Research Article
Simultaneous Incomplete Traffic Data Imputation and Similarity Pattern Discovery with Bayesian Nonparametric Tensor Decomposition
Algorithm 1
Bayesian nonparametric tensor decomposition (BNPTD).
| Input: incomplete tensor , indicator tensor , CP rank , maximum clusters . | | Output: estimated tensor , the results of similarity pattern discovery. Initialize factor matrices and hyperparameters. | | (1) repeat | | (2) for to do | | (3) Update the variational posterior distribution . | | (4) Update the variational posterior distribution and . | | (5) for to do | | (6) Update the variational posterior distribution . | | (7)for to do | | (8) Update the variational posterior distribution . | | (9) for to do | | (10) Update the variational posterior distribution . | | (11) Update the variational posterior distribution . | | (12) until maximum iterations exhausted |
|