Detecting Evidence of Organization in groups by Trajectories

TL;DR

This paper introduces two novel methods for detecting organizational structures in groups based on trajectory data, improving accuracy over existing approaches through experiments on simulated animal group scenarios.

Contribution

The paper presents two new approaches for network inference from trajectories, utilizing graph entropy and clustering indices, validated on diverse animal simulation scenarios.

Findings

New methods outperform previous approaches in identifying group organization

Approaches effectively distinguish organizational structures in simulated scenarios

Experimental validation on NetLogo animal simulations demonstrates improved detection accuracy

Abstract

Effective detection of organizations is essential for fighting crime and maintaining public safety, especially considering the limited human resources and tools to deal with each group that exhibits co-movement patterns. This paper focuses on solving the Network Structure Inference (NSI) challenge. Thus, we introduce two new approaches to detect network structure inferences based on agent trajectories. The first approach is based on the evaluation of graph entropy, while the second considers the quality of clustering indices. To evaluate the effectiveness of the new approaches, we conducted experiments using four scenario simulations based on the animal kingdom, available on the NetLogo platform: Ants, Wolf Sheep Predation, Flocking, and Ant Adaptation. Furthermore, we compare the results obtained with those of an approach previously proposed in the literature, applying all methods to simulations of the NetLogo platform. The results demonstrate that our new detection approaches can more clearly identify the inferences of organizations or networks in the simulated scenarios.