In this dissertation, we proposed an alternant supervised fast learning algorithm and some applications of neural network. In the part of new learning algorithm, both linear multi-regression (LMR) and BP learning methods were used alternately to train the neural model. From the simulation results, it can obviously find that the performance of neural model with such an alternant learning method is much better than the neural model with BP learning method only.
However, only the stationary signal processing problem was studied in our research. No non-stationary signal processing problem is studied. Therefore, we will continuously employ such an alternant learning algorithm into the application of non-stationary signal processing in our future study.
In the research of power load forecasting, several neural network models were studied.
From the simulation results shown, it could be clearly found that the neural model with modified hyperbolic tangent function in the output layer basically has the better performances in comparison with other models. We conclude that the item of (bj(k)/aj(k)) makes the network’s weight updating become more flexible. That also means this item leads each node of neural model to have different learning steps based on immediate learning condition.
The other neural network applications include “The Optoelectronic Attributes of LED chip” and “A Quality Inspection System for Riveting Process”. In these researches, only the
traditional neural model was applied. The research results might not be the best. In our future research, other neural model and learning algorithm will be continuously studied. For instance, in the research of “A Quality Inspection System for Riveting Process”, the accelerometer sensed lots of noises due to the large impact forces. Thus, we could develop a hardware filter to eliminate the noise in advance or develop an algorithm which can enhance signal characteristic in the future studies.
References
[1] A.J. Robinson and F. Fallside, “Static and dynamic error propagation networks with applications to speech coding,” Neural Information Processing System, pp. 632-641, 1988.
[2] J.A. Anderson, M.T. Gately, P.A. Penz, and D.R. Collins, “Radar signal categorization using a neural network,” Proceedings of the IEEE, Vol. 78, Iss. 10, pp. 1646-1657, 1990.
[3] S. Chen, S.A. Billings, and P.M. Grant, “Non-linear system identification using neural networks,” International Journal of Control, Vol. 51, pp. 1191-1214, 1990.
[4] W.H. Schiffman and H.W. Geffers, “Adaptive control of dynamic systems by backpropagation networks,” Neural Networks, Vol. 6, Iss. 4, pp. 517-524, 1993.
[5] C. Wohler and J.K. Anlauf, “An adaptive time-delay neural-network algorithm for image sequence analysis,” IEEE Transactions on Neural Neworks, Vol. 10, Iss. 6, pp.
1531-1536, 1999.
[6] P.J. Edwards, A.F. Murray, G. Papadopoulos, A.R. Walllace, J. Barnard, and G. Smith,
“The application of neural networks to the papermaking industry,” IEEE Transactions on Neural Neworks, Vol. 10, Iss. 6, pp. 1456-1464, 1999.
[7] D.E. Rumelhart, G.E. Hinton and R.J. Williams, “Learning internal representations by error propagation,” Parallel Distributed Processing, MIT Press, Vol. 1, pp. 673-695, 1988.
[8] B. Widrow and M.A. Lehr, “30 years of adaptive neural networks: perceptron, madalin and backpropagation,” Proceedings of the IEEE, Vol. 78, Iss. 9, pp. 1415-1442, 1990.
[9] S. Haykin, “Neural Networks: A comprehensive foundation, 2 edition,” Prentice Hall, 1998.
[10] S.A. Solla, E. Levin and M. Fieisher, “Accelerated learning in layered neural networks,”
Complex Systems, Vol. 2, Iss. 6, pp. 625-639, 1988.
[11] F.M. Silva and L.B. Almeida, “Speeding-up backpropagation,” Advance Neural Computers, pp. 151-158, North-Holland, Amsterdam, 1990.
[12] A.F. Atiya and A.G. Parlos, “New results on recurrent network training: unifying the algorithms and acceleration convergence,” IEEE Transactions on Neural Neworks, Vol.
11, Iss. 3, pp. 697-709, 2000.
[13] G.J. Wang and C.C. Chen, “A fast multilayer neural network training algorithm based on the layer-by-layer optimizing procedures,” IEEE Transactions on Neural Neworks, Vol.
7, Iss. 3, pp. 768-775, 1996.
[14] Y.Q. Chen, T. Yin and H.A. Babri, “A stochastic backpropagation algorithm for training neural networks,” 1997 International Conference of Information, Communication and Signal Processing, Vol. 2, pp. 703-707, 1997.
[15] B. Vema, “Fast training of multilayer perceptrons,” IEEE Transactions on Neural Neworks, Vol. 8, Iss. 6, pp. 1314-1320, 1977.
[16] A. Kielbasinski and H. Schwetlick, “Numerical linear algebra,” Warsaw, Poland, Polish Scientific Press, 1992.
[17] M.R. Azimi-Sadjadi and R.-J. Liou, “Fast learning process of multilayer neural networks using recursive least squares method,” IEEE Transactions on Signal Processing, Vol. 4, Iss. 2, pp. 446-450, 1992.
[18] J. Leonard and M.A. Kramer, “Improvement of the backpropagation algorithm for training neural network,” Computers and Chemical Engineer, Vol. 14, Iss. 3, pp.
337–341, 1990.
[19] F. Biegler-König and F. Bärmann, “A learning algorithm for multilayered neural networks based on linear least squares problems,” Neural Networks, Vol. 6, Iss. 1, pp.
127–131, 1993.
[20] B.K. Verma and J.J. Mulawka, “Training of the multilayer perceptron using direct solution methods,” The 12th IASTED International Conference, pp. 18–24, Annecy, France, 1994.
[21] J.J. Mulawka and B.K. Verma, “Improving the training time of the backpropagation algorithm,” International Journal of Microcomputer Application, Vol. 13, pp. 85–89, 1994.
[22] F. Stäger and M. Agarwal, “Three methods to speed up the training of feedforward and feedback perceptrons,” Neural Networks, Vol. 10, Iss. 8, pp. 1435–1443, 1997.
[23] J. Wang B.L. Chenguang L.J. Liu, “Research of new learning method of feedforward neural network, ” Proceedings of the 2008 International Symposiums on Information Processing, pp. 102–106, 2008.
[24] P. Stubberud and J.W. Bruce, “An LMS algorithm for training single layer globally recursive neural networks,” 1998 IEEE World Congress on Computational Intelligence, Vol. 3, pp. 2214–2217, 1998.
[25] S. Abid, F. Fnaiech and M. Najim, “A fast feedforward training algorithm using a modified form of the standard backpropagation algorithm,” Neural Networks, IEEE, Vol.
12, Iss. 2, pp. 424–430, 2001.
[26] T.S. Dillon, “Artificial neural network applications to power systems and their relationship to symbolic methods,” International Journal of Electrical Power and Energy Systems, Vol. 13, Iss. 2, pp. 66–72, 1991.
[27] S.T. Chen, D.C. Yu, and A.R. Moghaddamjo, “Weather sensitive short-term load forecasting using nonfully connected artificial neural network,” IEEE Transactions on Power Systems, Vol. 7, Iss. 3, pp. 1098–1105, 1992.
[28] C.N. Lu, N.T. Wu and S. Vemuri, “Neural network based shor term load forecasting,”
IEEE Transactions on Power Systems, Vol. 8, Iss. 1, pp. 336-342, 1993.
[29] A. Kaotanzad, R. C. Hwang, A. Abaye, and D. Maratukulam, “An adaptive modular artificial neural network hourly load forecaster and its implementation at electric utilities,” IEEE Transactions on Power Systems, Vol. 10, Iss. 3, pp. 1716–1722, 1995.
[30] G. Purushothaman and N. B. Karayiannis, “Quantum neural networks (QNNs):
inherently fuzzy feedforward neural networks,” IEEE Transactions on Neural Network, Vol. 8, Iss. 3, pp. 679-693, 1997.
[31] E.C. Behrman, L.R. Nash, J.E. Steck, V.G. Chandrashekar and S.R. Skinner,
“Simulations of quantum neural networks,” Information Sciences, Vol. 128, Iss. 3-4, pp.
257-269, 2000.
[32] R.C. Hwang, H.C. Huang and J.G. Hsieh, “A new artificial intelligent peak power load forecaster based on non-fixed neural networks,” International Journal of Electrical Power and Energy Systems, Vol. 24, Iss. 3, pp. 245–250, 2002.
[33] Y.J. Chen, T.C. Huang and R.C. Hwang, “Power signal prediction by neural network with a new fuzzy BP learning algorithm,” 2002 IEEE International Conference on Industrial Technology, Vol. 2, pp. 845–849, 2002.
[34] O.A. Alsayegh, “Short-term load forecasting using seasonal artificial neural networks,”
International Journal of Power and Energy Systems, Vol. 23, Iss. 3, pp. 137–142, 2003.
[35] Y.J. Chen, T.C. Huang and R.C. Hwang, “Reliable power load forecaster by neural networks with a modified FBP learning algorithm,” Engineering Intelligent Systems for Electrical Engineering and Communications, Vol. 12, No. 4, pp. 211–216, 2004.
[36] R.C. Hwang, Y.J. Chen, S.J. Chuang, H.C. Huang and W.D. Chuang, “Fast learning neural network with modified neurons,” 2005 IEEE International Conference on Information Technology and Applications, pp. 313–318, 2005.
[37] K. Nahi, W. Rene, S. Maarouf and G. Semaan, “An efficient approach for short term load forecasting using artificial neural networks,” International Journal of Electrical Power and Energy Systems, Vol. 28, Iss. 8, pp. 525–530, 2006.
[38] M. Corporation and C.K. Hakozakicho, “A neural network based several-hour-ahead electric load forecasting using similar days approach,” International Journal of Electrical Power and Energy Systems, Vol. 23, No. 6, pp. 367–373, 2006.
[39] M. Ghiassi, D.K. Zimbra and H. Saidane, “Medium term system load forecasting with a dynamic artificial neural network model,” Electric Power Systems Research, Vol. 76, Iss.
5, pp. 302-316, 2006.
[40] F.L. Chen and S.F. Liu, “A neural-network approach to recognize defect spatial pattern in semiconductor fabrication,” IEEE Transactions on Semiconductor Manufacturing, Vol.
13, Iss. 3, pp. 366–373, 2000.
[41] R.A. Zoroofi, H. Taketani, S. Tamura, Y. Sato and K. Sekiya, “Automated inspection of IC wafer contamination,” Pattern Recognition, Vol. 34, Iss. 6, pp. 1307–1317, 2001.
[42] C.T. Su, T. Yang and C.M. Ke, “A neural-network approach for semiconductor wafer post-sawing inspection,” IEEE Transactions on Semiconductor Manufacturing, Vol. 15, Iss. 2, pp. 260–266, 2002.
[43] S.R. Bhatikar and R.L. Mahajan, “Artificial neural-network-based diagnosis of CVD barrel reactor,” IEEE Transactions on Semiconductor Manufacturing, Vol. 15, Iss. 1, pp.
71–78, 2002.
[44] B. Kim and K. Park, “Modeling plasma etching process using a radial basis function network,” Microelectronic Engineering, Vol. 77, Iss. 2, pp. 150–157, 2005.
[45] F.L. Chen, S.F. Liu, K.Y.Y. Doong and K.L. Young, “LOGIC product yield analysis by Wafer Bin Map pattern recognition supervised neural network,” 2003 IEEE International Symposium on Semiconductor Manufacturing, pp. 501–504, 2003.
[46] W.C. Chen, C.T. Chen, T.H. Ho, J.H. Chen and L.J. Sheu, “Use of neural network in pattern recognition of semiconductor etching process,” 2005 IEEE International Conference on Industrial Engineering and Engineering Management, Vol. 1, pp.
719–725, 2005.
[47] F.Di. Palma, G.De. Nicolao, G. Miraglia, E. Pasquinetti and F. Piccinini, “Unsupervised spatial pattern classification of electrical-wafer-sorting maps in semiconductor manufacturing,” Pattern Recognition Letters, Vol. 26, Iss. 12, pp. 1857–1865, 2005.
[48] C.J. Huang, “Clustered defect detection of high quality chips using self-supervised multilayer perceptron,” Expert Systems with Applications, Vol. 33, Iss. 4, pp. 996–1003, 2007.
[49] W.C. Chen and S.W. Hsu, “A neural-network approach for an automatic LED inspection system,” Expert Systems with Applications, Vol. 33, Iss. 2, pp. 531–537, 2007.
[50] H.D. Lin, “Automated defect inspection of light-emitting diode chips using neural network and statistical approaches,” Expert Systems with Applications, Vol. 36, Iss. 1, pp. 219–226, 2009.
[51] H.L. Wang, “Investigation on characteristics of a pneumatic rivet tool,” 2005 Joint Conference Meeting, AASRC/CSCA, Kaohsiung, S06, 2005.
[52] H.L. Wang, and T.C. Chen, “Investigation on characteristics of riveting procedure,”
Journal of Aeronautics, Astronautics and Aviation, Series A, Vol. 38, No. 4, pp. 251–258, 2006
[53] H.L. Wang, T.C. Chen, and H.T. Hsu, “Quality verification on riveting process of a pneumatic rivet tool,” Experimental Techniques, Vol. 31, No. 6, pp. 57–63, 2007.
[54] X. Wu, J. Ghaboussi and J.H. Garrett, “Use of neural networks in detection of structural damage,” Computers and Structures, Vol. 42, Iss. 4, pp. 649-659, 1992.
[55] K.W. Ko and H.S. Cho, “Solder joints inspection using a neural network and fuzzy rule-based classification method,” IEEE Transactions on Electronics Packaging Manufacturing, , Vol. 23, Iss. 2, pp. 93-103, 2000.
[56] M. Toparli, S. Sahin, E. Ozkaya and S. Sasaki, “Residual thermal stress analysis in cylindrical steel bars using finite element method and artificial neural networks,”
Computers and Structures, Vol. 80, No. 23, pp. 1763-1770, 2002.
[57] P.H. Weng, Y.J. Chen, H.C. Huang and R.C. Hwang, “Power load forecasting by neural models,” Engineering Intelligent Systems for Electrical Engineering and Communications, Vol. 15, pp. 33-39, 2007.