Hybrid statistical and recurrent neural network architecture implementation in FPGA device used for severe acute respiratory syndrome coronavirus detector

Abstract

The Severe Acute Respiratory Syndrome (SARS) are caused by the strain of the corona virus causes cold and influenza. In recent years, the covid pandemic spread throughout the world killing millions of people. The fatality rate has increased and it also leads to pneumonia for breathing problems. Several methods like wavelet filter banks, time series methods, Neural networks was developed for the diagnosis of severe acute respiratory syndrome coronavirus, still the accuracy can be improved. Less works is carried out for hardware implementation for syndrome detectors. This proposed work represents the FPGA (Field Programmable Gate Array) implementation of the hybrid method using Convolutional Recurrent neural network and Independent Components Analysis (ICA). The architecture extracts the ccomplex features from ECG (Electrocardiogram) samples. The hybrid Statistical and Recurrent Neural Network (RNN) Architecture implementation in a real time hardware detects the Severe Acute Respiratory Syndrome presented. The proposed method can be implemented in MATLAB, Embedded and DSP (Digital Signal Processor). But, the FPGAs consume less power computationally efficient. Since, ICA is an efficient method due to its blind source separation property accumulate the extraction of features accurate described. The mathematical model for the analysis of ECG signal using RNN is analyzed and based on that the proposed model is selected. On investigation the hybrid method using the statistical and neural network model is efficient in the analysis of biomedical signal especially ECG. The proposed ICA based RNN model is mathematically evaluated and tested with real time data. For implementation, Quartus software is used for effectiveness of the proposed model.