NEURO-HOLOGRAPHY: TRANSLATING BRAIN SIGNALS INTO 3D VISUALS

This paper presented Neuro-Holography, a Brain–Computer Interface framework designed to interpret EEG signals and convert them into assistive commands and visual outputs. The proposed system integrates EEG signal preprocessing, feature extraction using the Common Spatial Pattern (CSP) algorithm, and machine learning–based classification to identify motor imagery tasks such as left hand, right hand, feet, and tongue movements. Two machine learning classifiers, Support Vector Machine (SVM) and Random Forest (RF), were implemented and evaluated for motor imagery classification. Experimental results demonstrated that the SVM classifier achieved the highest classification accuracy of 85.46%, outperforming the Random Forest model and confirming the effectiveness of the CSP–SVM pipeline for EEG signal interpretation. The classified signals were utilized in two output modules: an assistive control simulation module, which demonstrates brain-driven wheelchair navigation commands, and a brain-to-AI visualization module, which converts interpreted neural patterns into visual outputs using artificial intelligence models. Although the current implementation operates in a simulation-based environment, the results highlight the potential of integrating EEG signal interpretation with AI-based visualization systems. Future work may focus on integrating real-time EEG acquisition hardware, improving classification performance through advanced machine learning techniques, and developing more immersive visualization interfaces. Overall, the Neuro-Holography framework demonstrates how Brain–Computer Interface technology can extend beyond traditional command control to enable intuitive human–computer interaction through neural signal decoding and visual representation.

 1] F. Lotte, M. Congedo, A. Lécuyer, F. Lamarche, and B. Arnaldi, “A Review of Classification Algorithms for EEG-Based Brain–Computer Interfaces,” Journal of Neural Engineering, vol. 4, no. 2, pp. R1–R13, 2007. Available: https://pubmed.ncbi.nlm.nih.gov/17409472/ [2] S. A. A. Shiam, et al., “Motor Imagery Classification Using Effective Channel Selection in EEG-BCI Systems,” Brain Sciences, vol. 14, no. 5, 2024. Available: https://www.mdpi.com/2076-3425/14/5/462 [3] X. Wang, et al., “Deep Learning Methods for Motor Imagery EEG Classification: A Survey,” Artificial Intelligence in Medicine, 2023. Available: https://www.sciencedirect.com/science/article/pii/S093336572300252X [4] Y. Bai, X. Wang, and Y. Cao, “DreamDiffusion: Generating High-Quality Images from Brain EEG Signals,” arXiv preprint arXiv:2306.16934, 2023. Available: https://arxiv.org/abs/2306.16934 [5] T. Qu, et al., “NeuroVision: EEG-to-Image Reconstruction via Progressive Neural Encoding,” Expert Systems with Applications, 2026. Available: https://www.sciencedirect.com/science/article/abs/pii/S0957417426004392 [6] K. G. R. Atla, et al., “CNN-Based Motor Imagery EEG Classification,” Alexandria Engineering Journal, 2025. Available: https://www.sciencedirect.com/science/article/pii/S1110016825001681