Ensemble Convolutional Neural Networks for Mode Inference in Smartphone Travel Survey

TL;DR

This paper presents an ensemble of CNN models with different hyper-parameters for accurately classifying transportation modes from smartphone travel survey data, achieving high accuracy through various ensemble strategies.

Contribution

The study introduces a novel ensemble CNN approach with multiple combination methods and employs a Random Forest as a meta-learner to improve transportation mode classification accuracy.

Findings

Ensemble CNN with Random Forest meta-learner achieves 91.8% accuracy.

Majority and optimal weights voting methods reach around 89% accuracy.

Average voting yields approximately 85% accuracy.

Abstract

We develop ensemble Convolutional Neural Networks (CNNs) to classify the transportation mode of trip data collected as part of a large-scale smartphone travel survey in Montreal, Canada. Our proposed ensemble library is composed of a series of CNN models with different hyper-parameter values and CNN architectures. In our final model, we combine the output of CNN models using "average voting", "majority voting" and "optimal weights" methods. Furthermore, we exploit the ensemble library by deploying a Random Forest model as a meta-learner. The ensemble method with random forest as meta-learner shows an accuracy of 91.8% which surpasses the other three ensemble combination methods, as well as other comparable models reported in the literature. The "majority voting" and "optimal weights" combination methods result in prediction accuracy rates around 89%, while "average voting" is able to achieve an accuracy of only 85%.