Feasibility of anomalous event detection based on Mobile Spatial Statistics
A study of six cases in Japan
Bibliographic Data
| ID | 22028205 |
|---|---|
| Authors | Erick Mas (0000-0002-4861-5739, Tohoku University, corresponding author), Shunichi Koshimura (0000-0002-8352-0639, Tohoku University) |
| Year | 2024 |
| Volume | 110 |
| Pages | 104625 |
| Publication date | 2024-08-01 |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | International Journal of Disaster Risk Reduction (JOURNAL) |
| Journal identifiers | ISSN: 2212-4209 |
| Publisher | Elsevier BV (PUBLISHER) |
| DOI | 10.1016/j.ijdrr.2024.104625 |
| OpenAlex | W4399849928 |
| Language | EN |
| Citations received | 1 |
| References cited | 23 |
One of the primary goals of disaster risk management is to minimize the loss of life in the event of a disaster. To reduce the number of victims in disasters is important to know the amount of exposed population to a hazard. Similarly, population distribution in real-time is required to estimate post-disaster needs and resources for disaster relief. In this study, we explore the use of Mobile Spatial Statistics (MSS) as the basis to acquire offline and online population data and detect anomalies that may relate to a disaster. For instance, mobile spatial data could identify sudden changes in the number of people indicating an anomalous event or change in population dynamics. Here we use the Matrix Profile (MP) method in time-series analysis to test the feasibility of detecting anomalies in the MSS data. We selected mass gatherings and disaster events with rapid and slow onset and small and large scales. We discuss the applicability of this method for real-time anomaly detection of spatial population distribution within the context of disaster risk management. Our results show that the applicability of the MP method in anomaly detection is sensitive to the size of the areas used during monitoring and analysis, the subsequence length and the threshold applied
Medical emergency · Physics · Statistics · Anomaly Detection Techniques and Applications · Computer Science · Data-Driven Disease Surveillance · Human Mobility and Location-Based Analysis · Mathematics · Medicine
| Citations per year | 1 |
|---|---|
| Citation span | 2025 - 2025 (1) |
| Highly cited | No |