半導體產業在台灣製造業扮演一舉足輕重的角色，在半導體研發過程中，半導體製程工程師會利用測試載具(Test Vehicle)來取得晶圓上晶方的電性參數，取得WAT資料後，半導體工程師將可進一步研究晶方的電性參數，進而找出符合當初設計的最佳晶方及最佳晶方參數。傳統尋找黃金晶方的過程中會遇到幾個問題，一是WAT電性參數資料龐大，二是通常一批晶方參數可能有上百顆晶方，在上百顆晶方中，每顆晶方內含三四百筆電性參數。如此龐大的資料量，對於半導體工程師從中尋找黃金晶方，是一大考驗。有鑑於此，本研究建構一系統性的方法，以工程師最初定義的黃金晶方為基礎，首先利用因素分析將WAT資料維度縮減後，再透過類神經網路中自適應共振理論網路II將資料維度縮減過後的晶方做分群。如此便可快速的找出黃金晶方所屬的類黃金晶方群，可縮減研發製程所需時間以及加快產品上市時間。本研究以竹科某半導體廠之研發階段WAT參數做為實驗數據，並建構一模型將晶方分群，如此可有效且快速找出類黃金晶方。經實驗證實，本研究所提出之分析方法，可有效的輔助半導體工程師尋找類黃金晶方，減少研發階段的耗時。

Semiconductor industry has played a prominent role in Taiwan manufacturing industry. In the semiconductor research and design stage, the semiconductor engineers would use test vehicle to retain the wafer acceptance test data(WAT) from the wafer, then the semiconductor engineers could find a best die by checking the WAT data. But there are some problems to find the best die by traditional ways, the first problem is that the amount of WAT data is quiet big, the second problem is that there are hundreds of dies in a batch of wafer. It’s really a big test for semiconductor engineers to find the best dies (golden dies) from such a large WAT data. Accordingly, this research aims to build a system model to analyze the WAT data at R&D stage basing on the golden dies which semiconductor engineers defined earlier to help semiconductor engineers find the golden dies. At first step, this research use factor analysis to reduce the WAT data amount. The second step, this research use Adaptive Resonance Theory Network II (ART-2) to cluster the wafer dies. Real WAT data during semiconductor fortification are collected from a semiconductor manufacturing company and were experimented through the presented analysis model. Therefore, the proposed methodology in this research can help the semiconductor engineer find the golden dies more quickly and efficiently, and the analysis time can be reduced during semiconductor fortification.

AISP情報顧問服務網站，半導體產業現況，2010。
SPSS官方網站。
林昇甫、洪成安，2002，<神經網路入門與圖樣辨識>，全華科技圖書。
張光佑，2005，「探討特徵萃取要素於小樣本分類問題」，國立台中教育大學教育測驗統計研究所碩士論文。
許文豪，2000，「圖形辨識概述與實作」，國立清華大學資訊系統與應用研究所碩士論文。
陳信伊，2005，「星狀座標之軸排列於群聚視覺化之應用」，國立成功大學資訊工程研究所碩士論文。
陳秋雲，1998， <VLSI製造技術>，全華圖書公司。
陳惠菁，2007，植基於自適應共振理論網路II 的演化式分類器
陳麗伃，2004，「以資料挖礦為基礎之半導體測試性WAT資料分析診斷」，國立清華大學工業工程與工程管理研究所碩士論文。
曾憲雄、蔡秀滿、蘇東興、曾秋蓉、王慶堯，2005，資料探勘，旗標出版股份有限公司。
游淑敏，2008，「以WAT參數資料建構半導體研發設計階段黃金晶方群聚分析」，國立清華大學工業工程與工程管理研究所碩士論文。
黃靜文，2005，「維度縮減應用於蛋白質質譜儀資料」，國立政治大學統計學研究所碩士論文。
溫在昇，2005，半導體測試專欄：半導體製程的監視器參數測試讓製程更完善- 學技術
經濟部工業局半導體產業推動辦公室，半導體產業現況，2009。
葉怡成，1999，類神經網路模式應用與實作，儒林圖書公司
葉怡成，1999，類神經網路模式應用與實作，儒林圖書有限公司。
廖建倫，2002，「整合自適應共振理論網路與遺傳演算法為輔K-means之資料採礦技術於推薦代理系統之研究」，國立台北科技大學生產系統工程與管理研究所碩士論文。
蔡易牟，2004，「普適提之變數選擇」，國立東華大學應用數學系研究所碩士論文。
謝祥文，2004，「區域分割為基礎之晶圓缺陷圖樣辨識演算法」，國立清華大學工業工程與工程管理學系研究所博士論文。
魏連均，2006，「應用類神經網路建構晶圓圖故障圖樣辨識模式」，國立清華大學工業工程與工程管理研究所碩士論文。
蘇朝墩，Dept. of IE & NTHU Neural Network Models and Applications

Alpaydin, E., 2004. Introduction to machine learning. MIT Press.

Anaparthi, K.K., Chaudhuri, B., and Thornhill, N.F., 2005. Coherency identification in power systems through principal component analysis, IEEE Transactions on Power Systems, 20, 1658-1660.

Ankerst, M., Breunig, M., and Kriegel, H.P., 1999. OPTICS: Ordering points to identify the clustering structure, In Proc. ACM-SIGMOD Int. Conf. Management of Data, Philadelphia, PA, 49-60.

Azevedo and Rotandi, D.N., 2007. Application of data mining techniques to the storage management and online distribution of satellite images, Rio de Janeiro, Brazil, 955-960.

Balasinski, A., 2005. DfM for SoC, Proceedings of the 9th International Database Engineering & Application Symposium, 41-46.

Barbancho, J., Leon, C., and Molina, F.J., 2007. Using artificial intelligence in routing schemes for wireless networks, Computer Communications, 30, 2802-2811.

Bohr, M.T. and El-Mansy, Y.A., 1998. Technology for advanced high-performance microprocessors, IEEE Trans. Electron Devices, 45, 620-625.

Bose, B.K., 2007. Neural network applications in power electronics and motor drives: An introduction and perspective, IEEE Transactions on Industrial Electronics, 54, 14-33.

Chen, T.S., Lin, C.C, Chiu, Y.H., and Chen, R.C., 2006. Combined density and constraint-based algorithm for clustering, In Proceedings of 2006 International Conference on Intelligent System and Knowledge Engineering.

Cheng, C.Y. and Cheng F.T, 2005. Engineering-chain requirements for semiconductor industry, Proceedings of the 2005 IEEE International Conference on Automation Science and Engineering, Edmonton, 381-386.

Chien, C.F., Hsu, S.C., Peng, S., and Wu, C.H., 2000. A cost-based heuristic for statistically determining sampling frequency in a wafer fab, Semiconductor Manufacturing Technology Workshop, 217-229.

Cook, R.D. and Weisberg, S., 1994. On the interpretation of regression polts, Journal of the American Statistical Association, 89, 177-189.

Chung, S.H., Huang, C.Y., and Lee, A.H.I., 2006. Capacity allocation model for photolithography workstation with the constraints of process window and machine dedication, Production Planning and Control, 17(7), 678-688.

Du, Q., 2007, Modified fisher's linear discriminant analysis for hyperspectral imagery, IEEE Geoscience and Remote Sensing Letters, 4, 503-507.

Dunham, M.H., 2002, Data mining introductory and advanced topics, Pearson Education: New Jersey.

Fan, C.M., Guo, R.S., and Chang, S.C., 2000. SHEWMA: An end-of-line SPC scheme using wafer acceptance test data, IEEE Transactions on Semiconductor manufacturing.

Fayyad, U., 1997. Data mining and knowledge discovery in dataBase: Implication for scientific databases, Scientific and Statistical Database Management.

Fukunaga, K., 1990. Introduction to statistical pattern recognition, San Diego: Academic Press Inc.

G.A. Carpenter and S. Grossberg, 1987, ART2: Selforganisation Of Stable
Category Rrecognition Codes For Analog Input Patterns.

Jolliffe IT, 1986. Principal Component Analysis.

Kaufman., L. and Rousseeuw, P.J., 1990. Finding groups in data: An introduction to cluster analysis, John Wiley & Sons.

Han, J. and Kamber, M., 2000. Data mining: Concepts and techniques, Morgan Kaufmann.

Hsieh, S., Lin, S.C., Lee, M.H, Wang, J.R., and Lin, C., et al., 1999. A novel assessment of process control monitor in advanced semiconductor manufacturing: A complete set of addressable failure site test structures, in Proc. Int. Symp. Semiconductor Manufacturing (ISSM).

Lee, J.H., Yu, S.J., and Park, S.C., 2001. Design of intelligent data sampling methodology based on data mining, IEEE Transactions on Robotics and Automation, 17(5).

Lee, J.H., 2002. Artifical intelligence-based sampling planning system for dynamic manufacturing process, Expert systems with applications 22.

Li, K.C., 1991. Sliced inverse regression for dimension reduction,” Journal of the American Statistical Association.

Li, K.C., 1992. On principal hessian directions for data visualization and dimension reduction: Another application of Stein’s Lemma, Journal of the American Statistical Association, 87.

Liu, X.S., Shi, C.S., and Cheng, Y.Y., 2007. A fast method for identifying the quality of Chinese medicine injections based on self-organizing maps neural network, Chinese Journal of Analytical Chemistry, 35, 1483-1486.

Lukaszek, W., Grambow, K.G., and Tarbrough, W.J., 1990. Test chip based approach to automated diagnosis of CMOS yield problems, IEEE Trans. Semiconduct. Manufact., 3, 18-27.

Miyamoto, K., Inoue, K., Tamura, I., Kondo, N., Inoto, H., et al., 2000. Yield management methodology for SoC vertical yield Ram, in Proc. Int. Electron Device Meeting.

Nag, P.K., Maly, W., and Jocobs, H.J., 1997. Simulation of yield/cost learning curves with Y4,” IEEE Transactions on Semiconductor Manufacturing, 10(2), 256-266.

Narendra, P.M. and Fukunage, K., 1997. A branch and bound algorithm for feature subset selection, IEEE Trans. Computers, 6(9), 917-922.

Nauck, D., Klawonn, F., and Kruse, R., 1997. Foundations of neuro-fuzzy systems, John Wiley & Sons.

Pelissier, J.L. and Flinois, X., 1989. Fully-integrated dynamic fault imaging system for failure analysis and performance enhancement of VLSI, Proceedings of the 1st European Test Conference, Paris, France, 180-183.

Pudil, P., Novovicova, J., and Kittler, J., 1994. Floating search methods in feature selection, Pattern Recognition Letters, 15, 1119-1125.

Ravi, V., Kurniawan, H., Thai, P.N.K, and Kumar, P.R., 2008. Soft computing system for bank performance prediction, Applied Soft Computing, 8, 305-315.

Roberto, B., 1994. Using mutual information for selecting features in supervised neural net learning, IEEE Transactions on Neural Networks, 5, 337-550.

Schalkoff, R.J., 1997. Artificial neural networks, Mcgraw-hill International Editions.

Sekar, R., Bendre, M., Dhurjati, D., and Bollineni, P., 2001. A fast automaton-based method for detecting anomalous program behaviors, Proceedings 2001 IEEE Symposium on Security and Privacy, Oakland, California, 144 – 155.

Siedlecki, W. and Sklansky, J., 1989. A note on genetic algorithms for large-scale feature selection, Pattern Recognition Letters, 10, 335-347.

Wang, H.Y., Wang, Z.F., and Leng, Y., 2007. PCA plus F-LDA: A new approach to face recognition, International Journal of Pattern Recognition and Artificial Intelligence, 21, 1059 – 1068.

Wilson, D. and Walton, A.J., 1994. Automatic in-line to end-of-line defect correlation using FSRAM test structure for quick killer defect identification, in Proc. IEEE Int. Conf. Microelectronic Test Structures, 160-163.

Witten, H.I. and Frank, E., 2005. Data mining: Practical machine learning tools techniques, Rio de Janeiro, Brazil, 2nd ed, Elsevier.

Yan, A.M., Kerschen, G., and Boe, P.D., Structural damage diagnosis under varying environmental conditions-Part I: A linear analysis, Mechanical Systems and Singal Processing, 21, 847-864.