Abstract | ||
---|---|---|
We apply mixture of principal component analyzers (MPCA) to missing value estimation problems. A variational Bayes (VB) method for MPCA with missing values is developed. The missing values are regarded as hidden variables aud their estimation is done simultaneously with the parameter estimation. It is found that VB method is better than maximum likelihood method by using artificial data. We also applied our method to DNA microarray data and the performance outweighed the conventional k-nearest neighbor method. |
Year | DOI | Venue |
---|---|---|
2002 | 10.1007/3-540-46084-5_80 | ICANN |
Keywords | Field | DocType |
principal component analyzer,parameter estimation,artificial data,missing value estimation problem,missing value,missing value estimation,hidden variable,maximum likelihood method,conventional k-nearest neighbor method,dna microarray data,vb method,hidden variables,missing values,k nearest neighbor | Dna microarray data,Pattern recognition,Maximum likelihood,Artificial intelligence,Missing data,Estimation theory,Hidden variable theory,System identification,Principal component analysis,Mathematics,Bayes' theorem | Conference |
Volume | ISSN | ISBN |
2415 | 0302-9743 | 3-540-44074-7 |
Citations | PageRank | References |
4 | 0.64 | 4 |
Authors | ||
6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Shigeyuki Oba | 1 | 290 | 27.68 |
Masa-aki Sato | 2 | 224 | 18.60 |
Ichiro Takemasa | 3 | 188 | 13.99 |
Morito Monden | 4 | 253 | 26.12 |
Ken-ichi Matsubara | 5 | 193 | 15.33 |
Shin Ishii | 6 | 532 | 43.99 |