Parallel Factorization to Implement Group Analysis in Brain Networks Estimation
When dealing with complex functional brain networks, group analysis still represents an open issue. In this paper, we investigated the potential of an innovative approach based on PARAllel FActorization (PARAFAC) for the extraction of the grand average connectivity matrices from both simulated and r...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/3/1693 |
| _version_ | 1797623150377172992 |
|---|---|
| author | Andrea Ranieri Floriana Pichiorri Emma Colamarino Valeria de Seta Donatella Mattia Jlenia Toppi |
| author_facet | Andrea Ranieri Floriana Pichiorri Emma Colamarino Valeria de Seta Donatella Mattia Jlenia Toppi |
| author_sort | Andrea Ranieri |
| collection | DOAJ |
| description | When dealing with complex functional brain networks, group analysis still represents an open issue. In this paper, we investigated the potential of an innovative approach based on PARAllel FActorization (PARAFAC) for the extraction of the grand average connectivity matrices from both simulated and real datasets. The PARAFAC approach was solved using three different numbers of rank-one tensors (PAR-FACT). Synthetic data were parametrized according to different levels of three parameters: network dimension (NODES), number of observations (SAMPLE-SIZE), and noise (SWAP-CON) in order to investigate the way they affect the grand average estimation. PARAFAC was then tested on a real connectivity dataset, derived from EEG data of 17 healthy subjects performing wrist extension with left and right hand separately. Findings on both synthetic and real data revealed the potential of the PARAFAC algorithm as a useful tool for grand average extraction. As expected, the best performances in terms of FPR, FNR, and AUC were achieved for great values of sample size and low noise level. A crucial role has been revealed for the PAR-FACT parameter, revealing that an increase in the number of rank-one tensors solving the PARAFAC problem leads to an increase in FPR values and, thus, to a worse grand average estimation. |
| first_indexed | 2024-03-11T09:24:33Z |
| format | Article |
| id | doaj.art-db65ae57bca944efbb6d748edb0a7db6 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T09:24:33Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-db65ae57bca944efbb6d748edb0a7db62023-11-16T18:04:47ZengMDPI AGSensors1424-82202023-02-01233169310.3390/s23031693Parallel Factorization to Implement Group Analysis in Brain Networks EstimationAndrea Ranieri0Floriana Pichiorri1Emma Colamarino2Valeria de Seta3Donatella Mattia4Jlenia Toppi5Department of Computer, Control and Management Engineering, Sapienza University of Rome, Via Ariosto, 25, 00185 Rome, ItalyNeuroelectrical Imaging and Brain Computer Interface Lab, IRCCS Fondazione Santa Lucia, 00179 Rome, ItalyDepartment of Computer, Control and Management Engineering, Sapienza University of Rome, Via Ariosto, 25, 00185 Rome, ItalyDepartment of Computer, Control and Management Engineering, Sapienza University of Rome, Via Ariosto, 25, 00185 Rome, ItalyNeuroelectrical Imaging and Brain Computer Interface Lab, IRCCS Fondazione Santa Lucia, 00179 Rome, ItalyDepartment of Computer, Control and Management Engineering, Sapienza University of Rome, Via Ariosto, 25, 00185 Rome, ItalyWhen dealing with complex functional brain networks, group analysis still represents an open issue. In this paper, we investigated the potential of an innovative approach based on PARAllel FActorization (PARAFAC) for the extraction of the grand average connectivity matrices from both simulated and real datasets. The PARAFAC approach was solved using three different numbers of rank-one tensors (PAR-FACT). Synthetic data were parametrized according to different levels of three parameters: network dimension (NODES), number of observations (SAMPLE-SIZE), and noise (SWAP-CON) in order to investigate the way they affect the grand average estimation. PARAFAC was then tested on a real connectivity dataset, derived from EEG data of 17 healthy subjects performing wrist extension with left and right hand separately. Findings on both synthetic and real data revealed the potential of the PARAFAC algorithm as a useful tool for grand average extraction. As expected, the best performances in terms of FPR, FNR, and AUC were achieved for great values of sample size and low noise level. A crucial role has been revealed for the PAR-FACT parameter, revealing that an increase in the number of rank-one tensors solving the PARAFAC problem leads to an increase in FPR values and, thus, to a worse grand average estimation.https://www.mdpi.com/1424-8220/23/3/1693connectivity estimationtensor decompositionparallel factorizationgroup analysisEEGpartial directed coherence |
| spellingShingle | Andrea Ranieri Floriana Pichiorri Emma Colamarino Valeria de Seta Donatella Mattia Jlenia Toppi Parallel Factorization to Implement Group Analysis in Brain Networks Estimation Sensors connectivity estimation tensor decomposition parallel factorization group analysis EEG partial directed coherence |
| title | Parallel Factorization to Implement Group Analysis in Brain Networks Estimation |
| title_full | Parallel Factorization to Implement Group Analysis in Brain Networks Estimation |
| title_fullStr | Parallel Factorization to Implement Group Analysis in Brain Networks Estimation |
| title_full_unstemmed | Parallel Factorization to Implement Group Analysis in Brain Networks Estimation |
| title_short | Parallel Factorization to Implement Group Analysis in Brain Networks Estimation |
| title_sort | parallel factorization to implement group analysis in brain networks estimation |
| topic | connectivity estimation tensor decomposition parallel factorization group analysis EEG partial directed coherence |
| url | https://www.mdpi.com/1424-8220/23/3/1693 |
| work_keys_str_mv | AT andrearanieri parallelfactorizationtoimplementgroupanalysisinbrainnetworksestimation AT florianapichiorri parallelfactorizationtoimplementgroupanalysisinbrainnetworksestimation AT emmacolamarino parallelfactorizationtoimplementgroupanalysisinbrainnetworksestimation AT valeriadeseta parallelfactorizationtoimplementgroupanalysisinbrainnetworksestimation AT donatellamattia parallelfactorizationtoimplementgroupanalysisinbrainnetworksestimation AT jleniatoppi parallelfactorizationtoimplementgroupanalysisinbrainnetworksestimation |