{
  "id": "1902.10768",
  "version": "v1",
  "published": "2019-02-27T20:29:02.000Z",
  "updated": "2019-02-27T20:29:02.000Z",
  "title": "Semi-supervised GANs to Infer Travel Modes in GPS Trajectories",
  "authors": [
    "Ali Yazdizadeh",
    "Zachary Patterson",
    "Bilal Farooq"
  ],
  "categories": [
    "cs.LG",
    "stat.ML"
  ],
  "abstract": "Semi-supervised Generative Adversarial Networks (GANs) are developed in the context of travel mode inference with uni-dimensional smartphone trajectory data. We use data from a large-scale smartphone travel survey in Montreal, Canada. We convert GPS trajectories into fixed-sized segments with five channels (variables). We develop different GANs architectures and compare their prediction results with Convolutional Neural Networks (CNNs). The best semi-supervised GANs model led to a prediction accuracy of 83.4%, while the best CNN model was able to achieve the prediction accuracy of 81.3%. The results compare favorably with previous studies, especially when taking the large-scale real-world nature of the dataset into account.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2019-02-27T20:29:02.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "infer travel modes",
      "prediction accuracy",
      "large-scale smartphone travel survey",
      "uni-dimensional smartphone trajectory data",
      "convert gps trajectories"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}