Implementation of a steady state visual evoked potantial based brain computer interface

The aim of this study is to determine the effect of room's light condition to brain response. Brain response to repetitive visual stimulation is called Steady-State Visual Evoked Potential (SSVEP) based Brain-Computer Interface (BCI). In this study, flickering Light Emitting Diode (LED) is used as visual stimulation. Mostly, brain response is recorded using electroencephalograph (EEG) and recorded in the brain's occipital lobe that is associated with human vision. Welch's method of power spectral estimation is implemented for estimating the power spectral of recorded signal. The result shows that the highest-power of brain response to repetitive visual stimulus can be detected either in the dark-room or in the bright-room.

High-frequency steady-state visual evoked potential-based brain-computer interface (SSVEP-BCI) systems offer improved user comfort but suffer from reduced performance compared to their low-frequency counterparts, limiting their practical application. To address this issue, we propose a transfer learning-based method that leverages low-frequency SSVEP data to enhance high-frequency SSVEP performance. A filtering mechanism is designed to extract informative components from low-frequency signals, and the least squares algorithm is employed to generate high-quality synthetic high-frequency data. Experiments conducted on two public datasets using TDCA, eTRCA, and advanced TRCA-based algorithms demonstrate significant performance improvements. Our approach requires only two calibration trials, achieving 9.03% and 14.49% accuracy increases for eTRCA and TDCA in Dataset 1, and 13.91% and 14.53% improvements in Dataset 2, all within 1.5s. Moreover, our approach effectively addresses the issue of single calibration data for high-frequency SSVEP-BCI systems. These results support the feasibility of fast calibration and improved performance in real-world high-frequency BCI applications.

Major depressive disorder (MDD) is a prevalent mental health condition associated with substantial emotional and functional impairment. While interest in neurophysiological markers is growing, gender-specific neural oscillatory patterns measured by portable electroencephalogram (EEG) devices remain underexplored. This study examined whether relative spectral power in the high alpha band (11–13 Hz), recorded by a three-channel prefrontal EEG device during eyes-closed resting state, is associated with emotional states and clinical diagnosis, with attention to gender differences. Forty participants from the MODMA dataset were included, comprising 18 patients with MDD (8 females, 10 males; mean age = 30.39 ± 10.91 years) and 22 healthy controls (8 females, 14 males; mean age = 30.86 ± 9.40 years). All participants completed EEG recordings using both a 128-channel laboratory system and a portable three-channel device (Fp1, Fpz, Fp2). Emotional status was assessed using the Patient Health Questionnaire-9 (PHQ-9), Generalized Anxiety Disorder-7 (GAD-7), and Childhood Trauma Questionnaire-Short Form (CTQ-SF). Pearson correlations between relative spectral power and emotional scale scores were computed separately for males and females, with false discovery rate (FDR) correction applied to multiple comparisons. Spectral features from the portable EEG closely matched those of the lab system (r = 0.975). High alpha power was positively correlated with PHQ-9 and GAD-7 scores, with stronger and more extended correlations observed in females, sometimes reaching into the low beta range. After FDR correction, significant correlations were observed primarily at 11–14 Hz. At 11.9 Hz, PHQ-9 correlations were significant for both males (r = 0.40, p = 0.011) and females (r = 0.33, p = 0.037). High alpha power also distinguished MDD from controls (r = 0.32, p = 0.042), independent of age and education. Frontal high alpha activity measured by a portable EEG device is a promising neural marker of emotional dysregulation, with stronger and broader associations observed in females. These findings support gender-sensitive EEG-based screening approaches for mood disorders in community and clinical settings.

A new dual-frequency stimulation method to increase the number of visual stimuli for multi-class SSVEP-based brain–computer interface (BCI)

Objective: To use SMOTE to enhance class balance and compare the performance of different classification methods before and after applying SMOTE. Methods: The study used a dataset from Kaggle. Consisted of several health-related features linked to obesity prediction. Checking for class imbalance within the dataset affected initial model performance. SMOTE was applied to synthetically increase the representation of minority classes, reducing the class imbalance. It was conducted in two stages: 1. Training and testing the classification algorithms before applying SMOTE. 2. Training and testing the same models after applying SMOTE to enhance class balance. The performance of all models was evaluated based on metrics before and after the SMOTE application. Results: Models Logistic Regression and Naive Bayes struggled with low sensitivity and specificity, and KNN (k=5) showed poor specificity. Significant improvements were observed across all models after applying SMOTE. Logistic Regression, despite a decrease in accuracy(-8.8), sensitivity and specificity increased substantially(+56.7%), with balanced accuracy improving(+16.6%). Naive Bayes saw a modest accuracy increase(+2.3%), with sensitivity and specificity improving(+47.9%). The KNN classifier exhibited a transformative enhancement with sensitivity and specificity increasing(+96.0%) and balanced accuracy(+28.3%). Deep Learning showed a significant increase in sensitivity (+69.8%), balanced accuracy (+29.4%), and an improvement in precision and F1-score despite a slight decrease in specificity(-10.9%). Conclusion: The results demonstrate that while there might be slight trade-offs, the overall improvements in key metrics such as sensitivity, specificity, balanced accuracy, precision, and F1-score affirm the utility of SMOTE in enhancing model performance for imbalanced datasets

Robust centroid based classification with minimum error rates for high dimension, low sample size data

We study the problem of question topic classification using a very large real‐worldCommunityQuestionAnswering (CQA) dataset fromYahoo!Answers. The dataset comprises 3.9 million questions and these questions are organized into more than 1,000 categories in a hierarchy. To the best knowledge, this is the first systematic evaluation of the performance of different classification methods on question topic classification as well as short texts. Specifically, we empirically evaluate the following in classifying questions intoCQAcategories: (a) the usefulness of n‐gram features and bag‐of‐word features; (b) the performance of three standard classification algorithms (naive Bayes, maximum entropy, and support vector machines); (c) the performance of the state‐of‐the‐art hierarchical classification algorithms; (d) the effect of training data size on performance; and (e) the effectiveness of the different components ofCQAdata, including subject, content, asker, and the best answer. The experimental results show what aspects are important for question topic classification in terms of both effectiveness and efficiency. We believe that the experimental findings from this study will be useful in real‐world classification problems.

Stroke identification using a portable EEG device – A pilot study

This paper presents an electroencephalogram (EEG) based brain computer interface (BCI) design as a control mechanism for the Open Vibe Space shooter game. BCI using Steady State Visual Evoked Potential (SSVEP) is designed. The SSVEP is generated in response to a flickering visual stimulus. The setup uses different flickering frequencies which are displayed on a Liquid Crystal Display (LCD) monitor to elicit SSVEP responses. The EEG signals are recorded over the visual cortex of the brain. These signals are pre-processed to remove undesired information. To extract features, the power information contained in the corresponding frequency bands are calculated. The feature set is fed as an input to the classifier to identify the target class. This study tried to compare the performance of different classification algorithms in terms of accuracy, information transfer rate and the response time. Based on the outcome, support vector machine classifier with radial basis function recorded the best average accuracy of 90%.

This paper analyzes the performance of different classification methods for online activity recognition on mobile phones using the built-in accelerometers. First, we evaluate the performance of activity recognition using Naive Bayes and minimum distance classifiers and next we propose an improvement of Minimum Distance and K-Nearest Neighbor (KNN) classification algorithms called Clustered KNN. Clustered KNN eliminates the computational complexity of KNN by creating clusters, training sets for each activity. Classification is performed based on these reduced sets. We evaluate the performance of these classifiers on five test subjects for activities of walking, running, sitting and standing, and find that Naive Bayes provides not satisfactory results whereas Clustered KNN gives promising results.

Humans have a sense of time; however, this sense is subjective. We have all experienced that periods of boredom feel longer, and periods spent in pleasant activities feel shorter. The relationship between humans’ sense of time and visual stimuli has been studied in many research fields, including psychology and informatics. In the field of informatics, there have been attempts to use the relationship between the sense of time and visual stimuli for practical purposes. Studies using visual stimuli on a computer monitor have had some degree of positive results. This research attempts to apply this pertinent knowledge obtained in informatics to architectural spaces and examine whether the presentation of periodic visual stimuli to peripheral vision can act as a spatial element that changes one’s sense of time. This research focuses on the frequency and presentation position of periodic visual stimuli. This research investigates the influence of periodic visual stimuli on the sense of time through two virtual reality experiments. Experiments were conducted in a room of dimensions 4 x 4 x 2.4, created in an immersive virtual environment. The participants were immersed in the virtual environment using a head-mounted display and they remained seated while the experiments were conducted. Light bulbs were set at equal distances of 30 cm on walls of the room in the virtual environment and repeatedly flashed to present periodic visual stimuli to the participants' peripheral vision. The participants evaluated the time in a virtual environment based on a set of conditions. The first experiment examined the frequency of periodic visual stimuli on the participants’ sense of time by setting four frequencies: 0(no stimuli), 30, 60, and 90 times per minute. The participants evaluated time twice at each frequency, and all eight trials were conducted in random order. The first experiment showed that the participants perceived time as significantly longer in the condition wherein the frequency was 90 times per minute as compared to that in conditions wherein the frequencies were 0, 30, 60 times per minute. Thus, the results suggest that a presentation of periodic visual stimuli with a high frequency has the effect of making time feel longer. The second experiment examined the relationship between the presentation position of periodic visual stimuli and the sense of time. The frequency of periodic visual stimuli was set at 90 times per minute, and there were four presentation positions: sidewall, floor-ceiling, sidewall-floor-ceiling, and no stimuli. The participants evaluated time twice at each presentation position, and the order of eight trials was designed in a manner that there was no duplication between the stimuli presented to the participants. The second experiment revealed that the participants perceived time as significantly longer in the condition including the position sidewall-floor-ceiling as compared to that in conditions including the positions sidewall and floor-ceiling. The results suggest that regardless of the presentation position, visual stimuli presented in extensive view make time feel longer. These findings have the potential to create methods to change one’s sense of time in architectural spaces intentionally.

Electrophysiological recordings in monkeys have now revealed several brain regions that contain bimodal visuotactile neurons capable of responding to either tactile or visual stimuli placed on or near the hands, arms, and face. These cells have now been found in frontal, parietal, and subcortical areas of the monkey brain, suggesting a cortical network of neurons that preferentially represent near peripersonal space. The degree to which the visual responses of such cells rely on input from the primary visual cortex and the extent to which they may contribute to visual perception is not completely understood. Nonetheless, recent neuropsychological studies suggest that a similar representation of near space may be bimodally coded in humans as well. Given the accumulating evidence for specialized processing of visual stimuli placed near the hands and arms, we hypothesized that arm position may be capable of modulating human visual ability. Here we report the case of WM, who lost his ability to see in his left visual hemifield after sustaining damage to his right primary visual cortex. Interestingly, the placement of WM's left arm into his "blind" field resulted in significantly better detection of left visual field stimuli compared to when his hand was placed in his lap at midline. Moreover, we found this attenuation to be confined to stimuli presented within reaching distance (unless a tool that extended WM's reach was held while he performed the test). These findings are highly consistent with the characteristics of the bimodal visuo-tactile neurons that have been described in monkeys. Thus, it seems that arm position can modulate human visual ability, even after damage to the primary visual cortex. This study provides an exciting bridge between monkey neurophysiology and human visual capacity while also offering a novel approach for improving visual defects acquired via cortical injury.

A convergent series of studies in monkeys and man suggests that the computation of visual space is performed in several brain regions for different behavioural purposes. Among these multiple spatial areas, the ventral intraparietal cortex, the putamen and the ventral aspect of the premotor cortex (area 6) contain a system for representing visual space near the face (peripersonal space). In these cerebral areas some neurons are bimodal: they have tactile receptive fields on the face, and they can also be driven by visual stimuli located near the tactile field. The spatial correspondence between the visual and tactile receptive fields provides a map of near visual space coded in body-part-centred co-ordinates. In the present study we demonstrate for the first time the existence of a visual peripersonal space centred on the face in humans. In patients with right hemispheric lesions, visual stimuli delivered in the space near the ipsilesional side of the face extinguished tactile stimuli on the contralesional side (cross-modal visuotactile extinction) to the same extent as did an ipsilesional tactile stimulation (unimodal tactile extinction). Furthermore, a visual stimulus presented in the proximity of the contralesional side of the face improved the detection of a left tactile stimulus: i.e. under bilateral tactile presentation patients were more accurate to report the presence of a left tactile stimulus when a simultaneous visual stimulus was presented near the left side of the face. However, when visual stimuli were delivered far from the face, visuotactile extinction and visuotactile facilitation effects were dramatically reduced. These findings are consistent with the hypothesis of a representation of visual peripersonal space coded in bodypart-centred co-ordinates, and they provide a striking demonstration of the modularity of human visual space.

Effects of allocation of visuo-spatial attention to visual stimuli triggering unilateral arm abduction on anticipatory postural control

Effect of the concreteness of robot motion visual stimulus on an event-related potential-based brain-computer interface