CloudLSTM: A Recurrent Neural Model for Spatiotemporal Point-cloud Stream Forecasting

Chaoyun Zhang, Marco Fiore, Iain Murray, Paul Patras

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

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 spatio temporal 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.
Original languageEnglish
Title of host publicationThe Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21)
PublisherAAAI Press
Number of pages8
Publication statusAccepted/In press - 2 Dec 2020
EventThe Thirty-Fifth AAAI Conference on Artificial Intelligence - Virtual Conference
Duration: 2 Feb 20219 Feb 2021
Conference number: 35
https://aaai.org/Conferences/AAAI-21/

Conference

ConferenceThe Thirty-Fifth AAAI Conference on Artificial Intelligence
Abbreviated titleAAAI-21
Period2/02/219/02/21
Internet address

Fingerprint Dive into the research topics of 'CloudLSTM: A Recurrent Neural Model for Spatiotemporal Point-cloud Stream Forecasting'. Together they form a unique fingerprint.

Cite this