Software
The ruptures package developed by my former PhD student Charles Truong is a Python library for offline change-point detection. Source code is available under the BSD license and deployed with complete documentation that includes installation instructions and explanations with code snippets on advanced use. It includes a large range of state-of-the-art change-point detection algorithms and some new methods as well!
A dataset of 1020 multivariate gait signals collected with two inertial measurement units, from 230 subjects undergoing a fixed protocol: standing still, walking 10 m, turning around, walking back and stopping. In total, 8.5 h of gait time series are distributed. The measured population was composed of healthy subjects as well as patients with neurological or orthopedic disorders. An outstanding feature of this dataset is the amount of signal metadata provided. In particular, the start and end timestamps of more than 40,000 footsteps are available, as well as contextual information about each trial.
Data (IPOL)
Source codeSeveral source codes in C for sound denoising/interpolation can be found in the Sound section of the IPOL journal along with articles describing the implementation and online demos.
Here are the chord recognition algorithms submitted to MIREX 2010 & 2009 for the Audio Chord Detection task (Results 2009 & 2010). Released under the GNU General Public License.
