Efficient CNN Architecture on FPGA Using High Level Module for Healthcare Devices

Modern wearable healthcare devices require new technologies with resource efficiency in terms of high performance, low energy consumption and diagnostic accuracy. In the field artificial intelligence, convolutional neural network (CNN) has performed as an effective algorithm. Field-programmable gate arrays (FPGAs) have been extensively utilised to construct hardware accelerators for CNNs. This paper suggests using accelerator create a specific 1-D CNN classify electrogram (ExG). ExGs used here include electrocardiogram, electroencephalogram electromyography. The pipelined structure is designed register middle facilitate easy data transfer. A categorise ExG signals implemented on Xilinx Zynq xc7z045 platform outperforms FPGA peer applications same by 1.14× speed. addition, proposed operates very efficiently due use tristate buffer multiplexer substitution shift multiplier, resulting resource-efficient 161 GOP/s/W 28 GOP/s/KLUT, improvement 1.67 over previous model. Finally, performance applied operating at 442.948MHz was calculated, achieving 1.145 TFLOP/s.