PredLife: Predicting Fine-Grained Future Activity Patterns

Activity pattern prediction is a critical part of urban computing, urban planning, intelligent transportation, and so on. Based on a dataset with more than 10 million GPS trajectory records collected by mobile sensors, this research proposed a CNN-BiLSTM-VAE-ATT-based encoder-decoder model for fine-grained individual activity sequence prediction. The model combines the long-term and short-term dependencies crosswise and also considers randomness, diversity, and uncertainty of individual activity patterns. The proposed results show higher accuracy compared to the ten baselines. The model can generate high diversity results while approximating the original activity patterns distribution. Moreover, the model also has interpretability in revealing the time dependency importance of the activity pattern prediction.

Automated summary

This research proposes a CNN-BiLSTM-VAE-ATT-based encoder-decoder model for fine-grained individual activity sequence prediction. The model combines long-term and short-term dependencies, considers randomness, diversity, and uncertainty of individual activity patterns, and achieves higher accuracy compared to baselines. It generates diverse results approximating the original activity patterns distribution and reveals the importance of time dependency in activity pattern prediction.