Integrated Machine Learning in the Kepler Scientific Workflow System
Nguyen, M., Crawl, D., Masoumi, T., Altintas, T., Integrated Machine Learning in the Kepler Scientific Workflow System, In proceedings of the Third International Workshop on Advances in the Kepler Scientific Workflow System and Its Applications at the International Conference on Computational Science (ICCS 2016). doi:10.1016/j.procs.2016.05.545
Abstract
We present a method to integrate multiple implementations of a machine learning algorithm in Kepler actors. This feature enables the user to compare accuracy and scalability of various implementations of a machine learning technique without having to change the workflow. These actors are based on the Execution Choice actor. They can be incorporated into any workflow to provide machine learning functionality. We describe a use case where actors that provide several implementations of k-means clustering can be used in a workflow to process sensor data from weather stations for predicting wildfire risks.