Managing crowded museums: Visitors flow measurement, analysis, modeling, and optimization

https://doi.org/10.1016/j.jocs.2021.101357Get rights and content
Under a Creative Commons license
open access

Highlights

  • We developed an IoT-based system for tracking visitors in crowded museums.

  • We reconstruct visitors trajectories at room-scale by means of a neural network approach.

  • We classify visitors trajectories by a hierarchical clustering analysis.

  • We build a digital twin of the museum for simulating visitors trajectories and room occupancy.

  • We optimize the visitor flows by re-engineering the museum entrance system.

  • Our case study is Galleria Borghese museum in Rome, Italy.

Abstract

We present an all-around study of the visitors flow in crowded museums: a combination of Lagrangian field measurements and statistical analyses enable us to create stochastic digital-twins of the guest dynamics, unlocking comfort- and safety-driven optimizations. Our case study is the Galleria Borghese museum in Rome (Italy), in which we performed a real-life data acquisition campaign.

We specifically employ a Lagrangian IoT-based visitor tracking system based on Raspberry Pi receivers, displaced in fixed positions throughout the museum rooms, and on portable Bluetooth Low Energy beacons handed over to the visitors. Thanks to two algorithms: a sliding window-based statistical analysis and an MLP neural network, we filter the beacons RSSI and accurately reconstruct visitor trajectories at room-scale. Via a clustering analysis, hinged on an original Wasserstein-like trajectory-space metric, we analyze the visitors paths to get behavioral insights, including the most common flow patterns. On these bases, we build the transition matrix describing, in probability, the room-scale visitor flows. Such a matrix is the cornerstone of a stochastic model capable of generating visitor trajectories in silico. We conclude by employing the simulator to enhance the museum fruition while respecting numerous logistic and safety constraints. This is possible thanks to optimized ticketing and new entrance/exit management.

Keywords

IoT
Machine learning
Clustering
Tracking system
Museum simulator
Museum optimization

Cited by (0)

Pietro Centorrino obtained a bachelor degree in Physics and Advanced Technologies in 2017 at University of Siena, Italy, and a master degree in Physics in 2020 at Sapienza University, Rome, Italy. His research fields concern modelling of biological system, optimization problems, forecasting simulations and STEM education.

Alessandro Corbetta is a university researcher at the Department of Applied Physics at Eindhoven University of Technology. His research activity is at the interface between complex flowing matter, physics for society and machine learning for nonlinear physical systems. Since 2012, in the context of the “Crowdflow” topical group, is interested in furthering our fundamental understanding of pedestrian crowd flows. He aims at quantitative models for the emergent physics of crowds to allow safer and more efficient pedestrian environments. He is furthermore active in the application of recent machine and deep learning techniques to the analysis of chaotic and turbulent dynamics.

Emiliano Cristiani is senior researcher at Istituto per le Applicazioni del Calcolo “Mauro Picone”, National Research Council of Italy. His research focuses on mathematical models and methods for the simulation of collective behaviour (vehicular and pedestrian traffic, animal groups), numerical solution of hyperbolic PDEs, and Hamilton-Jacobi equations with application to optimal control theory and differential games. He has 15+ year research experience and 50+ peer reviewed publications.

Elia Onofri obtained a bachelor degree in Mathematics in 2018 and a master degree in Computational Sciences in 2020 at Roma Tre University, Rome, Italy. Currently he is a Ph.D. student in Mathematics at Roma Tre University, under a collaboration with the National Research Council of Italy. His research fields concern applied mathematics in cryptography, machine learning, biology and forecasting simulations.