Related Experiment Videos
Classification of homomorphic segmented phonocardiogram signals using grow and learn network
Cota Navin Gupta1, Ramaswamy Palaniappan, Sundaram Swaminathan
1Biomedical Engineering Research Center, Nanyang Technological University, Singapore-639815 (phone: 65- 91496723 ; fax: 65-67920415; e-mail: cnavin_gupta@ pmail.ntu.edu.sg).
Summary
This study presents a novel algorithm for segmenting and classifying heart sounds from Phonocardiogram (PCG) signals. The method achieves high accuracy in identifying normal and abnormal heart sounds without needing a reference signal.
Area of Science:
- Biomedical Engineering
- Signal Processing
- Artificial Intelligence
Background:
- Phonocardiogram (PCG) signal analysis is crucial for diagnosing cardiac conditions.
- Accurate segmentation and classification of heart sounds remain challenging.
- Existing methods often require reference signals, limiting their applicability.
Purpose of the Study:
- To develop an automated algorithm for segmenting cardiac cycles from PCG signals.
- To classify heart sounds into Normal (N), Systolic murmur (S), and Diastolic murmur (D).
- To evaluate the performance of Homomorphic filtering, K-means clustering, and Grow and Learn (GAL) neural network for PCG analysis.
Main Methods:
- Segmentation of single cardiac cycles using Homomorphic filtering and K-means clustering.
- Feature extraction using Daubechies-2 wavelet detail coefficients.
- Classification of segmented heart sounds using a Grow and Learn (GAL) neural network.
Main Results:
- The proposed segmentation algorithm achieved 90.45% performance.
- The GAL network achieved a classification accuracy of 97.02% for heart sound classification.
- The developed method successfully segmented and classified PCG signals without a reference signal.
Conclusions:
- Homomorphic filtering and K-means clustering provide effective segmentation of PCG signals.
- The GAL neural network offers high accuracy for classifying heart sounds.
- This approach enables automated, reference-free analysis of PCG signals for cardiac diagnostics.
Related Concept Videos
01:30Classification of Signals
In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
01:26Classification of Systems-I
Linearity is a system property characterized by a direct input-output relationship, combining homogeneity and additivity.
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as: