top of page

Publications

Journal Articles (Total: 03)

  1. S. S Dash and M. K. Nath, Non-Invasive Techniques for fECG Analysis in Fetal Heart Monitoring: A Systematic Review, Signals (MDPI), Vol. 6, Issue 4, pp. 1- 39 (2025). (Indexed in Scopus & ESCI)
    DOI:     https://doi.org/10.3390/signals6040061

  2. K. Mookkandi, M. K. Nath, S. S. Dash, M. Mishra, and R. Blange, A Robust Lightweight Vision Transformer for Classification of Crop Diseases, AgriEngineering (MDPI), Vol. 7, Issue 8, pp. 1- 31 (2025). (Indexed in Scopus  & ESCI)
    DOI: https://doi.org/10.3390/agriengineering7080268

  3. S. S. Dash, M. K. Nath, A novel approach for detecting fetal QRS and estimating fetal heart rate from abdominal ECG using EMD and wavelet decomposition, Circuits, Systems, and  Signal Processing (CSSP) (Springer), Vol. 44, pp. 9209–9232 (2025). (Indexed in Scopus & SCIE)
    DOI: https://doi.org/10.1007/s00034-025-03215-5

Conference Proceedings (Total: 03)

  1.  M. K. Nath, M. Tabdula, N. K. Uppu, V. Gajjala, and S. S. Dash, Emotion Recognition from ECG Signals Using Deep Neural Networks, Proceedings of the 6th International Conference on Data Science and Applications (ICDSA 2025), Lecture Notes in Networks and Systems (Springer), Vol. , pp. 1- (2025). (Indexed in Scopus)
    DOI:     https://doi.org/10.1007/978-3-032-12827-0_10

  2. S. S. Dash, A. B. Varghese, M. K. Nath, Computation of Fetal Heart Rate Variability from Abdominal ECG Using Adaptive Filtering and Independent Component Analysis, Proceedings of the 5th International Conference on Computer Vision and Robotics (CVR 2025), Lecture Notes in Networks and Systems (Springer), Vol. 1644, pp. 85-99 (2025). (Indexed in Scopus)
    DOI: https://doi.org/10.1007/978-3-032-06253-6_7

  3. S. S. Dash, M. K. Nath, T. Anbalagan, Identification of FECG from AECG Recordings using ICA over EMD, Proceedings of the 5th International Conference on Medical Imaging and Computer-Aided Diagnosis (MICAD 2023), Lecture Notes in Electrical Engineering (Springer), Vol. 1166, pp. 236-248 (2024). (Indexed in Scopus)
    DOI: https://doi.org/10.1007/978-981-97-1335-6_21

Projects

  1. A customized DL model for identification and classification of fetal ECG signal 
    Performance: Accuracy of 100% with the PAF database and 98.75% for the FECGDARHA database.

  2. Novel fECG extraction technique utilizing TFA and NN
    Performance: Accuracy of 100% with the FECGDARHA database using pre-trained networks.

  3. Estimation of blood pressure using ML techniques
    Description: Prediction of BP and blood glucose level using ML algorithms (Random Forest, 

  4. Advancements In Non-Invasive Techniques For Monitoring Fetal Heart Abnormalities Through FECG Analysis: A Comprehensive Review
    Description: This project highlights the significance of fetal ECG (fECG) extraction from abdominal electrocardiogram (aECG) recordings and examines various algorithms for achieving clean fECG, along with their associated limitations.

  5. Extraction of fECG signals from aECG using EMD and WD
    Performance: Accuracy of 100% for mECG detection and 88.9% for fECG detection using the FECGDARHA database.

  6. Identification of FECG from AECG Recordings using ICA over EMD
    Performance metric: Kurtosis 

  7. Applications of Comb Filter

bottom of page