臺灣博碩士論文加值系統

近年來深度學習相關的研究與技術是持續的推陳出新，且因為電腦硬體運算的提升，進而開始思考如何利用機器取代重複性較高的人力工作，但是深度學習並沒有辦法明確的告知其分類的標準，因此無法得知更多的分類相關資訊，更無法有效地對模型進行修整，在應用發展上也容易遇到瓶頸停滯不前。
形狀探勘(Shapelets Mining)是資料探勘的方法之一，形狀探勘(Shapelets Mining)的方法主要是將時序資料擷取出多個形狀，再透過距離公式進行相似度的計算，但是形狀探勘(Shapelets Mining)卻無法有效的對二維圖像資料進行處理，因為二維圖像資料比一般資料多出上下左右關聯性的特性，因此本論文將針對這個缺點進行改良，同時結合了決策樹(Decision Tree)的功能，除了加強模型的精準度之外，而且還增強模型可解釋性的功能與增加了上下左右關聯性的特色，本論文稱改良的方法為2D形狀特徵決策樹(2D Shape Feature Decision Tree ,簡稱2DS-Tree)。

In recent years, research and technology related to deep learning have been continuously advancing. With the improvement of computer hardware, there has been a growing interest in exploring how to use machines to replace repetitive manual labor. However, deep learning lacks clear guidelines for classifying data, which limits our ability to obtain more classification-related information and effectively adjust models. As a result, there are often bottlenecks and stagnation in the application and development of deep learning.
Shapelets Mining is one method used in data mining. It involves extracting multiple shapes from time series data and calculating their similarities using distance formulas. However, Shapelets Mining is not effective in handling two-dimensional image data. Two-dimensional images have additional characteristics of spatial relationships in all directions, which pose a challenge for traditional Shapelets Mining approaches. In this paper, we propose an improvement to address this limitation by incorporating the functionality of decision trees. The proposed method not only enhances the accuracy of the model but also improves interpretability and incorporates the spatial relationship characteristics. We refer to this improved method as the 2D Shape Feature Decision Tree (2DS-Tree).

摘要 I
Abstract II
誌謝 III
目錄 IV
表目錄 VII
圖目錄 IX
第一章 緒論 1
1.1 研究背景 1
1.2 研究動機與目的 1
第二章 基本概念與定義 3
第三章 相關研究 5
3.1 相似度計算 5
3.2 形狀探勘 5
3.2.1 形狀探勘方法法簡介 5
3.2.2 輸入時序資料 6
3.2.3 滑動窗口切割時序資料 6
3.2.4 建立候選人資料集 7
3.2.5 相似度計算 7
3.2.6 建立相似度資料集 8
3.3 決策樹 8
3.4 可解釋性人工智慧 8
3.5 隨機森林 9
第四章 研究方法 10
4.1 建立所有矩陣候選的虛擬碼 10
4.2 相似度資料產生 10
4.3 建立矩陣候選 11
4.4 相似度計算 12
4.5 相似度資料集透過決策樹預測 13
4.6 決策樹的分類方式 13
第五章 實驗結果 14
5.1 資料集介紹 14
5.2 程式開發環境 15
5.3 載入資料集 15
5.4 切割的矩陣候選 15
5.5 1DS-Tree 16
5.6 D1使用2DS-Tree 16
5.7 D1使用1DS-Tree 19
5.8 D1使用決策樹 21
5.9 D1使用不同大小二維滑動窗口 24
5.10 D2用2DS-Tree 25
5.11 D2使用1DS-Tree 26
5.12 D2使用決策樹 27
5.13 D2使用不同大小二維滑動窗口 29
5.14 D3使用2DS-Tree 30
5.15 D3使用1DS-Tree 31
5.16 D3使用決策樹 33
5.17 D3使用不同大小二維滑動窗口 34
5.18 D4使用2DS-Tree 35
5.19 D4使用1DS-Tree 37
5.20 D4使用決策樹 38
第六章 結論與未來展望 41
6.1 結論 41
6.2 未來展望 43
參考文獻 44

[1]A. Adadi and M. Berrada, "Peeking inside the black-box: a survey on explainable artificial intelligence (XAI)," IEEE access, vol. 6, pp. 52138-52160, 2018.
[2]A. Adadi and M. Berrada, "Explainable AI for healthcare: from black box to interpretable models," in Embedded Systems and Artificial Intelligence: Proceedings of ESAI 2019, Fez, Morocco, pp. 327-337, 2020.
[3]R. Agrawal and R. Srikant, "Fast algorithms for mining association rules," in Proc. 20th int. conf. very large data bases, VLDB, vol. 1215, pp. 487-499, 1994.
[4]R. Agrawal and R. Srikant, "Mining sequential patterns," in Proceedings of the eleventh international conference on data engineering, pp. 3-14, 1995.
[5]G. Biau and E. Scornet, "A random forest guided tour," Test, vol. 25, pp. 197-227, 2016.
[6]L. Breiman, "Bagging predictors," Machine learning, vol. 24, pp. 123-140, 1996.
[7]L. Breiman, "Random forests," Machine learning, vol. 45, pp. 5-32, 2001.
[8]C. J. Burges, "A tutorial on support vector machines for pattern recognition," Data mining and knowledge discovery, vol. 2, no. 2, pp. 121-167, 1998.
[9]T. Chen and C. Guestrin, "Xgboost: A scalable tree boosting system," in Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, pp. 785-794, 2016.
[10]N. Deng, X. Chen, D. Li, and C. Xiong, "Frequent patterns mining in DNA sequence," IEEE Access, vol. 7, pp. 108400-108410, 2019.
[11]H. Ding, G. Trajcevski, P. Scheuermann, X. Wang, and E. Keogh, "Querying and mining of time series data: experimental comparison of representations and distance measures," Proceedings of the VLDB Endowment, vol. 1, no. 2, pp. 1542-1552, 2008.
[12]A. J. Myles, R. N. Feudale, Y. Liu, N. A. Woody, and S. D. Brown, "An introduction to decision tree modeling," Journal of Chemometrics: A Journal of the Chemometrics Society, vol. 18, no. 6, pp. 275-285, 2004.
[13]P. Fournier-Viger, J. C.-W. Lin, R. U. Kiran, Y. S. Koh, and R. Thomas, "A survey of sequential pattern mining," Data Science and Pattern Recognition, vol. 1, no. 1, pp. 54-77, 2017.
[14]J. H. Friedman, "Greedy function approximation: a gradient boosting machine," Annals of statistics, pp. 1189-1232, 2001.
[15]S. Gupta and R. Mamtora, "A survey on association rule mining in market basket analysis," International Journal of Information and Computation Technology, vol. 4, no. 4, pp. 409-414, 2014.
[16]B. Hartmann and N. Link, "Gesture recognition with inertial sensors and optimized DTW prototypes," in 2010 IEEE International Conference on Systems, Man and Cybernetics, pp. 2102-2109, 2010.
[17]I.-H. Ting, C. Kimble, and D. Kudenko, "UBB mining: finding unexpected browsing behaviour in clickstream data to improve a Web site's design," in The 2005 IEEE/WIC/ACM International Conference on Web Intelligence (WI'05), pp. 179-185, 2005.
[18]E. Keogh, L. Wei, X. Xi, S.-H. Lee, and M. Vlachos, "LB_Keogh supports exact indexing of shapes under rotation invariance with arbitrary representations and distance measures," in Proceedings of the 32nd international conference on Very large data bases, pp. 882-893, 2006.
[19]S. M. Lundberg, G. G. Erion, and S.-I. Lee, "Consistent individualized feature attribution for tree ensembles," arXiv preprint arXiv:1802.03888, 2018.
[20]S. M. Lundberg and S.-I. Lee, "A unified approach to interpreting model predictions," Advances in neural information processing systems, vol. 30, 2017.
[21]L. Ye and E. Keogh, "Time series shapelets: a new primitive for data mining," in Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining, pp. 947-956, 2009.
[22]A. Mahajan, D. Shah, and G. Jafar, "Explainable AI approach towards toxic comment classification," in Emerging Technologies in Data Mining and Information Security: Proceedings of IEMIS 2020, Volume 2, pp. 849-858, 2021.
[23]J. Michael, R. Labahn, T. Grüning, and J. Zöllner, "Evaluating sequence-to-sequence models for handwritten text recognition," in 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1286-1293, 2019.
[24]S. Niu and S. Cao, "Get A Sense of Accomplishment in Doing Exercises: A Reinforcement Learning Perspective," in 2022 IEEE 25th International Conference on Computer Supported Cooperative Work in Design (CSCWD), pp. 299-304, 2022.
[25]J. Han et al., "Prefixspan: Mining sequential patterns efficiently by prefix-projected pattern growth," in proceedings of the 17th international conference on data engineering, pp. 215-224, 2001.
[26]S. L. Salzberg, "On comparing classifiers: Pitfalls to avoid and a recommended approach," Data mining and knowledge discovery, vol. 1, pp. 317-328, 1997.
[27]T. Sellers, T. Lei, G. E. Jan, Y. Wang, and C. Luo, "Multi-objective optimization robot navigation through a graph-driven PSO mechanism," in International Conference on Sensing and Imaging, pp. 66-77, 2022.
[28]M. Shah, J. Grabocka, N. Schilling, M. Wistuba, and L. Schmidt-Thieme, "Learning DTW-shapelets for time-series classification," in Proceedings of the 3rd IKDD Conference on Data Science, pp. 1-8, 2016.
[29]M. Shokoohi-Yekta, B. Hu, H. Jin, J. Wang, and E. Keogh, "Generalizing DTW to the multi-dimensional case requires an adaptive approach," Data mining and knowledge discovery, vol. 31, pp. 1-31, 2017.
[30]R. Srikant and R. Agrawal, "Mining sequential patterns: Generalizations and performance improvements," in International conference on extending database technology, pp. 1-17, 1996.
[31]V. S. Tseng, C.-W. Wu, B.-E. Shie, and P. S. Yu, "UP-Growth: an efficient algorithm for high utility itemset mining," in Proceedings of the 16th ACM SIGKDD international conference on Knowledge discovery and data mining, pp. 253-262, 2010.
[32]M. Van Lent, W. Fisher, and M. Mancuso, "An explainable artificial intelligence system for small-unit tactical behavior," in Proceedings of the national conference on artificial intelligence, pp. 900-907, 2004.
[33]C.-W. Wu, J. Huang, Y.-W. Lin, C.-Y. Chuang, and Y.-C. Tseng, "Efficient algorithms for deriving complete frequent itemsets from frequent closed itemsets," Applied Intelligence, pp. 1-22, 2022.
[34]X. Xi, E. Keogh, C. Shelton, L. Wei, and C. A. Ratanamahatana, "Fast time series classification using numerosity reduction," in Proceedings of the 23rd international conference on Machine learning, pp. 1033-1040, 2006.
[35]Z. Yang, Y. Wang, and M. Kitsuregawa, "LAPIN: effective sequential pattern mining algorithms by last position induction for dense databases," in Advances in Databases: Concepts, Systems and Applications: 12th International Conference on Database Systems for Advanced Applications, DASFAA 2007, Bangkok, Thailand, April 9-12, 2007. Proceedings 12, pp. 1020-1023, 2007.
[36]M. J. Zaki, "SPADE: An efficient algorithm for mining frequent sequences," Machine learning, vol. 42, pp. 31-60, 2001.
[37]M. J. Zaki and K. Gouda, "Fast vertical mining using diffsets," in Proceedings of the ninth ACM SIGKDD international conference on Knowledge discovery and data mining, pp. 326-335, 2003.
[38]M. Zihayat, C.-W. Wu, A. An, V. S. Tseng, and C. Lin, "Efficiently mining high utility sequential patterns in static and streaming data," Intelligent Data Analysis, vol. 21, no. S1, pp. S103-S135, 2017.
[39]S. Zida, P. Fournier-Viger, J. C.-W. Lin, C.-W. Wu, and V. S. Tseng, "EFIM: a fast and memory efficient algorithm for high-utility itemset mining," Knowledge and Information Systems, vol. 51, no. 2, pp. 595-625, 2017.
[40]S. Zida, P. Fournier-Viger, C.-W. Wu, J. C.-W. Lin, and V. S. Tseng, "Efficient mining of high-utility sequential rules," in Machine Learning and Data Mining in Pattern Recognition: 11th International Conference, MLDM 2015, Hamburg, Germany, July 20-21, 2015, Proceedings 11, pp. 157-171, 2015.