An efficient graph structure inference strategy based on random walk model on graph Application to functional brain networks

S.A.-M. Al-Ali (1) , M. Youssf (1) , J. Rizkallah (2) , M. Hassan (2) , Ahmad Karfoul (2)

1 Al-Baath University [Homs]
2 LTSI - Laboratoire Traitement du Signal et de l'Image

A new strategy to solve the graph structure estimation problem from a noisy observed dependency matrix is proposed in this paper. It relies on an efficient inversion of the random walk model on graph employed to model the latter matrix. To this end, the sparsity assumption of the graph Laplacian associated to the target graph structure is optimally dealt with during the optimization process. The efficiency of the proposed algorithm is confirmed using both synthetic data and also using real electroencephalographic (EEG) signals in the context of inferring functional brain network. © 2019 IEEE.

Keywords: ADMM; brain connectivity; Graph inference; graph Laplacian; random walk on graph; sparsity

Domains: Life Sciences [q-bio]; Bioengineering

S.A.-M. Al-Ali, M. Youssf, J. Rizkallah, M. Hassan, Ahmad Karfoul. An efficient graph structure inference strategy based on random walk model on graph Application to functional brain networks. 5th International Conference on Advances in Biomedical Engineering, ICABME 2019, Oct 2019, Tripoli, Lebanon. pp.8940234, ⟨10.1109/ICABME47164.2019.8940234⟩. ⟨hal-02472487⟩