Loading...
Design and Efficient Implementation of ECG-based Detection Algorithm for Dangerous Myocardial Problems
Saadatnejad, Saeed | 2017
1082
Viewed
- Type of Document: M.Sc. Thesis
- Language: Farsi
- Document No: 50098 (05)
- University: Sharif University of Technology
- Department: Electrical Engineering
- Advisor(s): Hashemi, Matin; Vosooghi Vahdat, Bizhan
- Abstract:
- Cardiovascular diseases are the first leading cause of death in the world also in IRAN. Early detection of such problems can decrease the costs also can help to cure the patient but it needs continuous monitoring and automated classification of hearbeats. Mobile devices and wearable gadgets are good solutions which can help patients before visiting the doctor.In this research, an algorithm is introduced which with the help of ECG signal detects dangerous myocardial problems. Our approach is using deep learning method which were not considered much before. In the proposed algorithm ECG signal is processed in order to get features and with dimensionality reduction, input of the network gets ready. Then heartbeats will be classified by reccurent neural network. This method has been evaluated on standard databases and reach more than 98% accuracy in detection of dangerous heart problems. Also has better accuracies in comparision with previous works.Recurrent neural networks generally have high computational costs but with much optimizations on the method we implemented efficiently so it will be executed real-time on mobile devices and wearable gadgets -which have poor performance CPUs
- Keywords:
- Deep Learning ; Electrocardiogram ; Heart Diseases ; Wearable Assistive Device ; Wearable Gadgets
-
محتواي کتاب
- view
- مقدمه
- مبانی پژوهش
- بیماریهای خطرناک قلبی
- سیگنال الکتروکاردیوگرام
- هدف پژوهش
- پیشینه پژوهش
- راه حل پیشنهادی
- مبانی پژوهش
- روش پیشنهادی
- ورودی شبکه
- پیشپردازش داده
- ویژگیهای مرتبط با فاصله R سیگنال
- تبدیل موجک
- تحلیل مولفههای اصلی
- شبکه
- شبکه عصبی بازگشتی ساده
- شبکه عصبی بازگشتی با Long-Short-Term-Memory
- شبکه عصبی بازگشتی با Peephole-LSTM
- شبکه عصبی بازگشتی با Gated-Recurrent-Unit
- لایه تمام متصل
- الگوریتم آموزش شبکه
- جمعبندی
- ورودی شبکه
- پیادهسازی
- ابزار پیادهسازی
- پیادهسازی آموزش
- پیادهسازی آزمون
- جمعبندی
- آزمایش
- پایگاه داده
- نتایج آزمایش
- کاوش ورودی شبکه
- تبدیل موجک
- کم کردن ضرایب تبدیل موجک
- کاوش شبکه
- نوع شبکه عصبی بازگشتی
- پارامتر Nh
- جمع بندی
- نتیجهگیری و پیشنهادها
- toمنابع و مراجع