Comparative Analysis of Machine Learning Algorithms along with Classifiers for AF Detection using a Scale

In this paper, we present an implementation of a smart scale that can measure a subject's weight, heart rate and detect atrial fibrillation (AF). For weight measurement, four load cell sensors are used. For measuring heart rates and detecting AF, PSL-iECG2 is used. Load cell sensors and PSL-iEC...

Full description

Saved in:
Bibliographic Details
Published in2019 International Conference on Artificial Intelligence in Information and Communication (ICAIIC) pp. 427 - 429
Main Authors Kim, Hyun-Woo, Lee, Keonsoo, Moon, Chanki, Nam, Yunyoung
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.02.2019
Subjects
Atrial fibrillation
ECG
Electrocardiography
Heart rate
Intelligent sensors
Low pass filters
Smart Scale
Weight measurement
Online AccessGet full text

Cover

More Information
Summary:In this paper, we present an implementation of a smart scale that can measure a subject's weight, heart rate and detect atrial fibrillation (AF). For weight measurement, four load cell sensors are used. For measuring heart rates and detecting AF, PSL-iECG2 is used. Load cell sensors and PSL-iECG2 are connected to Arduino Uno. As Arduino Uno has not enough computing power to analyze ECG signals and determine AF, Arduino Uno is connected to smartphone in Bluetooth. From the ECG signals, R peaks are extracted and using the R-R intervals, heart rates are calculated. AF is detected using RMSSD and Shannon entropy extracted from R-R intervals. We evaluate three classifiers that are kNN, DT, and NNs. The accuracies of each classifier for detecting AF are 83.7%, 83.7%, and 89.1%, respectively.
DOI:10.1109/ICAIIC.2019.8669084