CloudLSTM: A Recurrent Neural Model for Spatiotemporal Point-cloud Stream Forecasting
- 1. Tencent Lightspeed & Quantum Studios
- 2. IMDEA Networks Institute
- 3. The University of Edinburgh
Description
This paper introduces CloudLSTM, a new branch of recurrent neural models tailored to forecasting over data streams generated by geospatial point-cloud sources. We design a Dynamic Point-cloud Convolution (DConv) operator as the core component of CloudLSTMs, which performs convolution directly over point-clouds and extracts local spatial features from sets of neighboring points that surround different elements of the input. This operator maintains the permutation invariance of sequence-to-sequence learning frameworks, while representing neighboring correlations at each time step -- an important aspect in spatiotemporal predictive learning. The DConv operator resolves the grid-structural data requirements of existing spatiotemporal forecasting models and can be easily plugged into traditional LSTM architectures with sequence-to-sequence learning and attention mechanisms. We apply our proposed architecture to two representative, practical use cases that involve point-cloud streams, i.e., mobile service traffic forecasting and air quality indicator forecasting. Our results, obtained with real-world datasets collected in diverse scenarios for each use case, show that CloudLSTM delivers accurate long-term predictions, outperforming a variety of competitor neural network models.
Notes
Files
aaai21_cloud-lstm.pdf
Files
(618.8 kB)
Name | Size | Download all |
---|---|---|
md5:9f12efb8cc29e9cb95295aa2e47f6ba9
|
618.8 kB | Preview Download |
Additional details
Related works
- Is previous version of
- Conference paper: http://arxiv.org/abs/1907.12410 (URL)