Skip to content

Exosite Insights available from Exchange

Beyond off the shelf functions available in ExoSense, Insight modules are available in the Exchange marketplace in Murano that Exosite maintains. This document provides some examples, others are available upon discussions about your project and application needs.

Anomaly Detection

The Anomaly Detection Insight can be linked to any ExoSense data signal for detecting abnormal dips/spikes in your streaming data.

This insight automatically detect anomalies from individual signals based on statistical evidence in history data Earlier detection of some abnormal symptoms like spikes/dips, which could be helpful for predictive maintenance Scalable and applicable to diverse kinds of signals, then you don’t need to rely on limited human experience to set proper alarm thresholds for hundreds or even thousands of monitored signals manually.

The Anomaly Detection Insight uses an Online Standard Deviation detection method. This method is based on the predefined standard deviation threshold as the upper and lower bounds for normal data, any data points appear out of the bounds will be labeled as anomalies. Following the 68-95-99.7 rule, it is usually set to 2 or 3.

Kalman filter

The Kalman Filter produces estimated values based on inaccurate and uncertain measurements. It works well to reduce the noise from sensors, producing a more even output. The noise from sensors is assumed to have a Gaussian distribution.


"Noisy sensor data, approximations in the equations that describe the system evolution, and external factors that are not accounted for all place limits on how well it is possible to determine the system's state. The Kalman filter deals effectively with the uncertainty due to noisy sensor data and, to some extent, with random external factors."