Machine Learning to Collect/Analyze Location Data
Indoor device tracking is becoming more necessary and useful as a technology because the granularity of location is constantly improving. As this trend continues, the concern of the organization moves from "can we track and why?", to "how do we scale the collection and analysis of such a large dataset?". In the past, DevNet has focused on "can we track and why?", when looking at location services solutions, but now is the time to transition to "how do we scale?". In this workshop session, we will look at cloud-based containerized solutions that can be implemented very quickly, robustly and securely, that scale with very little effort. We will then apply functionality from machine learning libraries to sift the data and understand what we can learn in order to make useful decisions.
Share this idea
Additional Supporting Materials
- An understanding of the challenges that are currently facing IoT developers.
- Get comfortable with deploying scalable containers to either Kubernetes Engine, Docker Swarm, or both.
- An understanding of what Tensorflow ML libraries provide to a developer and the basics of how they can be leveraged in application design.
- Matt DeNapoli, Developer Evangelist , Cisco DevNet
Dave Bertling, Founder, LIVE24