A revolutionary brain-computer interface (BCI) system, powered by quantum-enhanced AI, now enables individuals with mobility impairments to control wheelchairs using their brain signals, offering new hope for independent movement.
Researchers at the Birla Institute of Technology-Mesra have developed a brain-computer interface (BCI) system capable of translating electrical brain signals into real-time wheelchair navigation commands, using a hybrid quantum-enhanced deep learning model, an official said.
BCI systems are being explored as assistive technologies for individuals with conditions such as spinal cord injury, stroke, amyotrophic lateral sclerosis (ALS) and cerebral palsy, where independent mobility remains a major challenge, he said.
"The system, termed Hybrid Quantum-Enhanced CNN-LSTM (HQeCL), integrates electroencephalography (EEG) signal analysis methods with convolutional neural networks, long short-term memory networks and quantum-inspired feature processing," said Dr Prabhat Kumar Upadhyay, Assistant Professor in the Department of Electrical and Electronics Engineering.
He said the model analyses frequency-domain activity, spatial signal patterns across electrodes and non-linear signal complexity simultaneously, enabling more reliable detection of intended movement commands than conventional EEG-based systems, while maintaining speeds suitable for assistive devices.
During simulations, the system achieved a classification accuracy of 92.71 per cent with an average response time of 77.6 milliseconds, allowing near real-time wheelchair control. It recorded a false positive rate of 2.8 per cent compared to 5.2 per cent for conventional CNN-LSTM models, reducing unintended movements, he claimed.
The model uses around 0.12 million parametres, indicating suitability for deployment in portable assistive devices with limited computational resources and battery capacity, Upadhyay added.
EEG data for the study were recorded at the institute using an eight-channel wireless system from participants without prior experience in BCI tasks or motor imagery training, enhancing its real-world applicability.
The exercise was supported by the Indian Council of Medical Research, which funded the procurement of EEG recording equipment used in the trials.
The study aims to develop reliable, real-time brain-controlled assistive mobility systems capable of operating under practical constraints such as latency, safety, computational cost and user variability, he said.