Time series are a common data type in biomedical applications. Examples include heart rate, power output, and ECG. One of the typical analysis methods is to determine longest period a subject spent over a given heart rate threshold. While it might seem simple to find and measure such periods, biomedical data are often subject to significant noise and physiological artifacts. As a result, simple threshold calculations might not provide correct or expected results. A common way to improve such calculations is to use moving average filter. Length of the window is often determined using sum of absolute differences for various windows sizes. However, for real life biomedical data such approach might lead to extremely long windows that undesirably remove physiological information from the data. In this paper, we:
展开▼