EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Neuro-Informatics Approaches for Human-Machine Interaction and Brain-Inspired Artificial Intelligence

Safa Al- Shamma, David Baldwin

Frontora · 2023

DOI: 10.70945/f.v01i01.003 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontora, 2023. Verfasst von Safa Al- Shamma und 1 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Neuro-informatics integrates computational neuroscience and artificial intelligence to model human cognition, enabling more precise, adaptive, and ethically aligned human–machine interaction within cognitive informatics frameworks.

Objective

To evaluate neuro-informatic algorithms’ predictive performance and brain-inspired architectures in enhancing cognitive–machine synchronization, emotional recognition, and decision precision using multimodal neurophysiological datasets derived from controlled human–machine experiments.

Methods

This study enrolled 144 participants (mean age = 41.8 ± 7.9 years) at the Royal Bournemouth Hospital. Multimodal data—including EEG (32-channel), EMG, eye-tracking, and galvanic skin response—were analyzed using deep spiking neural networks, principal component reduction, and multivariate regression. Statistical significance was determined using ANOVA, Pearson correlation, and paired t-tests (p < 0.05) via SPSS v26.0.

Results

Neuro-adaptive synchronization accuracy improved significantly from 72.6 ± 8.4% to 91.3 ± 5.7% (p < 0.001). Mean EEG coherence increased from 0.42 ± 0.11 to 0.68 ± 0.09 (p = 0.002), while signal-to-noise ratio improved 35.2% (95% CI: 28.1–41.9). Emotional recognition precision rose from 77.4 ± 6.8% to 89.6 ± 5.1% (p < 0.001). Task-specific decision latency decreased from 0.84 ± 0.12 s to 0.59 ± 0.09 s (p = 0.004). Correlation between cortical activation density and adaptive network learning rate was r = 0.82 (p < 0.001). The integrated connectome-based AI model explained 78.6% of performance variance (Adjusted R² = 0.78, p < 0.001). Variability in attention indices decreased by 18.3% (SD ± 2.4), confirming enhanced stability of human-machine coupling.

Conclusion

Neuro-informatic integration substantially optimizes human–machine symbiosis, improving cognitive alignment, accuracy, and response efficiency. Brain-inspired AI provides a transformative framework for adaptive automation and cognitive augmentation in translational neurotechnology.

Zitieren

APA

Shamma, S. A., & Baldwin, D. (2023). Neuro-Informatics Approaches for Human-Machine Interaction and Brain-Inspired Artificial Intelligence. Frontora. https://doi.org/10.70945/f.v01i01.003

Vancouver

Shamma SA, Baldwin D. Neuro-Informatics Approaches for Human-Machine Interaction and Brain-Inspired Artificial Intelligence. Frontora. 2023. doi:10.70945/f.v01i01.003

BibTeX
@article{Shamma2023,
  author = {Shamma, Safa Al- and Baldwin, David},
  title = {Neuro-Informatics Approaches for Human-Machine Interaction and Brain-Inspired Artificial Intelligence},
  journal = {Frontora},
  year = {2023},
  doi = {10.70945/f.v01i01.003}
}
Kostenlos starten →