Sanghamitra Subhadarsini Dash


I am a signal-processing enthusiast!

"The worst thing you can do to yourself is 

not become the person that you could be in this lifetime."



EmailLinkLinkedInLinkLinkLink

Thanks for dropping by!

My name is Sanghamitra Subhadarsini Dash, and I am a third-year undergraduate student at the esteemed National Institute of Technology Puducherry in India. I am pursuing a Bachelor of Technology degree in Electronics and Communication Engineering, with an anticipated graduation in 2026.

I aspire to build a career in research, specifically in the field of signal processing. I believe that my diverse cultural and academic experiences in India provide a unique perspective that would benefit any team. With my unwavering dedication and expertise, I am confident in my ability to contribute significantly to organizations that prioritize innovation and excellence.

Area of research

Signal Processing  -  Biomedical signal analysis  -  Deep learning and neural networks

Projects and Internships

Extraction of FECG signals from AECG using EMD and Wavelet Transform (Biomedical Signal Processing)

NIT Puducherry, Karaikal

 November 2023 ‑ April 2024

The extraction of a clean fECG signal through a non‑invasive method is essential due to various interfering noises. This study aims to provide a robust methodology for extracting clear and accurate fECG from abdominal ECG (aECG), including fECG, mECG, and noises. The proposed methodology consists of empirical mode decomposition (EMD) and wavelet decomposition (WD) to identify different signal frequency components.

Identification of FECG from AECG Recordings using ICA over EMD (Biomedical Signal Processing) (Published Work)

NIT Puducherry, Karaikal

 June 2023 ‑ January 2024

Extraction of fetal ECG (fECG) signal is crucial for monitoring the fetus’s health during pregnancy and for early diagnosis of heart abnormalities, which can lead to increased infant mortality rate and post‑natal complications. This paper focuses on a robust approach for fECG extraction using empirical mode decomposition (EMD), independent component analysis (ICA), and FIR filtering. The technique has been validated on simulated signals and applied to fECG synthetic data and aECG data collected from PhysioBank ATM.