Kernel-Based Relevance Analysis with Enhanced Interpretability for Detection of Brain Activity Patterns

Álvarez-Meza, Andrés Marino; Gutiérrez, Álvaro Ángel Orozco; Castellanos-Domínguez, Germán

doi:10.3389/fnins.2017.00550

Cited by 18 publications

(11 citation statements)

References 65 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the grid search needed for tuning the free parameters increases the computational complexity exponentially to

, where

are related to grids defined over characteristic and similarity kernel widths. See that the performance of AKL-ABC depends on

and G ; however, in practice, the CKA and LNS algorithm have a fast convergence [ 32 , 35 ].…”

Section: Resultsmentioning

confidence: 99%

“…Concerning the feature space

, we assess the similarity via the Gaussian kernel function

, to build the matrix

where

and

is a feature mapping. Here, to perform the pairwise comparison between simulations in

we use also the Mahalanobis distance of the form [ 32 ]:

where

stands for the inverse covariance matrix of

and

(

). In this sense, we use the information respecting the similarities among candidates in

, represented via

, to state a notion of similarity between the simulations and a target observation in

, represented via

.…”

Section: Methodsmentioning

confidence: 99%

“…As suggested by authors in [ 32 ], we fixed the free parameters of the CKA algorithm regarding the gradient-descend optimization as follows: The adaptive step size of the learning rules are adjusted such that

and

decrease gradually from

through a maximum number of iterations empirically limited up to 100. Moreover, the initial guess for the rotation matrix

is computed using the well-known PCA method retaining the 95% of the variance explained (which defines the number of columns of

), while

is calculated as the median of the input data Euclidean distances.…”

Section: Methodsmentioning

confidence: 99%

See 2 more Smart Citations

AKL-ABC: An Automatic Approximate Bayesian Computation Approach Based on Kernel Learning

González-Vanegas

Álvarez-Meza

Hernández-Muriel

et al. 2019

Entropy

View full text Add to dashboard Cite

Bayesian statistical inference under unknown or hard to asses likelihood functions is a very challenging task. Currently, approximate Bayesian computation (ABC) techniques have emerged as a widely used set of likelihood-free methods. A vast number of ABC-based approaches have appeared in the literature; however, they all share a hard dependence on free parameters selection, demanding expensive tuning procedures. In this paper, we introduce an automatic kernel learning-based ABC approach, termed AKL-ABC, to automatically compute posterior estimations from a weighting-based inference. To reach this goal, we propose a kernel learning stage to code similarities between simulation and parameter spaces using a centered kernel alignment (CKA) that is automated via an Information theoretic learning approach. Besides, a local neighborhood selection (LNS) algorithm is used to highlight local dependencies over simulations relying on graph theory. Attained results on synthetic and real-world datasets show our approach is a quite competitive method compared to other non-automatic state-of-the-art ABC techniques.

show abstract

“…However, the grid search needed for tuning the free parameters increases the computational complexity exponentially to

, where

are related to grids defined over characteristic and similarity kernel widths. See that the performance of AKL-ABC depends on

and G ; however, in practice, the CKA and LNS algorithm have a fast convergence [ 32 , 35 ].…”

Section: Resultsmentioning

confidence: 99%

“…Concerning the feature space

, we assess the similarity via the Gaussian kernel function

, to build the matrix

where

and

is a feature mapping. Here, to perform the pairwise comparison between simulations in

we use also the Mahalanobis distance of the form [ 32 ]:

where

stands for the inverse covariance matrix of

and

(

). In this sense, we use the information respecting the similarities among candidates in

, represented via

, to state a notion of similarity between the simulations and a target observation in

, represented via

.…”

Section: Methodsmentioning

confidence: 99%

and

decrease gradually from

through a maximum number of iterations empirically limited up to 100. Moreover, the initial guess for the rotation matrix

is computed using the well-known PCA method retaining the 95% of the variance explained (which defines the number of columns of

), while

is calculated as the median of the input data Euclidean distances.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

AKL-ABC: An Automatic Approximate Bayesian Computation Approach Based on Kernel Learning

González-Vanegas

Álvarez-Meza

Hernández-Muriel

et al. 2019

Entropy

View full text Add to dashboard Cite

show abstract

“…The authors plan to enhance the Gaussian functional connectivity that was developed for feature extraction as future work, allowing a better understanding of their impact and interaction on BCI-related tasks. To identify potential non-learners, the efforts can be directed toward a twofold aim: to enhance the feature extraction by profiting from more elaborate methods for measuring multivariate similarity, like centered kernel alignment [58,59], and to explore the robust estimation approaches based on information metrics (like correntropy) for dealing better with the variability [55,60,61]. Besides, modeling the temporal-dependencies within each trail to compute the FC is an exciting research line.…”

Section: Discussionmentioning

confidence: 99%

Single-Trial Kernel-Based Functional Connectivity for Enhanced Feature Extraction in Motor-Related Tasks

García-Murillo

Álvarez-Meza

Castellanos-Domínguez

2021

Sensors

Self Cite

View full text Add to dashboard Cite

Motor learning is associated with functional brain plasticity, involving specific functional connectivity changes in the neural networks. However, the degree of learning new motor skills varies among individuals, which is mainly due to the between-subject variability in brain structure and function captured by electroencephalographic (EEG) recordings. Here, we propose a kernel-based functional connectivity measure to deal with inter/intra-subject variability in motor-related tasks. To this end, from spatio-temporal-frequency patterns, we extract the functional connectivity between EEG channels through their Gaussian kernel cross-spectral distribution. Further, we optimize the spectral combination weights within a sparse-based ℓ2-norm feature selection framework matching the motor-related labels that perform the dimensionality reduction of the extracted connectivity features. From the validation results in three databases with motor imagery and motor execution tasks, we conclude that the single-trial Gaussian functional connectivity measure provides very competitive classifier performance values, being less affected by feature extraction parameters, like the sliding time window, and avoiding the use of prior linear spatial filtering. We also provide interpretability for the clustered functional connectivity patterns and hypothesize that the proposed kernel-based metric is promising for evaluating motor skills.

show abstract

“…In particular, we match both estimated kernel-embeddings through the centered kernel alignment (CKA), as detailed in [ 40 ]:

where the kernel

is obtained from the matrix of predicted label probabilities

build by concatenating across the trial and subject sets all label probability vectors

.…”

Section: Materials and Methodsmentioning

confidence: 99%

Deep and Wide Transfer Learning with Kernel Matching for Pooling Data from Electroencephalography and Psychological Questionnaires

Collazos-Huertas

Velásquez-Martínez

Perez-Nastar

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

Motor imagery (MI) promotes motor learning and encourages brain–computer interface systems that entail electroencephalogram (EEG) decoding. However, a long period of training is required to master brain rhythms’ self-regulation, resulting in users with MI inefficiency. We introduce a parameter-based approach of cross-subject transfer-learning to improve the performances of poor-performing individuals in MI-based BCI systems, pooling data from labeled EEG measurements and psychological questionnaires via kernel-embedding. To this end, a Deep and Wide neural network for MI classification is implemented to pre-train the network from the source domain. Then, the parameter layers are transferred to initialize the target network within a fine-tuning procedure to recompute the Multilayer Perceptron-based accuracy. To perform data-fusion combining categorical features with the real-valued features, we implement stepwise kernel-matching via Gaussian-embedding. Finally, the paired source–target sets are selected for evaluation purposes according to the inefficiency-based clustering by subjects to consider their influence on BCI motor skills, exploring two choosing strategies of the best-performing subjects (source space): single-subject and multiple-subjects. Validation results achieved for discriminant MI tasks demonstrate that the introduced Deep and Wide neural network presents competitive performance of accuracy even after the inclusion of questionnaire data.

show abstract

Kernel-Based Relevance Analysis with Enhanced Interpretability for Detection of Brain Activity Patterns

Cited by 18 publications

References 65 publications

AKL-ABC: An Automatic Approximate Bayesian Computation Approach Based on Kernel Learning

AKL-ABC: An Automatic Approximate Bayesian Computation Approach Based on Kernel Learning

Single-Trial Kernel-Based Functional Connectivity for Enhanced Feature Extraction in Motor-Related Tasks

Deep and Wide Transfer Learning with Kernel Matching for Pooling Data from Electroencephalography and Psychological Questionnaires

Contact Info

Product

Resources

About