6533b828fe1ef96bd1288e12
RESEARCH PRODUCT
Estimation of brain connectivity through Artificial Neural Networks
Jlenia ToppiDonatella MattiaAntonio PietrabissaYuri AntonacciLaura Astolfisubject
Computer scienceFeature selection02 engineering and technologyConnectivity measurements03 medical and health sciences0302 clinical medicine0202 electrical engineering electronic engineering information engineeringArtificial neural networkbusiness.industryProcess (computing)BrainPattern recognitionElectroencephalographyCollinearityCausalityData pointCausality; Connectivity measurements; Physiological systems modeling - Multivariate signal processingNorm (mathematics)Physiological systems modeling - Multivariate signal processingRegression Analysis020201 artificial intelligence & image processingAnalysis of varianceArtificial intelligenceNeural Networks ComputerbusinessAlgorithms Brain Electroencephalography Regression Analysis Neural Networks Computer030217 neurology & neurosurgeryLinear equationAlgorithmsdescription
Among different methods available for estimating brain connectivity from electroencephalographic signals (EEG), those based on MVAR models have proved to be flexible and accurate. They rely on the solution of linear equations that can be pursued through artificial neural networks (ANNs) used as MVAR model. However, when few data samples are available, there is a lack of accuracy in estimating MVAR parameters due to the collinearity between regressors. Moreover, the assessment procedure is also affected by the lack of data points. The mathematical solution to these problems is represented by penalized regression methods based on l 1 norm, that can reduce collinearity by means of variable selection process. However, the direct application of l 1 norm during the training of an ANN does not result in an efficient learning process. With the introduction of the stochastic gradient descent-L1 (SGD-L1) it is possible to apply l 1 norm directly on the estimated weights in an efficient way. Even if ANNs has been used as MVAR model for brain connectivity estimation, the use of SGD-L1 algorithm has never been tested to this purpose when few data samples are available. In this work, we tested an approach based on ANNs and SGD-L1 on both surrogate and real EEG data. Our results show that ANNs can provide accurate brain connectivity estimation if trained with SGD-L1 algorithm even when few data samples are available.
| year | journal | country | edition | language |
|---|---|---|---|---|
| 2019-01-01 |