Generating synthetic mobility data for a realistic population with RNNs to improve utility and privacy

  title={Generating synthetic mobility data for a realistic population with RNNs to improve utility and privacy},
  author={Alex Berke and Ronan Doorley and Kent Larson and Esteban Moro Egido},
  journal={Proceedings of the 37th ACM/SIGAPP Symposium on Applied Computing},
Location data collected from mobile devices represent mobility behaviors at individual and societal levels. These data have important applications ranging from transportation planning to epidemic modeling. However, issues must be overcome to best serve these use cases: The data often represent a limited sample of the population and use of the data jeopardizes privacy. To address these issues, we present and evaluate a system for generating synthetic mobility data using a deep recurrent neural… 

Figures and Tables from this paper

A deep learning framework to generate realistic population and mobility data

This paper proposes a framework to generate a synthetic population that includes both socioeconomic features (e.g., age, sex, industry) and trip chains (i.e., activity locations) for Census and Household Travel Survey datasets.

Generating Synthetic Mobility Networks with Generative Adversarial Networks

The solution is MoGAN, a model based on Generative Adversarial Networks (GANs) to generate realistic mobility networks, and it is shown that MoGAN outperforms the classical Gravity and Radiation models regarding the realism of the generated networks.

Traffic Request Generation through a Variational Auto Encoder Approach

A variational autoencoder architecture has been trained on a floating car dataset in order to grasp the statistical features of the traffic demand in the city of Rome.

Deep Learning of Subject Context in Ideological and Political Class Based on Recursive Neural Network

A model based on HS-EEMD-RNN, which combines recurrent neural networks in the research direction of deep and innovative research on the subject context of ideological and political classrooms can significantly improve the prediction accuracy of its development direction.



Generating synthetic mobility traffic using RNNs

Recurrent Neural Networks are investigated to learn these hidden patterns contained in an original dataset to produce a realistic synthetic dataset, and it is shown that generating synthetic traffic by learning the innate structure of human mobility through RNNs is a promising approach.

DP-WHERE: Differentially private modeling of human mobility

Models of human mobility have broad applicability in urban planning, ecology, epidemiology, and other fields. Starting with Call Detail Records (CDRs) from a cellular telephone network that have gone

The TimeGeo modeling framework for urban mobility without travel surveys

This study proposes an individual mobility modeling framework, TimeGeo, that extracts required features from ubiquitous, passive, and sparse digital traces in the information and communication technology era to comprehensively model urban mobility without travel surveys.

DPT: Differentially Private Trajectory Synthesis Using Hierarchical Reference Systems

This paper presents DPT, a system to synthesize mobility data based on raw GPS trajectories of individuals while ensuring strong privacy protection in the form of e-differential privacy, the first system that provides an end-to-end solution.

Human mobility: Models and applications

Limits of Predictability in Human Mobility

Analysis of the trajectories of people carrying cell phones reveals that human mobility patterns are highly predictable, and a remarkable lack of variability in predictability is found, which is largely independent of the distance users cover on a regular basis.

The effect of recency to human mobility

This work proposes a model in which exploitation in human movement also considers recently-visited locations and not solely frequently-Visited locations, and test the hypothesis against different empirical data of human mobility and show that the proposed model replicates the characteristic patterns of the recency bias.

Understanding individual human mobility patterns

The trajectory of 100,000 anonymized mobile phone users whose position is tracked for a six-month period is studied, finding that, in contrast with the random trajectories predicted by the prevailing Lévy flight and random walk models, human trajectories show a high degree of temporal and spatial regularity.

Extracting Trips from Multi-Sourced Data for Mobility Pattern Analysis: An App-Based Data Example.

An Agent-Based Model of Epidemic Spread Using Human Mobility and Social Network Information

An agent-based system that uses social interactions and individual mobility patterns extracted from call detail records to accurately model virus spreading is proposed and applied to study the 2009 H1N1 outbreak in Mexico and to evaluate the impact that government mandates had on the spreading of the virus.