The Application of Wearable Electroencephalogram-Based

Neurofeedback in Attention-Deficit/Hyperactivity Disorder:

a Brain-Computer Interface Solution for Enhancing Attention

Langyan Zhu

Bard College at Simon’s Rock, Great Barrington, Massachusetts, U.S.A.

Keywords: Neurofeedback, Attention-Deficit/Hyperactivity Disorder (ADHD), Wearable Electroencephalogram

(EEG).

Abstract: Wearable electroencephalogram (EEG)-based neurofeedback has emerged as a promising non-

pharmacological approach for improving attention and managing core symptoms of attention-

deficit/hyperactivity disorder (ADHD). By providing immediate visual or auditory cues tied to neural

activity, individuals can learn to self-regulate specific brain rhythms associated with focus, impulsivity, and

hyperactivity. Recent technological advances in electrode design and artifact mitigation now allow for

practical, user-friendly solutions in everyday settings, including home and school environments.

Furthermore, integrating real-time motion tracking with EEG recording enhances data reliability,

particularly for children who tend to be restless during training. Personalized protocols that tailor the

intervention to individual EEG profiles have shown potential in increasing the proportion of successful

learners. In addition, combining EEG neurofeedback with other modalities and complementary behavioral

strategies may further strengthen therapeutic outcomes. This review explores the current state, challenges,

and prospects of wearable EEG neurofeedback for ADHD.

1 INTRODUCTION

Attention-deficit/hyperactivity disorder (ADHD) is

a common neurodevelopmental disorder, affecting

approximately 5% of children worldwide, often

leading to decreased academic performance,

impaired social interactions, and reduced quality

of life (Lansbergen et al. 2011). Traditional

therapeutic methods, such as pharmacological

treatment and behavioral interventions, have

demonstrated efficacy to some extent, yet

frequently come with adverse side effects and

inconsistent long-term effectiveness (Enriquez-

Geppert et al. 2019). Thus, exploring safe, non-

invasive, and sustainable alternative interventions

is of critical importance. In recent years, the rapid

advancement of wearable EEG technology has

opened new avenues for neurofeedback therapy.

Neurofeedback techniques collect real-time EEG

signals and translate specific frequency-band

activity into intuitive feedback, enabling

individuals to conduct self-regulation training in

natural environments and thereby improve their

attentional state (Flanagan & Saikia 2023). This

brain–computer interface-based intervention,

utilizing affordable and portable EEG devices,

overcomes traditional laboratory constraints and

can enhance patient engagement and adherence in

real-world settings such as home and school

(Zamora Blandón et al. 2016). Current studies

indicate that targeted modulation of EEG

parameters—for example, reducing theta-wave

power while enhancing beta-wave activity—can

improve attention control in patients with ADHD

(van Doren et al. 2019). Moreover, several

systematic reviews and meta-analyses have

demonstrated additive therapeutic effects when

EEG neurofeedback is combined with

pharmacological treatments, particularly in

improving core symptoms of ADHD (Lin et al.

2022). This non-invasive intervention not only

offers novel therapeutic approaches in clinical

practice but also lays the groundwork for

personalized and remote-monitoring strategies in

future treatment paradigms (Emish & Young

2024). Furthermore, individualized neurofeedback

programs guided by quantitative EEG (QEEG)

techniques allow tailored training strategies based

174

Zhu, L.

The Application of Wearable Electroencephalogram-Based Neurofeedback in Attention-Deﬁcit/Hyperactivity Disorder: A Brain-Computer Interface Solution for Enhancing Attention.

DOI: 10.5220/0014440200004933

Paper published under CC license (CC BY-NC-ND 4.0)

In Proceedings of the 1st International Conference on Biomedical Engineering and Food Science (BEFS 2025), pages 174-179

ISBN: 978-989-758-789-4

on each patient’s unique EEG characteristics,

potentially leading to more targeted improvements

in attention deficits and paving the way for

personalized medical care (Arns et al. 2012). This

review systematically examines the latest

advancements in wearable EEG-based

neurofeedback for ADHD treatment, emphasizing

its safety, efficacy, and long-term sustainability in

enhancing attention while reducing hyperactive

and impulsive symptoms. By integrating findings

from randomized controlled trials, meta-analyses,

and open-label studies, this paper not only

evaluates the clinical potential of EEG

neurofeedback in treating ADHD but also provides

theoretical guidance for designing future

individualized intervention strategies.

2 CURRENT RESEARCH

METHODS: COMPARATIVE

ANALYSES AND

IMPROVEMENT

RECOMMENDATIONS

Recent EEG-neurofeedback research on ADHD has

employed a diverse range of study designs, spanning

rigorous randomized controlled trials (RCTs) with

double-blind placebo or sham-feedback conditions

to more flexible open-label investigations

(Lansbergen et al. 2011, Enriquez-Geppert et al.

2019, Garcia Pimenta et al. 2021). While the

stringent RCT, double-blind approach can minimize

expectancy bias, its implementation often requires

considerable logistical resources and is not without

ethical implications. Consequently, several studies

use single-blind or open-label frameworks,

acknowledging that open-label designs, though less

cumbersome, remain prone to heightened placebo

effects (Zamora Blandón et al. 2016, Arns et al.

2012, Barth et al. 2021). Participant selection and

randomization strategies also vary: some

investigations focus solely on school-aged children,

whereas others enroll adolescents or adults. Notably,

these choices influence outcomes because factors

such as medication status, ADHD subtypes, and co-

occurring conditions can moderate training efficacy

(Zamora Blandón et al. 2016, Arns et al. 2012).

These divergences further complicate subsequent

meta-analyses, given the heterogeneous methods

that mix different age groups and symptom profiles

(Barth et al. 2021). Moreover, sample sizes in EEG-

neurofeedback trials for ADHD are typically

modest, undermining statistical power when

evaluating group-level changes (van Doren et al.

2019). Many researchers thus advocate multi-center

collaborations or data-sharing initiatives to enlarge

pooled datasets and enhance result generalizability.

In terms of analysis, repeated-measures ANOVAs

and paired t-tests are commonly employed to

compare baseline and post-training improvements.

However, machine learning algorithms are

increasingly being utilized to classify subtle EEG

patterns associated with ADHD (Chauhan & Choi

2023, Yaacob et al. 2023). Such approaches are

well-suited for capturing individualized response

trajectories and detecting potentially overlooked

brain-signal nuances. By moving beyond mere

group-level comparisons, these emerging methods

allow clinicians to account for personal brain

signatures, thereby advancing the prospects for

precision medicine in ADHD. Overall, while

research methodology is strengthening, further

standardization of both design and analysis is crucial

to firmly establish neurofeedback’s clinical

effectiveness and ensure cross-study comparability.

Reported findings indicate that EEG

neurofeedback can reduce core ADHD symptoms—

particularly inattention and impulsivity—across

multiple investigations (Lansbergen et al. 2011,

Garcia Pimenta et al. 2021). Nonetheless, these

apparent benefits should be interpreted judiciously.

A persistent issue involves participant

generalizability: although some individuals

(“learners”) readily acquire and maintain targeted

EEG modulation, others (“non-learners”) show

negligible training effects (Garcia Pimenta et al.

2021, Barth et al. 2021). Such disparities can distort

group-level assessments of neurofeedback outcomes

and may reflect differences in reward sensitivity,

baseline brain patterns, or motivation. Further

complicating the landscape, EEG signals are

notoriously vulnerable to artifacts arising from

muscle tension, eye blinks, or body movement,

especially among children whose restlessness may

substantially degrade signal quality (Zamora

Blandón et al. 2016, Pei et al. 2022). These artifacts

can mask meaningful neuronal patterns, diminishing

the reliability of real-time feedback. Differences in

control conditions also matter. Some studies employ

sham feedback or placebo interventions; others rely

on waiting-list controls or established cognitive

training regimens; and a few compare

neurofeedback directly with stimulant medications.

Because each control condition invokes distinct

nonspecific influences—from expectancy to

coaching—synthesizing results remains

challenging.

Indeed, comparing data across heterogeneous

The Application of Wearable Electroencephalogram-Based Neurofeedback in Attention-Deﬁcit/Hyperactivity Disorder: A Brain-Computer

Interface Solution for Enhancing Attention

175

designs demands considerable caution and

underscores the pressing need for consensus

protocols. In response, scholars have proposed

expanding sample sizes and enhancing

methodological uniformity to minimize random

variation and mitigate nonspecific confounds (van

Doren et al. 2019, Barth et al. 2021). Additionally,

advanced data-processing pipelines featuring robust

artifact rejection can better isolate genuine brain-

signal changes. Another recommended strategy

involves personalizing neurofeedback to each

participant’s QEEG profile (Garcia Pimenta et al.

2021, Barth et al. 2021). For instance, individuals

with abnormal theta/beta ratios might benefit from

frequency-specific training, whereas those

displaying atypical slow cortical potentials could

pursue alternative protocols. This tailored approach

aims to address the “non-learner” challenge by

aligning the feedback strategy with each child’s

neurophysiological profile, potentially increasing the

likelihood of consistent brain-signal modulation and

clinically meaningful outcomes.

3 EQUIPMENT TECHNOLOGY

AND SIGNAL ACQUISITION:

INNOVATIONS AND

OPTIMIZATIONS

Rising demand for at-home ADHD neurofeedback

protocols has accelerated the development of

convenient, user-friendly EEG headsets (Flanagan &

Saikia 2023). Typically, these consumer-grade

devices incorporate fewer electrodes, simplified

signal amplifiers, and faster setup procedures.

Because families can administer sessions

independently, children can receive more frequent

and potentially more ecologically valid training.

However, such portable gear may be especially

susceptible to electromagnetic noise and head-

motion artifacts if a child fidgets during lengthy

sessions. Consequently, stable electrode contact and

low impedance remain crucial. Conventional “wet”

electrodes using conductive gel offer strong

coupling and low resistive noise, but require

extensive preparation time and post-session cleanup,

potentially hindering daily home use. By contrast,

“dry” electrodes promise near-instant application yet

often exhibit higher contact impedance, risking

signal attenuation or drift over repeated movements

(Zamora Blandón et al. 2016, Pei et al. 2022). A

practical compromise has emerged in “semi-dry” or

“half-wet” electrodes that partially maintain

moisture via a minimal reservoir of saline or

hydrogel. These designs can markedly reduce setup

time while avoiding the dryness-induced noise

typical of conventional dry electrodes. Notably, pre-

gelled (PreG) electrodes—packaged with a stable

hydrogel—have gained attention for their quick

application and robust signal fidelity comparable to

standard wet electrodes (Pei et al. 2022). Because

ADHD training sessions may exceed 20–30 minutes,

consistent user comfort is also critical. If electrode

pressure or scalp friction causes irritation, data

quality and participant compliance can deteriorate.

Among pediatric populations, discomfort or time-

consuming routines may undermine adherence.

Consequently, hardware researchers emphasize

ergonomics, ensuring that headbands or caps apply

minimal scalp pressure while maintaining adequate

electrode-skin contact. Although most consumer

EEG solutions feature lower electrode density than

their laboratory-grade counterparts, they show

promise for cost-effectively scaling neurofeedback

interventions to larger ADHD cohorts in realistic

environments.

Beyond hardware innovations, advanced EEG

preprocessing is vital for maximizing data reliability,

particularly in dynamic or home-based settings.

Conventional methods include band-pass filtering

(e.g. 1–45 Hz) to remove low-frequency drifts and

line noise, followed by artifact correction.

Techniques such as independent component analysis

(ICA) excel at isolating ocular or muscle artifacts

from genuine neural oscillations, yet they typically

rely on offline post-processing and cannot fully

safeguard real-time feedback loops from abrupt

signal contamination. Accordingly, recent research

prioritizes integrated artifact detection that operates

continuously, enabling immediate suppression of

spurious signals (Zamora Blandón et al. 2016, Pei et

al. 2022, Yaacob et al. 2023). One promising

strategy involves merging inertial measurement unit

(IMU) sensors with EEG data: headsets equipped

with accelerometers or gyroscopes can track head

motion and automatically discount intervals of

abrupt movement, helping preserve feedback

fidelity. Given that ADHD participants often exhibit

restlessness, such automated artifact removal

contributes to more reliable training. In addition, the

field increasingly advocates standardization in

hardware design and data formatting. Drawing on

precedents in MRI and fNIRS research, many EEG

practitioners endorse Brain Imaging Data Structure

(BIDS)-like guidelines that outline consistent

naming conventions, metadata files, and directory

architectures. Aligning with these protocols reduces

BEFS 2025 - International Conference on Biomedical Engineering and Food Science

176

confusion when merging datasets from multiple sites

and bolsters large-scale meta-analyses. For example,

if certain PreG electrode setups or real-time motion

filters become widespread, researchers relying on

BIDS-based references can compare data more

systematically. In essence, the intersection of refined

electrode technology, continuous artifact mitigation,

and standardized data practices underpins a more

robust, scalable, and clinically viable framework for

EEG-based neurofeedback—bridging the gap

between controlled lab studies and everyday ADHD

interventions in schools or homes.

4 CROSS-DISCIPLINARY

INTEGRATION AND

MULTIMODAL DATA FUSION

IN NEUROFEEDBACK

APPLICATIONS

Traditional ADHD assessments have predominantly

relied on behavior rating inventories (e.g. parent- or

teacher-report scales) and the continuous

performance test (CPT). Although instrumental for

diagnostic screening and follow-up, these measures

can suffer from subjective biases and limited

ecological validity (Wiebe et al. 2023).

Consequently, there is growing interest in

augmenting standard assessments with objective

neurophysiological markers, especially EEG. For

example, a VR-based CPT can situate participants in

a quasi-realistic environment replete with distractors,

while simultaneously recording EEG data to detect

cortical oscillation deviations at moments of

inattention or impulsivity (Wiebe et al. 2023). Such

integrated methods can better identify ADHD

subgroups that fail to filter out irrelevant stimuli,

thereby enhancing diagnostic precision. When self-

reports yield conflicting or unclear outcomes,

corresponding EEG signatures may clarify the

underlying attentional deficits. In both clinical and

research applications, integrating EEG into ADHD

assessment confers dual benefits: it provides

continuous, real-time neural activity to supplement

subjective rating scales, and it enables objective

tracking of therapy responsiveness—whether from

medication, behavioral interventions, or

neurofeedback. Researchers have noted that stable

shifts in fronto-central EEG rhythms frequently

accompany improvements in daily functioning.

Conversely, if post-treatment rating scales suggest

progress but EEG metrics remain largely unchanged,

clinicians might investigate whether external biases

inflated subjective judgments. Thus, combining

qualitative and quantitative insights can yield a more

comprehensive and trustworthy view of patient

progress. Early results from integrated protocols

show that repeated self-regulation of specific EEG

rhythms—guided by continuous neural feedback—

may help participants sustain improvements beyond

training sessions. Observing these gains in more

naturalistic tasks, such as VR-based or real-world

scenarios, reinforces confidence in the potential

generalizability of EEG-based interventions.

However, broader clinical adoption will require

greater uniformity in VR task designs, outcome

metrics, and data-analytics pipelines.

From a human–computer interaction (HCI)

perspective, neurofeedback systems must provide

feedback that meaningfully engages users with

ADHD without overloading their cognitive capacity.

Virtual reality (VR) offers a promising solution:

immediate visual and auditory cues in an immersive

environment can promote active participation.

Preliminary studies suggest that integrating VR into

EEG neurofeedback training can boost user

motivation and sustain interest, potentially reducing

dropout rates (Cho et al. 2004). Designing such

systems demands attention to interface clarity,

adjustable task difficulty, and minimal latency to

ensure tight coupling between neural events and on-

screen feedback. On a broader scale, multimodal

approaches that combine EEG with functional near-

infrared spectroscopy (fNIRS), eye-tracking, or

peripheral physiological measures (e.g. heart rate) are

becoming increasingly prevalent (Emish & Young

2024, Chen et al. 2024). Each

modality contributes

distinct information—fNIRS reveals cerebral

hemodynamics in the prefrontal cortex, eye-tracking

uncovers gaze shifts to irrelevant stimuli, and heart-

rate variability indicates arousal or stress levels.

Collectively, these signals yield a more holistic

understanding of ADHD’s diverse manifestations.

Nonetheless, researchers must address

synchronization issues due to varying sampling rates

or temporal resolutions, highlighting the need for

unified triggers, shared reference frames, and

integrated software frameworks. Another obstacle

lies in the absence of consistent standards for

multimodal setups, including recommended electrode

or emitter placements and validated data fusion

algorithms. Following the BIDS initiative, experts

are championing universal protocols specifying

metadata formats, data-collection timing, and file

structures for combined EEG–fNIRS–eye-tracking

recordings (Pernet et al. 2019, Chen et al. 2024).

Once established, such guidelines can strengthen data

The Application of Wearable Electroencephalogram-Based Neurofeedback in Attention-Deﬁcit/Hyperactivity Disorder: A Brain-Computer

Interface Solution for Enhancing Attention

177

quality, reproducibility, and cross-laboratory

collaboration. Ultimately, refining these multimodal

neurofeedback systems will depend on

interdisciplinary partnerships among neuroscientists,

engineers, clinicians, and HCI specialists. Future

platforms that seamlessly integrate multiple

biometrics, adapt training dynamically in real time,

and maximize ecological validity may prove

instrumental in optimizing ADHD interventions and

expanding their clinical impact.

5 CONCLUSION

Advances in wearable EEG neurofeedback for

ADHD have offered new avenues for improving

attentional regulation and addressing core symptoms

such as inattention, hyperactivity, and impulsivity.

Across various studies, advancements in device

design—ranging from PreG and semi-dry electrodes

to sophisticated artifact-rejection algorithms—have

led to greater convenience and reliability in data

acquisition. By reducing setup time and enhancing

comfort, these developments aid consistent user

adherence, a critical requirement given the need for

repeated neurofeedback sessions. Furthermore,

home-friendly EEG systems are increasingly

recognized for their ecological validity, as children

and adolescents often respond more naturally in

familiar day-to-day environments than they would in

clinical laboratories. While many trials report

encouraging outcomes—particularly reductions in

inattention and impulsivity—findings must be

viewed with caution due to methodological

disparities and limited sample sizes. Notably, a

recent meta-analysis focusing on self-reported

outcomes found no significant advantage of

neurofeedback over control interventions on core

ADHD symptom ratings (Fan et al. 2022). The

heterogeneity of control conditions further

complicates the extraction of firm conclusions.

Additionally, the phenomenon of “learners” versus

“non-learners” underscores substantial inter-

individual variability. Some participants master EEG

self-regulation with relative ease, whereas others

show negligible change in their cortical rhythms or

behavioral measures. For researchers, pinpointing

why some individuals respond more favorably than

others remains a key challenge. One potential

answer lies in tailoring training protocols according

to each participant’s QEEG profile. Although these

personalized approaches have demonstrated

promise, larger-scale and multi-center studies are

needed to systematically assess their superiority over

“one-size-fits-all” methods.

On the technical side, real-time artifact detection

has emerged as a vital component for ensuring robust

feedback loops. By incorporating IMUs into

wearable headsets, clinicians can swiftly filter out

data segments compromised by motion or muscle

activity. This integration of additional sensors not

only preserves data quality but also aligns well with

modern trends in multimodal neuroscience research.

Synchronizing these signals, however, requires

carefully harmonized hardware/software solutions as

well as shared standards, analogous to the BIDS

initiative. Although efforts toward such

standardization are ongoing, more concerted cross-

disciplinary collaborations—spanning neuroscience,

engineering, data science, and clinical practice—

could rapidly accelerate the refinement of

multimodal neurofeedback frameworks. From a

clinical standpoint, combining EEG neurofeedback

with psychosocial or behavioral therapies may

bolster overall treatment outcomes, particularly

parents and teachers remain engaged and supportive.

Early evidence suggests that such integrated

interventions can yield improvements not only in

core ADHD symptoms but also in related behavioral

or cognitive domains (Luo et al. 2023). Nonetheless,

further validation via randomized, multi-center trials

is crucial to solidify claims of lasting therapeutic

benefit. Another avenue involves bridging

neurofeedback with psychopharmacology.

Preliminary meta-analyses indicate that

neurofeedback may act synergistically with stimulant

medications by either lowering the required dosage

or complementing existing regimens (Lin et al.

2022). More extensive comparative-effectiveness

studies should clarify the longevity and relative

efficacy of these combination strategies.

In sum, wearable EEG neurofeedback for ADHD

has reached a notable inflection point: hardware

miniaturization, improved electrodes, and advanced

machine learning techniques have converged to

create systems that may soon become routine in both

clinical and home settings. Still, critical challenges

loom. Researchers must resolve inconsistencies in

outcome measures and refine best-practice protocols

for open-label and blinded studies alike.

Concurrently, the field should prioritize larger

sample sizes, standard data formats, and real-time

noise mitigation to ensure replicable, high-quality

findings. Ultimately, by combining technical

ingenuity with robust methodological design, EEG

neurofeedback stands poised to advance from an

emerging adjunctive therapy to a mainstay

intervention for ADHD—one that can be flexibly

BEFS 2025 - International Conference on Biomedical Engineering and Food Science

178

adapted to individual neurophysiological profiles and

seamlessly integrated into daily life.

REFERENCES

Arns, M., Drinkenburg, W., & Kenemans, J. L. 2012. The

effects of QEEG-informed neurofeedback in ADHD:

an open-label pilot study. Applied Psychophysiology

and Biofeedback 37(3): 171–180.

Barth, B., Mayer-Carius, K., & Strehl, U., et al. 2021. A

randomized-controlled neurofeedback trial in adult

attention-deficit/hyperactivity disorder. Scientific

Reports 11: 16873.

Chauhan, N. & Choi, B.-J. 2023. Regional contribution in

electrophysiological-based classifications of attention-

deficit/hyperactivity disorder using machine learning.

Computation 11(9): 180.

Chen, J., Yu, K., & Bi, Y., et al. 2024. Strategic

integration: a cross-disciplinary review of the fNIRS-

EEG dual-modality imaging system for delivering

multimodal neuroimaging to applications. Brain

Sciences 14(10): 1022.

Cho, B.-H., Kim, S., & Shin, D. I., et al. 2004.

Neurofeedback training with virtual reality for

inattention and impulsiveness. CyberPsychology &

Behavior 7(5): 519–526.

Emish, M. & Young, S. D. 2024. Remote wearable

neuroimaging devices for health monitoring and

neurophenotyping: a scoping review. Biomimetics

9(4): 237.

Enriquez-Geppert, S., Smit, D., & Garcia Pimenta, M., et

al. 2019. Neurofeedback as a treatment intervention in

ADHD: current evidence and practice. Current

Psychiatry Reports 21(6): 46.

Fan, H.Y., Sun, C.K., & Cheng, Y.S., et al. 2022. A pilot

meta-analysis on self-reported efficacy of

neurofeedback for adolescents and adults with ADHD.

Scientific Reports 12: 9958.

Flanagan, K. & Saikia, M. J. 2023. Consumer-grade

electroencephalogram and functional near-infrared

spectroscopy neurofeedback technologies for mental

health and wellbeing. Sensors 23(20): 8482.

Garcia Pimenta, M., Brown, T., & Arns, M., et al. 2021.

Treatment efficacy and clinical effectiveness of EEG

neurofeedback as a personalized and multimodal

treatment in ADHD: a critical review.

Neuropsychiatric Disease and Treatment 17: 637–648.

Lansbergen, M. M., van Dongen-Boomsma, M., &

Buitelaar, J. K., et al. 2011. ADHD and EEG-

neurofeedback: a double-blind randomized placebo-

controlled feasibility study. Journal of Neural

Transmission 118(2): 275–284.

Lin, F.L., Sun, C.K., & Cheng, Y.S., et al. 2022. Additive

effects of EEG neurofeedback on medications for

ADHD: a systematic review and meta-analysis.

Scientific Reports 12: 20401.

Luo, X., Zhang, L., & Xia, L., et al. 2023. Efficacy of

behavior modification training combined with

electroencephalographic biofeedback therapy for

ADHD in children: a randomized controlled trial.

Frontiers in Child and Adolescent Psychiatry 2:

1235310.

Pei, W., Wu, X., & Zhang, X., et al. 2022. A pre-gelled

EEG electrode and its application in SSVEP-based

BCI. IEEE Transactions on Neural Systems and

Rehabilitation Engineering

30: 843–850.

Pernet, C. R., Appelhoff, S., & Gorgolewski, K. J., et al.

2019. EEG-BIDS, an extension to the brain imaging

data structure for electroencephalography. Scientific

Data 6: 103.

van Doren, J., Arns, M., & Heinrich, H., et al. 2019.

Sustained effects of neurofeedback in ADHD: a

systematic review and meta-analysis. European Child

& Adolescent Psychiatry 28(3): 293–305.

Wiebe, A., Aslan, B., & Brockmann, C., et al. 2023.

Multimodal assessment of adult attention-deficit

hyperactivity disorder: a controlled virtual seminar

room study. Clinical Psychology & Psychotherapy

30(5): 1111–1129.

Yaacob, H., Hossain, F., & Shari, S., et al. 2023.

Application of artificial intelligence techniques for

BCI in mental fatigue detection: a systematic review

(2011–2022). IEEE Access 11: 74736–74758.

Zamora Blandón, D., Muñoz, J. E., & Lopez, D. S., et al.

2016. Influence of a BCI neurofeedback videogame in

children with ADHD: quantifying the brain activity

through an EEG signal processing dedicated toolbox.

2016 IEEE 11th Colombian Computing Conference

(CCC): 1–8.

The Application of Wearable Electroencephalogram-Based Neurofeedback in Attention-Deﬁcit/Hyperactivity Disorder: A Brain-Computer

Interface Solution for Enhancing Attention

179