Artificial neural network-based classification of body movements in ambulatory ECG signal
1G. H. Patel College of Engineering and Technology, V.V. Nagar , Gujarat , India.
Insights
This study developed an adaptive filtering method to detect motion artifacts in ambulatory electrocardiogram (ECG) signals. This technique helps differentiate cardiac signals from body movements for improved heart condition diagnosis.
Area of Science:
- Biomedical Engineering
- Cardiology
- Signal Processing
Background:
- Ambulatory electrocardiogram (ECG) monitoring captures heart activity during daily routines.
- ECG signals during normal activities are often contaminated by motion artifacts from body movements.
- Accurate detection of these artifacts is crucial for reliable cardiac diagnosis.
Purpose of the Study:
- To analyze ambulatory ECG signals for detecting various motion artifacts caused by physical activities.
- To develop and apply an adaptive filtering approach for motion artifact detection.
Main Methods:
- ECG signals were recorded from five healthy subjects using a BIOPAC MP 36 system.
- Subjects performed various movements: arm raises, waist twisting, and sit-to-stand transitions.
- An adaptive filter was employed to extract motion artifact components from the ECG data.
- Gabor transform was used to extract features from the motion artifact signals.
- An artificial neural network (ANN) was trained using these features for body movement classification.
Main Results:
- The adaptive filter successfully extracted motion artifact components from ambulatory ECG signals.
- Features extracted using Gabor transform enabled the classification of different body movements.
- The artificial neural network achieved classification of body movements based on extracted artifact features.
Conclusions:
- Adaptive filtering is an effective method for isolating motion artifacts in ambulatory ECG.
- Feature extraction and ANN classification can identify specific body movements from ECG artifact data.
- This approach holds potential for enhancing the accuracy of cardiac diagnosis in ambulatory settings.
Abstract:
Abstract Ambulatory ECG monitoring provides electrical activity of the heart when a person is involved in doing normal routine activities. Thus, the recorded ECG signal consists of cardiac signal along with motion artifacts introduced due to a person's body movements during routine activities. Detection of motion artifacts due to different physical activities might help in further cardiac diagnosis. Ambulatory ECG signal analysis for detection of various motion artifacts using adaptive filtering approach is addressed in this paper. We have used BIOPAC MP 36 system for acquiring ECG signal. The ECG signals of five healthy subjects (aged between 22-30 years) were recorded while the person performed various body movements like up and down movement of the left hand, up and down movement of the right hand, waist twisting movement while standing and change from sitting down on a chair to standing up movement in lead I configuration. An adaptive filter-based approach has been used to extract the motion artifact component from the ambulatory ECG signal. The features of motion artifact signal, extracted using Gabor transform, have been used to train the artificial neural network (ANN) for classifying body movements.
