Processing IoT data with Apache Kafka, KSQL, and Machine Learning

Processing IoT data with Apache Kafka, KSQL, and Machine Learning

IoT devices generate large amounts of data that must be continuously processed and analyzed. Apache Kafka is a highly scalable open source streaming platform for reading, storing, processing and forwarding large amounts of data from thousands of IoT devices. KSQL is an open source streaming SQL engine based natively on Apache Kafka to enable stream processing for everyone using simple SQL commands.

This talk shows with a scenario from the health care sector how Kafka and KSQL can help to continuously conduct health checks of patients. A live demo shows how machine learning models – trained with frameworks such as TensorFlow, DeepLearning4J or H2O – can be deployed into a runtime-critical and scalable real-time application.

Takeaways:
* Apache Kafka is a streaming platform for reading, storing, processing and forwarding large volumes of data from thousands of IoT devices.
* KSQL allows continuous integration and analysis without external big data clusters and without writing source code.
* Machine learning models can be easily trained and used in the Apache Kafka environment.

2bded62396ea66c84bd10e91c718dea9?s=128

Robin Moffatt

June 05, 2018
Tweet