國小教師供需問題是目前教育界中的一個重要問題，教師需求量的預測精確與否，將影響及教育政策的制定。本研究中，我們使用單變量 ARIMA 及類神經網路，以預測台灣地區 1996 到 1998 年之間的國小教師需求量。
研究結果顯示，在預測國小教師數列上，ARIMA 及類神經望陸均有很好的表現。類神經網路的可用範圍寬廣，適於各種複雜的情境，然而就本研究的主要探討對象--國小教師數列而言，以單變數的神經網路便已足夠。如果能選擇適當、具明顯特徵的資料，則網路將有更佳的預測效果。
由於類神經網路具有自我學習、自我調適、及平行處理等優點，因此在發展教師供需預測系統時，除了 ARIMA 之外，類神經網路為另一可行方法。 / The demand for and supply of teachers in elementary schools is an important problem in education administration. An accurate forecast of the number of teachers needs in elementary schools may heavily affect educational policy. In this thesis, we use the univariate time series analysis and Neural Networks to forecast the number of teacher in elementary schools in Taiwan Area during a period from 1996 to 1998.
According to the result, both Box-Jenkins model and Neural Network perform well for prediction. Neural Network can be widely used in different circumstance, especially complicated situation. In this research, however, it is enough to predict number of teacher by the univariate neural network. In other word, if selecting suitable data variables, we could obtain better predictable effect by neural network.
With the advantages of self-learning, self adaptation, and parallel processing, the Neural Network approach is a promising alternative approach to time series for developing a teacher demand and supply forecasting system.
| Identifer | oai:union.ndltd.org:CHENGCHI/B2002001930 |
| Creators | 陳嘉甄, Chen, Chia-Chen |
| Publisher | 國立政治大學 |
| Source Sets | National Chengchi University Libraries |
| Language | 中文 |
| Detected Language | English |
| Type | text |
| Rights | Copyright © nccu library on behalf of the copyright holders |
Page generated in 0.0022 seconds