隨著面板需求成長趨緩，製造商極需開發新的技術並尋找新的應用領域。然而如何在維持高產出良率下，縮短新產品開發週期與新製程導入時程，以提前將新產品上市而取得搶奪市場先機，是一個值得研究的議題。本研究以個案公司導入化學強化玻璃製程為例，然在檢驗其化學強化製程特性時，需進行破壞性檢驗，是故在考量其試產資料特性後，提出一個新虛擬樣本產生法。藉由將輸入數值屬性視為名目屬性，學習輸入值與輸出值之模糊關係，並基於此關係產生虛擬樣本而增加訓練樣本數量。在實驗部分，本研究從個案公司取得29筆真實試產資料進行不同訓練樣本數的交互驗證，並以支撐向量迴歸(support vector regression, SVR)並搭配Polynomial以及radial basis function 兩種運算核心進行預測模式的建構。方法比較部分，本論文採用Bootstrap aggregating (Bagging) 以及Synthetic Minority Over-sampling Technique (SMOTE)兩種虛擬樣本產生法，進行樣本增量後的預測準確度比較。實驗結果發現，除本研究所提出的方法外，Bagging與SMOTE並無法有效改善SVR 對於個案資料的預測準確度。透過本論文之方法，期能持續協助個案公司之製程工程師推斷高產出良率的製造參數。

Accelerating development of new products has become an important marketing strategy for manufacturers in global competition. However, this may lead to the learning issue of small data, because machine learning algorithms such as the support vector regressions (SVRs) are majorly applied to extract knowledge from sufficient training samples, but the data sizes are often limited and thus do not contain sufficient properties of populations. Consequently, virtual sample generation (VSG) approaches are widely considered as an effective method to overcome the small-data-learning issue. This paper reveals a real case taken from a TFT-LCD (thin film transistor liquid crystal display) maker when a new strengthened cover glass is developed in the chemical processes. With very little prior experience about the processes, engineers tried to improve the yielding rates by learning parameter settings from a few pilot-run data; and however, owing to the different process from those to make old TFT-LCD panels, the high uncertain characteristics of the new product have made two well-known VSG approaches—Bagging (bootstrap aggregating) and SMOTE (synthetic minority over-sampling technique) output unsatisfying results. Accordingly, this paper designs a unique VSG method based on fuzzy theory to tackle the specific learning issue. The experimental results show that SVRs built with the training sets which contain the proposed samples present more precise predictions and thus can help engineers infer more correct manufacturing parameters.

Anthony, M., & Biggs, N. (1997). Computational Learning Theory. Cambridge University Press.
Arbelaez Garces, Giovanny, Auguste Rakotondranaivo, and Eric Bonjour. (2016). Improving Users’Product Acceptability: An Approach Based on Bayesian Networks and a Simulated Annealing Algorithm. International Journal of Production Research 54 (17), pp. 5151–5168.
Breiman, L. (1996). Bagging Predictors. Machine Learning, 24(2), pp. 123-140.
Breiman, L. (2001). Random Forests. Machine Learning 45(1), 45(1), pp. 5-32.
Chan, K. Y., Kwong, C. K., & Tsim, Y. C. (2010). A Genetic Programming Based Fuzzy Regression Approach to Modelling Manufacturing Processes. International Journal of Production Research, 48(7), pp. 1967-1982.
Chao, G. Y., Tsai, T. I., Lu, T. J., Hsu, H. C., Bao, B. Y., Wu, W. Y., Lu, T.L. (2011). A New Approach to Prediction of Radiotherapy of Bladder Cancer Cells In Small Dataset Analysis. Expert Systems with Applications, 38(7), pp. 7963-7969.
Chawla, N. V., Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002). SMOTE: Synthetic Minority over-Sampling Technique. Journal of Artificial Intelligence Research, 16, pp. 321-357.
Chen, Jiyao, Richard R. Reilly, and Gary S. Lynn. (2012). New Product Development Speed: Too Much of a Good Thing? Journal of Product Innovation Management, 29(2), pp. 288–303.
Efron, B., & Tibshirani, R. J. (1993). An Introduction to the Bootstrap. New York: Chapmen & Hall.
Fayyad, U., Piatetsky-Shapiro, G., & Smyth, P. (1996). From Data Mining to Knowledge Discovery in Databases. AI Magazine, 17(3), p. 37.
Frank, Eibe, Yong Wang, Stuart Inglis, Geoffrey Holmes, and Ian H. Witten. (1998). Using Model Trees for Classification. Machine Learning, 32(1), pp. 63–76.

Guo, G. D., & Dyer, C. R. (2005a). Learning from Examples in the Small Sample Case: Face Expression Recognition. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 35(3), pp. 477-488.
Guo, G. D., & Dyer, C. R. (2005b). Learning from Examples in the Small Sample Case: Face Expression Recognition. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 35(3), pp. 477-488.
Hong, T. P., Tseng, L. H., & Chien, B. C. (2010). Mining from Incomplete Quantitative Data by Fuzzy Rough Sets. Expert Systems with Applications, 37(3), pp. 2644-2653.
Huang, C. F. (1997). Principle of Information. Fuzzy Sets and Systems, 91(1), pp. 69-90.
Huang, C. F., & Moraga, C. (2004). A Diffusion-Neural-Network for Learning from Small Samples. International Journal of Approximate Reasoning, 35(2), pp. 137-161.
Huang, C. J., Wang, H. F., Chiu, H. J., Lan, T. H., Hu, T. M., & Loh, E. W. (2010a). Prediction of the Period of Psychotic Episode in Individual Schizophrenics by Simulation-data Construction Approach. Journal of Medical Systems, 34(5), pp. 799-808.
Huang, C. J., Wang, H. F., Chiu, H. J., Lan, T. H., Hu, T. M., & Loh, E. W. (2010b). Prediction of the Period of Psychotic Episode in Individual Schizophrenics by Simulation-Data Construction Approach. Journal of Medical Systems, 34(5), pp. 799-808.
Huang, Z., Li, J., Su, H., Watts, G. S., & Chen, H. (2007). Large-scale Regulatory Network Analysis from Microarray Data: Modified Bayesian Network Learning and Association Rule Mining. Decision Support Systems, 43(4), pp. 1207-1225.
Ivănescu, V. C., Bertrand, J. W. M., Fransoo, J. C., & Kleijnen, J. P. C. (2006). Bootstrapping to Solve the Limited Data Problem in Production Control: An Application in Batch Process Industries. Journal of the Operational Research Society, 57(1), pp. 2-9.
Jang, J. S. (1993). ANFIS: Adaptive-network-based Fuzzy Inference System. IEEE Transactions on Systems, Man and Cybernetics, 23(3), pp. 665-685.
Jennrich, R. I., & Schluchter, M. D. (1986). Unbalanced Repeated-Measures Models with Structured Covariance Matrices. Biometrics, 42(4), pp. 805-820.
Kuo, Y., Yang, T., Peters, B. A., & Chang, I. (2007). Simulation Metamodel Development Using Uniform Design and Neural Networks for Automated Material Handling Systems in Semiconductor Wafer Fabrication. Simulation Modelling Practice and Theory, 15(8), pp. 1002-1015.
Laird, N. M., & Ware, J. H. (1982). Random-effects Models for Longitudinal Data. Biometrics, 38(4), pp. 963-974.
Lanouette, R., Thibault, J., & Valade, J. L. (1999). Process Modeling with Neural Networks Using Small Experimental Datasets. Computers & Chemical Engineering, 23(9), pp. 1167-1176.
Li, D. C., & Lin, L. S. (2013). A New Approach to Assess Product Lifetime Performance for Small Data Sets. European Journal of Operational Research, 230(2), pp. 290-298.
Li, D. C., & Lin, L. S. (2014). Generating Information for Small Data Sets with a Multi-modal Distribution. Decision Support Systems, 66, pp. 71-81.
Li, D. C., Chang, C. J., Chen, C. C., & Chen, W. C. (2012a). Forecasting Short-term Electricity Consumption Using the Adaptive Grey-based Approach—An Asian Case. Omega, 40(6), pp. 767-773.
Li, D. C., Chang, F. M., & Chen, K. C. (2010b). Building Reliability Growth Model Using Sequential Experiments and the Bayesian Theorem for Small Datasets. Expert Systems with Applications, 37(4), pp. 3434-3443.
Li, D. C., Chen, C. C., Chang, C. J., & Chen, W. C. (2012b). Employing Box-and-Whisker Plots for Learning More Knowledge in TFT-LCD Pilot Runs. International Journal of Production Research, 50(6), pp. 1539-1553.
Li, D. C., Chen, C. C., Chen, W. C., & Chang, C. J. (2012c). Employing Dependent Virtual Samples to Obtain More Manufacturing Information in Pilot Runs. International Journal of Production Research, 50(23), pp. 6886-6903.
Li, D. C., Chen, L. S., & Lin, Y. S. (2003). Using Functional Virtual Population as Assistance to Learn Scheduling Knowledge in Dynamic Manufacturing Environments. International Journal of Production Research, 41(17), pp. 4011-4024.
Li, D. C., Fang, Y. H., Lai, Y. Y., & Hu, S. C. (2009). Utilization of Virtual Samples to Facilitate Cancer Identification for DNA Microarray Data in the Early Stages of an Investigation. Information Sciences, 179(16), pp. 2740-2753.
Li, D. C., Gu, H., & Zhang, L. Y. (2010a). A Fuzzy C-means Clustering Algorithm Based on Nearest-neighbor Intervals for Incomplete Data. Expert Systems with Applications, 37(10), pp. 6942-6947.
Li, D. C., Lin, W. K., Lin, L. S., Chen, C. C., & Huang, W. T. (2017). The Attribute-trend-similarity Method to Improve Learning Performance for Small Data sets. International Journal of Production Research, 55(7), pp. 1898-1913.
Li, D. C., Liu, C. W., Fang, Y. H., & Chen, C. C. (2010c). A Yield Forecast Model for Pilot Products Using Support Vector Regression and Manufacturing Experience the Case of Large-size Polariser. International Journal of Production Research, 48(18), pp. 5481-5496.
Li, D. C., W. K. Lin., L. S. Lin., C. C. Chen., & W. T. Huang. (2017). The Attribute-trend-similarity Method to Improve Learning Performance for Small Datasets. International Journal of Production Research, 55(7), pp. 1898–1913.
Li, D. C., Wu, C. S., & Chang, F. M. M. (2005). Using Data-fuzzification Technology in Small Data Set Learning to Improve FMS Scheduling Accuracy. International Journal of Advanced Manufacturing Technology, 27(3-4), pp. 321-328.
Li, D. C., Wu, C. S., Tsai, T. I., & Chang, F. M. M. (2006). Using Mega-fuzzification and Data Trend Estimation in Small Data Set Learning for Early FMS Scheduling Knowledge. Computers & Operations Research, 33(6), pp. 1857-1869.

Li, D. C., Wu, C. S., Tsai, T. I., & Lina, Y. S. (2007). Using Mega-trend-diffusion and Artificial Samples in Small Data Set Learning for Early Flexible Manufacturing System Scheduling Knowledge. Computers & Operations Research, 34(4), pp. 966-982.
Liu, Jinfeng, Honggen Zhou, Liu Xiaojun, and Xuwen Jing. (2017). A Flexible Process Information Reuse Method for Similar Machining Feature. International Journal of Advanced Manufacturing Technology, 92(1–4), pp. 217–229.
Maudes, Jesus, Andrés Bustillo, Antonio J Guerra, and Joaquim Ciurana. (2017). Random Forest Ensemble Prediction of Stent Dimensions in Microfabrication Processes. International Journal of Advanced Manufacturing Technology, 91(1–4), pp. 879–893.
Millson, Murray R., S. P. Raj, and David Wilemon. (1992). A Survey of Major Approaches for Accelerating New ProductDevelopment. Journal of Product Innovation Management, 9(1), pp. 53–69.
Niyogi, P., Girosi, F., & Poggio, T. (1998). Incorporating Prior Information in Machine Learning by Creating Virtual Examples. Proceedings of the IEEE, 86(11), pp. 2196-2209.
Oniśko, A., Druzdzel, M. J., & Wasyluk, H. (2001). Learning Bayesian Network Parameters From Small Data Sets: Application of Noisy-OR Gates. International Journal of Approximate Reasoning, 27(2), pp. 165-182.
Şeref, Michelle M. H., Janice E. Carrillo, and Arda Yenipazarli. (2016). Multi-generation Pricing and Timing Decisions in New Product Development. International Journal of Production Research, 54(7), pp. 1919–1937.
Sezer, E. A., Nefeslioglu, H. A., & Gokceoglu, C. (2014). An Assessment on Producing Synthetic Samples by Fuzzy C-means for Limited Number of Data in Prediction Models. Applied Soft Computing, 24, pp. 126-134.
Shao, C., Song, X., Yang, X., & Wu, X. (2015). Extended Minimum-squared Error Algorithm for Robust Face Recognition via Auxiliary Mirror Samples. Soft Computing, pp. 1-11.
Shao, C., Song, X., Yang, X., & Wu, X. (2016). Extended Minimum-squared Error Algorithm for Robust Face Recognition Via Auxiliary Mirror Samples. Soft Computing, 20(8), pp. 3177-3187.
Song, X., Shao, C., Yang, X., & Wu, X. (2016). Sparse Representation-based Classification Using Generalized Weighted Extended Dictionary. Soft Computing, pp. 1-14.
Tang, D., Zhu, N., Yu, F., Chen, W., & Tang, T. (2014). A Novel Sparse Representation Method Based on Virtual Samples for Face Recognition. Neural Computing and Applications, 24(3-4), pp. 513-519.
Thomas, M., Kanstein, A., & Goser, K. (1997). Rare Fault Detection by Possibilistic Reasoning. Computational Intelligence Theory and Applications, pp. 294-298.
Tsai, T. I., & Li, D. C. (2008). Approximate Modeling for High Order Non-linear Functions Using Small Sample Sets. Expert Systems with Applications, 34(1), pp. 564-569.
Tukey, J. W. (1977). Exploratory data analysis. Reading (MA): Addison-Wesley.
Vapnik, V. N. (2000). The Nature of Statistical Learning Theory. Springer:New York.
Wang, F. K., Du, T., & Wen, F. C. (2007). Product Mix in the TFT-LCD Industry. Production Planning & Control, 18(7), pp. 584-591.
Wang, H. F., & Huang, C. J. (2009). Data Construction Method for the Analysis of the Spatial Distribution of Disastrous Earthquakes in Taiwan. International Transactions in Operational Research, 16(2), pp. 189-212.
Wang, Y. F. (2003). On-demand Forecasting of Stock Prices Using A Real-Time Predictor. IEEE Transactions on Knowledge and Data Engineering, 15(4), pp. 1033-1037.
Wang, Y., Song, Q. B., MacDonell, S., Shepperd, M., & Shen, J. Y. (2009). Integrate the GM(1,1) and Verhulst Models to Predict Software Stage Effort. IEEE Transactions on Systems Man and Cybernetics Part C-Applications and Reviews, 39(6), pp. 647-658.

Willemain, T. R., Bress, R. A., & Halleck, L. S. (2003). Enhanced Simulation Inference Using Bootstraps of Historical Inputs. IIE Transactions, 35(9), pp. 851-862.
Witten, I. H., & Frank, E. (2005). Data Mining : Practical Machine Learning Tools and Techniques. Burlington, Massachusetts: Morgan Kaufmann.
Wolpert, D. H. (1992). Stacked Generalization. Neural Networks, 5(2), pp. 241-259.
Zadeh, L. A. (1965). Fuzzy Sets. Information and Control, 8(3), pp. 338-353.