Prabhu Sethuramalingam

Work place: Department of Mechanical Engineering, SRM Institute of Science and Technology, Kattankullathur, Chennai-603203, India

E-mail: prabhus@srmist.edu.in

Website: https://orcid.org/0000-0003-0707-2720

Research Interests:

Biography

Prabhu Sethuramalingam attained his Bachelor's in Mechanical Engineering from Bharathiar University, India, in 1996, and subsequently earned a Master's in Production Engineering from Madurai Kamaraj University in 2000. Presently, he serves as a Professor in the Department of Mechanical Engineering at SRM Institute of Science and Technology, Chennai, India. With a comprehensive background, he brings 3.5 years of industrial experience as a Production Engineer and an impressive 25 years in teaching and research. Additionally, he has garnered 4.5 years of experience as the Head of the Mechanical Department. Prof.Prabhu Sethuramalingam has been recognized with the Best Teacher Award and the Best Project Award for his notable contributions. As a prolific author, he has been the corresponding author for 127 international journal papers, 56 international conference papers, and 20 national conference papers. His work has resulted in the publication of 2 patents and 6 Patents granted, with a notable presence in Scopus Citations, boasting 1202 citations and an H-index of 20 and Google scholar citation of 2304 with an H-index of 27 and i-10 Index of 61. Dr.S.Prabhu's research interests span a wide spectrum, encompassing Artificial Intelligence, Machine Learning, Optimization, Fuzzy Logic, Robotics, Data Science, Nanotechnology, and Nanomachining. Currently, he is actively guiding seven Ph.D. research scholars, and he has successfully mentored three Ph.D. scholars in the field of Carbon Nanotube-based applications in Cutting Tools and Grinding Tools, Silicon Machining, FGM Composite, and Robotics with Machine Learning.

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

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

DOI: https://doi.org/10.5815/ijigsp.2026.01.05, Pub. Date: 8 Feb. 2026

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.

[...] Read more.
Other Articles