Exploring the Potential of BCI in Education: An Experiment in Musical Training

Abstract

Brain–computer interfaces (BCIs) have gained significant attention in recent years for various applications, including education and skill development: studies have shown that BCIs can boost memory, concentration, and even creativity and can improve learning and memory retention in healthy people. In our current study, we investigated the effectiveness of real-time feedback provided by a BCI system for improving performance on a specific task. A total of 20 participants completed a pre-training assessment, followed by a training period with the BCI system and a post-training assessment. The BCI system provided real-time feedback based on the participants’ level of accuracy, with positive feedback given for scores above 70%. Results showed a significant improvement in accuracy scores from pre- to post-training, with an average improvement of 15%. Participants also reported high levels of satisfaction with the feedback provided by the BCI system. These findings suggest that real-time feedback provided by a BCI system can be an effective tool for skill development and education, particularly when tailored to the specific needs of individual learners. Further research is needed to explore the potential of BCIs for a wide range of educational applications.

1. Introduction

Brain–computer interface (BCI) technology has the potential to revolutionize education by creating new ways of teaching and learning. A BCI system uses electrodes on a person’s scalp to detect and measure brain activity [1]. This activity can allow a person to interact with digital media without physical input devices by controlling a computer. BCI technology has many potential applications in education, from helping students with disabilities [2,3] to improving concentration and focus [4]. This work explores the use of BCI technology in education, as well as its benefits and potential challenges. In a previous study, we investigated the effect of gamification on education [5,6]. Here, we aim to verify if students receiving real-time feedback on their performance modulate their attitude in studying, choosing a better mindset or approach to maximize the effectiveness of a training session. Some studies [7] argue that biofeedback can help individuals understand better how their brain works to improve their skills in a discipline using the feedback as a guide to achieving the target, such as a greater focus during their training session or/and a better physical performance. Current research hypotheses state that performance is a matter of brain-and-body coordination, not only in sports but also in other disciplines [8]. We wanted to explore if receiving BCI-based biofeedback during a training session could be a reinforcement learning tool to improve learning performance without distracting learners from the subject they are studying. To this extent, we experimented with subjects involving both physical and mental focus. Playing an instrument consists of reading and understanding the score and—depending on the instrument—using fingers, arms, or mouth to play. Among all the instruments, we chose the guitar because we wanted to minimize the possible discomfort of wearing a BCI headset whilst playing wind instruments, percussion, piano, or violin, which involve more movements and muscles by a player’s head.

This study is motivated by the increasing potential of BCI technology to transform education and skill development. By exploring how real-time neurofeedback improves cognitive engagement and motor coordination, this research seeks to connect neuroscience with pedagogy, ultimately promoting more personalized and compelling learning experiences.

The paper is organized as follows: Section 2 illustrates the background of BCI technology, while Section 3 illustrates the applications and benefits of BCIs in education. Section 4 addresses potential challenges and limitations. Section 5 describes the experiment we conducted to test the effectiveness of BCIs in skill development by improving learning performance through BCI-based biofeedback. The results are discussed in Section 6. The paper ends with presenting possible further developments and final consideration.

2. Background of BCI Technology

Born for entertainment purposes to introduce the possibility of interacting with games through EEG-based commands, BCI technology [9] is a relatively new field that has gained momentum in recent years. BCI technology measures brain activity and translates it into commands that can control a computer or other devices [10], implicitly exploiting the brain’s ability to learn how to achieve these results.

BCI devices interpret neural signals to execute commands, opening avenues for enhanced interaction with technology. BCI can decode motor imagery patterns, allowing users to control external devices by merely imagining specific movements. This capability can be harnessed for hands-free computer operation or device manipulation (such as drones, wheelchairs, exoskeletons, etc.) [11]. The interpretation of P300 event-related potentials also represents a significant example of command execution through BCI: it enables communication by spelling out words based on the user’s visual attention [12].

The ability of the brain to implicitly learn how to achieve these results is mainly based on neurofeedback. BCI systems provide real-time feedback on brain activity, aiding users in developing self-regulation skills [13]. This is particularly relevant in the context of empowering individuals for skill acquisition. The integration of BCI in guitar training, examined in this study, holds promising potential for empowering learners. Key aspects, further discussed, include the following:

• Real-time feedback on Cognitive States during guitar practice. This information aids in refining focus, concentration, and mental preparedness
• Adaptive Learning Environments allow tailoring guitar exercises based on the learner’s neural responses, optimizing the training curriculum for individual needs.
• Brain–Computer–Music Interface (BCMI): BCIs translate brain signals into musical elements, allowing learners to create music through thought. This innovative approach enhances creativity and engagement in the learning process.
• Cognitive Load Monitoring during guitar practice ensures an optimal balance between challenge and skill acquisition, contributing to an efficient and enjoyable learning experience.

Similar to traditional neurofeedback, BCI systems are powerful tools to train the brain and activate neuroplasticity, which is the brain’s ability to change and adapt over time. The first BCI systems were developed in the 1970s [14], but it was in the 1990s that the technology began to gain widespread attention. Since then, BCI technology has advanced rapidly, and new applications are developing yearly. BCI technology appears in many fields, including medicine [15], entertainment and gaming [16], and recently, education [17].

In research and medicine, BCIs have been used to study brain function and the neural basis of behavior [18], to investigate how the brain processes sensory information [1], how memories are formed and retrieved [19], and how different areas of the brain communicate [20].

In medicine, BCIs have shown potential for helping individuals with various conditions. For example, BCIs can help individuals with paralysis regain control over their movements by translating their brain activity into control signals for prosthetic limbs [21]. BCIs have also been used to help individuals with epilepsy detect and prevent seizures [22].

BCIs have been explored in the entertainment industry to create more immersive and interactive experiences [23]. BCIs have also been used in virtual and augmented reality applications [24] to create more realistic and engaging experiences.

3. Applications and Benefits of Using BCI Technology in Education

BCI technology has many potential benefits in education [25]. One of the most significant benefits is that it can help students with disabilities [26]. For example, students with physical disabilities, such as cerebral palsy, may find it challenging to use traditional input devices, such as a mouse or keyboard. BCI technology can allow these students to control a computer using only their thoughts, which can help them to participate in classroom activities and interact with digital media.

BCIs can control robotic experiments, allowing students to conduct and observe results without physically interacting with the apparatus. For example, students could control robotic arms and run experiments in physics or chemistry just by using a BCI to understand human–computer interaction issues better [27].

BCIs have shown potential for helping individuals with learning disorders [28,29] and Attention-Deficit/Hyperactivity Disorder (ADHD) [30] in the educational context.

In the case of ADHD, BCIs can help individuals improve their attention and focus. For example, researchers have explored BCI-based games and applications to help individuals with ADHD improve their working memory and attention skills [31]. Games require players to pay attention to specific stimuli while ignoring distractors. Usually, games use real-time feedback to adjust the difficulty level based on the player’s performance, making it more challenging as their skills improve. In other applications, students receive real-time brain activity feedback while completing academic tasks to enhance their performance. The feedback aims to help students learn to regulate their attention and reduce distractibility.

For individuals with learning disabilities, BCIs can help provide a more personalized learning experience. For example, they can track students’ attention and engagement levels in real-time [32], assisting teachers in noticing when students are struggling with specific topics or losing focus and adjusting their instruction accordingly. BCIs can also provide feedback to students about their learning progress, helping them identify areas where they need more practice or support. Another benefit of using BCI technology in education is that it can help to improve concentration and focus [33]. Using BCI technology to monitor brain activity, teachers can identify when students are distracted or disengaged and create personalized learning experiences [34,35,36].

BCIs can also track a student’s brain activity while they practice a musical instrument and provide feedback on their performance, such as whether they are playing on time or hitting the correct notes [37]. Jointly with the works on focus and attention improvement, experiments involving playing an instrument could help test the potential of BCI-based feedback in improving individuals’ attitudes from learning to skilled performance.

Overall, the potential for interactive learning experiences made possible through BCIs is vast, and researchers and educators are exploring new ways to use this technology to enhance education.

4. The Experiment, Methods, and Data

To corroborate our thesis about the potential to empower the learning process by providing biofeedback based on EEG, we experimented (see Figure 1) using a BCI device to provide a real-time progress bar (green color in Figure 1) showing students their coordination between focus and action during a guitar training session. Specifically, the progress bar showed low values (on the left) if action (playing the guitar) was predominant on focus (reading the score) or vice versa, and high values (going on the right) if achieving coordination. In this latter case, a green light LED was light on; however, if there is no balance, a red light was light on. The traffic light aims to give an immediate alert to students, whilst the scrollbar serves to help them to granularly self-regulate to improve in time. The values above the bar were calculated by a ratio between beta brain rhythms collected through the sensors AF7–AF8, positioned in the frontal area, where voluntary motor control is located, and the beta brain rhythms collected through the sensors TP9–TP10, recording values related to the auditory system and long-term memory [38].

The ratio was calculated to determine coordination between focus and action, following the equation:

$$\mathrm{C}\mathrm{o}\mathrm{o}\mathrm{r}\mathrm{d}\mathrm{i}\mathrm{n}\mathrm{a}\mathrm{t}\mathrm{i}\mathrm{o}\mathrm{n}\mathrm{R}\mathrm{a}\mathrm{t}\mathrm{i}\mathrm{o}(\mathrm{C}\mathrm{R})={\displaystyle \frac{{Beta}_{AF7-AF8}}{{Beta}_{TP9-TP10}}}$$

(1)

where

• Beta_AF7–AF8 represents the beta brain rhythms collected from the frontal area (sensors AF7 and AF8), which are associated with voluntary motor control and focus.
• Beta_TP9–TP10 represents the beta brain rhythms collected from the temporal area (sensors TP9 and TP10), which are associated with the auditory system and long-term memory.

In Equation (1), the CR can assume values in the interval [0, 1], with CR ≈ 1 indicating a balance between focus (reading the score) and action (playing the guitar), resulting in high coordination. The progress bar would show high values (toward the right), and the green LED would light up. CR < 1 indicates that action (playing the guitar) is predominant over focus (reading the score). The progress bar would show a low value (toward the left), and the red LED would light up. CR > 1 indicates that focus (reading the score) is predominant over action (playing the guitar). The progress bar would also show low values (toward the left), and the red LED would light up.

Within the system, the progress bar provides granular feedback, allowing students to self-regulate and adjust their focus and action in real time. The LED traffic light provides an immediate visual alert: green for balanced coordination and red for imbalance.

The study was designed considering all the best practices from the literature and all the issues related to safety and privacy addressed in Section 5. In the following, participants, methods, and approaches are described in detail.

Participants:

• The study included 20 novice guitar players, comprising 10 females and 10 males. The mean age for females was 17.9 years, while the mean age for males was 18.0 years, resulting in an overall mean age of 18 years for all participants.

Materials:

• An EEG-based BCI to measure brain activity. Specifically, we used Muse2 (https://choosemuse.com/, accessed on 18 March 2025) to let participants feel comfortable and free in their movements.
• A software specifically developed to collect data recorded by the BCI for further analysis also provided real-time feedback to the participants on the laptop screen put in front of individuals during the experiment. The software was developed in Python ver 3.13. The code is available at https://github.com/Foraf/EEGfeedback, accessed on 18 March 2025.
• Acoustic guitars for participants to practice.

Method:

• Informed consent was provided to the experiment participants, including safety information. Subjects have information about the experiment’s aim and the anonymization of data (removal of personal identifiers, replaced by anonymous IDs) regarding data protection rules.
• Participants were divided into a BCI group and a control group. In each group, genders were equally distributed.
• At the beginning of the experiment, all the participants were assessed to collect data used as a baseline. For two months, three times a week:
• Both groups received a 30 min training session on basic guitar chord progressions.
• The BCI group then received an additional 30 min session where they practiced playing the chords while wearing the EEG headset and receiving real-time feedback on their brain activity.
• The control group practiced the same chords for 30 min without the EEG headset or real-time feedback
• After two months, at the end of the experiment, all participants were tested on their ability to play the chords accurately and in time with a metronome. The BCI group was also tested wearing the headset to check whether, in time, their ability to self-regulate improved.

Data collection

• EEG data were collected using the Muse2 headset (InteraXon Inc., Toronto, Canada), which recorded signals from four electrodes (AF7, AF8, TP9, TP10) at a sampling rate of 256 Hz.
• The electrodes were positioned according to the manufacturer’s guidelines, ensuring proper contact with the scalp.
• Before each session, the Muse headset was calibrated to ensure optimal signal quality. Participants were instructed to remain still with their eyes closed for 1–2 min to record baseline activity.

EEG Data Preprocessing and Artifact Handling

EEG data were preprocessed to remove artifacts and noise. A band-pass filter (0.5–50 Hz) was applied to eliminate high-frequency noise and low-frequency drifts. Independent Component Analysis (ICA) was used to identify and remove components corresponding to eye blinks, muscle activity, and other artifacts. Epochs with amplitudes exceeding ±100 µV were automatically rejected. Additionally, all data were visually inspected, and any remaining artifacts were manually removed. To minimize movement-related artifacts, participants were instructed to remain as still as possible during the recording sessions, and short breaks were provided to reduce fatigue. The signal-to-noise ratio (SNR) was calculated to ensure the quality of the cleaned EEG data.

Addressing potential packet loss

To address potential packet loss, the Muse headset was paired with a laptop in close proximity (within 1 m), and the custom software included a buffering mechanism to handle temporary disruptions in the Bluetooth connection. The software also monitored the data stream for missing or corrupted packets. If packet loss exceeded 5%, the session was paused, and the headset was reconnected. After each session, the EEG data were checked for continuity, and sessions with significant packet loss (>10%) were excluded from the analysis.

In addition, the headset was connected to a laptop via Bluetooth, and participants were instructed to remain still during the recording to minimize motion artifacts. Before each session, the headset was calibrated, and baseline activity was recorded with participants’ eyes closed.

The BCI system used in this experiment was designed to measure the participants’ brain activity while they played the guitar and provide real-time feedback on their performance. The system was programmed to detect specific brainwave patterns associated with attention, focus, and relaxation balanced with brain activity related to movements whilst they were playing.

Compared to the previous diagram shown in Figure 1, the following Figure 2 provides further details and offers a summary of the methodology adopted and the steps followed during implementation.

In the experiment, the desired range for users to let the system provide positive feedback was set at 70% accuracy or above. This threshold was chosen based on previous research suggesting that giving input at this level can help reinforce learning and promote skill development [39]. By setting the threshold at 70% accuracy or above, the system aimed to provide positive feedback to participants making significant progress in developing their skills.

5. Results

The experiment results showed that the BCI group performed significantly better than the control group on the post-training guitar test. The BCI group also improved their ability to play the chords accurately and in time with the metronome compared to the control group. The scores assigned to students ranged from 0 to 100.

Table 1. Mean scores on post-training guitar test.

Group	Post-Training Mean Score	Standard Deviation
BCI	83	4.2
Control	72	6.1

shows the mean scores for the BCI and control groups on the post-training guitar test. A t-test was conducted to compare the mean scores of the BCI and control groups on the post-training guitar test. The results showed that the mean score for the BCI group (M = 83, SD = 4.2) was significantly higher than the mean score for the control group (M = 72, SD = 6.1), t(18) = 3.42, p = 0.003, Cohen’s d = 1.14, indicating a large effect size.

In addition, the change in accuracy scores from pre- to post-training was calculated for each group. Table 1 shows the results.

A t-test was also conducted to compare the change in accuracy scores from pre- to post-training between the BCI and control groups. As shown in Figure 3, the results showed that the BCI group (M = 18.7, SD = 2.8) had a more significant improvement in accuracy scores compared to the control group (M = 11.2, SD = 4.5), t(18) = 4.56, p < 0.001, Cohen’s d = 1.53, indicating a large effect size.

As shown in

Table 2. Change in accuracy scores from pre- to post-training.

Group	Mean Pre-Training Accuracy Score	Mean Post-Training Accuracy Score	Mean Change in Accuracy Score	Standard Deviation
BCI	64.3	83	18.7	2.8
Control	60.8	72	11.2	4.5

, both groups had similar scores on the pre-training guitar test, indicating similar proficiency levels before the training sessions. In the post-training, the BCI group had a more remarkable improvement in accuracy scores from pre- to post-training than the control group. This difference was statistically significant, as shown by the t-test results.

Table 3. Correlations between EEG measures and guitar performance.

EEG Measure	Correlation with Accuracy Score	p-Value
Alpha power	0.72	<0.001
Beta power	−0.43	0.05

shows the correlations between two EEG measures (alpha and beta power collected through the sensors AF7-AF8, positioned in the frontal area of the scalp) and guitar performance. Alpha power was positively correlated with accuracy score, indicating that higher levels of alpha power were associated with better guitar performance. Beta power was negatively correlated with accuracy score, indicating that higher levels of beta power were associated with poorer performance. The correlations provide evidence that the BCI system measured relevant brain activity related to skill development.

These statistical results show that real-time feedback during practice can improve skill development. The BCI group showed significantly higher scores on the post-training test and significantly improved accuracy than the control group. The correlations between EEG measures and guitar performance also provide further support for the validity of the BCI feedback system.

The t-test was conducted to compare the change in accuracy scores from pre- to post-training between the BCI and control groups.

It is worthwhile to specify that the null hypothesis states that there is no significant difference in the change in accuracy scores from pre- to post-training between the BCI group and the control group. The tested null hypothesis can be expressed as follows:

$$H_0:{\mu }_{BCI}={\mu }_{Control}$$

where

• μ_BCI is the mean change in accuracy scores for the BCI group.
• μ_Control is the mean change in accuracy scores for the control group.

The study thus involves two independent groups (BCI and control). The dependent variable (change in accuracy scores) is continuous. The goal is to determine if there is a statistically significant difference between the means of the two groups.

The results showed that the BCI group (M = 18.7, SD = 2.8) had a more significant improvement in accuracy scores compared to the control group (M = 11.2, SD = 4.5): t(18) = 4.56, p < 0.001, Cohen’s d = 1.53, where t(18) indicates the t-statistic with 18 degrees of freedom (df = n1 + n2 − 2, where n1 and n2 are the sample sizes of the two groups); p > 0.001, which indicates the probability of observing the results under the null hypothesis, suggests the results are statistically significant at α = 0.05 level; Cohen’s d = 1.53 represents the effect size, which indicates the magnitude of the difference between the two groups. The obtained value of 1.53 is considered a large effect size.

The null hypothesis is rejected because the p-value (p < 0.001) is less than the significance level (α = 0.05). This indicates that there is a statistically significant difference in the change in accuracy scores between the BCI group and the control group, with the BCI group showing a larger improvement.

Furthermore, we also analyzed (

Table 4. Changes in Power of Theta, Alpha, and Beta Frequency Bands during Learning.

Frequency Band	Frequency Range	Change in Mean Power
Theta	4–7 Hz	+20%
Alpha	8–12 Hz	+15%
Beta	12–30 Hz	−10%

) the changes in power of theta, alpha, and beta frequency bands during learning. The power of each frequency band was measured using a wavelet transform. The mean power before and after the learning experience was calculated across all 20 participants. A percentage difference between pre-and post-learning values expresses the change in mean power. Standard deviation represents the variability of individual power values within each frequency band.

The following equation is used to calculate the percentage change in mean power for each frequency band:

$$PercentageChangeinMeanPower=\left({\displaystyle \frac{{MeanPower}_{post}-{MeanPower}_{pre}}{{MeanPower}_{pre}}}\right)\times 100$$

(2)

where

• Mean Power_pre is the mean power of a specific frequency band (theta, alpha, or beta) before the learning experience.
• Mean Power_post is the mean power of the same frequency band after the learning experience.

Using the data from Table 4, the percentage change in mean power for each frequency band can be expressed as follows:

$$\%ChangeinThetaPower=\left({\displaystyle \frac{{MeanPower}_{post,theta}-{MeanPower}_{pre,theta}}{{MeanPower}_{pre,theta}}}\right)\times 100=+20\%$$

$$\%ChangeinAlphaPower=\left({\displaystyle \frac{{MeanPower}_{post,alpha}-{MeanPower}_{pre,alpha}}{{MeanPower}_{pre,alpha}}}\right)\times 100=+15\%$$

$$\%ChangeinBetaPower=\left({\displaystyle \frac{{MeanPower}_{post,beta}-{MeanPower}_{pre,beta}}{{MeanPower}_{pre,beta}}}\right)\times 100=-10\%$$

Following Equation (2), a positive percentage change indicates an increase in mean power for that frequency band after the learning experience.

A negative percentage change indicates a decrease in mean power for that frequency band after the learning experience.

The increase in low-frequency (theta) power is exciting since previous studies have shown that theta might be linked to sequential learning [40], a process that may be thought to be the focus of the task used in our study. In particular, theta increase enables subjects to prepare for future actions, such as playing the right note after a previous sequence.

The alpha/beta ratio increases (given that alpha increased and beta decreased in the same period) in another index related to learning, particularly sequential learning. An increase in alpha/theta facilitates the execution of a given sequence, creating a brain tuning that links what is currently being done to what is expected to be done. When someone learns a sequence or distinguishes consistent sequences from inconsistent ones, she can prepare action plans to increase execution speed and prevent errors. It is like if the person learns to predict what will happen. This process is marked by an increased alpha/beta ratio during the task execution [41].

It is important to note that these hypotheses are based on the mean power values for each frequency band and that individual differences in brain function and the specific task being performed can influence the patterns of brain activity observed in the EEG data. Therefore, despite this study representing a significant indication of the possible use of BCI feedback in training, these hypotheses should be considered tentative and subject to further investigation. Additionally, some issues should be considered, as better investigated in the following paragraph.

5.1. Potential Challenges of Using BCI Technology in Education

Despite its potential benefits, one must consider the challenges and limitations of using BCI technology in education. One major challenge is the cost. BCI systems are expensive and not widely available, which can limit their use in classrooms. However, as technology advances and becomes more affordable, this may become less of a barrier. Currently, some commercial devices (https://neurosky.com/, https://www.emotiv.com/ and https://choosemuse.com/, all accessed on 18 March 2025) are low-cost, widely used in research, and tested perfectly comparable to more expensive ones. Also, they are wireless or Bluetooth, cable-free, allowing users to feel more comfortable, avoid stress, and move freely in a real or virtual environment, making them suitable for training.

Another challenge is that teachers and other education professionals may need training in BCI technology and interpreting its data, which can be a limitation for some schools and educational institutions. Anyway, the need for training could be addressed through several approaches:

• Through the development of user-friendly interfaces to simplify the use of BCI technology (such as the traffic light and scrollbar system presented in this study);
• Adopting methods such as machine learning to analyze brain activity and automatically adjust the system parameters to optimize the performance for individual users without extensive training;
• Gamification techniques can also be used to make BCI training more engaging and motivating;
• Support materials like videos and manuals can help users learn how to use BCI technology effectively.

By making BCI-based tools more user-friendly, automated, engaging, and supported, the need for specialized training to use BCI technology effectively can be minimized.

Privacy and security concerns are also a potential challenge when using BCI tools in education. BCI technology involves collecting and analyzing sensitive data, such as brain activity. It is essential to ensure these data are kept secure and protected from unauthorized access or use [42]. Some strategies to help protect BCI data include encryption, user authentication restricting access to data to authorized users only, data storage in secure locations, and data anonymization to protect the privacy of individuals. In addition, BCI data should be managed in compliance with relevant regulations, such as the General Data Protection Regulation (GDPR) (Regulation, 2018) or the Health Insurance Portability and Accountability Act (HIPAA) [43]. This includes obtaining consent from individuals, notifying individuals of any data breaches, and implementing appropriate data protection measures. This latter point also recalls some ethical considerations [44] that must be addressed when using BCI technology in education. For example, it is vital to ensure that BCI is voluntary and that students understand how their data will be used, not to feel judged. It is essential to consider potential biases in the data and ensure that the technology is not aimed at disadvantaging certain student groups unfairly. For example, participants must be provided with sufficient information about the nature of the study and the risks and benefits associated with BCI to make an informed decision about whether to participate. All participants must give informed consent before participating in the study. This informed consent should also include an indication of data and privacy protection. Furthermore, the use of BCI in education must be fair and accessible to all individuals, regardless of their socioeconomic status, gender, race, or disability, without discriminating against individuals or inequities in access to educational opportunities.

Additional issues that should be known are related to possible health-related risks. Using brain-guided tools in education may cause fatigue, headaches, or other adverse effects.

The ethical considerations associated with using BCI technology in education require careful consideration and attention to ensure responsible and ethical use. Researchers and educators must adhere to moral principles and guidelines, such as the Belmont Report [45], to protect participants’ rights and well-being.

5.2. Implications

The findings of this study underscore the transformative potential of BCI technology in education, particularly in skill acquisition and training. The notable improvement in guitar performance among participants who received real-time neurofeedback indicates that BCIs can enhance cognitive engagement, focus, and learning efficiency. This holds significant implications for educational environments, where adaptive learning frameworks can be developed to cater to students’ individual needs.

Beyond music education, the study highlights the potential applications of BCIs in various fields, including language learning, sports training, and rehabilitation. By offering personalized feedback based on cognitive and neural activity, BCIs can assist learners in honing their skills and improving performance outcomes. However, the practical implementation of this technology encounters challenges, such as cost, accessibility, and ethical concerns related to data privacy. Future research should aim to develop cost-effective and user-friendly BCI systems while exploring their integration with emerging technologies like virtual and augmented reality to enhance immersive learning experiences.

This study makes a valuable contribution to the expanding field of BCI in education by demonstrating the effectiveness of real-time neurofeedback in skill acquisition. The findings provide empirical evidence that BCIs can enhance learning outcomes by fostering improved focus, cognitive engagement, and coordination. Moreover, the study enhances our understanding of the neural mechanisms that underpin motor skill learning, particularly in the context of musical training. This research offers valuable insights into optimizing BCI applications in educational settings by analyzing EEG data and correlating brainwave activity with performance improvements. Additionally, it underscores the potential for broader applications in adaptive learning, rehabilitation, and cognitive training across various disciplines.

6. Conclusions

The findings of this study highlight the potential of BCI-based neurofeedback to enhance skill acquisition in musical training, particularly for guitar playing. However, the applicability of this approach may extend to other musical instruments, such as wind instruments, percussion, and keyboards, each presenting unique challenges and opportunities. For wind instruments, which require precise breath control and embouchure, BCI systems could monitor and provide feedback on respiratory patterns and cognitive focus, potentially improving synchronization between breathing and musical execution. In the case of percussion, where rhythmic precision and motor coordination are critical, BCI feedback could assist in refining timing and limb coordination by detecting and reinforcing neural patterns associated with rhythmic accuracy. For keyboard instruments, which demand simultaneous cognitive and motor engagement across both hands, BCI systems could offer insights into hemispheric coordination and attentional balance, aiding in the development of bimanual dexterity. In future research, we intend to explore these applications, taking into account the distinct physiological and cognitive demands of each instrument type, to further validate and optimize BCI-based training methodologies across diverse musical domains.

At this stage, despite the limited number of participants in the experiments and the fact that additional investigation should be performed to give a more granular individual assessment, the study gave exciting indications about the possible use of BCI-based feedback in training. Feedback on brain activity helped participants in the experiment regulate their attention and focus, resulting in better performance. The BCI group showed significantly higher scores on the post-training guitar test and improved accuracy than the control group. This approach could be applied to other types of skill development in various domains, such as sports or language learning, to provide more personalized and practical training.

The use of BCI technology in education is still in its early stages, but there is great potential for its application in the classroom. One potential future direction is the development of more specialized BCI-based systems explicitly designed for educational purposes, making them more accessible and user-friendly. In particular, students and teachers could be involved in targeted research to design and implement systems that are attuned to the specific needs of the education setting. Another potential direction is integrating BCI technology with other emerging technologies, such as virtual and augmented reality. This integration could create new opportunities for interactive and immersive learning experiences. Finally, multi-brain–computer interfaces [46] (B2CI, Vanutelli & Lucchiari, 2022) could be developed and applied to small groups or classes in order to monitor other essential factors such as group cohesion, group creativity, cooperation, and joint strategies to enhance shared experiences and learning.

In conclusion, the development of BCI-based tools in education has the potential to revolutionize teaching and learning by creating new opportunities for personalized, interactive, and engaging educational experiences. While some challenges and limitations are still present, the potential benefits of this technology make it an exciting area of research and development.