A comprehensive review of AI-based brain-computer interface with prefrontal cortex and sensory-motor rhythms systemization for rehabilitation
Background: Brain–Computer Interface (BCI) is a prominent sector for multidisciplinary research, since advances in neuroscience and neurorehabilitation strengthen the brain's capacity for communication and interaction with its surroundings. Moreover, as Artificial Intelligence (AI) develops, th...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-09-01
|
| Series: | Results in Engineering |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2590123025025526 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Background: Brain–Computer Interface (BCI) is a prominent sector for multidisciplinary research, since advances in neuroscience and neurorehabilitation strengthen the brain's capacity for communication and interaction with its surroundings. Moreover, as Artificial Intelligence (AI) develops, there is a huge increase in fascination with the prefrontal cortex (eye state) and sensory motor rhythms (motor imagery) from Electroencephalogram (EEG) systemization for BCI-related movement, visual, rehabilitation, and textual applications based on AI. Motivation: The key gaps in the multidisciplinary field of BCI are limited generalizability in the classification of motor imagery (MI) states or eye state conditions. It can be filled by this comprehensive review study's investigation of the published literature related to the categorization of MI and eye state conditions for EEG-based BCI implementations. Methods: This review mainly analyses the four distinct states of the brain from EEG signals, including MI of right-hand movements, MI of left-hand movements, eyes open, and eyes closed states. For better understanding, an updated categorisation of the existing techniques has been provided. Appropriate works in the field have validated an exhaustive account of the signal processing approaches, like preprocessing, feature extraction, and classification. This review article is conveniently offered by the statistical descriptions of the numerical outcomes in the form of tables for the classification results with different datasets. Key findings: The results show that the random forest classifier is more suitable for eye state classification, achieving an accuracy up to 99.80 %, and support vector machine classification provides a higher accuracy of 100 % for MI conditions. Conclusion: These findings provide insight into the combined works of eye state and MI categorization. In the future, BCI will develop through this fusion work, and it offers the directional based movements of the assistive device for rehabilitation. |
|---|---|
| ISSN: | 2590-1230 |