For systems that exhibit abrupt changes while the data is being collected, you might want to develop models for separate data segments such that the system does not change during a particular data segment. Such modeling requires identification of the time instants when the changes occur in the system, breaking up the data into segments according to these time instants, and identification of models for the different data segments.
The following cases are typical applications for data segmentation:
Segmentation of speech signals, where each data segment corresponds to a phonem.
Detection of trend breaks in time series.
Failure detection, where the data segments correspond to operation with and without failure.
Estimating different working modes of a system.
segment to build polynomial
models, such as ARX, ARMAX, AR, and ARMA, so that the model parameters
are piece-wise constant over time. For detailed information about
this command, see the corresponding reference page.
To see an example of using data segmentation, run the Recursive Estimation and Data Segmentation demonstration by typing to the following command at the prompt: