While IOT data comes in different forms, it is always processed through essentially the same steps, from segmentation all the way through the formation of a machine learning example. To save time and labor, we propose a cloud-based master-worker architecture that can accomplish these steps in parallel. In the SenseML platform, some steps—such as pre-processing—are automated, while others are surfaced strategically to allow data scientists to input their expertise.

Publications

SenseML: A Platform for Constructing IOT Data Pipelines (PDF)
Donghyun Michael Choi, MEng. Thesis, MIT EECS, August 2017. Advisor: Kalyan
Veeramachaneni.

Contributors

Michael Choi (2016-17)