Analyzing and visualizing results

Once a set of operations have been computed on a time-series dataset, the results are stored in a local HCTSA.mat file. The result can be used to perform a wide variety of highly comparative analyses, such as those outlined in our paper.

The type of analysis employed should the be motivated by the specific time-series analysis task at hand. Setting up the problem, guiding the methodology, and interpreting the results requires strong scientific input that should draw on domain knowledge, including the questions asked of the data, experience performing data analysis, and statistical considerations.

The first main component of an hctsa analysis involves filtering and normalizing the data using TS_normalize, described here, which produces a file called HCTSA_N.mat. Information about the similarity of pairs of time series and operations can be computed using TS_cluster, described here which stores this information in HCTSA_N.mat. The suite of plotting and analysis tools that we provide with hctsa work with this normalized data, stored in HCTSA_N.mat, by default.

Plotting and analysis functions:

Tools for classification tasks:

For time-series classification tasks, groups of time series can be labeled using the TS_LabelGroups function described here; this group label information is stored in the local HCTSA*.mat file, and used by default in the various plotting and analysis functions provided. Additional analysis functions are provided for basic time-series classification tasks:

  • Explore the classification performance of the full library of features using TS_classify

  • Determine the features that (individually) best distinguish between the labeled groups using TS_TopFeatures