Bayesian nonparametric hidden semi-Markov models

By Matthew J. Johnson, Alan S. Willsky. Journal of machine learning research, 2012

377 citations recorded by the source corpus.

United States. Army Research Office. Multidisciplinary University Research Initiative (Grant W911NF-06-1-0076)

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Big IoT data mining for real-time energy disaggregation in buildings (2016, methodology): “…(e.g. Factorial Hidden Markov models (FHMM) [13], Factorial Hidden Semi-Markov Model (FHSMM) [13], Conditional FHMM [13], Conditional Factorial Hidden Semi-Markov Model (CFHSMM) [13], additive FHMM [21] or Bayesian Nonparametric Hidden Semi-Markov Models [22]) to perform energy disaggregation.”
Unsupervised Incremental Online Learning and Prediction of Musical Audio Signals (2015, methodology): “Inference in the HDP-HMM is performed using the weak limit approximation [18] implemented in pyhsmm [31].”
Exploiting HMM Sparsity to Perform Online Real-Time Nonintrusive Load Monitoring (2016, methodology): “Recently, Johnson et al. [16] considered using the factorial variant of a hidden semi-Markov model (HSMM) because they provided a means of representing state durations in a load model.”
NILMTK: an open source toolkit for non-intrusive load monitoring (2014, methodology): “First, Kolter and Johnson [5] proposed an accuracy metric which captures the error in assigned energy normalised by the actual energy consumption in each time slice averaged over all appliances, which was also later used by Rahayu et al. [22] and Johnson and Willsky [20].”
Discovering linguistic structures in speech: models and applications (2014, methodology): “We adopt the notation used in [85] and define B and B∗ as follows.”