Brain-Controlled Assistive Device Using EEG and IoT for Physically Disabled

The developed Brain-Controlled Assistive Device using EEG and IoT technology demonstrates the feasibility of controlling electrical appliances through concentration-based brain activity. The proposed system successfully acquires EEG signals using gel electrodes, processes them through the BioAmp EXG Pill and Arduino UNO R4 WiFi, and transmits control commands wirelessly using HC-05 Bluetooth modules. The experimental implementation confirmed that the user's concentration level could be utilized to control a relay-operated bulb without requiring any physical interaction. Although the developed prototype successfully demonstrated real-time appliance control, the performance of the system is influenced by factors such as signal noise, electrode placement, and variations in user concentration. In some cases, maintaining a stable concentration level for prolonged periods may affect the consistency of system operation. Therefore, further improvements in signal acquisition and processing techniques are necessary to enhance system reliability and responsiveness. The proposed system can be further improved by collecting a larger set of EEG data and implementing advanced signal-processing or machine-learning algorithms for more accurate concentration detection. The use of additional EEG channels and improved electrode configurations may also increase signal quality and system accuracy. Furthermore, integrating multiple control commands could enable the operation of several appliances simultaneously, thereby expanding the functionality of the system. The results obtained from this work indicate that EEG-based Brain–Computer Interface technology has significant potential for assistive applications. With further optimization and testing, the proposed system could be effectively deployed in real-world environments to improve the independence and quality of life of physically disabled individuals. Future work will focus on enhancing accuracy, supporting multiple device control, and evaluating system performance under different users and operating conditions.

[1] R. Meligy, A. R. Ahmad, and S. Mekid, “An IoT-Based Smart Wheelchair with EEG Control and Vital Sign Monitoring,” Engineering Proceedings, vol. 82, no. 1, pp. 46, 2024. [2] S. Ramadhani, A. Hidayat, and R. Putra, “A Systematic Review of EEG-Based Assistive Devices and Brain–Computer Interface Applications,” ASEAN Journal of Electrical and Electronic EngiNeering Technology, vol. 3, no. 1, pp. 1–12, 2024. [3] A. Sharma, R. Patel, and P. Singh, “EEG-Based IoT Smart Home Automation System for Assistive Applications,” International Journal of Advanced Research in Computer Science and Electronics Engineering, vol. 11, no. 4, pp. 45–52, 2022. [4] M. Palumbo, A. Coronato, and G. De Pietro, “A Systematic Review of EEG-Based BCI Applications for Wheelchair Control,” Sensors, vol. 21, no. 3, pp. 1–21, 2021. [5] A. Meligy, M. Abouelatta, and A. Eladl, “An IoT-Based Smart Wheelchair with EEG Control and Vital Sign Monitoring,” MDPI Electronics, vol. 13, no. 2, pp. 1–15, 2024. [6] R. Barea, L. Boquete, M. Mazo, and E. López, “System for Assisted Mobility Using EEG-Based Brain–Computer Interfaces,” IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 10, no. 4, pp. 209–218, 2022. [7] A. K. Jain and S. Shukla, “Real-Time Brainwave Monitoring Using EEG and IoT for Disabled Persons,” International Journal of Advanced Research in Electronics and Communication Engineering (IJARECE), vol. 11, no. 6, pp. 220–227, 2023. [8] P. Kumar and S. Dey, “IoT Enabled Assistive System for Physically Challenged Using Brainwave Sensor,” IEEE International Conference on Communication and Signal Processing (ICCSP), Chennai, India, pp. 111–115, 2023. [9] L. M. Mathew, P. Anil, S. John, V. Anilkumar, and S. S., “Brain-Computer Interface for Mouse Automation,” International Journal of Engineering Technology Research & Management (IJETRM), May 2024. [10] N. V. S. Sasi Preetham, V. Koushik, and S. Paneerselvam, “Enhancing Quality of Life: An AI-Enabled Assistive System Integrating BCI and Transformer Model for Elderly and Disabled Individuals,” in Proceedings of the International Conference on Computing, Communication and Networking Technologies (ICCCNT), IEEE, 2024, doi: 10.1109/ICCCNT61001.2024.10725697.