臺灣博碩士論文加值系統

本文提出了一種新的混合動力技術，稱為共生有機體搜索 - 量子神經網絡（SOS - 量子神經網絡）來預測高性能混凝土的抗壓強度。量子神經網絡是指類神經網絡模型，人工或生物，這依賴於靈感以某種方式從量子力學原理。當SOS是一個新的優化技術。 SOS - 量子神經網絡的性能與人工神經網絡（ANN）和量子神經網絡（QNN）本身相比。 SOS功能是優化內量子神經網絡的所有參數，因此它會提高量子神經網絡在解決HPC案件的能力。結果表明，SOS-QNN高效，準確地解決各種複雜的問題。此外SOS - 量子神經網絡具有基於均方根誤差，MAE，MAPE和R與其他算法比較最佳的性能。

This paper presents a new hybrid technique called Symbiotic Organism Search-Quantum Neural Network (SOS-QNN) to predict the compressive strength of high performance Concrete. QNN refers to the class of neural network models, artificial or biological, which rely on principles inspired in some way from quantum mechanics. While SOS is a new optimization technique. The performance of SOS-QNN is compared with artificial neural network (ANN) and quantum neural network (QNN) itself. SOS function is to optimize all parameters within QNN so it will improve QNN ability in solving HPC cases. Results indicate that SOS-QNN efficiently and accurately solves various complex problems. Furthermore SOS-QNN has the best performance based on RMSE, MAE, MAPE, and R compare with other algorithms.

ABSTRACT i
ACKNOWLEDGEMENT iii
TABLE OF CONTENTS v
LIST OF FIGURES ix
LIST OF TABLES xi
ABBREVIATIONS xiii
CHAPTER 1: INTRODUCTION 1
1.1 Research Motivation 1
1.1.1 Significance of Predicting High Performance Concrete Compressive Strength 1
1.1.2 Shortcomings of Predicting High Performance Concrete Compressive Strength 1
1.1.3 Direction to Deal with the Shortcomings 2
1.1.4 Promise of combining QNN and SOS 3
1.2 Research Objective 4
1.3 Research Scope 4
1.4 Research Methodology 4
1.5 Research Outline 7
CHAPTER 2: LITERATURE REVIEW 9
2.1 High Performance Concrete (HPC) 9
2.2 Symbiotic Organism Search 12
2.2.1 Symbiosis in real-world 12
2.2.2 The Symbiotic Organisms Search (SOS) 13
2.2.3 Mutualism Phase 15
2.2.4 Commensalism Phase 15
2.2.5 Parasitism Phase 16
2.3 Artificial Neural Network 20
2.3.1 Activation Functions 21
2.3.2 Learning Method 22
2.3.3 Weighting Factors 24
2.3.4 Threshold 24
2.3.5 Liner Function 24
2.3.6 Threshold Function 25
2.3.7 Piecewise Liner Function 25
2.3.8 Sigmoidal (S shaped) function 26
2.3.9 Type of Artificial Neural Network 27
2.4 Quantum Neural Network Model 30
2.4.1 Quantum Theory 30
2.4.2 Quantum Neuron Model 33
2.4.3 Quantum Complex-valued Neuron Model 38
2.4.4 Node Operation 38
2.4.5 Quantum Neural Network Model 39
2.4.6 Quantum Neural Learning Algorithm 40
2.4.7 Feature of Quantum Neural Network 41
2.4.8 Mapping a Number into Quantum State 43
2.4.9 Quantum State Output Interpretation 43
2.4.10 Compression the classical and quantum manifestations: 44
CHAPTER 3: SYMBIOTIC ORGANISMS SEARCH-QUANTUM NEURAL NETWORK (SOS-QNN) 45
3.1 SOS-QNN Architecture 45
3.2 Numerical Example 49
3.1 Modified Predicted Output Value 50
CHAPTER 4: CASE STUDY 53
4.1 Dataset 53
4.2 Tuning Parameter 53
4.3 Performance Measurement 55
4.4 Result and Discussion 57
CHAPTER 5: CONCLUSIONS AND RECOMMENDATIONS 69
5.1 Conclusions 69
5.2 Future Research and Recommendations 69
REFERENCES 71
APPENDIX A: Historical Data 76
APPENDIX B: MatLab Source Code 102

REFERENCES

Aitcin, P. C. (2003). The Durability Characteristics of High Performance Concrete: A Review. Cement &; Concrete Composites, 25, 409-420.
Behrman, E. C., &; Steck, J. E. (2013). A Quantum Neural Network Computes its Own Relative Phase. Quantum Physics.
Bonnell, G., &; Papini, G. (1997). Quantum Neural Network. International Journal of Theoritical Physics, 2885-2875.
Castelli, M., Vanneschi, L., &; Silva, S. (2013). Prediction of High Performance Concrete Strength Using Genetic Programming with Geometric Semantic Genetic Operators. Expert Systems with Applications, 40, 6856–6862.
Chen, L., &; Wang, T. S. (2010). Modeling Strength of High Performance Concrete Using an Improved Grammatical Evolution Combined with Macrogenetic Algorithm. Journal of Computing in Civil Engineering, 24, 281-288.
Cheng, M. Y., Chou, J. S., Roy, A. F., &; Wu, Y. W. (2012). High-performance Concrete Compressive Strength Prediction using Time-Weighted Evolutionary Fuzzy Support Vector Machines Inference Model. Automation in Construction, 28, 106-115.
Cheng, M.-Y., &; Prayogo, D. (2014). Symbiotic Organisms Search: A New Metaheuristic Optimization Algorithm. Computers and Structures, 98-112.
Cheng, M.-Y., Firdausi, P. M., &; Prayogo, D. (2013). High-performance Concrete Compressive Strength Predection Using Genetic Weighted Pyramid Operation Tree (GWPOT). Engineering Application of Artificial Intelligence.
Chou, J. S., &; Tsai, C. F. (2012). Concrete Compressive Strength analysis Using a Combined Classification and Regression Technique. Automation in Construction, 24, 52-60.
Chou, J. S., Chiu, C. K., Farfoura, M., &; Al-Taharwa. (2011). Optimizing the Preiction Accuracy of Concrete Compressive Strength Based on a Comparison of Data-Mining Techniques. Journal of Computing in Civil Engineering, 25, 242-253.
Chou, J.-S., &; Tsai, C.-F. (2012). Concrete Compressive Strength Analysis Using a Combined Classification and Regression Technique. Automation in Construction, 52-60.
Deepa, C., Kumari, K. S., &; Sudha, V. P. (2010). Prediction of the Compressive Strength of High Performance Concrete Mix Using Tree Based Modeling. International Journal of Computer Applications, 6 - No. 5, 18-24.
Erdal, I. H. (2013). Two-level and Hybrid Ensembles of Decisiontrees for High Performance Concrete Compressive Strength Prediction. Engineering ApplicationsofArtificial Intelligence, 26, 1689–1697.
Ezhov, A. A., &; Ventura, D. (2013, May 26). Publication. Retrieved from BSTU laboratory of Artificial Neural Network: http://neuro.bstu.by/ai/To-dom/My_research/Papers-0/For-research/Needle/2-Quantom-c/Quantum-NN/Ezhov1.pdf
Fie, L., &; Baoyu, Z. (2003). A Study of Quantum Neural Network. IEEE Intl. Conf. Neural Network &; Signal Processing (pp. 539-542). Nanjing: IEEE.
Hopfield, J. (1982, April 15). Neural Network and Phsyical Systems with Emergent Collcetive Computational Abbilities. Proceedings of the national Academy of Sciences of the United States of America Vol. 79. No.8, pp. 2554-2558.
Hsie, M., Ho, Y. F., Lin, C. T., &; Yeh, I. C. (2012). Modeling Asphalt Pavement Overlay Transverse Cracks Using the Genetic Pperation Tree and Levenberg–Marquardt Method. Expert Systems with Applications, 39, 4874-4881.
Kumar, M., &; Singh, V. (2009). Quantum Neural Network Training Algoritm. Patiala: Thapar University.
Laskar, A. I., &; Talukdar, S. (2008). A New Mix Design Method for High Performance Concrete. Asian Journal of Civil Engineering (Building and Housing), 15-23.
Li, Y., &; Wu, X. (2012). Harmonic Measuring Approach Based on Quantum Neural Network. Physics Procedia, 337-344.
Lim, C.-H., Yoon, Y.-S., &; Kim, J.-H. (2003). Genetic Algortihm in Mix Propotioning of High-performance Concrete. Cement and Concrete, 409-420.
Mahajan, R. (2010). Stock Price Prediction using Quantum Neural Network. Journal of Global Research in Computer Science, 59-64.
Mehta, P., &; Aitcin, P. (1990). Microstrutural Basis of Selection of Materials and Mix Propotions for Hig-Strength Concrete. Proceedings of the 2th International Symposium on High Strength Concrete (pp. 265-268). Detroit: American Concrete Institute.
Mousavi, S. M., Aminian, P., Gandomi, A. H., Alavi, A. H., &; Bolandi, H. (2012). A New Predictive Model for Compressive Strength of HPC Using Gene Expression Programming. Advances in Engineering Software, 45, 105-114.
Mu, D., Guan, Z., &; Zhang, H. (2013). Learning Algorithm and Application of Quantum Nerural Network with Quantum Weights. International Journal of Computer Theory and Engineering, 788-792.
Prayogo, D. (2011). A Novel Genetic Algorithm-Based Evolutionary Support Vector Machine for Optimizing High-Performance Concrete Mixture. Thesis, National Taiwan University of Science and Technology, Taiwan.
Rajasekaran, S., &; Amalrj, R. (2002). Prediction of Strength and Workability of High Performance Concrete using Artificial Neural Networks. Indian Journal of Engineering &; Materials Sciences, 109-114.
Singh, G. (2009). Quantum Neural Network Application for Weather Forcasting. Patiala: Thapar University.
Takahashi, K., Kurokawa, M., &; Hashimoto, M. (2014). Multi-layer Neural Network Controller Trained by Real-coded Genetic Algorithm. Neurocomputing, 159-164.
Time Travel Research Center. (2005, 07 01). Quantum Computing. Retrieved from Atoms: http://www.zamandayolculuk.com
U.S. Departement of Transportation Federal High Way Administration. (2014, June 20). What is High Performance Concrete. Retrieved from Bridges and Structures: http://www.fhwa.dot.gov
Uoregon. (2001, 07 01). Quantum Physics. Retrieved from Cosmology: http://abyss.uoregon.edu
Widodo, P. P., &; Handayanto, R. T. (2012). Penerapan Soft Computing dengan MatLab. Bandung: Rekayasa Sains.
Wikimedia Foundation, Inc. (2013, October 16). Quantum Neural Network. Retrieved from Wikipedia The Free Encyclopedia: http://en.wikipedia.org
Yeh, I. C. (1998). Modeling of Strength of High-Performance Concrete Using Artificial Neural Networks. Cement and Concrete Research, 28, 1797-1808.
Yeh, I. C., &; Lien, L. C. (2009). Knowledge Discovery of Concrete Material using Genetic Operation Trees. Expert System with Applications, 36, 5807-5812.
Yeh, I. C., Lien, C. H., Peng, C. H., &; Lien, L. C. (2010). Modeling Concrete Strength Using Genetic Operation Trees. International Conference on Machine Learning and Cybernetics. Qingdao: IEEE.
Yeh, I.-C. (1998). Modeling of Strength of High-performance Concrete Using Artificial Neural Networks. Cement and Concrete Research, 1797-1808.