Please use this identifier to cite or link to this item: http://hdl.handle.net/11455/48980
標題: Biometric Personnel Identification and Applications Based on Chaotic ECG Signals
基於心電混沌訊號之生物辨識技術與應用
作者: 林俊良
關鍵字: 心電圖
Electrocardiogram
電子電機工程類
安全通訊
混沌加密
混沌同步
應用研究
Security communication
chaotic encryption
chaoticsynchronization
摘要: Electrocardiography (ECG) is a noninvasive recording produced by anelectrocardiographic device which is a transthoracic interpretation of the electrical activity ofthe human's heart over time captured. From the data base of medical ECG signals forthousands of people, ECG seems to be irregular, random, and changing from person to person.Because of high randomness and complexity of ECG in human beings, its feature is extremelyhard and is likely impossible to be duplicated artificially. However, it has recently beenshown in the literature that the kind of signals is, in fact, chaotic. Because people's ECGs areextremely hard to be artificially duplicated, this project thus intends to investigate the way toextract the specific biometric features of ECG signals for possible use in the biometricpersonnel identification. Since the specific features of ECGs are difficult to be extracted fromthe time domain expression, the signal is converted into the phase plane and ECG chaosextractor is applied to capture the major indices of ECG chaos, i.e. Lyapunov exponentsspectrum, correlation dimension, central tendency, K-S entropy, etc. The features are thenused as the key input variables for neural networking training and used in a personalauthentication scheme. From the viewpoint of applications, the developed identifier would beappropriate for secure communication as well. After successful development of theECG-based personal authentication system, it will be incorporated with cryptography toperform chaotic encryption and de-encryption in secure communication. A hardware systemconsisting of sensors, ECG extractor, and post signal processing identifier will beimplemented to experimentally show the applicability of the proposed approach.
心電圖為記錄人體心肌細胞電性改變後,身體體液電位變化以非侵入方式擷取之資訊。數醫學ECG信號數據庫中顯示,每個人的ECG信號均極複雜且隨機變化,由於ECG信號的這種特質,因此個人ECG信號很難以人為方式變造複製。最近幾年國内外研究人員對生命循環系统的核心-ECG的非線性特性作了深入研究,研究論文顯示,心電訊號看似複雜,但卻顯現混沌動態特質,也就是ECG雖為非線性動態行為但具有特殊規律性。國際上關於ECG的相關研究均未涉及個人身份辨識的應用,基於此觀察,本研究嘗試以非線性心電訊號為研究對象,規劃此一研究主題,提出一種使用混沌心電訊號進行個人身份辨識的系統。由於心電訊號在時域上很難看出有什麼特徵,因此將心電訊號轉至相平面並利用混沌理論分析心電訊號狀態的關聯維數、李亞普若夫(Lyapunov)指數譜與柯氏熵等三種特徵值,結合神經網路學習與辨識在人們不同生理條件下,如休息、和緩運動與劇烈運動等,所反映的心臟動力學整體特性,作為個人身份生物辨識的基礎。混沌系統具有寬頻功率頻譜、軌跡難以估測及近似隨機訊號的特性,因此廣泛被應用於通訊安全的研究。本研究亦從應用觀點,將所建構完成之混沌心電訊號身份辨識系統,結合密碼學,建構一個嶄新的私人安全通訊系統,將欲傳送的明文訊號加入私人的混沌心電訊號作編碼,利用混沌同步技術將加密的訊號傳送出去,接收端將加密訊號與另一個同步混沌心電訊號相減,使有意義的明文訊號還原,達到個人資料安全通訊的目的。
URI: http://hdl.handle.net/11455/48980
其他識別: NSC99-2221-E005-066
文章連結: http://grbsearch.stpi.narl.org.tw/GRB/result.jsp?id=2112613&plan_no=NSC99-2221-E005-066&plan_year=99&projkey=PB9907-11386&target=plan&highStr=*&check=0&pnchDesc=%E5%9F%BA%E6%96%BC%E5%BF%83%E9%9B%BB%E6%B7%B7%E6%B2%8C%E8%A8%8A%E8%99%9F%E4%B9%8B%E7%94%9F%E7%89%A9%E8%BE%A8%E8%AD%98%E6%8A%80%E8%A1%93%E8%88%87%E6%87%89%E7%94%A8
Appears in Collections:電機工程學系所

文件中的檔案:

取得全文請前往華藝線上圖書館



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.