Advances in Non-Invasive and Hybrid Brain–Computer Interfaces: Signal Processing, AI, and Emerging Semantic Decoding

Dear Colleagues,

Brain–Computer Interfaces (BCIs) are rapidly evolving from laboratory prototypes toward robust real-world systems. Recent progress has been driven by (i) improved non-invasive sensing (EEG and hybrid EEG-based setups), (ii) more reliable signal processing pipelines, and (iii) machine learning and deep learning methods that enhance decoding accuracy, generalization, and usability. At the same time, new application domains are emerging, including neurorehabilitation, assistive communication, closed-loop neurofeedback, and real-time adaptive human–machine interaction.

This Special Issue aims to collect high-quality contributions that advance the state of the art in non-invasive and hybrid BCIs, with an emphasis on methodological rigor, reproducibility, and translational relevance. In particular, it will focus on modern AI-driven decoding, robust feature learning, cross-subject generalization, and next-generation paradigms such as semantic information decoding and intention recognition from brain signals.

Topics of interest include but are not limited to:

Non-invasive BCI systems (EEG) and hybrid BCI configurations (e.g.,EEG+EMG, EG+physiological signals)

Signal processing for BCI: filtering, artifact removal, spatial filtering, time–frequency methods, connectivity, and representation learning

Machine learning and deep learning for BCI (CNNs, RNN/LSTM, Transformers, self-supervised learning, foundation-model approaches)

Robustness and generalization: cross-subject/cross-session adaptation, domain adaptation, calibration reduction, data-efficient learning

Semantic and intention decoding from brain signals; task-independent or higher-level representations

Clinical and translational applications: neurorehabilitation, disorders of consciousness, assistive communication, neuroergonomics

Evaluation best practices: open datasets, benchmarking protocols, interpretability, uncertainty estimation, calibration, and fairness

Real-time BCI, edge/embedded deployment, and closed-loop systems

Privacy, security, and responsible AI considerations in BCI

Expected Contributions:

Original research articles, methodological papers, and high-quality reviews that provide clear experimental protocols, strong baselines, and well-supported conclusions.

Dr. Luca Mesin
Guest Editor

Dr. Hossein Ahmadi
Guest Editor Assistant

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Bioengineering is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2700 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• brain–computer interface (BCI)
• electroencephalography (EEG)
• non-invasive BCI
• hybrid BCI (EEG–EMG)
• EEG signal processing
• artifact removal
• time–frequency analysis
• EEG decoding
• deep learning for EEG
• cross-subject generalization
• domain adaptation
• semantic decoding
• intention recognition