Articles producció científica> Enginyeria Informàtica i Matemàtiques

Generation of Synthetic Trajectory Microdata from Language Models

  • Dades identificatives

    Identificador: imarina:9282083
    Autors:
    A. Blanco-Justicia, N. Jebreel, J. A. Manjón and J. Domingo-Ferrer
    Resum:
    Releasing and sharing mobility data, and specifically trajectories, is necessary for many applications, from infrastructure planning to epidemiology. Yet, trajectories are highly sensitive data, because the points visited by an individual can be identifying and also confidential. Hence, trajectories must be anonymized before releasing or sharing them. While most contributions to the trajectory anonymization literature take statistical approaches, deep learning is increasingly being used. We observe that natural language sentences and trajectories share a sequential nature that can be exploited in similar ways. In this paper, we present preliminary work on generating synthetic trajectories using machine learning models typically used for natural language processing. Our empirical results attest to the quality of the generated synthetic trajectories. Furthermore, our methods allow discovering natural neighborhoods based on trajectories.
  • Altres:

    Autor segons l'article: A. Blanco-Justicia, N. Jebreel, J. A. Manjón and J. Domingo-Ferrer
    Departament: Enginyeria Informàtica i Matemàtiques
    Autor/s de la URV: Blanco Justicia, Alberto / Domingo Ferrer, Josep / Jebreel, Najeeb Moharram Salim / Manjón Paniagua, Jesús Alberto
    Codi de projecte: 101006879
    Resum: Releasing and sharing mobility data, and specifically trajectories, is necessary for many applications, from infrastructure planning to epidemiology. Yet, trajectories are highly sensitive data, because the points visited by an individual can be identifying and also confidential. Hence, trajectories must be anonymized before releasing or sharing them. While most contributions to the trajectory anonymization literature take statistical approaches, deep learning is increasingly being used. We observe that natural language sentences and trajectories share a sequential nature that can be exploited in similar ways. In this paper, we present preliminary work on generating synthetic trajectories using machine learning models typically used for natural language processing. Our empirical results attest to the quality of the generated synthetic trajectories. Furthermore, our methods allow discovering natural neighborhoods based on trajectories.
    Accès a la llicència d'ús: https://creativecommons.org/licenses/by/3.0/es/
    Adreça de correu electrònic de l'autor: najeeb.jebreel@urv.cat alberto.blanco@urv.cat josep.domingo@urv.cat jesus.manjon@urv.cat jesus.manjon@urv.cat jesus.manjon@urv.cat najeeb.jebreel@urv.cat
    Identificador de l'autor: 0000-0002-1108-8082 0000-0001-7213-4962 0000-0003-3513-8109 0000-0003-3513-8109 0000-0003-3513-8109
    Data d'alta del registre: 2023-11-19
    Versió de l'article dipositat: info:eu-repo/semantics/acceptedVersion
    Enllaç font original: https://link.springer.com/chapter/10.1007/978-3-031-13945-1_13
    Programa de finançament: Horizon 2020
    Referència a l'article segons font original: Lecture Notes In Computer Science. 13463 172-187
    Referència de l'ítem segons les normes APA: A. Blanco-Justicia, N. Jebreel, J. A. Manjón and J. Domingo-Ferrer (2022). Generation of Synthetic Trajectory Microdata from Language Models. Lecture Notes In Computer Science, 13463(), 172-187
    URL Document de llicència: https://repositori.urv.cat/ca/proteccio-de-dades/
    Acrònim: MOBIDATALAB
    Entitat: Universitat Rovira i Virgili
    Any de publicació de la revista: 2022
    Acció del programa de finançament: Labs for prototyping future Mobility Data sharing cloud solutions
    Tipus de publicació: Journal Publications
  • Paraules clau:

    Privacy; Synthetic data generation; Mobility data
  • Documents:

  • Cerca a google

    Search to google scholar