請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/78896完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 吳政鴻(Cheng-Hung Wu) | |
| dc.contributor.author | Sheng-Wei Chen | en |
| dc.contributor.author | 陳聖崴 | zh_TW |
| dc.date.accessioned | 2021-07-11T15:27:28Z | - |
| dc.date.available | 2023-09-17 | |
| dc.date.copyright | 2018-09-17 | |
| dc.date.issued | 2018 | |
| dc.date.submitted | 2018-09-10 | |
| dc.identifier.citation | [1] Ahmed, H., Wong, M. D., & Nandi, A. K. (2016). Effects of deep neural network parameters on classification of bearing faults. Paper presented at the Industrial Electronics Society, IECON 2016-42nd Annual Conference of the IEEE.
[2] Aviv, Y., & Pazgal, A. (2005). A partially observed Markov decision process for dynamic pricing. Management Science, 51(9), 1400-1416. [3] Baguley, T. (2009). Standardized or simple effect size: What should be reported? British journal of psychology, 100(3), 603-617. [4] Bitran, G., & Caldentey, R. (2003). An overview of pricing models for revenue management. Manufacturing & Service Operations Management, 5(3), 203-229. [5] Boyd, E. A., & Bilegan, I. C. (2003). Revenue management and e-commerce. Management Science, 49(10), 1363-1386. [6] DeShon, R. P. (2002). A generalizability theory perspective on measurement error corrections in validity generalization. Validity generalization: A critical review, 365-402. [7] Gallego, G., & Van Ryzin, G. (1994). Optimal dynamic pricing of inventories with stochastic demand over finite horizons. Management Science, 40(8), 999-1020. [8] Gerchak, Y., Gupta, D., & Henig, M. (1996). Reservation planning for elective surgery under uncertain demand for emergency surgery. Management Science, 42(3), 321-334. [9] Hinton, G. E., Srivastava, N., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. R. (2012). Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv:1207.0580. [10] Hirose, Y., Yamashita, K., & Hijiya, S. (1991). Back-propagation algorithm which varies the number of hidden units. Neural networks, 4(1), 61-66. [11] Hochreiter, S. (1998). The vanishing gradient problem during learning recurrent neural nets and problem solutions. International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, 6(02), 107-116. [12] Hornik, K., Stinchcombe, M., & White, H. (1989). Multilayer feedforward networks are universal approximators. Neural networks, 2(5), 359-366. [13] Jiang, G.-f., & Wu, C. (1998). Learning to control an inverted pendulum using Q-learning and neural networks. Acta Automatica Sinica, 24, 666-669. [14] Karsoliya, S. (2012). Approximating number of hidden layer neurons in multiple hidden layer BPNN architecture. International Journal of Engineering Trends and Technology, 3(6), 714-717. [15] Kaya, G. O., & COşGUN, Ö. (2016). Stochastic Dynamic Programming for Natural Gas Pricing in the Turkish Energy Market. Journal of Multiple-Valued Logic & Soft Computing, 26. [16] Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. Paper presented at the Advances in neural information processing systems. [17] Lin, K. Y. (2006). Dynamic pricing with real-time demand learning. European Journal of Operational Research, 174(1), 522-538. [18] Marbach, P., Mihatsch, O., & Tsitsiklis, J. N. (2000). Call admission control and routing in integrated services networks using neuro-dynamic programming. IEEE Journal on selected areas in communications, 18(2), 197-208. [19] Meyn, S. P. (2005). Workload models for stochastic networks: Value functions and performance evaluation. IEEE Transactions on Automatic Control, 50(8), 1106-1122. [20] Ødegaard, F., & Wilson, J. G. (2016). Dynamic pricing of primary products and ancillary services. European Journal of Operational Research, 251(2), 586-599. [21] Panchal, F., & Panchal, M. (2015). Optimizing Number of Hidden Nodes for Artificial Neural Network using Competitive Learning Approach. International Journal of Computer Science and Mobile Computing, 4(5), 358-364. [22] Piri, S., & Liu, T. (2014). Adjustable robust optimization for pricing and ordering with dynamic programming. Paper presented at the IIE Annual Conference. Proceedings. [23] Ronghuan, G. (2013). Ticket Pricing Model for Group Passenger Based on Dynamic Programming LISS 2012 (pp. 513-518): Springer. [24] Saerens, M. (2000). Building cost functions minimizing to some summary statistics. IEEE Transactions on neural networks, 11(6), 1263-1271. [25] Schuetz, H.-J., & Kolisch, R. (2012). Approximate dynamic programming for capacity allocation in the service industry. European Journal of Operational Research, 218(1), 239-250. [26] Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. (2014). Dropout: A simple way to prevent neural networks from overfitting. The Journal of Machine Learning Research, 15(1), 1929-1958. [27] Taguchi, G. (1986). Introduction to quality engineering: designing quality into products and processes. Retrieved from [28] Wei, Q., Lewis, F. L., Sun, Q., Yan, P., & Song, R. (2017). Discrete-time deterministic $ Q $-learning: A novel convergence analysis. IEEE transactions on cybernetics, 47(5), 1224-1237. [29] Williams, K. R. (2017). Dynamic airline pricing and seat availability. [30] Zéphyr, L., & Anderson, C. L. (2018). Stochastic dynamic programming approach to managing power system uncertainty with distributed storage. Computational Management Science, 15(1), 87-110. [31] Zeiler, M. D. (2012). ADADELTA: an adaptive learning rate method. arXiv preprint arXiv:1212.5701. [32] Zhang, D., & Cooper, W. L. (2009). Pricing substitutable flights in airline revenue management. European Journal of Operational Research, 197(3), 848-861. [33] Zhou, F.-Y. (2017). 基於深層學習的生產系統動態控制. 臺灣大學工業工程學研究所學位論文, 1-51. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/78896 | - |
| dc.description.abstract | 本研究嘗試結合動態規劃與深度學習應用在決策與時間有關之問題。動態規劃由於受限於維度詛咒，在求解計算上需耗費相當大量的時間甚至是會導致硬體上的不足而無法計算，另外，現實中有些問題是必須及時處理無法等待的。本研究認為動態規劃的最佳決策中是有規律可循的，若能利用動態規劃的部分決策中找出動態規劃的參數與決策的函數關係，則能克服動態規劃計算上的時間限制，在未來需要重新計算最佳決策時降低計算時間，並應用在求解的規模擴大的情況。
本研究考量一個可替代性航班的機票訂價問題，目標為最大化總銷售金額。我們利用正交實驗設計建立了動態規劃的系統參數組合，並挑選適合的決策作為深層神經網路的訓練資料，並且討論神經網路的架構比較，找出較佳的神經網路模型。最後驗證經過學習後的深層神經網路能夠應用在其他系統參數下，並利用模擬程式比較動態規劃與深層神經網路的決策獲得的銷售額差距。結果表明，本研究所提出的方法可以應用在時間限制的決策問題。 | zh_TW |
| dc.description.abstract | This study attempts to combine dynamic programming and deep learning applied on time-related decision problem. Dynamic programming is limited by the curse of the dimension. It takes a lot of time to solve the problem and even leads to the lack of hardware and cannot be calculated. In addition, some problems in reality must be handled in time and cannot be waited. This study believes that the best decision policy in dynamic programming exit some rule can be functionalization. If we can use the partial decision of dynamic programming to find the function between the system parameters of dynamic programming and corresponding decision, we can overcome the time limit of dynamic programming.
This study considers the problem of the ticket pricing for substitutable flights with the goal of maximizing the total revenue. We use the orthogonal experimental design to establish the set of dynamic programming system parameters, and select the appropriate decision as the training data of the deep neural network, and analysis the architecture and hyperparameters of the neural network to find the better neural network model. Finally, we verified that the learned deep neural network can be applied to other system parameters, and the simulation program is used to compare the revenue between the dynamic programming and the deep neural network. The results show that the method proposed in this study can be applied to decision-making problems with time constraints. | en |
| dc.description.provenance | Made available in DSpace on 2021-07-11T15:27:28Z (GMT). No. of bitstreams: 1 ntu-107-R05546019-1.pdf: 2839031 bytes, checksum: 622c73b113488a8783043ba60bf55f7d (MD5) Previous issue date: 2018 | en |
| dc.description.tableofcontents | 中文摘要 II
ABSTRACT III 目錄 IV 表目錄 VII 圖目錄 VIII 第一章 前言 1 1.1 研究背景 1 1.1.1 動態訂價 1 1.1.2 動態規劃的維度詛咒 1 1.1.3 動態規劃的障礙 2 1.2 研究動機與目的 2 1.3 研究問題 3 1.4 研究方法與流程 4 第二章 文獻探討 5 2.1 營收管理與動態訂價 5 2.2 動態規劃 6 2.3 神經網路及動態學習 7 2.4 神經網路及其應用 7 第三章 動態規劃 9 3.1 研究問題描述 9 3.2 研究問題假設及數學符號定義 10 3.2.1 基本假設 10 3.2.2 數學符號定義 10 3.3 動規劃模型 11 3.4 動態規劃程式 13 3.4.1 數值範例 13 3.4.2 計算需求 15 第四章 神經網路 17 4.1 資料蒐集 18 4.1.1 動態規劃參數實驗設計 18 4.1.2 動態規劃與神經網路結合 19 4.1.3 訓練資料篩選 20 4.2 神經網路架構 25 4.2.1 Fully connected 25 4.2.1.1 optimizer與learning rate 26 4.2.1.2 Activation function 28 4.2.1.3 隱藏層與神經元數 30 4.2.1.4 Dropout 33 4.2.2 其他架構 34 第五章 數據分析 41 5.1 訓練資料範例 41 5.2 測試資料分析 43 5.3 模擬 48 第六章 結論與未來研究 52 6.1 結論 52 6.2 未來研究方向 52 參考文獻 53 | |
| dc.language.iso | zh-TW | |
| dc.title | 應用深層神經網路之替代性多航班動態定價方法 | zh_TW |
| dc.title | A Deep Neural Network Approach for Dynamic Pricing of Substitutable Flights | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 107-1 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 洪一薰(I-Hsuan Hong),陳文智(Wen-Chih Chen) | |
| dc.subject.keyword | 動態規劃,決策訂價,神經網路,深度學習, | zh_TW |
| dc.subject.keyword | Dynamic Programming,Pricing,Neural Network,Deep Learning, | en |
| dc.relation.page | 56 | |
| dc.identifier.doi | 10.6342/NTU201804102 | |
| dc.rights.note | 有償授權 | |
| dc.date.accepted | 2018-09-10 | |
| dc.contributor.author-college | 工學院 | zh_TW |
| dc.contributor.author-dept | 工業工程學研究所 | zh_TW |
| dc.date.embargo-lift | 2023-09-17 | - |
| 顯示於系所單位： | 工業工程學研究所 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-107-R05546019-1.pdf 目前未授權公開取用 | 2.77 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。