Robust Motor Imagery Tasks Classification Approach Using Bayesian Neural Network.

The development of Brain-Computer Interfaces based on Motor Imagery (MI) tasks is a relevant research topic worldwide. The design of accurate and reliable BCI systems remains a challenge, mainly in terms of increasing performance and usability. Classifiers based on Bayesian Neural Networks are proposed in this work by using the variational inference, aiming to analyze the uncertainty during the MI prediction. An adaptive threshold scheme is proposed here for MI classification with a reject option, and its performance on both datasets 2a and 2b from BCI Competition IV is compared with other approaches based on thresholds. The results using subject-specific and non-subject-specific training strategies are encouraging. From the uncertainty analysis, considerations for reducing computational cost are proposed for future work.

Smartphones dependency risk analysis using machine-learning predictive models.

Recent technological advances have changed how people interact, run businesses, learn, and use their free time. The advantages and facilities provided by electronic devices have played a major role. On the other hand, extensive use of such technology also has adverse effects on several aspects of human life (e.g., the development of societal sedentary lifestyles and new addictions). Smartphone dependency is new addiction that primarily affects the young population. The consequences may negatively impact mental and physical health (e.g., lack of attention or local pain). Health professionals rely on self-reported subjective information to assess the dependency level, requiring specialists' opinions to diagnose such a dependency. This study proposes a data-driven prediction model for smartphone dependency based on machine learning techniques using an analytical retrospective case-control approach. Different classification methods were applied, including classical and modern machine learning models. Students from a private university in Cali-Colombia (n = 1228) were tested for (i) smartphone dependency, (ii) musculoskeletal symptoms, and (iii) the Risk Factors Questionnaire. Random forest, logistic regression, and support vector machine-based classifiers exhibited the highest prediction accuracy, 76-77%, for smartphone dependency, estimated through the stratified-k-fold cross-validation technique. Results showed that self-reported information provides insight into predicting smartphone dependency correctly. Such an approach opens doors for future research aiming to include objective measures to increase accuracy and help to reduce the negative consequences of this new addiction form.

Monte Carlo Dropout for Uncertainty Estimation and Motor Imagery Classification.

Motor Imagery (MI)-based Brain-Computer Interfaces (BCIs) have been widely used as an alternative communication channel to patients with severe motor disabilities, achieving high classification accuracy through machine learning techniques. Recently, deep learning techniques have spotlighted the state-of-the-art of MI-based BCIs. These techniques still lack strategies to quantify predictive uncertainty and may produce overconfident predictions. In this work, methods to enhance the performance of existing MI-based BCIs are proposed in order to obtain a more reliable system for real application scenarios. First, the Monte Carlo dropout (MCD) method is proposed on MI deep neural models to improve classification and provide uncertainty estimation. This approach was implemented using Shallow Convolutional Neural Network (SCNN-MCD) and with an ensemble model (E-SCNN-MCD). As another contribution, to discriminate MI task predictions of high uncertainty, a threshold approach is introduced and tested for both SCNN-MCD and E-SCNN-MCD approaches. The BCI Competition IV Databases 2a and 2b were used to evaluate the proposed methods for both subject-specific and non-subject-specific strategies, obtaining encouraging results for MI recognition.

Exergames Training Effects on Gait During Single and Dual Tasks in Sexagenarian Women.

Objective: This study was designed to analyze the effects of an exergames training program on gait parameters while holding a cellphone conversation at self-selected walking speed (SSWS) and fast walking speed (FWS). Materials and Methods: Twenty-one older women (66.3 ± 4.0 years) practiced exergames for 12 weeks and were assessed for spatiotemporal gait parameters at SSWS and FWS under single task and dual task. The strength of the lower limbs was measured by an isokinetic dynamometer (Byodex System 3). The cognitive function was assessed with the Montreal Cognitive Assessment (MoCA). The tests were assessed 4 weeks before the start of the exergames training (baseline, T0), immediately before (pretraining, T1), and at the end of 12 weeks of the exergame training (post-training, T2), except for the MoCA test that was assessed at T0 and T2. Results: The spatiotemporal gait parameters at SSWS and FWS showed extensive changes when a cellphone conversation was sustained (e.g., 6.5% and 5.8% reduction in walking speed, respectively). Exergames training was not effective in minimizing these changes or improving muscle strength after 12 weeks (<3.0%). Minor cognitive improvements (0.5 points) were observed in response to training. Conclusion: Holding a cellphone conversation while walking changed several gait parameters, irrespective of the walking speed. The spatiotemporal gait parameters and lower limb muscle strength in sexagenarian women remained unchanged after the exergames training program.