This is the Meat dataset from UCR Archive modified for Salient discovery. The original data is mixed with Random Walks and the algorithm must pick only the originals.

mp_meat_data

## Format

original is the original dataset with 60+60 observations mixed with 120 random walks:

data

240 time series with length of 448 each.

labels

label of each time series, -666 means a random walk.

sub_len

size of sliding window.

sub is the original dataset embedded in random walks:

data

One time series with length of 107520.

labels

label of each original data.

labels_idx

starting point where the original data was placed.

sub_len

size of sliding window.

## Source

http://www.cs.ucr.edu/~eamonn/time_series_data/

## References

• Yeh CCM, Van Herle H, Keogh E. Matrix profile III: The matrix profile allows visualization of salient subsequences in massive time series. Proc - IEEE Int Conf Data Mining, ICDM. 2017;579-88.

• Hu B, Rakthanmanon T, Hao Y, Evans S, Lonardi S, Keogh E. Discovering the Intrinsic Cardinality and Dimensionality of Time Series Using MDL. In: 2011 IEEE 11th International Conference on Data Mining. IEEE; 2011. p. 1086-91.