Machine Learning on Spark for the Optimal IDW-based Spatiotemporal Interpolation

What:
Poster
When:
Wednesday Sep 28   05:00 PM to 07:00 PM (2 hours)
Tags:
spatiotemporal interpolationSparkmachine learninginverse distance weighted (IDW)air pollutionpublic health
Discussion:
0
In order to improve current spatiotemporal interpolation methods for public health applications (Li et al., 2010), we combine the extension approach (Li and Revesz, 2004) and several machine learning methods, employ the efficient k-d tree structure to store data, and implement our method on Spark (Spark, 2016). The preliminary results demonstrate the excellent computation ability and amazing scalability of our method, which outperforms the previous work (Li et al., 2014). Future research will continue exploring the current method to improve the interpolation accuracy and computation efficiency, as well as establishing associations between air pollution exposure and adverse health effects.
Participant
Participant
Georgia Southern University
Participant
Georgia Southern University
Participant
Georgia Southern University
Participant
Augusta University

My Schedule

Add to Your Schedule