An Integrated Autoencoder-Based Filter for Sparse Big Data
This work addresses data sparsity issues in big data applications, such as GPS trajectory analysis, but appears incremental as it builds on existing autoencoder methods.
The authors tackled the problem of sparse big data by proposing an integrated autoencoder filter that uses auxiliary information to improve prediction accuracy and robustness, achieving better performance than state-of-the-art methods on a GPS trajectory dataset.
We propose a novel filter for sparse big data, called an integrated autoencoder (IAE), which utilizes auxiliary information to mitigate data sparsity. The proposed model achieves an appropriate balance between prediction accuracy, convergence speed, and complexity. We implement experiments on a GPS trajectory dataset, and the results demonstrate that the IAE is more accurate and robust than some state-of-the-art methods.