Related Experiment Video
Updated: Jun 27, 2026

Using Wavelet Entropy to Demonstrate how Mindfulness Practice Increases Coordination between Irregular Cerebral and Cardiac Activities
Published on: May 10, 2017
Evaluation of Bubble Entropy Using Heart Rate Variability
Dimitrios Platakis1, Roberto Sassi2, George Manis1
1Department of Computer Science and Engineering, University of Ioannina, 45500 Ioannina, Greece.
Bubble entropy, a new entropy definition, effectively classifies cardiac RR time series. It outperforms Sample entropy, Approximate entropy, and Permutation entropy in accuracy and feature ranking for biomedical engineering applications.
Area of Science:
- Biomedical Engineering
- Complex Systems Analysis
- Information Theory
Background:
- Entropy measures are crucial for analyzing physiological time series, particularly RR intervals in electrocardiography.
- Existing entropy measures like Sample Entropy, Approximate Entropy, and Permutation Entropy have limitations in capturing complex signal dynamics.
- Bubble entropy offers a novel approach with a physical interpretation based on ordering vectors in an embedding space.
Purpose of the Study:
- To evaluate the efficacy of Bubble entropy in classifying cardiac RR time series.
- To compare Bubble entropy's performance against established entropy measures (Sample Entropy, Approximate Entropy, Permutation Entropy).
- To assess the utility of Bubble entropy as a feature for machine learning-based cardiac patient classification.
Main Methods:
- RR time series data from healthy individuals and cardiac patients were analyzed.
- Bubble entropy was calculated and compared with Sample entropy, Approximate entropy, and Permutation entropy.
- Machine learning classifiers (k-NN, SVM, Logistic Regression, Gaussian Naive Bayes) were employed for classification tasks.
- Feature evaluation methods were used to assess the discriminative power of each entropy measure.
Main Results:
- Bubble entropy demonstrated superior classification accuracy compared to Sample entropy, Approximate entropy, and Permutation entropy.
- Feature ranking analysis indicated that Bubble entropy provides more effective features for distinguishing between healthy and patient groups.
- The proposed Bubble entropy metric showed robust performance across different machine learning models.
Conclusions:
- Bubble entropy is a promising new metric for the analysis of biomedical time series, particularly RR intervals.
- Its ability to accurately classify cardiac conditions suggests potential clinical applications in cardiology.
- Bubble entropy offers advantages over traditional entropy measures in terms of both discriminatory power and feature interpretability.
Related Concept Videos
Factors Influencing Heart Rate
Let us explore the significant factors affecting heart rate, including age, body temperature, posture, acute pain, chemical influences,...
Special considerations while measuring oxygen saturation
Ensuring accuracy in vital sign recordings while prioritizing patient comfort and minimizing anxiety is important.
Assessment of Ventilation I: Respiratory Rate
A Ventilation assessment is critical for monitoring a patient's health status. Respiration, one of the most accessible vital signs, provides insights into the function of numerous body systems and can indicate serious health issues, such as brainstem injuries from head trauma.
Critical Guidelines for Assessing Ventilation:
Correlation between ECG and Cardiac Cycle
A cardiac action potential originates in the SA node and spreads throughout the atria and the AV node in approximately 0.03 seconds. This results in the P wave in an ECG and triggers atrial contraction. The action potential is then briefly slowed at the AV node, allowing the atria to contract and fill the ventricles with blood before...
Pulse rhythm
Conversely, an irregular pulse pattern is termed dysrhythmia, stemming from disruptions in cardiac muscle...

