| Abstract: | 在資訊爆炸的時代,處於日趨複雜的環境及多重資訊來源管道之下,如何從大量及瑣碎的的資訊中找出「重要且有用」的部分,藉以輔助企業或個人制定正確的決策,並降低資訊取得的成本,是資訊人員在設計資訊系統時所必須考量的重要因素之一,因此,資訊篩選(Information filtering)已成為當務之急,更顯示出其重要性。 本研究之主要目的在於整合類神經網路與模糊理論以建立一個通用型資訊篩選之演算法,藉由此演算法可篩選出重要之決策變數,減少資訊的使用量,達到相同或類似的決策結果,進而降低後續資訊蒐集之成本。最後並以四個XOR實驗及國內上市公司股價預測為例,以測試本研究所開發出來之演算法的正確性及實用性。就XOR實驗結果顯示均能迅速且正確的篩選出重要的輸入資訊;而在股價預測方面,結合基本面分析及技術面分析,根據個別公司的特性及不同的時間點,能夠篩選出其重要的預測變數,可作為股市投資者之重要參考依據。因此,藉由本演算法所開發出來的系統,可以達到資訊篩選的目的。
At the time of information explosion, how to filter the important and useful parts from a large and trivial information pool is one of the most important factors considering in designing information systems which are used to assist users making right decisions by MIS managers. The purpose of this research is to integrate two technologies, Artificial Neural Network and Fuzzy Theory, to develop a generalized algorithm to filter important information. We hope that using this algorithm we can (1) filter the important decision variables, (2) decrease the information usage, and (3) reduce the cost of information collection. Finally, we made four experiments on the XOR system and stock market forecasting to test the accuracy and practicability of the information filter algorithm. The results of experiments showed that the algorithm could filter the important information correctly and quickly. |
