![](bg6.png)
automatically adjust the hyperparameters during the
training phase.
The procedure for determining the optimal
structure of the classification standard neural
network (the growing and pruning technique) has
not been mentioned in this paper as this approach
requires a lot of statistical tasks. The main
disadvantage of the Bayesian learning for feed-
forward neural networks is that it takes a quite long
time on evaluating the Hessian matrix, especially
when the number of network parameters (weights
and biases) is relatively large.
Table 1: The change of hyperparameters according to the
periods of re-estimation.
Periods
1 31.392 1.371 0.529 0.775
2 99.919 2.389 0.334 2.432
3 198.498 4.055 0.231 3.949
Table 2: The three-state prediction accuracy and
Matthew’s correlation coefficients of classification
Bayesian neural network.
Matthew’s Correlation
Coefficients
Fold
3
(%)Q C
C
loo
C
A 75.840 0.699 0.531 0.565
B 78.187 0.728 0.607 0.604
C 72.422 0.635 0.510 0.524
D 75.319 0.658 0.550 0.540
E 74.826 0.641 0.580 0.542
F 76.362 0.697 0.598 0.569
G 77.462 0.696 0.578 0.604
Average 75.774 0.679 0.565 0.564
Table 3: The three-state prediction accuracy and
Matthew’s correlation coefficients of standard
classification Bayesian neural network.
Matthew’s Correlation
Coefficients
Fold
3
(%)Q C
C
loo
C
A 75.927 0.689 0.543 0.565
B 77.347 0.725 0.583 0.587
C 71.321 0.619 0.496 0.502
D 74.826 0.646 0.551 0.536
E 73.812 0.622 0.571 0.521
F 74.739 0.669 0.572 0.548
G 76.796 0.669 0.568 0.604
Average 74.967 0.663 0.555 0.552
REFERENCES
B. Rost and C. Sander, "Prediction of protein secondary
structure at better than 70% accuracy," J.Mol.Biol.,vol.
232, pp. 584-599, 1993a.
B. Rost and C. Sander, "Improved prediction of protein
secondary structure by use of sequence profiles and
neural networks.," Proc, Natl, Acad, Sci, Biophysics,
USA, pp. 7558 - 7562, 1993b.
L. H. Holley and M. Karpus, "Protein secondary structure
prediction with a neural network," Proc, Natl, Acad,
Sci, Biophysics, USA, vol. 86, pp. 152 - 156, 1989.
L. Lee, J. L. Leopold, and R. L. Frank, "Protein secondary
structure prediction using BLAST and exhaustive RT-
RICO, the search for optimal segment length and
threshold," 2012 IEEE Symposium on Computational
Intelligence in Bioinformatics and Computational
Biology (CIBCB), pp. 35 – 42, 2012.
S. T. Nguyen, H. T. Nguyen, and P. Taylor, "Hands-Free
Control of Power Wheelchairs using Bayesian Neural
Networks," Proceedings of IEEE Conference on
Cybernetics and Intelligent Systems, Singapore, 2004,
pp. 745 - 749, 2004.
S. T. Nguyen, H.T.Nguyen, P. Taylor, and J. Middleton,
"Improved Head Direction Command Classification
using an Optimised Bayesian Neural Network,"
Proceedings of IEEE International Conference of the
Engineering in Medicine and Biology Society, New
York City, New York, USA, August 30-Sept. 3, 2006.
W.D. Penny and S. J. Roberts, "Bayesian neural networks
for classification: how useful is the evidence
framework," Neural Networks, vol. 12, pp. 877 - 892,
1999.
H. H. Thodberg, "A review of Bayesian neural networks
with an application to near infrared spectroscopy,"
IEEE Transactions on Neural Networks, vol. 7, pp. 56
- 72, 1996.
D. MacKay, "A practical Bayesian Framework for
Backpropagation Networks," Computation and Neural
Systems, vol. 4, pp. 448-472, 1992a.
D. MacKay, "The Evidence Framework Applied to
Classification Networks," Neural Computation, vol. 4,
pp. 720 -736, 1992b.
C. M. Bishop, "Neural networks for pattern recognition,"
Oxford: Clarendon Press; New York: Oxford
University Press, 1995.
M. A. Mottalib, M. S. R. Mahdi, A. B. M. Z. Haque, S. M.
A. Mamun, and H. A. Al-Mamun, "Protein Secondary
Structure Prediction using Feed-Forward Neural
Network," JCIT, vol. 1, pp. 64 - 68, 2010.
N. Qian and T. J. Sejnowski, "Predicting the Secondary
Structure of Globular Proteins Using Neural Network
Models," J. Mol. Biol. 202, pp. 865 - 884, 1988.
M. F. Moller, "A Scaled Conjugate Gradient Algorithm
for Fast Supervised Learning," Neural Networks, vol.
6, pp. 525 - 533, 1993.
Jpred 3, http://www.compbio.dundee.ac.uk/www-jpred/
David T. Jones, "Protein Secondary Structure Prediction
Based on Position-specific Scoring Matrices,"
J.Mol.Biol.,vol.292, pp.195-202, 1999.
IJCCI2013-InternationalJointConferenceonComputationalIntelligence
456