Optimal AdaBoost kernel support vector machine for monitoring arrhythmia patients utilizing Internet of Things‐cloud environment

Summary In general, heart disease is considered as the most severe disease that results in high mortality rate globally. An arrhythmia is one type of heart disease caused due to asymmetrical heartbeat rhythm rate (i.e., heartbeat will be too slow or too fast). The generation of IoT devices as well a...

Full description

Saved in:
Bibliographic Details
Published in:Concurrency and computation 2022-12, Vol.34 (27), p.n/a
Main Author: Hemalatha, M.
Format: Article
Language:English
Subjects:
Accuracy
AdaBoost kernel support vector machine
Algorithms
Arrhythmia
Cardiac arrhythmia
Cardiovascular disease
cloud
Cloud computing
ECG signal
Emergency vehicles
fog
Heart diseases
Internet of Things
IoT
Kernels
Optimization
remora
Rhythm
sensor
Support vector machines
Time lag
Wearable technology
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Summary In general, heart disease is considered as the most severe disease that results in high mortality rate globally. An arrhythmia is one type of heart disease caused due to asymmetrical heartbeat rhythm rate (i.e., heartbeat will be too slow or too fast). The generation of IoT devices as well as ECG signals is capable of tracking the heart rhythm of the patients consistently. Even though, analyzing ECG signals using cloud‐based techniques achieves a certain accuracy level with high latency. Then by evaluating the ECG signals with fog‐based approaches minimizes the latency but the computing capability is minimum. Therefore, wearable devices and fog devices are linked directly to attain high service quality with minimum latency. To conquer such drawbacks, this article proposes a novel AdaBoost kernel support vector machine‐based remora optimization (AKSVM based RO) algorithm to analyze the ECG signals and to initiate the crisis with minimum time delay. The proposed approach predicts the ECG signals of arrhythmia affected persons from an IoT wearable device. In addition to this, the proposed AKSVM‐RO approach is more feasible to deploy in fog environment. Also, it assists in optimizing the time delay in calling the ambulance service during emergency situations. Finally, the experimental investigations are conducted for various approaches with respect to simulation measures to minimize the latency and accuracy of the proposed system.
ISSN:1532-0626
1532-0634
DOI:10.1002/cpe.7298