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

2021 ◽  
Vol 2021 ◽  
pp. 1-19
Author(s):  
H. M. Mohan ◽  
S. Anitha ◽  
Rifai Chai ◽  
Sai Ho Ling
Keyword(s):  
Myocardial Infarction ◽  
Real Time ◽  
Performance Metrics ◽  
Color Image ◽  
Learning Algorithm ◽  
Rapid Evolution ◽  
Vital Signs ◽  
Recognition System ◽  
Single Shot ◽  
Noninvasive Technique

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%.

scholarly journals Hand Gesture Recognition Based on Single-Shot Multibox Detector Deep Learning

2019 ◽  
Vol 2019 ◽  
pp. 1-7 ◽  
Author(s):  
Peng Liu ◽  
Xiangxiang Li ◽  
Haiting Cui ◽  
Shanshan Li ◽  
Yafei Yuan
Keyword(s):  
Deep Learning ◽  
Gesture Recognition ◽  
Learning Algorithm ◽  
Recognition System ◽  
Hand Gesture Recognition ◽  
Hand Gesture ◽  
Single Shot ◽  
Complex Scene ◽  
Hand Gestures ◽  
Benchmark Database

Hand gesture recognition is an intuitive and effective way for humans to interact with a computer due to its high processing speed and recognition accuracy. This paper proposes a novel approach to identify hand gestures in complex scenes by the Single-Shot Multibox Detector (SSD) deep learning algorithm with 19 layers of a neural network. A benchmark database with gestures is used, and general hand gestures in the complex scene are chosen as the processing objects. A real-time hand gesture recognition system based on the SSD algorithm is constructed and tested. The experimental results show that the algorithm quickly identifies humans’ hands and accurately distinguishes different types of gestures. Furthermore, the maximum accuracy is 99.2%, which is significantly important for human-computer interaction application.

Abstract P182: Usefulness of Mobile Telemedicine System in Real-time Transmission of Out-of-hospital 12-lead ECG

Circulation ◽  
2008 ◽  
Vol 118 (suppl_18) ◽  
Author(s):  
Hiroshi Nonogi ◽  
Hiroyuki Yokoyama ◽  
Yoritaka Otsuka ◽  
Yoichiro Kasahara ◽  
Yu Kataoka ◽  
...  
Keyword(s):  
Myocardial Infarction ◽  
Acute Myocardial Infarction ◽  
Emergency Department ◽  
Real Time ◽  
Field Test ◽  
Vital Signs ◽  
Telemedicine System ◽  
Coronary Syndrome ◽  
Real Time Transmission ◽  
Set Up

[Purpose] AHA/ACC guidelines recommend routine use of 12-lead ECG and advance notification for patients with acute coronary syndrome. However, transmission of out-of-hospital 12-lead ECG to emergency department is still not spread and ECG interpretation on the prehospital and emergency department is not established. Therefore, we have developed and tested the clinical usefulness of the mobile telemedicine system to transmit 12-lead ECG between moving ambulances and physicians in cardiovascular emergency. [Method] We set up the mobile telemedicine using the third-generation digital mobile phone to promote communications between an ambulance and diverse hospital. Compatibility issue among device vendors was solved by the implementation of open-standard medical waveform encoding rule with motion noise-reduction system. Real time 12-lead ECG was transferred together with vital signs and live video during transfer the patient by an ambulance. The performance of the mobile telemedicine system in the field-test was checked to transfer 12-lead ECG in different scenarios such as transferred ECG from a volunteer moving hand or leg, coughing or twisting body in an ambulance driving on common road or highway. In the next step, we set up the mobile telemedicine on an ambulance to promote communications between moving 5 ambulances in Suita-city and National Cardiovascular Center since 2008 June 2. To establish the efficacy of real-time transmission of out-of-hospital 12-lead ECG, the time-line from the onset of acute myocardial infarction to reperfusion is analyzed. [Results] Totally 36 patters of 12-lead ECG were checked in the field test and all of them were comparable than those original one in the ambulance. Time-delay for transmission of 12 lead ECG was within 10seconds and for one-lead ECG monitoring and vital signs including BP, HR and oxygen saturation was 1 second without the difficulties for the interpretation. [Conclusion] Those results indicate the usefulness and reliability of transmission of 12-lead ECG using the mobile telemedicine system from the ambulance. Further investigation is on-going to determine the efficacy in clinical conditions to reduce the treatment delay for acute myocardial infarction.

scholarly journals Efficient Face Recognition System for Operating in Unconstrained Environments

2021 ◽  
Vol 7 (9) ◽  
pp. 161
Author(s):  
Alejandra Sarahi Sanchez-Moreno ◽  
Jesus Olivares-Mercado ◽  
Aldo Hernandez-Suarez ◽  
Karina Toscano-Medina ◽  
Gabriel Sanchez-Perez ◽  
...  
Keyword(s):  
Real Time ◽  
Face Detection ◽  
High Speed ◽  
Learning Algorithm ◽  
Facial Recognition ◽  
Processing System ◽  
Recognition System ◽  
Support Vector ◽  
The Face ◽  
Facial Recognition System

Facial recognition is fundamental for a wide variety of security systems operating in real-time applications. Recently, several deep neural networks algorithms have been developed to achieve state-of-the-art performance on this task. The present work was conceived due to the need for an efficient and low-cost processing system, so a real-time facial recognition system was proposed using a combination of deep learning algorithms like FaceNet and some traditional classifiers like SVM, KNN, and RF using moderate hardware to operate in an unconstrained environment. Generally, a facial recognition system involves two main tasks: face detection and recognition. The proposed scheme uses the YOLO-Face method for the face detection task which is a high-speed real-time detector based on YOLOv3, while, for the recognition stage, a combination of FaceNet with a supervised learning algorithm, such as the support vector machine (SVM), is proposed for classification. Extensive experiments on unconstrained datasets demonstrate that YOLO-Face provides better performance when the face under an analysis presents partial occlusion and pose variations; besides that, it can detect small faces. The face detector was able to achieve an accuracy of over 89.6% using the Honda/UCSD dataset which runs at 26 FPS with darknet-53 to VGA-resolution images for classification tasks. The experimental results have demonstrated that the FaceNet+SVM model was able to achieve an accuracy of 99.7% using the LFW dataset. On the same dataset, FaceNet+KNN and FaceNet+RF achieve 99.5% and 85.1%, respectively; on the other hand, the FaceNet was able to achieve 99.6%. Finally, the proposed system provides a recognition accuracy of 99.1% and 49 ms runtime when both the face detection and classifications stages operate together.

Development of Real-Time Emotion Recognition System Based on Machine Learning Algorithm

2021 ◽  
pp. 101-114
Author(s):  
Mohd Amzar Azizan ◽  
Muhammad Ismail Al Fatih ◽  
Alya Nabila ◽  
Nurhakimah Norhashim ◽  
Mohd Nadzeri Omar
Keyword(s):  
Machine Learning ◽  
Emotion Recognition ◽  
Real Time ◽  
Learning Algorithm ◽  
Recognition System ◽  
Machine Learning Algorithm

Research on Face Recognition Technology of Real-Time Video High Performance Similarity

2015 ◽  
Vol 713-715 ◽  
pp. 2160-2164
Author(s):  
Zhao Nan Yang ◽  
Shu Zhang
Keyword(s):  
Feature Extraction ◽  
Face Recognition ◽  
Real Time ◽  
High Performance ◽  
Learning Algorithm ◽  
Recognition Rate ◽  
Recognition System ◽  
Image Preprocessing ◽  
Face Images ◽  
Face Recognition System

A new similarity measurement standard is proposed, namely background similarity matching. Learning algorithm based on kernel function is utilized in the method for feature extraction and classification of face image. Meanwhile, a real-time video face recognition method is proposed, image binary algorithm in similarity calculation is introduced, and a video face recognition system is designed and implemented [1-2]. The system is provided with a camera to obtain face images, and face recognition is realized through image preprocessing, face detection and positioning, feature extraction, feature learning and matching. Design, image preprocessing, feature positioning and extraction, face recognition and other major technologies of face recognition systems are introduced in details. Lookup mode from top down is improved, thereby improving lookup accuracy and speed [3-4]. The experimental results showed that the method has high recognition rate. Higher recognition rate still can be obtained even for limited change images of face images and face gesture with slightly uneven illumination. Meanwhile, training speed and recognition speed of the method are very fast, thereby fully meeting real-time requirements of face recognition system [5]. The system has certain face recognition function and can well recognize front faces.

scholarly journals Implementation of an Obstacle Recognition System for the Blind

2019 ◽  
Vol 10 (1) ◽  
pp. 282 ◽  
Author(s):  
Soobin Ou ◽  
Huijin Park ◽  
Jongwoo Lee
Keyword(s):  
Neural Network ◽  
Remote Control ◽  
Object Detection ◽  
Convolutional Neural Network ◽  
Real Time ◽  
Support Systems ◽  
Acoustic Signals ◽  
Recognition System ◽  
Single Shot ◽  
Program Interface

The blind encounter commuting risks, such as failing to recognize and avoid obstacles while walking, but protective support systems are lacking. Acoustic signals at crosswalk lights are activated by button or remote control; however, these signals are difficult to operate and not always available (i.e., broken). Bollards are posts installed for pedestrian safety, but they can create dangerous situations in that the blind cannot see them. Therefore, we proposed an obstacle recognition system to assist the blind in walking safely outdoors; this system can recognize and guide the blind through two obstacles (crosswalk lights and bollards) with image training from the Google Object Detection application program interface (API) based on TensorFlow. The recognized results notify the blind through voice guidance playback in real time. The single shot multibox detector (SSD) MobileNet and faster region-convolutional neural network (R-CNN) models were applied to evaluate the obstacle recognition system; the latter model demonstrated better performance. Crosswalk lights were evaluated and found to perform better during the day than night. They were also analyzed to determine if a client could cross at a crosswalk, while the locations of bollards were analyzed by algorithms to guide the client by voice guidance.

Sign in / Sign up

Export Citation Format

Share Document