Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2020 Jul 16;20(14):3966.
doi: 10.3390/s20143966.

A Smartphone Crowdsensing System Enabling Environmental Crowdsourcing for Municipality Resource Allocation with LSTM Stochastic Prediction

Theodoros Anagnostopoulos  1   2 , Theodoros Xanthopoulos  1 , Yannis Psaromiligkos  1
Affiliations

A Smartphone Crowdsensing System Enabling Environmental Crowdsourcing for Municipality Resource Allocation with LSTM Stochastic Prediction

Theodoros Anagnostopoulos et al. Sensors (Basel). .

Abstract

Resource allocation of the availability of certain departments for dealing with emergency recovery is of high importance in municipalities. Efficient planning for facing possible disasters in the coverage area of a municipality provides reassurance for citizens. Citizens can assist with such malfunctions by acting as human sensors at the edge of an infrastructure to provide instant feedback to the appropriate departments fixing the problems. However, municipalities have limited department resources to handle upcoming emergency events. In this study, we propose a smartphone crowdsensing system that is based on citizens' reactions as human sensors at the edge of a municipality infrastructure to supplement malfunctions exploiting environmental crowdsourcing location-allocation capabilities. A long short-term memory (LSTM) neural network is incorporated to learn the occurrence of such emergencies. The LSTM is able to stochastically predict future emergency situations, acting as an early warning component of the system. Such a mechanism may be used to provide adequate department resource allocation to treat future emergencies.

Keywords: LSTM; department resource allocation; edge mobile applications; environmental crowdsourcing; municipality; smartphone crowdsensing; stochastic prediction.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflicts of interest.

Figures

Figure 1
Figure 1
Overview of the four layers of the proposed system. (a) Municipality headquarters layer; (b) inference engine model layer; (c) smartphone crowdsensing layer; and (d) environmental crowdsourcing municipality layer.
Figure 2
Figure 2
Three steps required to face the problem: (a) track the problem on the municipality map road address; (b) citizen annotates the problem and submits it to the system; (c) system informs citizen that the problem has been fixed.
Figure 3
Figure 3
Web application: (a) left is observed the municipality map with road addresses; (b) right are observed the emerged problems that should be fixed by the system.
Figure 4
Figure 4
Proposed crowdsourcing system architecture.
Figure 5
Figure 5
Data flow of the proposed system.
Figure 6
Figure 6
Prediction accuracy of municipality and municipality sections per year.
Figure 7
Figure 7
Prediction accuracy of municipality sections per season.
Figure 8
Figure 8
Actual and predicted distribution of municipality section Papagos department resource allocation per season.
Figure 9
Figure 9
Actual and predicted distribution of municipality section Cholargos department resource allocation per season.
See this image and copyright information in PMC

References

    1. Niaros V. Introducing a Taxonomy of the “Smart City”: Towards a Commons-Oriented Approach? J. A Glob. Sustain. Inf. Soc. 2016;14:51–61. doi: 10.31269/triplec.v14i1.718. - DOI
    1. Ullah Z., Turjman F.A., Mostarda L., Gagliardi R. Applications of Artificial Intelligence and Machine learning in smart cites. Comput. Commun. 2020;154:313–323. doi: 10.1016/j.comcom.2020.02.069. - DOI
    1. Aguilera U., Pena O., Belmonte O., Ipina D.L.D. Citizen-centric data services for smarter cities. Future Gener. Comput. Syst. 2017;76:234–247. doi: 10.1016/j.future.2016.10.031. - DOI
    1. Vaughan J.W. Making Better Use of the Crowd: How Crowdsourcing Can Advance Machine Learning Research. J. Mach. Learn. Res. 2018;18:1–46.
    1. Li G., Wang J., Zheng Y., Franklin M.J. Crowdsourced Data Management: A Survey. IEEE Trans. Knowl. Data Eng. 2016;28:2296–2319. doi: 10.1109/TKDE.2016.2535242. - DOI