Tractable maximum likelihood estimation for latent structure influence models with applications to eeg & ecog processing
Published in IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023
This paper introduces a new tractable maximum likelihood estimation framework for Latent Structure Influence Models (LSIMs), which are a type of Coupled Hidden Markov Model. The work addresses the computational challenges associated with parameter estimation in these complex models and demonstrates applications in EEG and ECoG signal processing. The proposed method significantly improves the efficiency of parameter estimation while maintaining accuracy, making LSIMs more practical for real-world biomedical signal processing applications.
The work represents a significant theoretical advancement in statistical signal processing with direct applications to brain signal analysis and interpretation.
Recommended citation: Karimi, S., & Shamsollahi, M. B. (2023). "Tractable maximum likelihood estimation for latent structure influence models with applications to eeg & ecog processing." IEEE Transactions on Pattern Analysis and Machine Intelligence.
Download Paper