Abstract | ||
---|---|---|
Time-series segmentation in the fully unsupervised scenario in which the number of segment-types is a priori unknown is a fundamental problem in many applications. We propose a Bayesian approach to a segmentation model based on the switching linear Gaussian ... |
Year | DOI | Venue |
---|---|---|
2008 | 10.1109/ICMLA.2008.47 | ICMLA |
Keywords | Field | DocType |
time-series segmentation,bayesian approach,latent dirichlet allocation,analyzing software evolution,unsupervised scenario,linear gaussian,fundamental problem,segmentation model,unified modeling language,source code,software design,software evolution,statistical analysis,xml,generic programming,probabilistic logic,programming,topic models,automatic summarization,public domain software,software engineering,software mining,eclipse,history | Latent Dirichlet allocation,Source code,Computer science,Artificial intelligence,Software evolution,Software construction,Code refactoring,Software development,Software framework,Machine learning,Software sizing | Conference |
Citations | PageRank | References |
17 | 0.97 | 13 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Erik Linstead | 1 | 360 | 27.44 |
Cristina Lopes | 2 | 2576 | 207.71 |
Pierre Baldi | 3 | 4626 | 502.51 |