LSTAR Model for Sudden Cardiac Death Prediction
Publish place: 3rd International Conference on Electrical Engineering
Publish Year: 1397
نوع سند: مقاله کنفرانسی
زبان: English
View: 339
متن کامل این Paper منتشر نشده است و فقط به صورت چکیده یا چکیده مبسوط در پایگاه موجود می باشد.
توضیح: معمولا کلیه مقالاتی که کمتر از ۵ صفحه باشند در پایگاه سیویلیکا اصل Paper (فول تکست) محسوب نمی شوند و فقط کاربران عضو بدون کسر اعتبار می توانند فایل آنها را دریافت نمایند.
- Certificate
- من نویسنده این مقاله هستم
استخراج به نرم افزارهای پژوهشی:
شناسه ملی سند علمی:
ICELE03_070
تاریخ نمایه سازی: 18 اسفند 1397
Abstract:
The unexpected changes in heart signals, followed by stroke and cardiac arrest, are one of the most common causes ofsudden deaths. Analysis of the recorded signals is the responsibility of the expert. The severe changes in cardiacfunction usually occur suddenly and almost at the moment of the incident. Therefore, the probability of error indiagnosis of electrocardiography (ECG) signal is high and in most cases the lifes of patients falls at death risk. The aimof this study is to predict the sudden cardiac death (SCD) by processing of ECG signals. In the proposed method, afterextracting the hearth rate variability (HRV) signal from the ECG signal, we use the discrete wavelet transform (DWT)to desompse it into time-frequency sub-bands. By using the logistic smooth transition autoregressive (LSTAR) model,the sub-bands of DWT transform are modeled and then the model parameters are considered as features. Kernelprincipal component analysis (KPCA) method is used to reduce the number of features and support vector machine(SVM) classifier is employed for classifying healthy and risky individuals. The obtained results demonstrate theefficiencty of the proposed method.
Keywords:
Authors
Fariba Alizadeh
Department of Electrical & Computer Engineering, Urmia University, Urmia, Iran
Hashem Kalbkhani
Department of Electrical Engineering, Urmia University, Urmia, Iran
Mahrokh G Shayesteh
Department of Electrical Engineering, Urmia University, Urmia, Iran