Please use this identifier to cite or link to this item:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/62299
Title: | 透過隨機細胞自動機學習DNA序列規則 Find Rules From DNA Sequences By Stochastic Cellular Automata |
Authors: | Ching-Teng Ling 凌璟騰 |
Advisor: | 劉長遠 |
Keyword: | 機器學習,強化學習法,預測符號序列,DNA分析, machine learning,reinforcement learning,prediction of symbol sequence,DNA analyze, |
Publication Year : | 2013 |
Degree: | 碩士 |
Abstract: | 在這篇論文中,我們設計了一個可以預測一個有規則的序列中的下
一個符號的感測器,並且可以透過學習算出在符號序列中的規則。我 們使用的強化學習法來設計學習過程,並使用隨機格狀自動機來實作 強化學習法。這個感測器可以應用在許多問題上,例如:預測基因序 列、股票市場、偵測傳送錯誤或是網路攻擊。為了要展示我們的感測 器,在這篇論文中,我們設計一個感測器可以用來預測基因序列,並 分析結果。 In this paper, we present a ruled symbol sequence sensor which can predict the next symbol of a symbol sequence and extract the rules of the symbol sequence. In this sensor, we use the reinforcement learning mechanism to design the learning process, and use the stochastic cellular automata to implement the value function in the reinforcement learning model. This sensor can be applied on many problems, such as prediction of DNA sequence, stock market, transaction anomalies, internet Intrusion and transmission anomaly. For demonstrating our sensor, we apply the sensor on some DNA sequences and analyze the output. |
URI: | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/62299 |
Fulltext Rights: | 有償授權 |
Appears in Collections: | 資訊工程學系 |
Files in This Item:
File | Size | Format | |
---|---|---|---|
ntu-102-1.pdf Restricted Access | 1.71 MB | Adobe PDF |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.