Scholar
- Harry Zhang. 2004. The Optimality of Naive Bayes. In Proceedings of the Seventeenth International Florida Artificial Intelligence Research Society Conference. AAAI, Miami Beach, FL.Google Scholar
Index Terms
- A low-power, machine learning-based optical communications system for disaster relief
Recommendations
Promoting coordination for disaster relief: from crowdsourcing to coordination
SBP'11: Proceedings of the 4th international conference on Social computing, behavioral-cultural modeling and predictionThe efficiency at which governments and nongovernmental organizations (NGOs) are able to respond to a crisis and provide relief to victims has gained increased attention. This emphasis coincides with significant events such as tsunamis, hurricanes, ...
An Ecosystem for Disaster Relief Operations
iFIRE '19: Proceedings of the ACM MobiHoc workshop on innovative aerial communication solutions for FIrst REsponders network in emergency scenariosWhen disasters strike, communications, coordination, and information sharing among the first responders and emergency personnel become critical to the success and efficiency of relief operations, including response and recovery. This article explores ...
Evolutionary optimization for disaster relief operations
Graphical abstractDisplay Omitted HighlightsWe provide an overview of evolutionary algorithms for disaster relief operations.We show major strengths and shortcomings of the state-of-the-arts.We discuss potential directions for future research. Effective ...
Comments