成功大學博碩士論文系統

簡易檢索 / 詳目顯示

回結果列表

研究生：	王聲瑞 Wang, Sheng-Jui
論文名稱：	具容量分析之模糊神經網路技術於每日漁獲預測之應用 A Fuzzy Neural Network Technique for Daily Fish Catch Prediction with Capacity Analysis
指導教授：	陳智強 Chen, Chih-Chiang
學位類別：	碩士 Master
系所名稱：	工學院 - 系統及船舶機電工程學系 Department of Systems and Naval Mechatronic Engineering
論文出版年：	2020
畢業學年度：	108
語文別：	英文
論文頁數：	60
中文關鍵詞：	神經網路之容量估計、模糊神經網路、漁獲量預測
外文關鍵詞：	Capacity of neural networks, Fuzzy neural networks, Fish catch prediction
相關次數：	點閱：118 下載：0
分享至:	分享至facebook 分享至twitter

查詢本校圖書館目錄查詢臺灣博碩士論文知識加值系統勘誤回報

估計每日魚群的分佈範圍以及捕撈漁獲量對漁民來說相當重要且具有極高的經濟利益，捕魚位置、船隻航行方向、以及捕魚燈光開啟時間將能因此估計方法而獲得輔助並減少燃料成本的浪費；本論文根據捕魚船隻的歷史蒐集資料，套用至模糊神經網路（Fuzzy Neural Network）中，從而應用並實現了一個漁獲量預測（Fish Catch Prediction）模型；在模糊神經網路架構的設計上，我們加入了訓練容量估算進而避免計算資源的虛耗；除此之外，為了提高計算效率與增加訓練收斂的可能性，一項動態調變學習率的訓練方法亦套用到模糊神經網路的訓練中；模擬結果顯示本文呈現之模糊神經網路具備良好的分類能力，因而能夠將這套複雜度低的神經網路方法套用到實際的漁獲量預測中並加以實現。

Making estimation of the daily presence and size of fishing effort is practical and has significant economic advantages for fishers; it contributes to a proper fishing light time, a basis of sailing direction, reduction of fuel costs, and a general decrease in required fishing time. This paper presents a fuzzy neural network (FNN) model to make classification with historical fishing data, thereby bringing a fish catch prediction (FCP) model in real-world. On the basis of a capacity estimation, we provide a guidance in constructing the FNN model as well as selecting appropriate computing resources. Moreover, the FNN model is trained by a dynamic optimal manner, which improves the computing efficiency and increases the possibility of convergence of training. The results show that the resultant FNN model has a good performance in classification ability, providing a relatively simple FNN method in FCP applications with high reliability.

摘要ii
Abstract iii
誌謝iv
Table of Contents v
List of Figures vi
List of Tables vii
Abbreviations viii
Symbols ix
Introduction 1
Preliminary 6
1 Mathematical Preliminary . . . . . . . . . . . . . . . . . . . . . . . . . . . 6
2 Training Method for Neural Network (NN) . . . . . . . . . . . . . . . . . . 12
2.1 Two Layer Neural Network with Back-propagation (BP) . . . . . . . 12
2.2 Dynamic Optimal Learning Rate . . . . . . . . . . . . . . . . . . . . 16
3 Fuzzy Neural Network . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19
3.1 Dynamic Optimal Learning Rate for FNN . . . . . . . . . . . . . . . 22
3.2 Capacity Estimation for FNN . . . . . . . . . . . . . . . . . . . . . 27
4 Principal Component Analysis . . . . . . . . . . . . . . . . . . . . . . . . . 32
Data and Modeling Method 37
1 Data Preprocess . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 37
1.1 Data Pretreatment . . . . . . . . . . . . . . . . . . . . . . . . . . . . 37
v
Contents
1.2 Data Classification . . . . . . . . . . . . . . . . . . . . . . . . . . . 39
2 Modeling Method . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 40
3 Examing Partial Training . . . . . . . . . . . . . . . . . . . . . . . . . . . . 41
3.1 Model Training for Partial Training . . . . . . . . . . . . . . . . . . 41
3.2 Result and Discussion for Partial Training . . . . . . . . . . . . . . . 42
4 Examing Completely Training . . . . . . . . . . . . . . . . . . . . . . . . . 43
4.1 Model Training for Completely Training . . . . . . . . . . . . . . . 43
4.2 Result and Discussion for Completely Training . . . . . . . . . . . . 43
5 Construct FCP Model with Completely Training . . . . . . . . . . . . . . . . 45
5.1 Model Training for FCP Model . . . . . . . . . . . . . . . . . . . . 45
5.2 Result and Discussion for FCP Model . . . . . . . . . . . . . . . . . 45
6 Testing the Prediction Ability of FCP Model . . . . . . . . . . . . . . . . . . 47
6.1 Model Training for the Testing FCP Model . . . . . . . . . . . . . . 47
6.2 Result and Discussion for the FCP Model Testing . . . . . . . . . . 49
7 Summary . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 51
Conclusion and Future Work 53
1 Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 53
2 Future Work . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 54
Reference 56
                                    

[1] B. F. Phillips, “Prediction of commercial catches of the western rock lobster panulirus cygnus,” Canadian Journal of Fisheries and Aquatic Sciences, vol. 43, no. 11, pp. 2126–2130, 1986.
[2] J. R. Leathwick, J. Elith, M. P. Francis, T. Hastie, and P. Taylor, “Variation in demersal fish species richness in the oceans surrounding new zealand: an analysis using boosted regression trees,” Marine ecology progress series, vol. 321, pp. 267–281, 2006.
[3] C. U. Soykan, T. Eguchi, S. Kohin, and H. Dewar, “Prediction of fishing effort distributions using boosted regression trees,” Ecological Applications, vol. 24, no. 1, pp. 71–83, 2014.
[4] S. Zhou, “Application of artificial neural networks for forecasting salmon escapement,” North American Journal of Fisheries Management, vol. 23, no. 1, pp. 48–59, 2003.
[5] K. I. Stergiou, E. D. Christou, and G. Petrakis, “Modelling and forecasting monthly fisheries catches: comparison of regression, univariate and multivariate time series methods,” Fisheries Research, vol. 29, no. 1, pp. 55–95, 1997.
[6] G. E. Box, G. M. Jenkins, G. C. Reinsel, and G. M. Ljung, Time series analysis: forecasting and control. John Wiley & Sons, 2015.
[7] G. P. Zhang, “Time series forecasting using a hybrid arima and neural network model,” Neurocomputing, vol. 50, pp. 159–175, 2003.
[8] D. E. Rumelhart, G. E. Hinton, and R. J. Williams, “Learning representations by backpropagating errors,” nature, vol. 323, no. 6088, pp. 533–536, 1986.
[9] T. Komatsu, I. Aoki, I. Mitani, and T. Ishii, “Prediction of the catch of japanese sardine larvae in sagami bay using a neural network,” Fisheries science, vol. 60, no. 4, pp. 385–391, 1994.
[10] B. Cheng and D. M. Titterington, “Neural networks: A review from a statistical perspective,” Statistical science, pp. 2–30, 1994.
[11] V. Cherkassky, J. H. Friedman, and H. Wechsler, From statistics to neural networks: theory and pattern recognition applications. Springer Science & Business Media, 2012, vol. 136.
[12] B. D. Ripley, “Flexible non-linear approaches to classification,” pp. 105–126, 1994.
[13] S. Zhou, “Application of artificial neural networks for forecasting salmon escapement,” North American Journal of Fisheries Management, vol. 23, no. 1, pp. 48–59, 2003.
[14] A. Iglesias, B. Arcay, T. J. A. Cotos J. M. and, and C. Dafonte, “A comparison between functional networks and artificial neural networks for the prediction of fishing catches,” Neural Computing & Applications, vol. 13, no. 1, pp. 24–31, 2004.
[15] T. Nishida and T. Komatsu, “Analysis and prediction of yellowfin tuna (thunnus albacares) catch rates of longline fisheries in the western indian ocean using a neural network.” no. 1998.
[16] G. Huse and H. Gjøsæter, “A neural network approach for predicting stock abundance of the barents sea capelin,” Sarsia, vol. 84, no. 5-6, pp. 457–464, 1999.
[17] A. Iglesias, C. Dafonte, B. Arcay, and J. M. Cotos, “Integration of remote sensing techniques and connectionist models for decision support in fishing catches,” 22, vol. 22, no. 6, pp. 862–870, 2007.
[18] L. A. Zadeh, Fuzzy sets. Elsevier, 1965, vol. 8, no. 3.
[19] R. R. Yager and D. P. Filev, “Generation of fuzzy rules by mountain clustering,” Journal of Intelligent & Fuzzy Systems, vol. 2, no. 3, pp. 209–219, 1994.
[20] T. Nishida and D. Fluharty, “Toward sustainable and responsible tuna fisheries,” Reviews in Fisheries Science, vol. 7, no. 3-4, pp. 281–302, 1999.
[21] S. Horikawa, T. Furuhashi, and Y. Uchikawa, “On fuzzy modeling using fuzzy neural networks with the back-propagation algorithm,” IEEE transactions on Neural Networks, vol. 3, no. 5, pp. 801–806, 1992.
[22] C. H.Wang,W. Y.Wang, T. T. Lee, and P. S. Tseng, “Fuzzy b-spline membership function (bmf) and its applications in fuzzy-neural control,” IEEE transactions on systems, man, and cybernetics, vol. 25, no. 5, pp. 841–851, 1995.
[23] D. E. Rumelhart, G. E. Hinton, and R. J. Williams, “Learning representations by backpropagating errors,” nature, vol. 323, no. 6088, pp. 533–536, 1986.
[24] C. H.Wang, H. L. Liu, and C. T. Lin, “Dynamic optimal learning rates of a certain class of fuzzy neural networks and its applications with genetic algorithm,” IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), vol. 31, no. 3, pp. 467– 475, 2001.
[25] J. Wang, C. H. Wang, and C. P. Chen, “The bounded capacity of fuzzy neural networks (fnns) via a new fully connected neural fuzzy inference system (f-confis) with its applications,” IEEE Transactions on Fuzzy Systems, vol. 22, no. 6, pp. 1373–1386, 2013.
[26] C. P. Chen, J. Wang, C. H. Wang, and L. Chen, “A new learning algorithm for a fully connected neuro-fuzzy inference system,” IEEE transactions on neural networks and learning systems, vol. 25, no. 10, pp. 1741–1757, 2014.
[27] J. S. Arora, Introduction to optimum design. Elsevier, 2004.
[28] C. A, “M´ethode g´en´erale pour la r´esolution des systemes d´equations simultan´ees,” Comp. Rend. Sci. Paris, vol. 25, no. 1847, pp. 536–538, 1847.
[29] M. F. Møller, “A scaled conjugate gradient algorithm for fast supervised learning,” Neural networks, vol. 6, no. 4, pp. 525–533, 1993.
[30] P. L. Narasimha, M. T. Manry, and F. Maldonado, “Upper bound on pattern storage in feedforward networks,” IEEE, pp. 1714–1719, 2007.
[31] G. Huang and H. Babri, “Upper bounds on the number of hidden neurons in feedforward networks with arbitrary bounded nonlinear activation functions,” IEEE transactions on neural networks, vol. 9, no. 1, pp. 224–229, 1998.
[32] T. M. P.L. Narasimha, Manry and F. Maldonado, “Upper bound on pattern storage in feedforward networks,” IEEE, pp. 1714–1719, 2007.
[33] K. Pearson, “Liii. on lines and planes of closest fit to systems of points in space,” The London, Edinburgh, and Dublin Philosophical Magazine and Journal of Science, vol. 2, no. 11, pp. 559–572, 1901.
[34] J. C. I. T. Jolliffe, Principal component analysis: a review and recent developments. The Royal Society Publishing, 2016, vol. 374, no. 2065.
[35] Y. Dodge, The concise encyclopedia of statistics. Springer Science & Business Media, 2008.
[36] M. J. Dreyfus-Le´on, “Individual-based modelling of fishermen search behaviour with neural networks and reinforcement learning,” Ecological Modelling, vol. 120, no. 2-3, pp. 287–297, 1999.
[37] P. Yugopuspito, S. Lukas, D. Krisnadi, and S. Albert, “Website design for fishing finder based on vms data in indonesia,” Proceedings of the 3rd International Conference on Telecommunications and Communication Engineering, pp. 80–84, 2019.
[38] J. C. Yu and Y. L. Tseng, “Evolutionary engineering optimization using recursive regional neural network and genetic algorithm,” Second International Conference on Innovative Computing, Informatio and Control (ICICIC 2007), pp. 325–325, 2007.
[39] R. Longadge and S. Dongre, “Class imbalance problem in data mining review,” arXiv preprint arXiv:1305.1707, 2013.
[40] A. Saengrung, A. Abtahi, and A. Zilouchian, “Neural network model for a commercial pem fuel cell system,” Journal of Power Sources, vol. 172, no. 2, pp. 749–759, 2007.
[41] Z. Jiang, Z. Zhang, and K. Friedrich, “Prediction on wear properties of polymer composites with artificial neural networks,” Composites Science and Technology, vol. 67, no. 2, pp. 168–176, 2007.
[42] 上野康弘・巣山哲・中神正康・伊藤正木, “平成１９年度サンマ太平洋北西部系群の資源評価,” Annual Report of Tohoku National Fisferies Research Institute, pp. 220–265, 2007.
[43] F. Camastra, “Data dimensionality estimation methods: a survey,” Pattern Recognition, vol. 36, no. 12, pp. 2945–2954, 2003.

校外：不公開電子論文及紙本論文均尚未授權公開

簡易檢索 / 詳目顯示

相關論文