Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Early Detection of Critical Urban Events using Mobile Phone Network Data

Pierre Lemaire, Angelo Furno, Stefania Rubrichi, Alexis Bondu, Zbigniew Smoreda, Cezary Ziemlicki, Nour-Eddin El Faouzi, Eric Gaume

TL;DR

Empirical evidence is presented that advanced NSD can detect anomalies in mobile traffic service consumption, attributable to critical urban events, with fine spatial and temporal resolutions, and introduces two methodologies for real-time anomaly detection from multivariate time series extracted from large-scale NSD.

Abstract

Network Signalling Data (NSD) have the potential to provide continuous spatio-temporal information about the presence, mobility, and usage patterns of cell phone services by individuals. Such information is invaluable for monitoring large urban areas and supporting the implementation of decision-making services. When analyzed in real time, NSD can enable the early detection of critical urban events, including fires, large accidents, stampedes, terrorist attacks, and sports and leisure gatherings, especially if these events significantly impact mobile phone network activity in the affected areas. This paper presents empirical evidence that advanced NSD can detect anomalies in mobile traffic service consumption, attributable to critical urban events, with fine spatial and temporal resolutions. We introduce two methodologies for real-time anomaly detection from multivariate time series extracted from large-scale NSD, utilizing a range of algorithms adapted from the state-of-the-art in unsupervised machine learning techniques for anomaly detection. Our research includes a comprehensive quantitative evaluation of these algorithms on a large-scale dataset of NSD service consumption for the Paris region. The evaluation uses an original dataset of documented critical or unusual urban events. This dataset has been built as a ground truth basis for assessing the algorithms performance. The obtained results demonstrate that our framework can detect unusual events almost instantaneously and locate the affected areas with high precision, largely outperforming random classifiers. This efficiency and effectiveness underline the potential of NSD-based anomaly detection in significantly enhancing emergency response strategies and urban planning.

Early Detection of Critical Urban Events using Mobile Phone Network Data

TL;DR

Empirical evidence is presented that advanced NSD can detect anomalies in mobile traffic service consumption, attributable to critical urban events, with fine spatial and temporal resolutions, and introduces two methodologies for real-time anomaly detection from multivariate time series extracted from large-scale NSD.

Abstract

Network Signalling Data (NSD) have the potential to provide continuous spatio-temporal information about the presence, mobility, and usage patterns of cell phone services by individuals. Such information is invaluable for monitoring large urban areas and supporting the implementation of decision-making services. When analyzed in real time, NSD can enable the early detection of critical urban events, including fires, large accidents, stampedes, terrorist attacks, and sports and leisure gatherings, especially if these events significantly impact mobile phone network activity in the affected areas. This paper presents empirical evidence that advanced NSD can detect anomalies in mobile traffic service consumption, attributable to critical urban events, with fine spatial and temporal resolutions. We introduce two methodologies for real-time anomaly detection from multivariate time series extracted from large-scale NSD, utilizing a range of algorithms adapted from the state-of-the-art in unsupervised machine learning techniques for anomaly detection. Our research includes a comprehensive quantitative evaluation of these algorithms on a large-scale dataset of NSD service consumption for the Paris region. The evaluation uses an original dataset of documented critical or unusual urban events. This dataset has been built as a ground truth basis for assessing the algorithms performance. The obtained results demonstrate that our framework can detect unusual events almost instantaneously and locate the affected areas with high precision, largely outperforming random classifiers. This efficiency and effectiveness underline the potential of NSD-based anomaly detection in significantly enhancing emergency response strategies and urban planning.
Paper Structure (18 sections, 8 equations, 4 figures, 4 tables)

This paper contains 18 sections, 8 equations, 4 figures, 4 tables.

Table of Contents

  1. Abstract
  2. Introduction
  3. Materials and Methods
  4. Results
  5. Conclusion
  6. Acknowledgments

Figures (4)

  • Figure 1: Timeline for the Notre-Dame fire on April 15th 2019. (a) shows the anomaly level observed on the closest outdoor antenna to the cathedral. (b), (c) and (d) show the corresponding map at different times, centered at the cathedral location. Disk sizes and colors are linked to the alarm level. Green spots correspond to antenna locations.
  • Figure 2: Timeline for May First demonstration. a and b show the anomaly levels observed on key locations (start of the demonstration, also visible on c) and the hospital (highest alarm level common to d and e). c, d, e and f show the corresponding map at different times. Disk sizes and colors are linked to the alarm level. Green spots correspond to antenna locations.
  • Figure 3: Precision Recall curves at minute and event granularity, for the Signature and the Adaptive methods fusing 4 services : Call and SMS, both in 3G and 4G.
  • Figure 4: Precision Recall curves at minute and event granularity, for the Signature method only, with individual outputs for Call and SMS services in 3G and 4G (dashed curves) and the fusion between several configurations.