Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
5.6
2.8
Journals
Brain Sciences
Special Issues
Robot and Brain–Computer Interface Therapies for Neurorehabilitation: Current State of...
share announcement

Robot and Brain–Computer Interface Therapies for Neurorehabilitation: Current State of the Art and Applications

A special issue of Brain Sciences (ISSN 2076-3425). This special issue belongs to the section "Neurorehabilitation".

Deadline for manuscript submissions: 20 June 2026 | Viewed by 1747

Special Issue Editor

Dr. Amin Hekmatmanesh

E-Mail Website
Guest Editor
Mechanical Engineering, LUT School of Energy Systems, LUT University, Lappeenranta, Finland
Interests: (bio)signal processing; machine learning; brain computer interface; health monitoring systems; mathematical models; control robot
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Brain–computer Interface (BCI) technology has been introduced to improve the quality of life of people with disabilities or difficulties in their daily lives. BCI applications such as driver assistance, sleep identification for drivers, and controlling bionic hand/ankle–foot orthosis are widely used by healthy people as well as paralyzed patients. BCI studies are not limited exclusively to EEG signals; indeed, other biosignals such as EMG, ECG, and GSR have proven beneficial in BCI applications. Research in the field mainly focuses on the development of mathematical calculations for brain-controlled vehicles, brain-controlled air vehicles, brain-controlled bionic hands, and brain-controlled foot–ankle braces using biosignals collected via electroencephalogram (EEG), electrooculogram (EOG), and electromyogram (EMG). Mathematical implementations are divided into five main steps: (1) pre-processing, (2) feature extraction, (3) feature selection, (4) classification, and (5) statistical analysis.

There are also some challenges in the field related to the identification of patterns generated in EEG signals due to motion intention or motion imagination, referred to as event-related synchronization and desynchronization (ERD/ERS). Depending on the BCI tasks, other patterns are generated in EEG signals that are also worthy of attention. These include readiness potentials, steady-state visual evoked potentials, P300s, and generated local evoked potential patterns. Some of the most well-known mathematical formulas and techniques for detecting EEG patterns are wavelets, common spatial patterns, and nonlinear calculations such as chaotic features (entropy, Lyapunov exponent, fractal dimensions, and recurrence graphs). It is also necessary to implement handcrafted features to increase the efficiency of the algorithms. Another challenge is linked to the development of classifiers to automate the procedures, such as support vector machines, deep learning, and neural networks.

BCI and rehabilitation projects have various limitations. In this Special Issue, we intend to focus on mathematical solutions based on signal denoising (filtering), feature extraction, and machine learning algorithms. This collection of articles aims to highlight mathematical innovations as well as new ideas for designing tasks to induce the generation of distinctive neuronal patterns within the brain. Our ultimate goal is to discover novel methods for use in BCI applications. We welcome manuscripts on the following subtopics:

  • Decoding brain neuron activities by developing mathematical methods for identifying patterns within the EEG signals automatically
  • Identifying EEG patterns relative to human actions and decisions automatically
  • Analyzing the patterns generated in a designed task to find out which method is more beneficial, for example, wavelet, chaotic methods, common spatial patterns, or reinforcing methods.

The development of classifiers to automate the identification procedures

Dr. Amin Hekmatmanesh
Guest Editor

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. Brain Sciences 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 2200 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.

Keywords

  • robot
  • brain computer interface
  • neurorehabilitation
  • machine learning

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.

Further information on MDPI's Special Issue policies can be found here.

Published Papers (3 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

Jump to: Other

31 pages, 2552 KB  
Article
Hippotherapy for Children with Autism Spectrum Disorder: Executive Function and Electrophysiological Outcomes
by Zahra Mansourjozan, Sepehr Foroughi, Amin Hekmatmanesh, Mohammad Mahdi Amini and Hamidreza Taheri Torbati
Brain Sci. 2026, 16(4), 413; https://doi.org/10.3390/brainsci16040413 - 14 Apr 2026
Cited by 1 | Viewed by 517
Abstract
Background: Hippotherapy, a sensorimotor-rich intervention proposed for children with Autism Spectrum Disorder (ASD), is suggested to influence executive function (EF). However, the underlying electrophysiological mechanisms, particularly changes observed in resting-state Electroencephalography (EEG), remain underexplored. Methods: A total of forty-eight children with ASD, aged [...] Read more.
Background: Hippotherapy, a sensorimotor-rich intervention proposed for children with Autism Spectrum Disorder (ASD), is suggested to influence executive function (EF). However, the underlying electrophysiological mechanisms, particularly changes observed in resting-state Electroencephalography (EEG), remain underexplored. Methods: A total of forty-eight children with ASD, aged 9–12 years, participated in this quasi-experimental, non-randomized pre-test–post-test study. Participants were assigned to either a standardized 12-session hippotherapy program (n = 24) or a waitlist Control group (n = 24). EF was evaluated pre- and post-intervention using validated measures: the Wisconsin Card Sorting Test, Stroop Color–Word Test, Corsi Block-Tapping Task, and Tower of London. Resting-state EEG data (19 channels, 250 Hz) were recorded before and after the intervention and analyzed for spectral power, pairwise Pearson correlation, phase-based functional connectivity using the Phase Lag Index (PLI), and directed effective connectivity using Phase Transfer Entropy (PTE). EEG effects were tested with linear mixed models in MATLAB (fitlme), with the measured values in each ROI as the dependent variable, group and time as fixed effects, and SubjectID included as a random intercept; EF outcomes were analyzed with ANCOVA/MANCOVA, adjusting post-test scores for baseline. The assumptions of homogeneity of slopes, Levene’s test, and the Shapiro–Wilk test were examined, and the Holm–Bonferroni correction together with partial η2 effect sizes were reported. Results: Following baseline adjustment, the hippotherapy group showed substantial and statistically significant improvements across all EF measures compared with controls partial η2 range = 0.473–0.855; all adjusted p < 0.001; e.g., Stroop Incongruent Reaction Time (F(1,45) = 265.80, p < 0.001, ηp2 = 0.855). EEG analyses revealed localized Group × Time interaction effects involving frontal delta power as well as selected alpha-, theta-, and beta-band connectivity measures within frontally anchored networks. In addition to these focal interaction effects, the hippotherapy group exhibited a narrower distribution of pre–post EEG changes across spectral power and connectivity metrics compared with controls, indicating greater temporal consistency in resting-state electrophysiological dynamics across sessions. Because group allocation was non-random (based on scheduling feasibility and parental preference), results should be interpreted as associations rather than causal effects. While the hippotherapy group exhibited significant EF improvements and relative stabilization in EEG spectral and connectivity metrics, particularly in frontal delta/theta/alpha/beta bands, a direct mapping between individual EEG changes and behavioral gains was not observed. Conclusions: A standardized 12-session hippotherapy program was associated with substantial improvements in EF and with relative stabilization of resting-state electrophysiological dynamics in children with ASD. However, the direct mechanistic link between these EEG and behavioral changes warrants further investigation. Larger randomized trials employing active control conditions, task-evoked electrophysiological measures, and extended longitudinal follow-up are needed to confirm efficacy, clarify mechanisms, and establish the durability of effects. Full article
(This article belongs to the Special Issue Robot and Brain–Computer Interface Therapies for Neurorehabilitation: Current State of the Art and Applications)
►▼ Show Figures

Figure 1

18 pages, 526 KB  
Article
Maximizing Single-Feature Separability for Improving Transfer Learning in Motor Imagery EEG Decoding
by Zefeng Xu and Zhuliang Yu
Brain Sci. 2026, 16(2), 230; https://doi.org/10.3390/brainsci16020230 - 14 Feb 2026
Viewed by 700
Abstract
Background/Objectives: Motor imagery (MI) EEG-based brain–computer interfaces (BCIs) are promising for neurorehabilitation, but practical use is often hindered by time-consuming per-user calibration and performance instability across sessions/users. Methods: To mitigate this issue, we aim to improve subject-dependent MI classification by leveraging labeled training [...] Read more.
Background/Objectives: Motor imagery (MI) EEG-based brain–computer interfaces (BCIs) are promising for neurorehabilitation, but practical use is often hindered by time-consuming per-user calibration and performance instability across sessions/users. Methods: To mitigate this issue, we aim to improve subject-dependent MI classification by leveraging labeled training data from other subjects within the same dataset via transfer learning. We propose Maximizing Single-Feature Separability (MSFS), a lightweight plug-in regularization applied during target–subject fine-tuning. MSFS operates on the network feature layer and constructs batch-wise target positions by maximizing a silhouette-based separability criterion for each feature dimension. The target position computation is implemented in a fully vectorized GPU-friendly manner. Results: We evaluate MSFS on BCI Competition IV-2a and IV-2b datasets using three representative backbone networks (EEGNet, ShallowConvNet, ATCNet). MSFS consistently improves standard transfer learning across both datasets and all backbones. When compared against representative transfer learning algorithms from the literature, MSFS remains competitive against the literature baselines. Ablation analysis confirms the effectiveness of each algorithm component. Few-shot experiments further indicate that MSFS is still beneficial when the target subject provides limited labeled data. Conclusions: MSFS provides a within-dataset transfer learning enhancement for MI EEG decoding, improving target–subject accuracy under limited calibration data without relying on external datasets, and can be readily integrated into common deep MI classification pipelines. Full article
(This article belongs to the Special Issue Robot and Brain–Computer Interface Therapies for Neurorehabilitation: Current State of the Art and Applications)
►▼ Show Figures

Figure 1

Other

Jump to: Research

24 pages, 1086 KB  
Systematic Review
Effects of Brain-Computer Interface-Controlled Hand Robot Training on Post-Stroke Recovery of Upper Limb Motor Functions: A Meta-Analysis of Dose-Matched Randomized Controlled Trials
by Song Hu, Fengjiao Wang, Xiaoxue Gao, Yong Zhi and Daehee Kim
Brain Sci. 2026, 16(6), 552; https://doi.org/10.3390/brainsci16060552 - 22 May 2026
Viewed by 69
Abstract
Objective: To systematically evaluate the rehabilitation effect of brain-computer interface (BCI)-controlled hand robot training on post-stroke motor functions, especially upper limb functions. Methods: PubMed, Embase, Web of Science, Cochrane Library, CNKI, SinoMed, WanFang Data, and VIP Database were searched from inception [...] Read more.
Objective: To systematically evaluate the rehabilitation effect of brain-computer interface (BCI)-controlled hand robot training on post-stroke motor functions, especially upper limb functions. Methods: PubMed, Embase, Web of Science, Cochrane Library, CNKI, SinoMed, WanFang Data, and VIP Database were searched from inception to 13 March 2026. Randomized controlled trials (RCTs) with dose-matched designs were included, where the test group underwent BCI-controlled hand robot training and the control group received either pure hand robot training or routine rehabilitation. Meta-analysis was performed on RevMan 5.4. Results: Totally 11 RCTs involving 380 patients were included. Compared with hand robot training alone, BCI-controlled hand robot training significantly improved Fugl-Meyer Assessment for Upper Extremity (FMA-UE) scores (MD = 4.87, 95% CI: 1.04 to 8.69) and FMA-UE proximal scores (MD = 4.44, 95% CI: 0.15 to 8.74), and significantly reduced finger flexor spasticity (MD = −0.44, 95% CI: −0.68 to −0.21), but showed no significant difference in distal upper limb motor function or Action Research Arm Test (ARAT) scores. Compared with routine rehabilitation, BCI-controlled hand robot training significantly improved FMA-UE scores (MD = 6.55, 95% CI: 3.49 to 9.61). Conclusions: BCI-controlled hand robot training can effectively improve overall upper limb and proximal motor function after stroke and alleviate finger flexor spasticity, but the evidence for distal hand function and long-term efficacy remains limited. Full article
(This article belongs to the Special Issue Robot and Brain–Computer Interface Therapies for Neurorehabilitation: Current State of the Art and Applications)
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-3
Back to TopTop