The technology known as a brain–computer interface, or BCI, has emerged as a promising means of allowing people with severe physical disabilities to communicate with external devices. A BCI-controlled wheelchair system with GPS and safety features is presented in this paper to enable hands-free and independent mobility. The proposed method uses publicly available EEG datasets for training and testing, in contrast to conventional systems that rely on real- time EEG acquisition hardware. As a result, system cost and complexity are reduced. Using machine learning algorithms like Linear Discriminant Analysis (LDA) and Convolutional Neural Networks (CNN), the system processes pre-recorded EEG signals through stages of preprocessing, feature extraction, and classification. The classified outputs are converted into motion commands for controlling the wheelchair, such as forward, left, right, and stop. The system has ultrasonic sensors for detecting obstacles and falls, as well as a GPS module for real-time location tracking and geofencing, to improve safety. In the event of unsafe conditions or boundary violations, caregivers are also notified by means of an alert mechanism. The proposed system demonstrates a cost-effective, non-invasive, and reliable assistive solution that improves mobility, safety, and independence for physically challenged individuals. The system provides a scalable and accessible alternative to conventional BCI-based wheelchair designs by making use of datasets that are made available to the public.

By enabling hands-free mobility through the use of brain signals, the GPS-controlled Brain-Computer Interface (BCI) wheelchair is an innovative solution for individuals with severe physical disabilities. Users can independently navigate without exerting any physical effort thanks to the system’s successful conversion of EEG signals into movement commands such as forward, left, right, and stop. The system guarantees accurate and dependable command classification by combining signal processing methods with machine learning algorithms like LDA/CNN. The GPS module with geofencing enables continuous location tracking and boundary-based alerts, while the addition of ultrasonic sensors improves safety by detecting obstacles and falls in real time. Additionally, the system is more cost-effective and accessible when public EEG datasets are used for training, reducing the need for costly hardware. By notifying caregivers in critical situations, the emergency alert mechanisms further enhance user safety. Overall, this project demonstrates a low-cost, non-invasive, and intelligent assistive technology that significantly improves mobility, safety, and independence, thereby enhancing the quality of life for physically challenged individuals.

1.D. Huang, K. Qian, X. Fei, and O. Bai, “EEG-based brain- computer interface for wheelchair control,” IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 20, no. 3, pp. 379–389, 2012. 2.Z. T. Al-Qaysi, Z. Z. Kowalski, and M. A. Al-Saadi, “A review of disability EEG-based wheelchair control system,” Biomedical Signal Processing and Control, vol. 43, pp. 297–307, 2018. 3.R. H. Abiyev, N. Akkaya, and E. Aytac, “Brain-computer interface for control of wheelchair using EEG signals,” Expert Systems with Applications, vol. 42, no. 2, pp. 639– 646, 2016. 4.T. Carlson and J. d. R. Millán, “Brain-controlled wheelchairs: A robotic architecture,” IEEE Robotics & Automation Magazine, vol. 20, no. 1, pp. 65–73, 2013. 5.M. F. Ansari, A. Gupta, and S. K. Singh, “Brain-computer interface for wheelchair control operations using hybrid signals,” Journal of King Saud University – Computer and Information Sciences, vol. 31, no. 4, pp. 456–465, 2019. 6.A. Palumbo, F. B. Vialatte, and M. Clerc, “Motor imagery EEG-based brain-computer interfaces for wheelchair control: A review,” IEEE Access, vol. 9, pp. 123456– 123470, 2021. 7.L. Jiang, Y. Zhang, and H. Wang, “SmartRolling: A multi- modal EEG-based smart wheelchair system,” Information Sciences, vol. 620, pp. 250–265, 2023. 8.R. Meligy, M. E. Abd Elaziz, and A. Darwish, “IoT-based smart wheelchair with EEG control and real-time monitoring,” Proceedings of the IEEE International Conference on Smart Healthcare, pp. 1–6, 2024. 9.B. Thapa, S. Shrestha, and R. K. Jha, “EEG-based AI-driven wheelchair using deep learning models,” IEEE Access, vol. 13, pp. 102345–102358, 2025. 10.S. Kumar and P. Singh, “Transformer-based EEG signal classification for assistive mobility systems,” International Journal of Intelligent Systems and Technologies, vol. 14, no. 2, pp. 89–102, 2025.

© 2025 International Journal of Engineering and Techniques (IJET).

Digital Object Identifier (DOI)

IJET assigns a unique DOI to every accepted article via Zenodo for persistent linking and citation. Your article’s DOI: https://doi.org/{{doi}}

Open DOI About Zenodo DOI

Close