Prabhat Mahanti

Dr. Prabhat Mahanti


Research Focus & Metrics

Academic Career Length

18Years (2009-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
8 April 2016 in International Journal of Intelligent Systems and Applications
Verified
Journal Article
Open access
PDF file
Sudip Kumar SahanaSudip Kumar Sahana
Sudip Kumar Sahana
MAMohammad Al-Fayoumi
Mohammad Al-Fayoumi
PMPrabhat Mahanti
Prabhat Mahanti
It is well known that multicast routing is combinatorial problem finds the optimal path between source destination pairs. Traditional approaches solve this problem by establishment of the spanning tree for the network which is mapped as an undirected weighted graph. This paper proposes a Modified Ant Colony Optimization (MACO) algorithm which is based on Ant Colony System (ACS) with some modification in the configuration of starting movement and in local updation technique to overcome the basic limitations of ACS such as poor initialization and slow convergence rate. It is shown that the proposed Modified Ant Colony Optimization (MACO) shows better convergence speed and consumes less time than the conventional ACS to achieve the desired solution.

23 February 2025 in Future Internet
Verified
Journal Article
Open access
PDF file
RMRashmi Nagawara Muralinath
Rashmi Nagawara Muralinath
VPVishwambhar Pathak
Vishwambhar Pathak
PMPrabhat Mahanti
Prabhat Mahanti
Classification of neurocognitive states from Electroencephalography (EEG) data is complex due to inherent challenges such as noise, non-stationarity, non-linearity, and the high-dimensional and sparse nature of connectivity patterns. Graph-theoretical approaches provide a powerful framework for analysing the latent state dynamics using connectivity measures across spatio-temporal-spectral dimensions. This study applies the graph Koopman embedding kernels (GKKE) method to extract latent neuro-markers of seizures from epileptiform EEG activity. EEG-derived graphs were constructed using correlation and mean phase locking value (mPLV), with adjacency matrices generated via threshold-binarised connectivity. Graph kernels, including Random Walk, Weisfeiler–Lehman (WL), and spectral-decomposition (SD) kernels, were evaluated for latent space feature extraction by approximating Koopman spectral decomposition. The potential of graph Koopman embeddings in identifying latent metastable connectivity structures has been demonstrated with empirical analyses. The robustness of these features was evaluated using classifiers such as Decision Trees, Support Vector Machine (SVM), and Random Forest, on Epilepsy-EEG from the Children’s Hospital Boston’s (CHB)-MIT dataset and cognitive-load-EEG datasets from online repositories. The classification workflow combining mPLV connectivity measure, WL graph Koopman kernel, and Decision Tree (DT) outperformed the alternative combinations, particularly considering the accuracy (91.7%) and F1-score (88.9%), The comparative investigation presented in results section convinces that employing cost-sensitive learning improved the F1-score for the mPLV-WL-DT workflow to 91% compared to 88.9% without cost-sensitive learning. This work advances EEG-based neuro-marker estimation, facilitating reliable assistive tools for prognosis and cognitive training protocols.

12 July 2018 in Pattern Recognition Letters
Verified
Journal Article
Closed access
ZKZubair Khan
Zubair Khan
SKShishir Kumar
Shishir Kumar
EREdel B. García Reyes
Edel B. García Reyes
PMPrabhat Mahanti
Prabhat Mahanti


11 July 2019 in Multimedia Tools and Applications
Verified
Journal Article
Closed access
PDF file
SKShishir Kumar
Shishir Kumar
PMPrabhat Mahanti
Prabhat Mahanti
SWSu-Jing Wang
Su-Jing Wang

27 July 2018
Verified
Book Chapter
Closed access
PDF file
VJVinay Kumar Jain
Vinay Kumar Jain
SKShishir Kumar
Shishir Kumar
PMPrabhat Mahanti
Prabhat Mahanti