Skip to article
AHFE AHFE Discoveries AHFE International Open Access Journal
AHFE OPEN ACCESS OPEN ACCESS CONFERENCE PROCEEDINGS PAPER

From Clinic to Space and Back Again: A Neuroadaptive Systems Approach to Optimized Human Performance

NTLGroup, Inc, Cave Creek, Az 85331, USA ↗
Publication year
Digital Object Identifier10.54941/ahfe1006759

Abstract

This paper presents a bifurcated model of EEG-based human–system integration, delineating two functionally distinct pathways: clinical recovery and neuroadaptive performance. The clinical recovery pathway targets persistent trait-level impairments from psychiatric, neurological, or developmental conditions using advanced signal processing techniques—including source-localized EEG, joint component ICA (JC-ICA)—to improve diagnostic accuracy and guide personalized interventions. In contrast, the neuroadaptive performance pathway addresses transient state-level fluctuations in healthy individuals, embedding real-time EEG metrics into dynamic environments such as aviation and adaptive gaming to sustain cognitive control and optimize performance under high workload and uncertainty. Together, these approaches support both adaptive responsiveness and proactive augmentation—marking a paradigm shift in cognitive engineering and human–machine teaming. Though methodologically aligned, they differ in goals, operational contexts, and populations. Maintaining this distinction enables more precise system design, ethical deployment, and scientific validation. The dual-pathway model thus provides a foundation for next-generation EEG-integrated technologies across clinical neuroscience and applied neuroergonomics.

INTRODUCTION

The integration of electroencephalography (EEG) into human–system interfaces is reshaping both clinical rehabilitation and performance- driven applications. A bifurcated model has emerged, defining two complementary roles for EEG-guided systems: (1) clinical recovery, focused on diagnosing and remediating neurological and psychiatric impairments, and (2) neuroadaptive performance, aimed at dynamically modulating system behaviour in response to real-time cognitive state fluctuations (Adey, 1963).

This distinction—between trait-level restoration and state-level modulation—anchors the evolving landscape of EEG applications, with both pathways supporting enhanced cognitive readiness and task fluency. Clinical systems aim to rebuild disrupted neural scaffolding, while neuroadaptive systems optimize the moment-to-moment deployment of cognitive resources in situ (Adey, 1963).

© 2025. Published by AHFE Open Access. All rights reserved. 36

From Clinic to Space and Back Again: A Neuroadaptive Systems Approach 37

Government and research initiatives increasingly reflect this dual imperative. DARPA’s Targeted Neuroplasticity Training (TNT) program explores non-invasive neurotechnologies to enhance learning via EEG- guided stimulation. NASA’s Multi-Modal Neurodiagnostic Tool monitors behavioural health in analog space missions using EEG-based state tracking. The U.S. Air Force’s 711th Human Performance Wing leverages EEG to sustain resilience and accelerate decision-making via real-time adaptive training (AFRL, 2023; Carrle et al., 2023; Cripe, 2025).

Historically, EEG’s dual utility evolved along two paths: operational and clinical. NASA’s early EEG digitization efforts in the 1960s established real-time brain monitoring for astronaut resilience under stress, catalysing neurometric models for adaptive state quantification (Cripe et al., 2021). Simultaneously, clinical EEG applications took shape in Sweden and at NYU, giving rise to remediation protocols grounded in cognitive rehabilitation and psychiatric diagnostics (DARPA, 2017; Ellis et al., 2024; John et al., 1977; Makeig et al., 1996).

Together, these streams form the foundation of modern EEG-based systems that not only detect and correct dysfunction but also expand cognitive capacity through real-time adaptation and long-term neural optimization.

Two dominant EEG system classes have emerged in practice:

1. Clinical Remediation Systems – targeting dysfunctional or underdeveloped cognitive traits via structured neuroadaptive protocols. 2. Neuroadaptive Performance Systems – modulating state-level brain dynamics in high-functioning individuals during task execution.

This paper illustrates this bifurcated model through two field-tested systems developed by the author. The first, NeuroCoach®, is engineered for clinical populations and employs EEG-guided neuroadaptive training. This approach integrates source-localized z-score targeting, cognitive remediation protocols, and adaptive feedback to support neural circuit recovery in individuals with TBI, substance use disorders, and trauma-induced dysregulation.

The second system, IQity®, was developed for enhancing real- time cognitive performance in high-functioning individuals—such as astronaut candidates—by monitoring EEG markers of situational awareness, executive function, and task-state fluency. This system was deployed in university-led NASA analog habitat studies. While both systems share a neurometric foundation—including ICA preprocessing, source localization, and normative z-scoring—they diverge in architecture, theoretical orientation, and user engagement, enabling tailored application across clinical, operational, and human-systems integration domains.

These implementations represent modern instantiations—not origin points—of two distinct neuroadaptive design paradigms. This paper delineates the theoretical models, toolchains, and system-level implications of each, offering a blueprint for deployment in areas such as behavioural medicine, education, aerospace, and neuroergonomics.

38 Cripe

To support this model, we analyse differentiating methods and goals. For instance, clinical systems incorporate clinical recordings of diagnosis-based EEG data to improve early detection of psychiatric conditions. In contrast, neuroadaptive performance systems embed continuous EEG feedback into real-time environments—such as aviation, gaming, and simulation— modulating interface parameters in response to fatigue, attentional drift, and workload. Through this dual lens, the paper formalizes a translational framework for future EEG-integrated human–system technologies.

FUNCTIONAL OBJECTIVES OF EEG-GUIDED SYSTEMS EEG-based systems serve two primary functions in cognitive neuroscience and neuroadaptive engineering: (1) cognitive remediation and (2) neuroadaptive performance optimization. Though both utilize EEG acquisition and analysis, they diverge in goals, populations, and outcomes. Remediation systems aim to restore disrupted neural traits in clinical populations, while performance systems modulate transient brain states in healthy individuals navigating high-demand environments.

This section outlines these two pathways—beginning with clinical recovery (2.1), followed by neuroadaptive performance systems (Section 3)—detailing their functional targets, methodologies, and validation approaches.

Clinical Recovery Applications Clinical EEG systems diagnose, monitor, and treat psychiatric and neurological disorders (e.g., MDD, PTSD, ADHD, mTBI). These systems prioritize objective neural assessment to improve diagnostic accuracy and treatment tracking, especially when self-reporting is limited (Adey, 1963; NASA, 2012).

Historically reliant on subjective measures, psychiatric diagnosis is now increasingly supported by EEG-based tools that detect abnormal brain activity and connectivity patterns. For instance, Carrle et al. (2023) demonstrated that GAN-generated synthetic EEG data can augment training datasets, improving diagnostic model sensitivity for MDD detection.

This reflects a broader movement to standardize EEG biomarkers in psychiatric protocols—paving the way for early detection, personalized care, and data-driven recovery planning.

EEG-Guided Remediation Systems Remediation systems address trait-level disruptions in core neurocognitive functions—executive control, working memory, emotional regulation— caused by injury, psychiatric disorders, or developmental delays. These systems use source-localized z-score comparisons to identify targets such as power deviations, coherence abnormalities, and maladaptive phase relationships.

Core therapeutic goals include:

  • Circuit Restoration: Normalize hypo-/hyperactive regions (e.g., DMN, FPN).
  • Network Synchronization: Reintegrate disrupted large-scale systems.

From Clinic to Space and Back Again: A Neuroadaptive Systems Approach 39

  • Affective Regulation: Enhance top-down prefrontal-limbic control.
  • Cognitive Load Management: Balance theta/beta ratios; reduce gamma instability.
  • Executive Function Recovery: Improve DLPFC–ACC connectivity and control.

Training typically involves guided neurofeedback using structured protocols (e.g., MAP1–MAP3) with progressive EEG normalization and behavioral metrics (e.g., BRIEF-A, Millon, WJIII) to track outcomes.

Importantly, remediation systems are not designed to enhance performance in healthy individuals, but to re-establish cognitive scaffolding necessary for functional independence and later use of adaptive systems.

EEG Biomarkers in Clinical Diagnosis Reliable EEG biomarkers are increasingly used for diagnosis, stratification, and treatment prediction in psychiatric and cognitive disorders. Biomarkers include:

  • Frequency band deviations (theta, alpha, beta)
  • Coherence and connectivity disruptions (DMN, FPN)
  • ERP components (e.g., P300 in MDD/PTSD) Synthetic data aids classifier training, while real EEG data—via source- localized modeling and JC-ICA—anchors findings in clinical neurobiology. This dual approach strengthens model reliability and interpretability, enabling hybrid diagnostic systems that use real-time data against machine- trained classifiers for early detection and targeted intervention.

Clinical Case Study: MDD and Substance Use Two recent studies highlight EEG-guided recovery:

1. Cripe et al. (2022) – A randomized controlled trial showed that outpatient substance abuse treatment augmented with EEG-based BCI protocols significantly improved sobriety and executive function, using personalized cognitive control training. 2. Ellis et al. (2024) – Applied deep learning to EEG data from MDD patients, achieving high classification accuracy by identifying delta, theta, and alpha band biomarkers across frontal and occipital regions.

Key findings:

  • EEG-based interventions improved outcomes in addiction and depression.
  • Machine learning enabled reliable MDD classification using spectral EEG features.
  • Both approaches support precision psychiatry, enabling individualized EEG-guided care.

40 Cripe

These examples underscore EEG’s transformative potential in clinical recovery—offering scalable, personalized, and objective tools for psychiatric treatment and early detection.

NEUROADAPTIVE PERFORMANCE IN EEG-BASED HUMAN–SYSTEM INTEGRATION Concept: Real-Time Cognitive Adaptation

Neuroadaptive performance refers to a system’s ability to dynamically adjust in response to real-time fluctuations in a user’s cognitive state, using EEG signals as input. This approach is essential in high-stakes environments—such as aviation, defense, and adaptive training—where continuous awareness, attention regulation, and cognitive fluency are critical.

In neuroergonomics, EEG enables real-time detection of attentional shifts, workload thresholds, and fatigue. Systems use this data to adapt task complexity, interface design, or automation level, transitioning from static control systems to co-adaptive architectures that blend physiological monitoring with cognitive modelling.

EEG-Based Cognitive State Assessment EEG provides high temporal resolution for monitoring fast-changing brain states. Neuroadaptive systems track:

  • Frontal Theta: Signals increased cognitive control or working memory load.
  • Parietal Alpha Suppression: Indicates attentional engagement or mental effort.
  • ERP Components (e.g., P300): Reflect stimulus recognition, decision latency, and situational awareness.
  • Coherence & Phase Dynamics: Identify early signs of cognitive strain, lapses in executive control, or fatigue.

These metrics are continuously analysed to trigger closed-loop interventions—e.g., task pacing, alerts, interface adjustments—to maintain optimal alignment between brain state and task demand.

Practical Applications - Aviation EEG-informed passive BCIs (pBCIs) enhance pilot safety by detecting lapses in cognitive engagement. For example, ERP-based classifiers trained on oddball paradigms (P300 response to target tones) have been used to trigger heads-up cues during simulated flight—preemptively mitigating breakdowns in attention and reducing out-of-the-loop risk.

Neuroadaptive Cognitive Modelling A key evolution in the field is integrating EEG data into computational cognitive models, enhancing prediction and system responsiveness. In one study, incorporating pBCI-derived ERP metrics into a flight decision-making model improved accuracy from 72% to 87%. Real-time EEG reduced

From Clinic to Space and Back Again: A Neuroadaptive Systems Approach 41

model uncertainty, offering a feedback loop where physiological input refines behavioral prediction—enabling human–system optimization beyond behavioral rules alone.

Cognitive Targets and Training Goals of Neuroadaptive Systems Unlike remediation systems, neuroadaptive platforms like IQity® focus on state-level optimization in healthy individuals. These systems continuously monitor and respond to subtle shifts in cognitive resources, offering proactive support to sustain performance.

Key EEG-informed indices include:

  • Focus Stability Index (FSI)
  • Mental Agility Index (MAI)
  • Task-State Performance Resilience Index (TSPRI) Core cognitive targets:
  • Sustained Attention: Monitor coherence drift to prompt focus recovery.
  • Fatigue Detection: Identify rising frontal theta to cue micro-breaks.
  • Mode Transitions: Support fluid shifts between planning, execution, and recovery modes.
  • Emotion–Cognition Integration: Stabilize VAN/iSEC network activity to reduce emotional disruption of task performance.
  • Working Memory Load: Track alpha/beta dynamics to modulate load- balancing.

Field trials confirm efficacy: EEG-based alerts have predicted performance errors up to 10 seconds in advance. In NASA/UND analog missions, IQity® EEG baselines flagged cognitive misalignment under pressure, prompting real-time corrective protocols using coherence markers (e.g., Fz–Pz beta).

These systems are anchored in cognitive science models such as Global Neuronal Workspace Theory (GNWT), Cognitive Load Theory (CLT), and Higher-Order Thought (HOT). They promote adaptive mastery and self- regulation, not by correcting dysfunction, but by augmenting cognitive fluency in the moment (Adey, 1963).

COMPARATIVE ANALYSIS OF THE BIFURCATED MODEL COMPONENTS Distinctive Features of Clinical Recovery and Neuroadaptive Performance

The bifurcated model of EEG-based human–system integration can be viewed as two synergistic components that, while distinct in their applications and methodologies, share common technical foundations. A comparative analysis reveals the following key distinctions and commonalities found in Table 1.

42 Cripe

Table 1: Comparison of clinical recovery vs. neuroadaptive performance (Adey, 1963; Carrle et al., 2023).

Table available in the original PDF paper.

Feature/Aspect Clinical Recovery Neuroadaptive Performance Primary Objective Diagnosis, monitoring, and treatment of disorders Real-time adaptation of systems based on cognitive state Data Requirements

Continuous, real-time EEG monitoring with emphasis on dynamic changes

High-quality, annotated EEG recordings and synthetic data augmentation for rare pathological patterns Key Biomarkers ERPs (e.g., P300), frequency power shifts in alpha, theta, and beta bands

ERPs, alpha/theta power changes, network connectivity patterns Typical Applications

Diagnosis of conditions such as major depressive disorder; tracking treatment efficacy

Flight simulation, adaptive gaming, workplace cognitive support environments Algorithmic Approaches

Deep learning, generative adversarial networks, statistical pattern recognition

Machine learning classifiers, cognitive modeling, passive brain–computer interfaces Integration Strategy

Real-time system adaptation, cognitive load management, and user state predictions

Augmentation of existing clinical protocols with objective EEG-based biomarkers

This table highlights how clinical recovery relies on retrospective analysis of EEG biomarkers to diagnose and monitor conditions, while neuroadaptive performance leverages immediate EEG feedback to continuously adjust system parameters. Despite these differences, both components demand rigorous signal processing and advanced machine learning techniques to interpret the highly noisy and variable EEG data.

Synergy Between Diagnostic and Adaptive Approaches While clinical remediation and neuroadaptive performance address distinct objectives—long-term trait restoration versus real-time state optimization— they are inherently complementary. Advances in one domain increasingly enhance the other. For instance, synthetic EEG data generation using GANs, initially developed to boost diagnostic sensitivity for Major Depressive Disorder (MDD), can also improve classifier accuracy in neuroadaptive systems that monitor pilot attention and cognitive engagement.

This methodological overlap enables a synergistic model, where clinical tools inform adaptive system design, and real-time neuroadaptive monitoring feeds back into longitudinal assessment. By integrating clinical recovery protocols with cognitive state modelling, future platforms can deliver both moment-to-moment performance tuning and long-term neural health tracking within a unified EEG-guided framework.

From Clinic to Space and Back Again: A Neuroadaptive Systems Approach 43

METHODOLOGICAL AND TECHNICAL CONSIDERATIONS Signal Acquisition and Pre-Processing

Reliable EEG signal acquisition is the foundational step in any human–system integration model. A wide spectrum of EEG hardware is now available ranging from traditional wet electrode systems, known for their spatial resolution, to newer dry and mobile EEG systems that prioritize comfort and usability. While wet systems are ideal for high-precision clinical recordings, they suffer from cumbersome setup and limited real-world applicability. In contrast, mobile dry systems enable long-term, in-field recordings but may introduce challenges with signal-to-noise ratio (SNR).

Regardless of hardware, robust signal pre-processing is non-negotiable. Techniques such as band-pass filtering (typically 2–30 Hz using Kaiser FIR filters), independent component analysis (ICA) for artifact rejection, and subject-level normalization are essential to isolate usable neural data. Fast Fourier Transforms (FFT) then extract key spectral features—such as frontal theta or parietal alpha power—feeding these metrics into real-time monitoring or cognitive models. These steps transform noisy raw signals into actionable neurometrics that inform both clinical and adaptive decisions.

Classifier Design and Cognitive Modelling Both clinical and neuroadaptive EEG systems rely heavily on machine learning classifiers—but their design priorities differ:

  • Clinical Recovery Models: Classifiers are optimized to detect trait- level dysfunctions—e.g., distinguishing MDD from healthy controls based on frontal alpha asymmetry or theta coherence. Deep learning approaches (CNNs, SVMs) trained on both real and synthetic EEG datasets consistently outperform traditional metrics, identifying subtle, previously unmodeled biomarkers.
  • Neuroadaptive Systems: Here, classifiers must be responsive to moment- to-moment shifts in user state. ERP-based classifiers (e.g., P300 detection in oddball paradigms) or power-spectrum models continuously monitor mental workload, attention, and fatigue. A classifier trained to detect auditory alert engagement in flight simulations achieved 86% accuracy— far exceeding the baseline of 78%—by integrating ERP signatures into a real-time feedback loop.

Together, these classifiers form the core of neuroadaptive cognitive models, combining EEG inputs with top-down cognitive architectures to predict behavior, reduce epistemic uncertainty, and improve system reactivity.

Real-Time Feedback and Adaptive System Integration At the systems level, EEG-based platforms function through closed-loop architectures that continuously adapt based on neural feedback. A full neuroadaptive pipeline includes:

44 Cripe

1. Data Acquisition – Continuous EEG recording via mobile or fixed platforms. 2. Pre-Processing – Artifact rejection, segmentation, and filtering. 3. Feature Extraction – FFT-derived power, ERP metrics, or connectivity estimates. 4. Classification – Cognitive or clinical state inference using trained models. 5. Adaptation Loop – System responses (e.g., UI shifts, difficulty tuning, diagnostic feedback) triggered in real time.

A strong example comes from a dry electrode-based flight simulation study, where real-time ERP monitoring of pilot attention was used to trigger interface adjustments. By embedding EEG-derived situational awareness into the simulation logic, system accuracy in predicting cognitive breakdowns rose from 72% (behavior-only model) to 87% (EEG-augmented neuroadaptive model)—a 15-point gain in anticipatory precision with direct safety implications.

Visualization: Comparative Analysis Table of Methodological Techniques Below is a table (Table 2) summarizing the key methodological techniques and their respective applications in both the clinical recovery and neuroadaptive performance branches.

Table 2: Summary of key methodological techniques in clinical recovery and neuroadaptive performance (Adey, 1963; Carrle et al., 2023; Cripe, 2025).

Table available in the original PDF paper.

Methodological Technique Application in Clinical Recovery

Application in Neuroadaptive Performance EEG Signal Acquisition High-resolution, artifact- free recordings for diagnosis Continuous, real-time recordings in dynamic settings Pre-Processing Methods Band-pass filtering, ICA, normalization

Real-time filtering, event segmentation, FFT for rapid analysis Data Augmentation (Synthetic EEG)

GANs for generating annotated EEG datasets

Augmentation to simulate various cognitive states Classifier Design Deep neural networks, SVMs for diagnostic classification

ERP-based classifiers for distinguishing cognitive load Cognitive Modeling Integration of biomarker patterns for disease prediction

Neuroadaptive cognitive modeling integrating pBCI outputs Real-Time Adaptation Diagnostic monitoring and treatment feedback

Dynamic adjustment of systems (e.g., flight simulators, games)

From Clinic to Space and Back Again: A Neuroadaptive Systems Approach 45

FUTURE DIRECTIONS AND ETHICAL CONSIDERATIONS Advances in Wearable EEG and Computational Models

The future of EEG-based human–system integration is closely tied to the evolution of hardware and computational architecture. A major leap forward is occurring in wearable EEG sensor design—with dry electrodes, in- ear systems, and smart textiles. Simultaneously, next-generation machine learning models are expanding the interpretability and precision of EEG analysis show strong promise in increasing classification accuracy and resolving subtle temporal shifts in cognitive state.

Integration of Multimodal Data for Richer Contextual Models EEG alone offers a valuable window into brain activity—but combining it with multimodal physiological inputs expands that window into a panoramic view of the mind–body system. Researchers are now fusing EEG with: (1) Cardiovascular markers (e.g., HRV), (2) Eye tracking (e.g., saccade patterns, pupil dilation), (3) Skin conductance (e.g., stress/arousal indicators). This sensor fusion approach enhances reliability and enables the construction of context-aware cognitive models. Advanced systems will include data fusion layers capable of aligning asynchronous inputs, weighting modality contributions, and resolving conflicts between signals—all in real time. This multimodal integration represents the next frontier in neuroadaptive system robustness and personalization.

Managing Uncertainty in Real-Time Cognitive Models A critical technical challenge is the management of uncertainty in both physiological data streams and inferred cognitive states. Two forms of uncertainty are particularly relevant: (1) Epistemic uncertainty: stemming from gaps in model knowledge or training data. Neuroadaptive models that integrate EEG signals can reduce this form significantly. In one study, such models decreased epistemic uncertainty from 0.28 to 0.13, showing stronger predictive reliability under dynamic conditions; (2) Aleatory uncertainty: representing the inherent randomness in biological signals—e.g., transient muscle twitches, environmental noise, or individual variability. This is harder to eliminate but can be bounded through rigorous signal pre-processing (e.g., ICA, real-time artifact rejection) and resilient model training across diverse populations and task contexts. The future of EEG-based integration depends on systems that are not just accurate in ideal conditions, but robust to variability, noise, and ambiguity—especially in mission-critical domains like spaceflight, emergency response, or behavioral health.

Ethical and Regulatory Considerations in EEG Deployment As EEG-based systems extend into consumer, clinical, and enterprise domains, ethical safeguards must evolve accordingly. Key issues include: (1) Data privacy and informed consent: EEG reveals sensitive cognitive and emotional states. Users must be fully informed about what is collected, how

46 Cripe

it’s used, and who has access; (2) Autonomy and interpretive caution: Over- reliance on algorithmic outputs—especially in clinical or hiring settings— raises risks of misinterpretation and reduced human agency; (3) Bias and fairness: EEG classifiers trained on homogeneous datasets may misclassify signals from underrepresented populations. Diversity in training sets and transparency in model logic are critical to preventing algorithmic harm.

To address these challenges, emerging EEG platforms should be governed by interdisciplinary oversight boards, integrating expertise from neuroscience, AI ethics, clinical care, and law. Regulatory bodies (e.g., FDA, EMA) will also need to update medical device classifications and data governance rules to include EEG-based digital therapeutics and adaptive interfaces. Ultimately, as these technologies grow in power and reach, so too must our commitment to ethical stewardship and human-centered design.

CONCLUSION

EEG-based human–system integration follows two complementary but functionally distinct pathways: clinical recovery and neuroadaptive performance. While both leverage shared methodologies—such as signal acquisition, advanced preprocessing, and machine learning—their goals, target populations, and operational frameworks differ.

Clinical models focus on diagnosing and remediating trait-level disruptions stemming from psychiatric, neurological, or developmental conditions. They use normative deviation analysis (e.g., swLORETA z-scores), JC-ICA, and synthetic data to identify deficits in executive control, emotional regulation, and working memory—guiding personalized therapeutic interventions in disorders like MDD, PTSD, and ADHD.

In contrast, neuroadaptive models optimize state-level performance in healthy individuals by monitoring transient cognitive shifts—such as fatigue or attentional lapses—relative to individualized baselines. These real-time systems embed EEG-derived metrics into environments (e.g., flight sims, adaptive gaming) to dynamically adjust interface control, task difficulty, and feedback—enhancing cognitive fluency and resilience without targeting dysfunction.

Despite technical overlap, these represent distinct paradigms: one stabilizes impaired systems; the other augments high-functioning ones. This bifurcation reflects key theoretical differences—trait vs. state, remediation vs. optimization, and population norms vs. individual baselines.

As EEG technologies evolve, maintaining this distinction will enable more precise, ethical, and effective applications. A clear dual-model framework ensures that interventions align with user needs, preserve conceptual boundaries, and advance both clinical care and human–system performance.

REFERENCES

Adey, W. R. (1963). The nature of cerebral integration. Brain Research, 3(4), 367–388. AFRL. (2023, May 25). AFRL researchers accelerate learning, enable decision

superiority. U.S. Air Force Research Laboratory.

From Clinic to Space and Back Again: A Neuroadaptive Systems Approach 47

Carrle FP, Hollenbenders Y and Reichenbach A (2023) Generation of synthetic EEG data for training algorithms supporting the diagnosis of major depressive disorder. Front. Neurosci. 17:1219133. doi: 10.3389/fnins.2023.1219133. Cripe, C. (2025). Real-Time Cognitive Tools for Space Systems. In: Tareq Ahram, Waldemar Karwowski, Carlo Martino, Giuseppe Di Bucchianico and Vincenzo Maselli (eds) Intelligent Human Systems Integration (IHSI 2025): Integrating People and Intelligent Systems. AHFE (2025) International Conference. AHFE Open Access, vol. 160. AHFE International, http://doi.org/ 10.54941/ahfe1005813. Cripe, C. T., Cooper, R., Mikulecky, P., Huang, J. H., & Hack, D. C. (2021). Improved

mild closed head traumatic brain injury outcomes with a brain-computer interface amplified cognitive remediation training. Cureus, 13(5), e14996. https://doi.org/ 10.7759/cureus.14996 DARPA. (2017, May 31). Targeted Neuroplasticity Training (TNT). Defense Advanced Research Projects Agency. https://www.darpa.mil/research/programs/ targeted-neuroplasticity-training Ellis, C. A., Lapera Sancho, M., Miller, R. L., & Calhoun, V. D. (2024, March 21).

Identifying EEG biomarkers of depression with novel explainable deep learning architectures [Preprint]. bioRxiv. https://doi.org/10.1101/2024.03.19.585728 John, E. R., Prichep, L. S., et al. (1977). Neurometrics: Clinical applications. Journal of Neuropsychiatry, 9(4), 444–463. Makeig, S. et al. (1996). ICA for EEG data. NeuroImage, 4(3), 145–168. NASA. (2012). Multi-Modal Neurodiagnostic Tool for Assessing Cognitive State.

NASA TechPort. https://techport.nasa.gov/view/12894 Pope, A. T., Bogart, E. H., & Bartolome, D. S. (1995). Biocybernetic system evaluation. Biological Psychology, 40(1–2), 95–111. Thatcher, R. W. (1992). Cyclic cortical reorganization. Human Brain Mapping, 1(4),

224–234.

Cover of the proceedings volume Human Systems Engineering and Design (IHSED2025): Future Trends and Applications

Explore the complete digital volume

Human Systems Engineering and Design (IHSED2025): Future Trends and Applications

Read this individual research paper free through the original publisher, or explore the full digital proceedings book.

ISBN 978-1-964867-74-8

Explore this ISBN in the AHFE Bookstore Listed in the July 2026 bookstore catalogue; search by ISBN to confirm current availability · Digital book purchase optional

Explore Related Research

Related research 8 matches

More papers from this volume

← Back to Research ExplorerBrowse the full library →