A joint autoencoder for prediction and its application in GPS trajectory data
share
In scientific fields, data sparsity greatly affects prediction performance. This study builds a deep learning-based scheme called a joint autoencoder (JAE), which utilizes auxiliary information to mitigate data sparsity. The proposed scheme achieves an appropriate balance between prediction accuracy, convergence speed, and complexity. Experiments are implemented on a GPS trajectory dataset, and the results demonstrate that the JAE is more accurate and robust than some state-of-the-art methods.
READ FULL TEXT
