Uma. M.; Mohammed Javidh S.; Ruchi Shah; Prabhu Sethuramalingam; M. M. Reddy

Segment Wise EEG Signal Compression Using LSTM Auto Encoder for Enhanced Efficiency

PDF (1303KB), PP.70-87

Views: 0 Downloads: 0

Author(s)

Uma. M. ¹ Mohammed Javidh S. ¹ Ruchi Shah ¹ Prabhu Sethuramalingam ^2,* M. M. Reddy ³

1. Department of Computational Intelligence, SRM Institute of Science and Technology, Kattankulathur, Chennai 603203, India

2. Department of Mechanical Engineering, SRM Institute of Science and Technology, Kattankullathur, Chennai-603203, India

3. Department of Mechanical Engineering, Curtin University, Miri, CDT 250, Malaysia

* Corresponding author.

DOI: https://doi.org/10.5815/ijigsp.2026.01.05

Received: 22 Jun. 2025 / Revised: 23 Sep. 2025 / Accepted: 18 Dec. 2025 / Published: 8 Feb. 2026

Index Terms

EEG Signal Compression, LSTM Auto encoder, Segment-Wise Processing, Biomedical Signal Processing

Abstract

Efficient compression of electroencephalogram (EEG) signals is crucial for enabling real-time monitoring, storage, and transmission in various medical and non-medical applications. This paper presents a segment-wise processing approach using temporal modeling-based auto encoders for EEG signal compression. By leveraging models such as Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), Recurrent Neural Network (RNN), and Self-Attention, the proposed method effectively captures temporal dependencies in the EEG data. Segment-wise processing not only enhances compression efficiency but also significantly reduces the processing time of these sequence models. Extensive experiments demonstrate that GRU-based auto encoders offer the best performance, particularly at lower Data Reduction Factors (DRFs), achieving a minimal signal loss of 0.2% at a 50% compression ratio, making it suitable for medical applications. For non-medical scenarios, a higher compression ratio of 75% with a signal loss of 5.4% is found to be acceptable. The results indicate that the proposed approach achieves a favorable balance between compression efficiency, signal fidelity, and computational performance.

Cite This Paper

Uma. M., Mohammed Javidh S., Ruchi Shah, Prabhu Sethuramalingam, M. M. Reddy, "Segment Wise EEG Signal Compression Using LSTM Auto Encoder for Enhanced Efficiency", International Journal of Image, Graphics and Signal Processing(IJIGSP), Vol.18, No.1, pp. 70-87, 2026. DOI:10.5815/ijigsp.2026.01.05

Reference

[1]G. Antoniol and P. Tonella, “EEG data compression techniques,” IEEE Trans. Biomed. Eng., vol. 44, no. 2, pp. 105–114, 1997.
[2]K. Srinivasan, J. Dauwels, and M. R. Reddy, “A two-dimensional approach for lossless EEG compression,” Biomedical Signal Processing and Control, vol. 6, no. 4, pp. 387–394, 2011, doi: https://doi.org/10.1016/j.bspc.2011.01.004.
[3]R. Yousri et al., “A design for an efficient hybrid compression system for EEG data,” in Proc. IEEE Int. Conf. Electronic Engineering (ICEEM), 2021, pp. 1–4.
[4]I. Ullah, M. Hussain, ul Emad-Haq Qazi, and H. Aboalsamh, “An automated system for epilepsy detection using EEG brain signals based on deep learning approach,” Expert Systems with Applications, vol. 107, pp. 61–71, 2018, doi: https://doi.org/10.1016/j.eswa.2018.04.021.
[5]O. Yildirim, R. S. Tan, and U. R. Acharya, “An efficient compression of ECG signals using deep convolutional autoencoders,” Cognitive Systems Research, vol. 52, pp. 198–211, 2018, doi: https://doi.org/10.1016/j.cogsys.2018.07.004.
[6]X. Wang et al., “A feature enhanced EEG compression model using asymmetric encoding–decoding network,” J. Neural Eng., vol. 21, no. 3, 2024.
[7]H. Gürkan, U. Guz, and B. S. Binboga Yarman, “EEG signal compression based on classified signature and envelope vector sets,” Int. J. Circ. Theor. Appl., vol. 37, no. 4, pp. 351–363, 2009.
[8]S. Nagar and A. Kumar, “Orthogonal features-based EEG signals denoising using fractional and compressed one-dimensional CNN autoencoder,” IEEE Trans. Neural Syst. Rehabil. Eng., vol. 30, pp. 2474–2487, 2022.
[9]Hochreiter, S., & Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation, 9(8), 1735–1780.
[10]Guttag, J. (2010). CHB-MIT Scalp EEG Database (version 1.0.0). PhysioNet. https://doi.org/10.13026/C2K01R.
[11]Niedermeyer, E., & da Silva, F. L. (2004). Electroencephalography: Basic principles, clinical applications, and related fields. Lippincott Williams & Wilkins.
[12]Ioffe, S., & Szegedy, S. (2015). Batch Normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167.
[13]Ali Shoeb. Application of Machine Learning to Epileptic Seizure Onset Detection and Treatment. PhD Thesis, Massachusetts Institute of Technology, September 2009.
[14]D. Bank, N. Koenigstein, and R. Giryes, Autoencoders. 2021. [Online]. Available: https://arxiv.org/abs/2003.05991
[15]Najafi, T.; Jaafar, R.; Remli, R.; Wan Zaidi, W.A. A Classification Model of EEG Signals Based on RNN-LSTM for Diagnosing Focal and Generalized Epilepsy. Sensors 2022, 22, 7269. https://doi.org/ 10.3390/s22197269
[16]Shaheen, A.; Ye, L.; Karunaratne, C.; Seppänen, T. Fully-Gated Denoising Auto-Encoder for Artifact Reduction in ECG Signals. Sensors 2025, 25, 801. https://doi.org/ 10.3390/s25030801.

International Journal of Image, Graphics and Signal Processing (IJIGSP)