4 November 2022 in IEEE Access
The market uptake of Brain-Computer Interface technologies for clinical and non-clinical applications is attracting the scientific world towards the development of daily-life wearable systems. Beyond the use of dry electrodes and wireless technology, reducing the number of channels is crucial to enhance the ergonomics of devices. This paper presents a review of the studies exploiting a number of channels less than 16 for electroencephalographic (EEG) based-emotion recognition. The main findings of this review concern: (i) the criteria to select the most promising scalp areas for EEG acquisitions; (ii) the attention to prior neurophysiological knowledge; and (iii) the convergences among different studies with respect to preferable areas of the scalp for signal acquisition. Three main approaches emerge for channel selection: data-driven, prior knowledge-based, and based on commercially-available wearable solutions. The most spread is the data-driven, but the neurophysiology of emotions is rarely taken into account. Furthermore, commercial EEG devices usually do not provide electrodes purposefully chosen to assess emotions. Considerable convergences emerge for some electrodes: Fp1, Fp2, F3 and F4 resulted the most informative channels for the valence dimension, according to both data-driven and neurophysiological prior knowledge approaches. The P3 and P4 resulted in being significant for the arousal dimension.
16 December 2021 in Brain-Computer Interfaces
A method for high-wearable EEG-based assessment of pediatric emotional and cognitive engagement in neuro-motor rehabilitation is proposed. A specific easy calibration is provided in the perspective of a personalized medicine. Due to the lack of studies evaluating pediatric multidimensional engagement, an observational non-interventional protocol was adopted for collecting the EEG data related to the high/low levels of engagement. The experimental validation of the proposed method involved four children performing a rehabilitation exercise in five 8-min sessions. Due to the age and frailty of the subjects, no negative emotions were expressly induced and an unbalanced dataset was obtained. Different Synthetic Minority Oversampling Technique (SMOTE)-based strategies for unbalanced dataset management and classification methods were compared. The highest performances were achieved by combining Artificial Neural Network (ANN) models with the KMeansSMOTE oversampling method. Balanced accuracies of 71.2 % and 74.5 % for the emotional engagement and the cognitive engagement are obtained, respectively.