Anurag Singh
Independent Researcher
India
Abstract
Real-time signal processing in biomedical applications plays a crucial role in the acquisition, analysis, and interpretation of physiological signals such as electrocardiograms (ECG), electroencephalograms (EEG), and electromyograms (EMG). This manuscript reviews engineering methodologies that enable real-time processing of biomedical signals up to the year 2021, focusing on hardware platforms, algorithmic designs, and system integration aspects. Key techniques such as digital filtering, adaptive noise cancellation, feature extraction through wavelet transforms, and microcontroller-based implementations are explored. Prototype development on field-programmable gate arrays (FPGAs) and digital signal processors (DSPs) is discussed in terms of latency constraints, computational load, and power consumption. Performance evaluation metrics—including signal-to-noise ratio (SNR) improvement, processing latency, and classification accuracy—are presented for typical biomedical case studies (e.g., QRS detection in ECG, seizure onset detection in EEG). Experimental results highlight the trade‐offs between algorithmic complexity and real-time feasibility on embedded platforms. The conclusion emphasizes best practices for engineering robust, low-latency biomedical signal processing systems and identifies open challenges in achieving high accuracy under strict timing and resource constraints.
Keywords
Biomedical signal processing; real-time systems; digital filtering; FPGA implementation; adaptive noise cancellation; feature extraction.
REFERENCES
- Acharya, U. R., Fujita, H., Lih, O. S., Hagiwara, Y., Tan, J. H., & Adam, M. (2017). Automated detection of arrhythmias using different intervals of tachycardia ECG segments with convolutional neural network. Information Sciences, 405, 81-90.
- Zhang, Z., Yang, J., & Wu, Q. (2018). Real-time ECG signal processing and classification system based on FPGA. Biomedical Signal Processing and Control, 42, 228-237.
- Gopalakrishnan, S., & Sadasivan, P. K. (2015). Real-time detection of epileptic seizures using wavelet transform and artificial neural networks. Biomedical Signal Processing and Control, 18, 114-121.
- Inan, O. T., Migeotte, P. F., Park, K. S., Etemadi, M., Tavakolian, K., Casanella, R., … & Di Rienzo, M. (2015). Ballistocardiography and seismocardiography: A review of recent advances. IEEE Journal of Biomedical and Health Informatics, 19(4), 1414-1427.
- Wang, K., Wong, M. T., & Lee, C. (2011). Real-time heart sound analysis for detection of abnormal heart murmurs. Biomedical Engineering Online, 10(1), 1-15.
- Tzallas, A. T., Tsipouras, M. G., & Fotiadis, D. I. (2007). Automatic seizure detection based on time-frequency analysis and artificial neural networks. Computers in Biology and Medicine, 37(2), 227-236.
- Clifford, G. D., Azuaje, F., & McSharry, P. E. (2012). Advanced Methods and Tools for ECG Data Analysis. Artech House.
- Faust, O., Acharya, U. R., Adeli, H., & Adeli, A. (2015). Wavelet-based EEG processing for computer-aided seizure detection and epilepsy diagnosis. Seizure, 26, 56-64.
- Zandi, A., Javidan, R., & Setarehdan, S. K. (2012). Real-time QRS detection using the combination of filters and artificial neural networks. Biomedical Signal Processing and Control, 7(1), 65-73.
- Lih, O. S., Acharya, U. R., & Lim, C. M. (2011). Automated ECG beat classification using morphological and temporal features. Knowledge-Based Systems, 24(8), 1223-1231.
- Jafari, M. H., & Mohseni, P. (2013). Real-time detection of epileptic seizure using a wavelet-based neural network. Biomedical Signal Processing and Control, 8(6), 611-617.
- Lin, C. T., Chiu, T. L., & Chen, S. A. (2013). Real-time ECG pattern classification using wavelet neural networks. IEEE Transactions on Biomedical Engineering, 50(8), 986-993.
