eFedDNN: Ensemble based Federated Deep Neural Networks for Trajectory Mode Inference

TL;DR

This paper introduces eFedDNN, a privacy-preserving federated learning approach using ensemble deep neural networks to accurately infer travel modes from GPS data without exposing user private information.

Contribution

The paper presents a novel ensemble-based federated deep neural network model that improves travel mode inference accuracy while ensuring user privacy.

Findings

Achieves high accuracy in travel mode inference on real-world data.

Outperforms existing models in privacy-preserving travel mode detection.

Demonstrates the effectiveness of ensemble FL in smart mobility applications.

Abstract

As the most significant data source in smart mobility systems, GPS trajectories can help identify user travel mode. However, these GPS datasets may contain users' private information (e.g., home location), preventing many users from sharing their private information with a third party. Hence, identifying travel modes while protecting users' privacy is a significant issue. To address this challenge, we use federated learning (FL), a privacy-preserving machine learning technique that aims at collaboratively training a robust global model by accessing users' locally trained models but not their raw data. Specifically, we designed a novel ensemble-based Federated Deep Neural Network (eFedDNN). The ensemble method combines the outputs of the different models learned via FL by the users and shows an accuracy that surpasses comparable models reported in the literature. Extensive experimental studies on a real-world open-access dataset from Montreal demonstrate that the proposed inference model can achieve accurate identification of users' mode of travel without compromising privacy.