Back

Bayesian Functional Connectivity and Graph Convolutional Network for Working Memory Load Classification

Gangapuram, H.; Manian, V.

2024-05-05 bioengineering
10.1101/2024.05.02.592218 bioRxiv
Show abstract

Brain responses related to working memory originate from distinct brain areas and oscillate at different frequencies. EEG signals with high temporal correlation can effectively capture these responses. Therefore, estimating the functional connectivity of EEG for working memory protocols in different frequency bands plays a significant role in analyzing the brain dynamics with increasing memory and cognitive loads, which remains largely unexplored. The present study introduces a Bayesian structure learning algorithm to learn the functional connectivity of EEG in sensor space. Next, the functional connectivity graphs are taken as input to the graph convolutional network to classify the working memory loads. The intrasubject (subject-specific) classification performed on 154 subjects for six different verbal working memory loads produced the highest classification accuracy of 96% and average classification accuracy of 89%, outperforming state-of-the-art classification models proposed in the literature. Furthermore, the proposed Bayesian structure learning algorithm is compared with state-of-the-art functional connectivity estimation methods through intersubject and intrasubject statistical analysis of variance. The results also show that the alpha and theta bands have better classification accuracy than the beta band.

Matching journals

The top 7 journals account for 50% of the predicted probability mass.

1
Biomedical Signal Processing and Control
18 papers in training set
Top 0.1%
14.2%
2
Human Brain Mapping
295 papers in training set
Top 0.8%
8.3%
3
Journal of Neural Engineering
197 papers in training set
Top 0.4%
6.7%
4
NeuroImage
813 papers in training set
Top 2%
6.3%
5
PLOS ONE
4510 papers in training set
Top 29%
6.2%
6
IEEE Transactions on Neural Systems and Rehabilitation Engineering
40 papers in training set
Top 0.1%
4.8%
7
Scientific Reports
3102 papers in training set
Top 25%
4.8%
50% of probability mass above
8
IEEE Access
31 papers in training set
Top 0.1%
3.9%
9
Computers in Biology and Medicine
120 papers in training set
Top 0.7%
3.9%
10
Frontiers in Neuroscience
223 papers in training set
Top 1%
3.6%
11
Network Neuroscience
116 papers in training set
Top 0.3%
3.5%
12
Sensors
39 papers in training set
Top 0.6%
2.7%
13
IEEE Journal of Biomedical and Health Informatics
34 papers in training set
Top 0.8%
2.0%
14
Brain Topography
23 papers in training set
Top 0.1%
1.9%
15
Neurocomputing
13 papers in training set
Top 0.2%
1.8%
16
Neuroinformatics
40 papers in training set
Top 0.6%
1.5%
17
Communications Biology
886 papers in training set
Top 11%
1.5%
18
Bioengineering
24 papers in training set
Top 0.6%
1.5%
19
IEEE Transactions on Biomedical Engineering
38 papers in training set
Top 0.7%
1.1%
20
Journal of Neuroscience Methods
106 papers in training set
Top 1%
0.9%
21
Brain Connectivity
22 papers in training set
Top 0.2%
0.9%
22
PLOS Computational Biology
1633 papers in training set
Top 24%
0.8%
23
Brain and Behavior
37 papers in training set
Top 1%
0.8%
24
Progress in Neurobiology
41 papers in training set
Top 2%
0.7%
25
Computational and Structural Biotechnology Journal
216 papers in training set
Top 10%
0.7%
26
Advanced Science
249 papers in training set
Top 19%
0.7%
27
European Journal of Neuroscience
168 papers in training set
Top 2%
0.7%
28
Imaging Neuroscience
242 papers in training set
Top 4%
0.6%