Related Experiment Video
Updated: Dec 13, 2025
06:49
Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment
Published on: December 11, 2015
9.2K
A Smartphone Crowdsensing System Enabling Environmental Crowdsourcing for Municipality Resource Allocation with LSTM
Theodoros Anagnostopoulos1,2, Theodoros Xanthopoulos1, Yannis Psaromiligkos1
1DigiT.DSS.Lab, Department of Business Administration, University of West Attica, Thivon 250, Egaleo 122 44 Athens, Greece.
Sensors (Basel, Switzerland)
|July 26, 2020
Summary
This study introduces a smartphone crowdsensing system using citizens as human sensors to improve municipal emergency response. A long short-term memory (LSTM) network predicts future emergencies, enabling better resource allocation.
Area of Science:
- Computer Science
- Urban Planning
- Public Administration
Background:
- Effective resource allocation for municipal emergency recovery is crucial for citizen safety and reassurance.
- Municipalities face resource limitations in handling diverse emergency events.
- Citizens can act as 'human sensors' to provide real-time infrastructure feedback.
Purpose of the Study:
- To propose a smartphone crowdsensing system for municipal emergency management.
- To leverage citizen input and environmental crowdsourcing for location-allocation.
- To enhance emergency preparedness through predictive analytics.
Main Methods:
- Development of a smartphone crowdsensing system utilizing citizen feedback.
- Integration of a long short-term memory (LSTM) neural network for emergency prediction.
- Exploitation of environmental crowdsourcing and location-allocation principles.
Main Results:
- The proposed system effectively utilizes citizens as distributed sensors.
- The LSTM model demonstrates capability in learning emergency occurrence patterns.
- Stochastic prediction of future emergencies is achieved, serving as an early warning system.
Conclusions:
- The smartphone crowdsensing system can supplement municipal resources for emergency recovery.
- LSTM-based prediction facilitates proactive and adequate department resource allocation.
- This approach enhances municipal resilience and citizen confidence in emergency management.
