Enterprise IIoT Edge Processing with Apache NiFi, MiniFi and Deep Learning

Tim Spann

Solutions Engineer at Hortonworks

In this talk I will do an overview on using Apache MiniFi with Apache MXNet and other Deep Learning Libraries on the edge device including Movidius and NVIDIA Jetson TX1. We run deep learning models on the edge device and send images, GPS data, sensor data and deep learning results if values exceed norms. Using the Site-to-Site protocol over HTTPS and MQTT data is sent to an Apache NiFi cluster for further processing, additional TensorFlow processing, data augmentation with weather and geolocation. This data is streaming into a Big Data platform for analysis, additional machine learning with Apache Spark and queries via Apache Hive. I will show a real-time running IoT application with an NVIDIA Jetson TX1. During this talk an emphasis on the industrial and commercial needs for IoT including security, multiple device support, powerful edge devices, rugged hardware, automation, command and control, enterprise data integration and end-to-end data provenance.

Use Cases: Container truck location monitoring, Delivery truck monitoring, Service Truck and Driver monitoring, Security Camera Monitoring, Utility Asset Anomaly Detection, Temperature and Humdiity filtering for devices.


Tags:

Location: Salon Franklin
April 5th, 2018
1:00 PM - 2:00 PM