Skip to main content

Table 4 Simulation results for dataset D 3

From: Unsupervised Bayesian linear unmixing of gene expression microarrays

(a) R= 2
  uBLU PCA NMF BFRM GB-GMF
MSE r 2 (×1 0 3 ) 0.01 0.83 0.82 N/A 1.14
  0.85 0.80 0.92 1.34 2.30
  1.15 N/A N/A 1.36 N/A
GMSE r 2 (×1 0 2 ) 7.75 7.29 7.72 N/A 8.94
  7.76 0.47 0.48 12.30 11.86
  9.84 N/A N/A 11.05 N/A
SAD r 2 (×1 0 1 ) 0.59 7.09 7.04 N/A 15.55
  7.13 6.71 7.19 8.41 16.43
  8.71 N/A N/A 8.54 N/A
GSAD (×10−1) 3.23 2.58 2.59 6.59 15.26
RE (×10−4) 3.11 0.70 0.70 0.47 2.50
Time (s) 1.59×103 0.01 0.70 42.02 0.40×103
(b) R = 3
  uBLU PCA NMF BFRM GB-GMF
MSE r 2 (×1 0 3 ) 0.01 0.15 0.15 1.74 1.20
  0.85 1.02 0.76 1.76 2.26
  1.15 1.57 1.03 1.55 2.40
GMSE r 2 (×1 0 2 ) 7.75 14.89 2.80 11.40 14.09
  7.76 0.11 0.40 12.11 12.33
  9.84 0.11 0.30 10.94 12.76
SAD r 2 (×1 0 1 ) 0.59 2.60 2.47 11.34 15.76
  7.13 7.16 6.59 9.45 16.40
  8.71 8.80 7.67 9.06 15.66
GSAD (×10−1) 3.23 2.58 1.71 6.88 15.20
RE (×10−4) 3.11 0.27 0.29 0.49 2.44
Time (s) 1.59×103 0.10 1.24 59.72 0.54×103
(c) R = 4
  uBLU PCA NMF BFRM GB-GMF
MSE r 2 (×1 0 3 ) 0.01 0.02 1.43 1.43 1.19
  0.85 1.48 5.49 3.92 2.06
  1.15 1.68 0.90 1.88 2.33
GMSE r 2 (×1 0 2 ) 7.75 13.78 20.56 16.66 13.15
  7.76 4.35 12.36 15.34 11.75
  9.84 3.99 2.67 11.25 13.29
SAD r 2 (×1 0 1 ) 0.59 0.97 10.27 10.24 15.97
  7.13 7.93 15.78 16.45 14.92
  8.71 8.66 6.93 10.98 15.89
GSAD (×10−1) 3.23 1.17 1.20 5.51 15.98
RE (×10−4) 3.11 0.16 0.16 0.41 2.45
Time (s) 1.59×103 0.13 1.15 67.71 0.69×103
  1. MSEs, GMSEs, SADs, GSADs, REs and computational times between the proposed uBLU algorithm and PCA, NMF, BFRM and GB-GMF methods.