本研究主要目的是要使用泛用型普氏分析(Generalized Procrustes Analysis,GPA)與支援向量機建立汽車前視圖之電腦輔助設計系統。以50台汽車前視圖輪廓為樣本，並把汽車前視圖分成九個部份，利用RIHNO繪製線稿，採取整台車前視圖輪廓的點座標，接著運用GPA來調整點資料後，再以集群分析去做分群。以往一般的樣本輪廓點資料，通常是直接利用集群分析，但分群效果不一定理想，因此本研究嘗試經過GPA把資料調整過後，再進行分群。本研究後段嘗試以支援向量回歸(Support Vector Regression)，把分群結果(自變數)和感性語彙的評分(依變數)輸入SVR來進行感性模型之訓練，目的是為了比較經過GPA調整的數據和未經過GPA調整的數據何者具有較良好的分群效果。結果顯示了經過GPA調整的分群數據，具有較低的均方根誤差(Root Mean Square Error)，證明了經過GPA調整的資料，可以增加分群的精準度。經過訓練的系統，可以用來當作專家預測系統，預測新車款的感性語彙評分。

The purpose of this study is to verify if General Procrustes Analysis (GPA) will increase the precision of the results of the sample cluster. This study uses the front view outline of each car (total 50 cars) as a sample, and we classify the sample into nine parts. We use RHINO to draw the outline and find out the coordinate of the points. After adjusting the points using GPA, we use cluster analysis to group our samples, In the past, coordinate of the points is usually classfied through cluster anaalysis directly. However, the clustering results were not always satisfied. In this study, we try to adjust the data through GPA before applying the cluster analysis. The study also tries to adopt Support Vector Regression (SVR) method. We input the clustering results and emotional vocabulary to train the emotional model. The purpose is to verify if there are any differences between the GPA adjusted data and non-adjusted ones. The results suggest that the clustered data after using GPA indeed show lower RMSE. The trained system could be adopted as an expert system to predict the emotional vocabulary scores of new cars.

1.Miyako Nagamachi, Kansei Engineering: A new ergonomic consumer-oriented technology for product development. International Journal of Industrial Ergonomics, 1995. 15(1): p. 3-11.
2.S.T.W. Schutte, Concepts, methods and tools in Kansei Engineering. Theoretical Issues in Ergonomics Sciencs, 2004:p.67-75.
3.J.C. Gower, Generalized Procrustes Analysis. Psychometrik, 1975.vol.40: p.1-19
4.Masashi Komori , Satoru Kawamura, Shigekazu Ishihara, Averageness or symmetry: Which is more important for facial attractiveness? Acta Psychologica, 2009:p.104-107.
5.Masashi Komori , Satoru Kawamura , Shigekazu Ishihara , Effect of averageness and sexual dimorphism on the judgment of facial attractiveness. Vision Research, 2009. vol.49: p.862-869.
6.Luis Guerrero, Sensory characterization of dry-cured ham using free-choice profiling. Food Quality and Preference, 2009.p.14-19.
7.Elena F. Kranioti, A geometric-morphometric study of the cretan humerus for sex identification. Forensic Science International, 2009.p.136-132.
8.Enrico Vezzetti, Flaviana Calignano, Sandro Moos, Computer-aided morphological analysis for maxillo-facial diagnostic: a preliminary study. Journal of Plastic, Reconstructive & Aesthetic Surgery, 2008: p.165-172.
9.Fabio Napolitano, The qualitative assessment of responsiveness toenvironmental challenge in horses and ponies. Animal Behaviour Science, 2007.p342-354.
10.Melanie Mireaux, David N. Cox , Amy Cotton, Greg Evans, An adaptation of repertory grid methodology to evaluate Australian consumers' perceptions of food products produced by novel technologies. Food Quality and Preference, 2007: p.834-848.
11.Kieran P. McNulty , Stephen R. Frost , David S. Strait , Examining affinities of the Taung child by developmental simulation. Journal of Human Evolution, 2006. vol.51: p.274-296.
12.Youngohc Yoon, George Swales, Predicting stock price performance : a neural network approach. Proceedings of the Twenty-Fourth AnnualHawaii International Conference on System Sciences, 1991: p.156-162.
13.J. Snyder, J. Sweat, M. Richardson and D. Pattie, Developing neural networks to forecast agricultural commodity prices. The Twenty-Fifth Hawaii International Conference on System Sciences, 1992. p.516-522.
14.Jehng Jung Kao, Forecasts using neural networks versus Box-Jenkins methodology for Ambient Air quality monitoring data. J. Air &Waste Manage. Assoc, 2000: p.219-226.
15.M.C. Medeiros, A hybrid linear-neural model for time series forecasting. IEEE Transactions on Neural Networks, 2000: p.1402-1412.
16.Francis E.H. Tay, Lijuan Cao, Application of support vector machines in financial time series forecasting. OMEGA, 2001: p. 309-317.
17.D.O. Whiteson, N.A. Naumann, Support vector regression as a signal discriminator in high energy physics. Neurocomputing, 2003. Vol.55: p.251-264.
18.Michael Tovey, Styling and design: intuition and analysis in industrial design. Design Studies, 1997. Vol.18: p.5-31.

19.Weizhen Lu, Wenjian Wang, Richard K.K. Yuen, Air Pollutant Parameter Forecasting Using Support Vector Machines. Proceedings of the 2002 International Joint Conference on Neural Networks, 2002: p.12-17.