One component of the modern industiral operations is streaming (continuously generating and transmitting) high-frequency sensor data from the field to remote locations for monitoring, storage, and analysis. However, monitoring several operations in real-time can be overwhelming. Real-time cloud-based streaming paired with machine learning can make the decision making on-the-fly much easier. This talk demostrates several approaches for automating event recognition in time-series data, including traditional machine learning and the application of signal processing techniques.