Project Overview
We introduce temporal multimodal multivariate learning, a new family of decision making models that can indirectly learn and transfer online information from simultaneous observations of a probability distribution with more than one peak or more than one outcome variable from one time stage to another. We approximate the posterior by sequentially removing additional uncertainties across different variables and time, based on data-physics driven correlation, to address a broader class of challenging time-dependent decision-making problems under uncertainty. Extensive experiments on real-world datasets ( i.e., urban traffic data and hurricane ensemble forecasting data) demonstrate the superior performance of the proposed targeted decision-making over the state-of-the-art baseline prediction methods across various settings.
Team
Hyoshin Park (ODU), Justice Darko (RockWell Automation), Niharika Deshpande (ODU), Venktesh Pandey (NCAT), Hui Su (NASA JPL), Masahiro Ono (NASA JPL), Dedrick Barkely (Chrysler), Larkin Folsom (Teledyne Tech), Derek Posselt (NASA JPL), and Steve Chien (NASA JPL)
Publications
[1] H. Park, J. Darko, N. Deshpande, V. Pandey, H. Su, M. Ono, D. Barkely, L. Folsom, D. Posselt, and S. Chien. Temporal Multimodal Multivariate Learning, SIGKDD Conference on Knowledge Discovery and Data Mining (KDD2022) Conference, Washington DC, USA, 2022. [2] U.S.Patent 17/467,046. Inventor H. Park, M. Ono, K. Otsu, L. Folsom [Accepted and In pRess] Systems and Methods for Efficient Navigation of Robotic Devices.