Semi-supervised GANs to Infer Travel Modes in GPS Trajectories
This work addresses travel mode inference for urban mobility analysis, but it is incremental as it applies existing semi-supervised GANs to a specific dataset.
The paper tackled the problem of inferring travel modes from GPS trajectories using semi-supervised GANs, achieving a prediction accuracy of 83.4%, which outperformed a CNN model at 81.3%.
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.