Non-invasive technique for real-time myocardial infarction detection using faster R-CNN

摘要

The medical history explores that Myocardial Infarction has been one of the leading factors of death in human beings since several decades globally. The researchers' key tasks are to emerge a novel real-time health vision-based monitoring system with added measurement features like high accuracy, robust, reliable, low-cost, low power with high data security. The main purpose of this research is to bestow an advanced non-invasive algorithmic approach for detecting the chest pain posture and fall posture based vital signs of Myocardial Infarction and analyzing the performance of a Faster Region-based Convolution Neural Network algorithm. This object detection computer vision technique is simulated for 3000 three-dimensional real-life indoor environment RGB color images for two datasets Nanyang Technological University Red Blue Green, and Depth dataset and private dataset-RMS trained datasets using TensorFlow object detection Application Programming Interface. The 3D RGB Images of NTU RGB database used for Vital Signs of Myocardial Infarction performance analysis is an improved approach. The simulation results have been compared with the existing works. The demonstrated results of ResNet-101 Faster RCNN showed the evaluated metric values: high mean precision and average recall value is a major contribution in this work.