AI-powered wheelchair uses Transformer EEG model for advanced BCI control

Researchers have developed a novel AI-powered Brain-Computer Interface (BCI) system for wheelchair control, utilizing electroencephalogram (EEG) data from motor imagery. The system, named TFormerEEG, employs a Transformer-based deep learning architecture to classify right-hand and left-hand movements, achieving a test accuracy of 93.04%. This approach demonstrated a mean accuracy of 91.18% through cross-validation, outperforming baseline models like XGBoost and EEGNet. A Tkinter-based interface simulates wheelchair navigation based on these classified movements. AI

IMPACT This research advances the capabilities of AI-driven BCIs, potentially improving assistive technologies for individuals with mobility impairments.

RANK_REASON The cluster describes a research paper detailing a new AI model and its performance on a specific task. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• arXiv
• Bipul Thapa
• EEG-Deformer
• EEGNet: a compact convolutional neural network for EEG-based brain-computer interfaces
• Hugging Face
• TFormerEEG
• Tkinter
• XGBoost

• paper
• model release
• product

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →