A model to find optimal percentage of training and testing data for efficient ECG analysis using neural network

Kartik Bhanot, Sateesh Kumar Peddoju, Tushar Bhardwaj

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Electrocardiogram (ECG) data is one of the most important physiological parameter for detecting heartbeat, emotions and stress levels of patients. The problem is to develop a model that can diagnose an ECG data efficiently with higher accuracy overtime. In this paper, Authors have proposed a model that identifies the percentage division of data so as to get the maximum possible accuracy for a particular dataset. For experimental purpose, the authors have used neural networks for the analysis of the standard and raw data taken from MIT-BIH long-term ECG database using R as a platform. The database is divided into different ratios of training and testing data and the model is trained to attain the best percentage division of the particular patient’s data based upon its accuracy.

Original languageEnglish
Pages (from-to)12-17
Number of pages6
JournalInternational Journal of Systems Assurance Engineering and Management
Volume9
Issue number1
DOIs
Publication statusPublished - 01-02-2018
Externally publishedYes

Fingerprint

Electrocardiography
Neural networks
Testing
Data base

All Science Journal Classification (ASJC) codes

  • Safety, Risk, Reliability and Quality
  • Strategy and Management

Cite this

@article{0001eff0783c45d9a02e266ac42194a8,
title = "A model to find optimal percentage of training and testing data for efficient ECG analysis using neural network",
abstract = "Electrocardiogram (ECG) data is one of the most important physiological parameter for detecting heartbeat, emotions and stress levels of patients. The problem is to develop a model that can diagnose an ECG data efficiently with higher accuracy overtime. In this paper, Authors have proposed a model that identifies the percentage division of data so as to get the maximum possible accuracy for a particular dataset. For experimental purpose, the authors have used neural networks for the analysis of the standard and raw data taken from MIT-BIH long-term ECG database using R as a platform. The database is divided into different ratios of training and testing data and the model is trained to attain the best percentage division of the particular patient’s data based upon its accuracy.",
author = "Kartik Bhanot and Peddoju, {Sateesh Kumar} and Tushar Bhardwaj",
year = "2018",
month = "2",
day = "1",
doi = "10.1007/s13198-015-0398-7",
language = "English",
volume = "9",
pages = "12--17",
journal = "International Journal of Systems Assurance Engineering and Management",
issn = "0975-6809",
publisher = "Springer India",
number = "1",

}

A model to find optimal percentage of training and testing data for efficient ECG analysis using neural network. / Bhanot, Kartik; Peddoju, Sateesh Kumar; Bhardwaj, Tushar.

In: International Journal of Systems Assurance Engineering and Management, Vol. 9, No. 1, 01.02.2018, p. 12-17.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A model to find optimal percentage of training and testing data for efficient ECG analysis using neural network

AU - Bhanot, Kartik

AU - Peddoju, Sateesh Kumar

AU - Bhardwaj, Tushar

PY - 2018/2/1

Y1 - 2018/2/1

N2 - Electrocardiogram (ECG) data is one of the most important physiological parameter for detecting heartbeat, emotions and stress levels of patients. The problem is to develop a model that can diagnose an ECG data efficiently with higher accuracy overtime. In this paper, Authors have proposed a model that identifies the percentage division of data so as to get the maximum possible accuracy for a particular dataset. For experimental purpose, the authors have used neural networks for the analysis of the standard and raw data taken from MIT-BIH long-term ECG database using R as a platform. The database is divided into different ratios of training and testing data and the model is trained to attain the best percentage division of the particular patient’s data based upon its accuracy.

AB - Electrocardiogram (ECG) data is one of the most important physiological parameter for detecting heartbeat, emotions and stress levels of patients. The problem is to develop a model that can diagnose an ECG data efficiently with higher accuracy overtime. In this paper, Authors have proposed a model that identifies the percentage division of data so as to get the maximum possible accuracy for a particular dataset. For experimental purpose, the authors have used neural networks for the analysis of the standard and raw data taken from MIT-BIH long-term ECG database using R as a platform. The database is divided into different ratios of training and testing data and the model is trained to attain the best percentage division of the particular patient’s data based upon its accuracy.

UR - http://www.scopus.com/inward/record.url?scp=85044260976&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85044260976&partnerID=8YFLogxK

U2 - 10.1007/s13198-015-0398-7

DO - 10.1007/s13198-015-0398-7

M3 - Article

VL - 9

SP - 12

EP - 17

JO - International Journal of Systems Assurance Engineering and Management

JF - International Journal of Systems Assurance Engineering and Management

SN - 0975-6809

IS - 1

ER -