Assessment of brain dynamics elicited by motor imagery (MI) tasks contributes to clinical and learning applications. In this regard, Event-Related Desynchronization/Synchronization (ERD/S) is computed from Electroencephalographic signals, which show considerable variations in complexity. We present an Entropy-based method, termed VQEnt, for estimation of ERD/S using quantized stochastic patterns as a symbolic space, aiming to improve their discriminability and physiological interpretability. The proposed method builds the probabilistic priors by assessing the Gaussian similarity between the input measured data and their reduced vector-quantized representation. The validating results of a bi-class imagine task database (left and right hand) prove that VQEnt holds symbols that encode several neighboring samples, providing similar or even better accuracy than the other baseline sample-based algorithms of Entropy estimation. Besides, the performed ERD/S time-series are close enough to the trajectories extracted by the variational percentage of EEG signal power and fulfill the physiological MI paradigm. In BCI literate individuals, the VQEnt estimator presents the most accurate outcomes at a lower amount of electrodes placed in the sensorimotor cortex so that reduced channel set directly involved with the MI paradigm is enough to discriminate between tasks, providing an accuracy similar to the performed by the whole electrode set.

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.

Motion capture (Mocap) data are widely used as time series to study human movement. Indeed, animation movies, video games, and biomechanical systems for rehabilitation are significant applications related to Mocap data. However, classifying multi-channel time series from Mocap requires coding the intrinsic dependencies (even nonlinear relationships) between human body joints. Furthermore, the same human action may have variations because the individual alters their movement and therefore the inter/intraclass variability. Here, we introduce an enhanced Hilbert embedding-based approach from a cross-covariance operator, termed EHECCO, to map the input Mocap time series to a tensor space built from both 3D skeletal joints and a principal component analysis-based projection. Obtained results demonstrate how EHECCO represents and discriminates joint probability distributions as kernel-based evaluation of input time series within a tensor reproducing kernel Hilbert space (RKHS). Our approach achieves competitive classification results for style/subject and action recognition tasks on well-known publicly available databases. Moreover, EHECCO favors the interpretation of relevant anthropometric variables correlated with players’ expertise and acted movement on a Tennis-Mocap database (also publicly available with this work). Thereby, our EHECCO-based framework provides a unified representation (through the tensor RKHS) of the Mocap time series to compute linear correlations between a coded metric from joint distributions and player properties, i.e., age, body measurements, and sport movement (action class).

Evaluation of brain dynamics elicited by motor imagery (MI) tasks can contribute to clinical and learning applications. The multi-subject analysis is to make inferences on the group/population level about the properties of MI brain activity. However, intrinsic neurophysiological variability of neural dynamics poses a challenge for devising efficient MI systems. Here, we develop a time-frequency model for estimating the spatial relevance of common neural activity across subjects employing an introduced statistical thresholding rule. In deriving multi-subject spatial maps, we present a comparative analysis of three feature extraction methods: Common Spatial Patterns, Functional Connectivity, and Event-Related De/Synchronization. In terms of interpretability, we evaluate the effectiveness in gathering MI data from collective populations by introducing two assumptions: (i) Non-linear assessment of the similarity between multi-subject data originating the subject-level dynamics; (ii) Assessment of time-varying brain network responses according to the ranking of individual accuracy performed in distinguishing distinct motor imagery tasks (left-hand vs. right-hand). The obtained validation results indicate that the estimated collective dynamics differently reflect the flow of sensorimotor cortex activation, providing new insights into the evolution of MI responses.

Motor Imagery (MI) promotes motor learning in activities, like developing professional motor skills, sports gestures, and patient rehabilitation. However, up to 30% of users may not develop enough coordination skills after training sessions because of inter and intra-subject variability. Here, we develop a data-driven estimator, termed Deep Regression Network (DRN), which jointly extracts and performs the regression analysis in order to assess the efficiency of the individual brain networks in practicing MI tasks. The proposed double-stage estimator initially learns a pool of deep patterns, extracted from the input data, in order to feed a neural regression model, allowing for infering the distinctiveness between subject assemblies having similar variability. The results, which were obtained on real-world MI data, prove that the DRN estimator fosters pre-training neural desynchronization and initial training synchronization to predict the bi-class accuracy response, thus providing a better understanding of the Brain–Computer Interface inefficiency of subjects.