時間序列分析發展至今,常常發現動態資料的走勢,隨著時間過程而演變.所以傳統的模式配適常無法得到很好的解釋,因此許多學者提出不同的模型建構方法.但是對於初始模式族的選擇,卻充滿相當的主觀與經驗認定成份.本文針對時變型時間序列分析,考慮利用知識庫,由模式庫來判斷初始模式.再藉由遺傳演算法的觀念,建立模式參數的遺傳關係.我們把這種遺傳演算法,稱之為時變遺傳演算法.針對台灣省國中數學教師人數,分別以時變遺傳演算法,狀態空間,與單變量ARIMA來建構模式,並作比較.比較結果發現,時變遺傳演算法較能掌握資料反轉的趨勢,且預測值增加較為平緩.因此時變遺傳演算法在模式建構上將是個不錯的選擇. / In time series analysis, we find often the trend of dynamic data changingwith time. Using the traditional model fitting can't get a good explanationfor dynamic data. Therefore, many savants developed a lot of methods formodel construction. However, these methods are usually influenced by personal viewpoint and experience in model base selection. In this thesis, we discussedtime-variant time series analysis. First, we builded a model base to judge inial models by knowledge base. Then, we set up the genetic relations of themodels' parameter. This method is called Time Variant Genetic Algorithm. We use the data if the number of junior high school mathematic teachers in Taiwan to ccompare the predictive performance of Time Variant Genetic Algorithmwith State Space and ARIMA. The forecasting performance shows the Time VariantGenetic Algorithm takes a better prediction result.

In this thesis there is a design of universal time-variant convolution FIR processor. Proposed algorithm is ready to process long signals with reduced process delay. Furthermore, there are proposed methods for smooth crossfade between different impulse responses. Algorithm is implemented in Matlab environment and later as a VST plugin.