An Efficient Deep Learning Framework for ECG and EEG Signal Classification in Embedded Healthcare Systems
Main Article Content
Abstract
Biomedical signal classification has become an important area of research in modern healthcare because ECG and EEG signals provide valuable information about the functional condition of the heart and the brain. ECG signals are widely used for detecting arrhythmia, abnormal heartbeat, myocardial infarction, and other cardiovascular disorders, while EEG signals are useful for identifying epileptic seizures, brain activity patterns, sleep disorders, and neurological abnormalities. However, manual interpretation of ECG and EEG signals is difficult, time-consuming, and dependent on expert knowledge because these signals are nonlinear, time-varying, and affected by noise and artifacts. To overcome these limitations, this paper presents an efficient deep learning framework for ECG and EEG signal classification in embedded healthcare systems. The proposed framework focuses on automated signal preprocessing, feature learning, classification, and embedded deployment. Deep learning models such as CNN, RNN, LSTM, and hybrid CNN-LSTM are suitable for learning spatial and temporal patterns from biomedical signals. CNN models can extract important waveform features, while LSTM models can learn time-based dependencies in sequential ECG and EEG data. The framework also emphasizes lightweight model design, model optimization, quantization, and pruning so that the trained model can be deployed on embedded healthcare devices with limited memory, processing power, and battery capacity. Integration with wearable ECG and EEG systems, IoT-based healthcare platforms, and edge computing can enable real-time monitoring, faster diagnosis, and immediate alert generation in critical conditions such as arrhythmia and epileptic seizure. This study highlights that deep learning-based ECG and EEG classification can support smart healthcare, remote patient monitoring, telemedicine, and preventive diagnosis. The proposed approach can assist healthcare professionals by reducing manual workload, improving diagnostic consistency, and providing early detection of cardiovascular and neurological abnormalities.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
References
Acharya, U. R., Oh, S. L., Hagiwara, Y., Tan, J. H., & Adeli, H. (2018). Deep convolutional neural network for the automated detection and diagnosis of seizure using EEG signals. Computers in Biology and Medicine, 100, 270–278.
Gao, J., Zhang, H., Lu, P., & Wang, Z. (2019). An effective LSTM recurrent network to detect arrhythmia on imbalanced ECG dataset. Journal of Healthcare Engineering, 2019, 6320651.
Goldberger, A. L., Amaral, L. A. N., Glass, L., Hausdorff, J. M., Ivanov, P. C., Mark, R. G., Mietus, J. E., Moody, G. B., Peng, C. K., & Stanley, H. E. (2000). PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals. Circulation, 101(23), e215–e220.
Greco, L., Percannella, G., Ritrovato, P., Tortorella, F., & Vento, M. (2020). Trends in IoT based solutions for health care: Moving AI to the edge. Pattern Recognition Letters, 135, 346–353.
Hannun, A. Y., Rajpurkar, P., Haghpanahi, M., Tison, G. H., Bourn, C., Turakhia, M. P., & Ng, A. Y. (2019). Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network. Nature Medicine, 25(1), 65–69.