Changes in version 0.5.0.9000                      

                 Changes in version 0.5.0 (2026-01-15)                  

New features

Add QTS transformations into:

  - smooth representation using b-spline smoothing curves;
  - angular velocity vector and magnitude;
  - angular acceleration vector and magnitude.

Minor improvements and bug fixes

  - Skip tests using gghightlight if not installed;
  - Some documentation updates;
  - Updates of GitHub action workflows.

                 Changes in version 0.4.0 (2025-05-20)                  

New features

  - Adaptation to new API of fdacluster.
  - Added rotation invariant elastic distance.
  - Added no alignment option in distance matrix computation via SRVF.
  - Added roll-pitch-yaw representation.
  - Added format()/print() pair correctly.

Minor improvements and bug fixes

  - Remove dependency to purrr in favor of base R *apply() family to
    reduce dependency trail.
  - Replace furrr with future.apply for consistency with the removal of
    purrr.
  - Update roxygen version.
  - Fix bug in predict from PCA with new data. Properly compute L2 inner
    product.
  - Fix bug in predict from prcomp object.

                 Changes in version 0.3.0 (2024-01-10)                  

New features

  - Added S3 specialization of the stats::predict() function for
    prcomp_qts objects.
  - Added function qts2aats() which allows to switch from quaternion to
    axis-angle representation of rotations.
  - Added usual operations +, -, * and inverse_qts() for quaternion time
    series using the Eigen library.

Small improvements

  - Make sure quaternion geodesic mean is not flipped.
  - Fix issues in PCA:
      - avoid numerical overflows due to bad choice of k in gam();
      - improved documentation;
      - Use same number of basis functions in uni- and multivariate
        decompositions.
  - Updated GHA scripts and README.
  - Fix bug related to Rcpp following RcppCore/Rcpp#1287.

                 Changes in version 0.2.1 (2023-07-09)                  

  - Add use_fence robustification option;
  - Adapt to changes in fdacluster;
  - Properly compute tangent spaces along mean QTS;
  - Update News section of website.

                 Changes in version 0.2.0 (2023-06-04)                  

Major features:

  - Added hierarichal clustering;
  - Added DBSCAN clustering;
  - Added distance matrix computation.

Minor improvements:

  - Adapted code to match new API in fdacluster package.

                 Changes in version 0.1.0 (2022-12-22)                  

Major statistical features

  - A first API proposal with a class qts and a class qts_sample for
    which a number of methods are properly implemented.
  - Available statistical methods for QTS samples:
      - random generation according to the Gaussian functional model via
        rnorm_qts(),
      - scale(),
      - mean(),
      - median(),
      - distance matrix computation via distDTW() (i.e. for now we use
        the dynamic time warping),
      - tangent principal component analysis via prcomp(),
      - k-means with optional alignment via kmeans().
  - Added multiple ways of displaying samples of QTS.
  - Added two example datasets.

Improvements

  - Make all functions applicable to a single QTS also applicable to QTS
    samples, with appropriate class for the output.
  - Enable as_qts_sample() to generate a QTS sample of size 1 from a
    single QTS as input argument.
  - Rename change_points argument to the plot.qts() function to better
    reflect its flexibility.
  - Added subset operator for QTS sample objects.
  - Added append S3 method for QTS sample objects.
  - Added hemispherize() function to remove any discontinuities in QTS
    due to quaternion flips.
  - Any parallelization computation is now handled using the futureverse
    principles and, in particular, implemented through the use of the
    furrr package.

                 Changes in version 0.0.1 (2022-09-27)                  

  - Added a NEWS.md file to track changes to the package.
  - Initial version.