Raised Cosine Dictionary for Modeling and Compressed Sensing of Multi-lead ECG Signals
Publish place: The first international conference of modern research engineers in electricity and computer
Publish Year: 1395
نوع سند: مقاله کنفرانسی
زبان: English
View: 607
This Paper With 6 Page And PDF Format Ready To Download
- Certificate
- من نویسنده این مقاله هستم
استخراج به نرم افزارهای پژوهشی:
شناسه ملی سند علمی:
CBCONF01_0363
تاریخ نمایه سازی: 16 شهریور 1395
Abstract:
nowadays, modern technology has a very crucial role in healthcare and medical systems. An important issue in biomedical and signal processing area, is compressing biomedical signals. One of the most important signals is Electrocardiogram (ECG) which plays an important role in diagnosing heart’s anomalies. In this paper, the compressed sensing (CS) theory is exploited in order to compress multi-lead ECG signals. To achieve the sparse representation of the ECG signals, a basis matrix using raised Cosine functions is constructed. Raised Cosine kernels nicely fit ECG signals and their low excess Kurtosis makes these functions a suitable choice to model ECGs. Finally, CS theory is used to achieve the compressed version of the signals. Exploiting some optimization techniques the reconstructed signals are obtained from their compressed version. Finally the proposed method is evaluated by three known performance metrics.
Keywords:
Authors
Siavash Eftekharifar
Department of Electrical and Computer Engineering University of Tabriz Tabriz, Iran
Tohid Yousefi Rezaii
Department of Electrical and Computer Engineering University of Tabriz Tabriz, Iran
Mahdi Shamsi
Department of Electrical and Computer Engineering University of Tabriz Tabriz, Iran
مراجع و منابع این Paper:
لیست زیر مراجع و منابع استفاده شده در این Paper را نمایش می دهد. این مراجع به صورت کاملا ماشینی و بر اساس هوش مصنوعی استخراج شده اند و لذا ممکن است دارای اشکالاتی باشند که به مرور زمان دقت استخراج این محتوا افزایش می یابد. مراجعی که مقالات مربوط به آنها در سیویلیکا نمایه شده و پیدا شده اند، به خود Paper لینک شده اند :