Edge Artificial Intelligence: Real-Time Noninvasive Technique for Vital Signs of Myocardial Infarction Recognition Using Jetson Nano

The history of medicine shows that myocardial infarction is one of the significant causes of death in humans. The rapid evolution in autonomous technologies, the rise of computer vision, and edge computing offers intriguing possibilities in healthcare monitoring systems. The major motivation of the...

Full description

Saved in:
Bibliographic Details
Main Authors: H. M. Mohan, S. Anitha, Rifai Chai, Sai Ho Ling
Format: Article
Language:English
Published: Wiley 2021-01-01
Series:Advances in Human-Computer Interaction
Online Access:http://dx.doi.org/10.1155/2021/6483003
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849684385934082048
author H. M. Mohan
S. Anitha
Rifai Chai
Sai Ho Ling
author_facet H. M. Mohan
S. Anitha
Rifai Chai
Sai Ho Ling
author_sort H. M. Mohan
collection DOAJ
description The history of medicine shows that myocardial infarction is one of the significant causes of death in humans. The rapid evolution in autonomous technologies, the rise of computer vision, and edge computing offers intriguing possibilities in healthcare monitoring systems. The major motivation of the work is to improve the survival rate during a cardiac arrest through an automatic emergency recognition system under ambient intelligence. We present a novel approach to chest pain and fall posture-based vital sign detection using an intelligence surveillance camera to address the emergency during myocardial infarction. A real-time embedded solution persuaded from “edge AI” is implemented using the state-of-the-art convolution neural networks: single shot detector Inception V2, single shot detector MobileNet V2, and Internet of Things embedded GPU platform NVIDIA’s Jetson Nano. The deep learning algorithm is implemented for 3000 indoor color image datasets: Nanyang Technological University Red Blue Green and Depth, NTU RGB + D dataset, and private RMS dataset. The research mainly pivots on two key factors in creating and training a CNN model to detect the vital signs and evaluate its performance metrics. We propose a model, which is cost-effective and consumes low power for onboard detection of vital signs of myocardial infarction and evaluated the metrics to achieve a mean average precision of 76.4% and an average recall of 80%.
format Article
id doaj-art-c1c8243661664a489ff1c3a8a18e78d0
institution DOAJ
issn 1687-5893
1687-5907
language English
publishDate 2021-01-01
publisher Wiley
record_format Article
series Advances in Human-Computer Interaction
spelling doaj-art-c1c8243661664a489ff1c3a8a18e78d02025-08-20T03:23:28ZengWileyAdvances in Human-Computer Interaction1687-58931687-59072021-01-01202110.1155/2021/64830036483003Edge Artificial Intelligence: Real-Time Noninvasive Technique for Vital Signs of Myocardial Infarction Recognition Using Jetson NanoH. M. Mohan0S. Anitha1Rifai Chai2Sai Ho Ling3R/S, Department of ECE, ACS College of Engineering, Visvesvaraya Technological University, Belagavi, IndiaDepartment of ECE, ACS College of Engineering, Bangalore, IndiaSchool of Software and Electrical Engineering, Swinburne University of Technology, Melbourne, AustraliaSchool of Biomedical Engineering, University of Technology Sydney, Ultimo, AustraliaThe history of medicine shows that myocardial infarction is one of the significant causes of death in humans. The rapid evolution in autonomous technologies, the rise of computer vision, and edge computing offers intriguing possibilities in healthcare monitoring systems. The major motivation of the work is to improve the survival rate during a cardiac arrest through an automatic emergency recognition system under ambient intelligence. We present a novel approach to chest pain and fall posture-based vital sign detection using an intelligence surveillance camera to address the emergency during myocardial infarction. A real-time embedded solution persuaded from “edge AI” is implemented using the state-of-the-art convolution neural networks: single shot detector Inception V2, single shot detector MobileNet V2, and Internet of Things embedded GPU platform NVIDIA’s Jetson Nano. The deep learning algorithm is implemented for 3000 indoor color image datasets: Nanyang Technological University Red Blue Green and Depth, NTU RGB + D dataset, and private RMS dataset. The research mainly pivots on two key factors in creating and training a CNN model to detect the vital signs and evaluate its performance metrics. We propose a model, which is cost-effective and consumes low power for onboard detection of vital signs of myocardial infarction and evaluated the metrics to achieve a mean average precision of 76.4% and an average recall of 80%.http://dx.doi.org/10.1155/2021/6483003
spellingShingle H. M. Mohan
S. Anitha
Rifai Chai
Sai Ho Ling
Edge Artificial Intelligence: Real-Time Noninvasive Technique for Vital Signs of Myocardial Infarction Recognition Using Jetson Nano
Advances in Human-Computer Interaction
title Edge Artificial Intelligence: Real-Time Noninvasive Technique for Vital Signs of Myocardial Infarction Recognition Using Jetson Nano
title_full Edge Artificial Intelligence: Real-Time Noninvasive Technique for Vital Signs of Myocardial Infarction Recognition Using Jetson Nano
title_fullStr Edge Artificial Intelligence: Real-Time Noninvasive Technique for Vital Signs of Myocardial Infarction Recognition Using Jetson Nano
title_full_unstemmed Edge Artificial Intelligence: Real-Time Noninvasive Technique for Vital Signs of Myocardial Infarction Recognition Using Jetson Nano
title_short Edge Artificial Intelligence: Real-Time Noninvasive Technique for Vital Signs of Myocardial Infarction Recognition Using Jetson Nano
title_sort edge artificial intelligence real time noninvasive technique for vital signs of myocardial infarction recognition using jetson nano
url http://dx.doi.org/10.1155/2021/6483003
work_keys_str_mv AT hmmohan edgeartificialintelligencerealtimenoninvasivetechniqueforvitalsignsofmyocardialinfarctionrecognitionusingjetsonnano
AT sanitha edgeartificialintelligencerealtimenoninvasivetechniqueforvitalsignsofmyocardialinfarctionrecognitionusingjetsonnano
AT rifaichai edgeartificialintelligencerealtimenoninvasivetechniqueforvitalsignsofmyocardialinfarctionrecognitionusingjetsonnano
AT saiholing edgeartificialintelligencerealtimenoninvasivetechniqueforvitalsignsofmyocardialinfarctionrecognitionusingjetsonnano