Self-tuning event detection
An event-adaptive technology, applied to measurement devices, computer components, instruments, etc., can solve problems such as incorrect results
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0074] figure 1 An example time series of raw signals 11 (ie raw data values) measured by environmental sensors and optionally preprocessed, eg by a calibration algorithm, is shown. In the example time series, the raw signal 11 fluctuates around some constant value (not shown), while some raw data values are far apart, ie significantly above or below this constant value. Raw data values that deviate so significantly (eg, by more than one or more than two standard deviations from the mean / average of the raw signal) are indicated as outliers.
[0075] also, figure 1 The lower and upper thresholds 12 determined without any gating are shown. The threshold 12 at a particular time is calculated as the mean plus (for an upper threshold) and minus (for a lower threshold) respectively the standard deviation of all raw data values for a defined period of time preceding that particular time. A known problem is that Threshold 12 is highly dependent on outliers, i.e. raw data valu...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


