隱藏式馬可夫模型應用於心電圖信號的自動分類 = Automatic EC...
國立高雄大學資訊工程學系碩士班

 

  • 隱藏式馬可夫模型應用於心電圖信號的自動分類 = Automatic ECG Signal Classification Using Hidden Markov Model
  • Record Type: Language materials, printed : monographic
    Paralel Title: Automatic ECG Signal Classification Using Hidden Markov Model
    Author: 陳弘晉,
    Secondary Intellectual Responsibility: 國立高雄大學
    Place of Publication: [高雄市]
    Published: 撰者;
    Year of Publication: 2012[民101]
    Description: 57面圖,表格 : 30公分;
    Subject: 心律不整
    Subject: cardiac arrhythmia
    Online resource: http://handle.ncl.edu.tw/11296/ndltd/17862656113826249018
    Notes: 107年4月10日公開
    Notes: 參考書目:面48-50
    Summary: 心臟,是人體中最重要的器官之一,心臟能夠正常的運作,血液才得以在體內維持新陳代謝,但是,當心臟無法進行規律的收縮時,血液便無法順利輸送,而使人產生胸痛、呼吸急促、頭暈等症狀,嚴重時更可能危及生命,這樣的情形則稱為心律不整(cardiac arrhythmia)。心律不整通常由專家及醫師藉著心電圖(electrocardiogram, ECG)的輔助來進行診察,因為在心電圖信號中,提供了許多重要的診斷資訊,但由於以人工的方式進行心電圖信號判讀十分費時,因此在本研究中採用了隱藏式馬可夫模型(Hidden Markov Model, HMM)來對不同類型的心電圖信號進行自動分類,而判讀對象包含了正常(normal)心電圖信號與心律不整心電圖信號,其中心律不整心電圖信號的種類有左束支傳導阻斷(left bundle branch block, LBBB)信號、右束支傳導阻斷(right bundle branch block, RBBB)信號、心房早期收縮(atrial premature complex, APC)信號以及心室早期收縮(premature ventricular contraction, PVC)信號,為了達到最佳的分類效果,研究中提出了三種不同的心電圖信號辨識架構,即針對不同類型的心電圖信號,而使用非固定的心電圖特徵值來進行隱藏式馬可夫模型的訓練以及心電圖信號的辨識,從實驗結果可得知,本研究提出的方法,為心電圖信號自動分類提供了一種快速且可靠的方式。 The heart is one of the most important organs in the human body. When the heart cannot pump regularly, it is called cardiac arrhythmia. During an arrhythmia, people may feel dizzy and pain in the chest. Furthermore, serious cardiac arrhythmias can result in death.Doctors and experts diagnose arrhythmias by using an electrocardiogram (ECG) because there are numerous useful information in ECG signal. Visual interpretation of ECG is a time-consuming process, therefore, we adopt a probabilistic approach based on Hidden Markov Model (HMM) for classifying ECG signal automatically. The ECG signals being classified including normal heartbeats, left bundle branch block heartbeats, right bundle branch block heartbeats, atrial premature complex heartbeats and premature ventricular contraction heartbeats. In order to perform well in classifying, we propose three different types of classification frameworks in our research. Besides, we use different amount of ECG features to train HMM models and classify ECG signals when processing different kinds of ECG signals. The results of the experiments show that the proposed method for automatic ECG signal classification is efficient and reliable.
Items
  • 2 records • Pages 1 •
 
310002317405 博碩士論文區(二樓) 不外借資料 學位論文 TH 008M/0019 464103 7511 2012 一般使用(Normal) On shelf 0
310002317413 博碩士論文區(二樓) 不外借資料 學位論文 TH 008M/0019 464103 7511 2012 c.2 一般使用(Normal) On shelf 0
  • 2 records • Pages 1 •
Reviews
Export
pickup library
 
 
Change password
Login