The Application of Grey Relational Analysis and Neural Network Learning On IC Packaging Quantity Forecasting

• Main Authors: Pi-lian Weng, 翁碧蓮
• Other Authors: Pei-tsang Wu
• Format: Others
• Language: zh-TW
• Published: 2009
• Online Access: http://ndltd.ncl.edu.tw/handle/04090208337942747556

碩士 === 義守大學 === 工業工程與管理學系碩士班 === 97 === Enterprises must take appropriate strategic to confront and react to such diversified circumstances. For them, the prediction will play an important role while planning. No matter making decisions or scheming out a plan, there are more or less uncertainties on upcoming implementation that also results in certain level of risks. Therefore, the main purpose of prediction is to estimate the oncoming events or situations in advance and provide the best information to management level to detect those uncertain conditions and help reduce the risks during decision-making process. Recently, artificial intelligence methods get more and more attention in these years. Among them, neural network is applied extensively and effectively on predictive questions. That’s because most predictive questions belong to non-linear model, and neural networks is capable to construct non-linear model. This article is to utilize grey relational analysis to find out the higher related factors among numerous parameters and then input these factors into forecasting model to proceed training and prediction. After that, apply the result on production output assessment to increase the accuracy of forecast and provide the consultation to related industries for production forecasting.