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, and 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%.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Ensemble Convolutional Neural Networks for Mode Inference in Smartphone Travel Survey


    Contributors:


    Publication date :

    2020-06-01


    Size :

    998205 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    DataMobile: Smartphone Travel Survey Experiment

    Patterson, Zachary / Fitzsimmons, Kyle | Transportation Research Record | 2016



    Ensemble convolutional neural networks for pose estimation

    Kawana, Yuki / Ukita, Norimichi / Huang, Jia-Bin et al. | British Library Online Contents | 2018


    Pedestrian detection based on deep convolutional neural network with ensemble inference network

    Fukui, Hiroshi / Yamashita, Takayoshi / Yamauchi, Yuji et al. | IEEE | 2015


    Design and Implementation of a Smartphone-Based Travel Survey

    Safi, Hamid / Assemi, Behrang / Mesbah, Mahmoud et al. | Transportation Research Record | 2019