Electrocardiogram sequences data analytics and classification using unsupervised and supervised machine learning algorithms

This paper explores the prediction of cardiovascular disease (CVD) through the classification of electrocardiogram (ECG) sequences using both supervised and unsupervised machine learning (ML) algorithms. ECG 5000 dataset is considered to perform essential data analytics, clustering, and classification, effectively categorizing ECG heartbeats into optimal groups to forecast CVD. The Elbow and Silhouette methods are applied to estimate optimal number of clusters within the dataset. Using K-means and hierarchical clustering algorithms, the data is grouped into two and five distinguishable clusters, with performance metrics indicating that two clusters are more viable. Subsequently, multiple supervised ML classifiers—including kernel classifiers, support vector machine (SVM), naïve Bayes (NB), decision trees (DT), k-nearest neighbor (KNN) and neural networks (NN)—are trained on the labeled and clustered datasets to ensure accurate classification of ECG sequences and anomaly detection. A novel modified ML classifier, kernel-SVM with Chi-Square (χ²) feature selection, is introduced and demonstrates exceptional performance, achieving an impressive accuracy of 0.9848, recall of 0.9973, and a training time of 1.6944 seconds, surpassing benchmarks from prior research. The results and discussion section includes a comparison of various algorithm performances, affirming that the proposed approach is an alternative to the complex deep learning (DL) and transformer-based models.

• Publication year

  2025

• Venue

  IAES International Journal of Artificial Intelligence (IJ-AI)

• Publication date

  2025-06-01

• Fields of study

  Not labeled

• Identifiers
  DOI 10.11591/ijai.v14.i3.pp2055-2071
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Advances in ECG and PCG-based cardiovascular disease classification: a review of deep learning and machine learning methods

  2024cited by this paper
• The Applications of Deep Learning in ECG Classification for Disease Diagnosis: A Systematic Review and Meta-Data Analysis

  2024influential reference
• ECG Arrhythmia Measurement and Classification for Portable Monitoring

  2024influential reference
• ECG-NET: A deep LSTM autoencoder for detecting anomalous ECG

  2023influential reference
• ECG Classification Using an Optimal Temporal Convolutional Network for Remote Health Monitoring

  2023influential reference
• Heart Disease and Stroke Statistics—2022 Update: A Report From the American Heart Association

  2022influential reference
• Robust Anomaly Detection in Time Series through Variational AutoEncoders and a Local Similarity Score

  2021influential reference
• Attention Autoencoder for Generative Latent Representational Learning in Anomaly Detection

  2021cited by this paper
• MED-NET: a novel approach to ECG anomaly detection using LSTM auto-encoders

  2021influential reference
• K-Means Clustering Algorithm Based Arrhythmic Heart Beat Detection in ECG Signal

  2021cited by this paper
• Statistical Learning Theory

  2021cited by this paper
• Effect of Distance Metrics in Determining K-Value in K-Means Clustering Using Elbow and Silhouette Method

  2020cited by this paper
• A review on deep learning methods for ECG arrhythmia classification

  2020cited by this paper
• LSTM-Based Auto-Encoder Model for ECG Arrhythmias Classification

  2020cited by this paper
• Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network

  2019cited by this paper
• A new approach for arrhythmia classification using deep coded features and LSTM networks

  2019cited by this paper
• Unsupervised representation learning and anomaly detection in ECG sequences

  2019influential reference
• Local Deep Field for Electrocardiogram Beat Classification

  2018cited by this paper
• Arrhythmia detection using deep convolutional neural network with long duration ECG signals

  2018cited by this paper
• Automated diagnosis of arrhythmia using combination of CNN and LSTM techniques with variable length heart beats

  2018cited by this paper
• A novel wavelet sequence based on deep bidirectional LSTM network model for ECG signal classification

  2018cited by this paper
• Anomaly Detection with Generative Adversarial Networks for Multivariate Time Series

  2018cited by this paper
• Research on Improved Depth Belief Network-Based Prediction of Cardiovascular Diseases

  2018cited by this paper
• A window-based time series feature extraction method

  2017cited by this paper
• LSTM Fully Convolutional Networks for Time Series Classification

  2017cited by this paper
• A deep convolutional neural network model to classify heartbeats

  2017cited by this paper
• Cardiac arrhythmia beat classification using DOST and PSO tuned SVM

  2016cited by this paper
• Anomaly detection in ECG time signals via deep long short-term memory networks

  2015cited by this paper
• Cardiac arrhythmia classification using hierarchical classification model

  2014cited by this paper
• Survey of Nearest Neighbor Techniques

  2010cited by this paper
• An empirical study of the naive Bayes classifier

  2001cited by this paper
• The Feature Selection Problem: Traditional Methods and a New Algorithm

  1992cited by this paper
• A survey of decision tree classifier methodology

  1991cited by this paper
• Neural networks for ECG classification

  1990cited by this paper

• No citing papers are available for this paper.