کنفرانس بین المللی فناوری و مدیریت انرژی

صفحه اصلی / هشتمین کنفرانس بین المللی فناوری و مدیریت انرژی

Energy consumption optimization & Improving performance in CPU of the implantable cardioverter defibrillator with using design and hardware implementation of CNN neural network on Zynq

نویسندگان :

Alireza Keyanfar¹ Reza Ghaderi² Soheila Nazari³ Behzad Hajimoradi⁴ Leila Kamalzadeh⁵

1- دانشگاه شهید بهشتی 2- دانشگاه شهید بهشتی 3- دانشگاه علوم پزشکی بهشتی 4- دانشگاه شهید بهشتی 5- دانشگاه شهید بهشتی

کلمات کلیدی :

Energy consumption optimization in medical devices

چکیده :

Arrhythmias of the heart such as ventricular fibrillation (VF) and ventricular tachycardia (VT) must be identified and treated as soon as possible. Implantable cardioverter-defibrillator (ICD) is a device that must detect VT and VF arrhythmias in a timely manner and treat them. In this project, one network is designed to introduce the practical methods of using deep learning in heart electrophysiology signals processing with the approach of optimizing energy consumption and increasing the performance of the boundary core of the implantable defibrillator device. This network is CNN for use in implantable defibrillators. For this network, a data set of 20 patients with cardiac arrhythmia and 20 patients without cardiac arrhythmia in an 8-month period of ICD check-up has been prepared. This network is designed to detect EGM signals in VF and VT modes with the optimal number of parameters and 100% accuracy. Since energy consumption in implanted medical equipment is very important, special attention should be paid to optimizing energy consumption in the design of these devices. The optimal number of parameters can increase network speed in signal processing and arrhythmia detection and can also be useful in reducing battery consumption. Finally, the designed CNN network hardware was implemented. zynq chips have the ability to process in parallel and can be useful in increasing the processing speed, so zynq chips were selected for the hardware target. After the hardware implementation stage, it is possible to proceed from the IP Core produced to design other parts of the defibrillator in the Vivado software.