Stigmergy-Based Modeling to Discover Urban Activity Patterns from Positioning Data

Abstract

Positioning data offer a remarkable source of information to analyze crowds urban dynamics. However, discovering urban activity patterns from the emergent behavior of crowds involves complex system modeling. An alternative approach is to adopt computational techniques belonging to the emergent paradigm, which enables self-organization of data and allows adaptive analysis. Specifically, our approach is based on stigmergy. By using stigmergy each sample position is associated with a digital pheromone deposit, which progressively evaporates and aggregates with other deposits according to their spatiotemporal proximity. Based on this principle, we exploit positioning data to identify highdensity areas (hotspots) and characterize their activity over time. This characterization allows the comparison of dynamics occurring in different days, providing a similarity measure exploitable by clustering techniques. Thus, we cluster days according to their activity behavior, discovering unexpected urban activity patterns. As a case study, we analyze taxi traces in New York City during 2015

Clustering Life Course to Understand the Heterogeneous Effects of Life Events, Gender, and Generation on Habitual Travel Modes

“…However, such methods have more commonly been applied to short-term trip data, especially with increasingly available global positioning system (GPS) data tracking daily human mobility. Specifically, cluster or classification based pattern mining machine-learning methods have been used to identify short-term dynamics and correlations between people's daily lives, events, and the built environment [31]. In contrast, research applying machine learning to the study of habitual travel behavior using longterm observations (from a life history perspective) has just started to emerge.…”

Brain-Inspired Stigmergy Learning

“…Originating from entomology, stigmergy has been widely studied in the aspect of social insects [5] and applied in different scenes [6]- [8]. But this concept has been rarely mentioned in the study of the brain, which is assumed to be the most complex system.…”

Methodological Proposals for the Development of Services in a Smart City: A Literature Review

“…It is essential to broaden the literature review, by focusing also on the advantages of a machine learning method for each city services group [17], e.g., in traffic management, machine learning provides the advantages to save the costs needed to create/adapt the heuristics to understand, predict, and manage anomalies in mobility [18]. The literature review of Section 4 is mainly based on numerals 1, 2, and 5 of the conceptual framework.…”