DLGC: dictionary learning based Granger causal discovery for cortico-muscular coupling
File(s)DLGC_camera_ready.pdf (642.35 KB)
Accepted version
Author(s)
Abbas, Farwa
McClelland, Verity
Cvetkovic, Zoran
Dai, Wei
Type
Conference Paper
Abstract
Investigating causal pathways between the brain and muscles is crucial for identifying biomarkers associated with movement disorders such as Parkinson’s disease, multiple sclerosis, and dystonia. The transmission of information from the brain to muscles is complicated by the background activities and various forms of noise and interference. Thus, extracting meaningful causal patterns from recorded sensor data presents a significant challenge. This paper presents a novel approach to disentangling causal information from physiological signals while addressing measurement noise and other forms of perturbations. We propose a dictionary learning based autoregressive model capable of extracting meaningful features from physiological signals while simultaneously eliminating noise. To efficiently solve the non-convex, non-smooth optimization problem inherent in our approach, we employ a recent second-order proximal algorithm that leverages a local surrogate function of the objective function to converge to a potentially better local minimum. Our experimental results, conducted on real physiological signals, demonstrate the effectiveness of our proposed method in disentangling causal information and mitigating noise, thereby advancing our understanding of brain-muscle interactions in movement control.
Date Issued
2024-08-26
Date Acceptance
2024-05-22
Citation
32nd European Signal Processing Conference EUSIPCO 2024, 2024, pp.1746-1750
ISBN
978-9-4645-9361-7
Publisher
EURASIP European Association For Signal Processing
Start Page
1746
End Page
1750
Journal / Book Title
32nd European Signal Processing Conference EUSIPCO 2024
Copyright Statement
Copyright ©2024 by IEEE. This is the author’s accepted manuscript made available under a CC-BY licence in accordance with Imperial’s Research Publications Open Access policy (www.imperial.ac.uk/oa-policy)
Identifier
https://eurasip.org/Proceedings/Eusipco/Eusipco2024/pdfs/0001746.pdf
Source
32nd European Conference on Signal Processing (EUSIPCO 2024)
Publication Status
Published
Start Date
2024-08-26
Finish Date
2024-08-30
Coverage Spatial
Lyon, France
Date Publish Online
2024-08-26