Modern engines are equipped with sensors which improve fuel efficiency, safety, reliability, and other functions. Many commercial IoT stacks address this problem, organizations which require additional customization must pay or to attempt to build their own system. Using Apache Software Foundation projects, the building blocks required to build such a system are already in place; organizations have an alternative to commercial products for their use cases.
In this talk we will show how vehicle telemetry data from and ODB2 sensor can be handled by an Apache Kafka broker, ingested by a stream processor such as Apache Flink, which can leverage the tensor math library Apache Mahout to create an online deep learning algorithm for prediction and prevention of failure with fault warnings, and thus reduce warranty claims.
Trevor is an open source evangelist at IBM in Watson IoT. He is also a PMC on the Apache Mahout, Apache Streams, and Apache Community Development projects. He has spoken at conferences and Meetups internationally.
