應用DNA計算於預測技術探討

Abstract

隨著科技的進步與工商業的發展，預測技術的創新與改進愈來愈受到重視，相對地對於預測準確度的要求也愈來愈高。尤其在經濟建設、人口政策、經營規畫、管理控制等問題上，預測更是管理決策過程中不可或缺的重要資訊。本計畫目標針對財經領域重要指標進行預測與決策分析。我們的計畫主題是:如何將科學家探索生物分子的計算力量的DNA 計算應用於預測技術上。DNA 計算資訊以一串DNA 型態分子的樣式表示。其資訊由服從操作它對精準設計之化學反應標記型態。我們應用DNA 計算的目的乃取決於它超強之平行計算能力以及問題優化處理。理論上在DNA 計算能力可為單一計算的無窮倍，因此評估它的未來發展極具潛力。我們可享受演示和保證檢查在鏈接之外更多資訊。本研究將對指標特性分別對點預測，區間預測，等第預測，轉折預測，並與傳統預測技術做比較與評估。希望經由這些預測技術性質的討論和模糊統計分析，將市場差異性與趨勢性更精確地呈現。

Recently, along with the advance of technology and industry, the innovation and improvement of forecasting techniques have caught more and more attention while the standard in forecasting accuracy becomes higher and higher. Especially, in the issues of economy development, population policy, and management planning and control, forecasting provides indispensable information in decision-making process. This project aims at developing a new forecasting technique by the use of DNA computing as well as its algorithm. The motivation stems from the fact that molecular biology is becoming ever more database driven, motivated nowadays, in part, by the introduction of large-scale functional genomics and proteomics experiments such as those comprehensively measuring gene expression. These provide abundant information on thousands of proteins which encoded by genome. Based on this reason, we propose the forecasting technique with DNA computing for important financial and economic data/index and forecast future trend while comparing the forecasting performance with other technique methods. We strongly believe that this technique will be profound of meaning in forecasting future trend of financial and economic market.