Practical Machine Learning Pipeline using Streaming IOT Sensor Data, Matthiew Dumoulin and Mateusz Dymczyk, Big Data Analytics Tokyo 2017

File uploaded by slimbaltagi on May 25, 2017Last modified by maprcommunity on May 31, 2017
Version 2Show Document
  • View in full screen mode

Talk given by  Mathieu Dumoulin at Big Data Analytics Tokyo 2017 and published on February 8, 2017
Real-time IoT sensor data collected from on a working, moving robot is used to predict failure using anomaly detection with autoencoders with H2O, all running on the MapR Converged Platform and MapR Streams (a Kafka superset implementation). This drives an AR headset to visualize the results (green OK red FAILURE) on a marker attached to the robot.

Demo video: https://vimeo.com/202732221/a2966bafd8

Source code: GitHub - mdymczyk/iot-pipeline 

Outcomes