Assessment of Texaco Syngas Components Using Extreme Learning Machine Based Quantum Neural Network - Intelligent Computing for Sustainable Energy and Environment - page 228

Tabl e 1. Comparisons of four methods

Methods

Train MSE Test MSE

CO H 2 CO 2 CO H 2 CO 2

SLFN 0.038 0.036 0.027 0.505 0.352 0.205

ELM-SLFN 0.201 0.168 0.068 0.781 0.437 0.196

ELM-QNN 0.210 0.188 0.082 0.382 0.311 0.110

PCA-ELM-QNN 0.219 0.188 0.079 0.335 0.267 0.121

the other compared methods and can provide more reliable assessment of the
Texaco syngas components.

5 Conclusions

A quantum neural network is proposed based on quantum mechanics. In the
network, the states of quantum neurons and their interactions are investigated
by using quantum theory of superposition and collapse. The extreme learning
machine is employed as the learning algorithm of the proposed QNN. ELM
randomly chooses the input weights, and then analytically identifies the output
weights. The ELM-QNN model combined with principal component analysis is
used to assess the syngas components in the Texaco gasification process. The
results implied that PCA-ELM-QNN performs better than the other compared
methods and is effective in the real-world application.

Acknowledgments. We are very grateful to the editors and anonymous re-
viewers for their valuable comments and suggestions to help improve our paper.
This work is supported by the National Key Basic Research Program of China
(No. 2012CB720500), the Key Program of National Natural Science Foundation
of China (No. 60736021), the National Natural Science Foundation of China (No.
61273166), the Specialized Research Fund for Doctoral Program of Higher Edu-
cation of China (No. 20100101110066), the Fundamental Research Funds for the
Central Universities, and the Shanghai Commission of Science and Technology
(Grant no. 11ZR1409800).

References

1. Kak, S.: On Quantum Neural Computing. Inform. Sci. 83, 143-160 (1995)
2. Perus, M.: Neuro-Quantum Parallelism in Brain-Mind and Computer. Informat-
ica 20, 173-183 (1996)
3. Behrman, E.C., Niemel, J., Steck, J.E., Skinner, S.R.: A Quantum Dot Neural
Network. In: Proceedings of the 4th Workshop on Physics of Computation, pp.
22-24 (1996)
4. Ventura, D., Martinez, T.: An Artificial Neuron with Quantum Mechanical Proper-
ties. In: Proceedings of the International Conference on Artificial Neural Networks
and Genetic Algorithms, pp. 482-485 (1997)