Smart Assistive System for Paralysis People

Abstract

Mobility impairments due to paralysis present significant challenges, limiting independence and daily activities. This research focuses on developing an Electrooculography (EOG)-Based Blink-Controlled Wheelchair, enabling hands-free movement using eye blinks as the primary input. The system utilizes the Bio Amp EXG Pill to capture EOG signals, which are processed by an ESP32microcontrollertodetect voluntaryeye blinks.Asingleblinktriggersforwardmovement,whiletheabsence ofablink stops the wheelchair. To enhance usability, an HTML-based web interface has been integrated, allowing users or caregivers to control the wheelchair in all directions remotely. The system employs an L298N motor driver to regulate two BO motors, ensuring efficient and reliable motion control. The proposed solution offers a cost-effective, power-efficient, and user-friendly alternative to traditional joystick or voice-controlled wheelchairs. The combination of blink-based control for autonomous movement and web-based remote control providesenhancedaccessibilityandflexibility.Futureimprovementsmayincludemachinelearningalgorithmsforbetterblink detection, wireless connectivity for remote monitoring, and adaptive calibration for different users. This research contributes to the advancement of assistive mobility solutions, empowering individuals with paralysis to navigate their surroundings independently.

Introduction

Mobility impairments caused by paralysis or severe motor disabilities greatly reduce individuals’ independence. Traditional wheelchair controls like joysticks or voice commands may not be accessible to these users. This research proposes an assistive wheelchair controlled by eye blinks using Electrooculography (EOG) signals. The system captures eye blink signals via the Bio Amp EXG Pill, processes them with an ESP32 microcontroller, and controls wheelchair movement—one blink moves it forward, no blink stops it. A web-based interface also allows remote manual control for caregivers or users.

The literature highlights the advantages of EOG over more complex brain-computer interfaces, showing high accuracy in detecting voluntary eye blinks and movements for wheelchair navigation. Current challenges include false blink detections and distinguishing voluntary from involuntary blinks, which this project addresses with filtering and signal processing improvements. The system integrates hardware components like electrodes, motor drivers, and a rechargeable battery, with software built on Arduino IDE and web server libraries.

Extensive testing confirmed the system’s responsiveness, accuracy, and usability under various conditions, demonstrating it as a cost-effective, user-friendly assistive technology. Future improvements may include machine learning for blink detection, wireless connectivity, and adaptive calibration to better serve users with severe motor impairments.

Conclusion

The blinking recognition system is proving to be efficient in making purposeful eye blinking an actuating system. Under diverse lighting conditions and distances,through rigorous testing,the systemhas been stable with minimal falsealarms and stableresponsestothe lamp. The systemisalsoimprovedbyseparatingpurposefulblinkingfromeyemovements.Long-termtestinghasalsoconfirmedstabilityandeffectivenessin continuous system operation. While available in an implemented shape with promising results, future work can focus on optimizing blink recognition algorithms to prevent spurious activations better. Adaptive learning algorithms can be added to adjust system response to user patterns.Makingitincreasinglycompatiblewithothersmartproductscanfurthersupportmakingitfunctional.Besidesbeing employedinhome automation, this system can be used in assistive technology in individuals with mobility limitations. As this system is developed further and usedinconjunction with othersmart control interfaces, thiscan bedevelopedintoan even moreuniversal system accessibletoeveryone. This work is an introduction to future work in hands-free systems to newer andimproved methods of interacting.

References

[1] Muhammad Ilhamdi Rusydi, Muhammad,RikoNofendra, None Syafii, Setiawan, A.W. and Sasaki, M.(2024).Wheelchair Control Basedon EOG Signalsof Eye Blinks and Eye Glances Based on The Decision Tree Method. pp.152–159. doi:https://doi.org/10.1109/icoict61617.2024.10698650. [2] Kaur A.Wheelchair control for disabled patientsusing EMG/EOG based human machine interface: a review. J Med Eng Technol. 2021 Jan;45(1):61-74. [3] Sivarajah,Yathunanthan & Chandrasena,L.U.R. & Umakanthan, A. & Vasuki,Yathunanthan & Munasinghe, R.. (2009).ControllingaWheelchair by Useof EOG Signal. 4th International Conference on Information and Automation for Sustainability (ICIAFS). [4] M. F. Bhuyain, M. A. -U. Kabir Shawon, N. Sakib, T. Faruk, M. K. Islamand K. M. Salim, \"DesignandDevelopment ofan EOG-basedSystemto ControlElectric Wheelchair for People Suffering from Quadriplegia or Quadriparesis,\" 2019 International Conference on Robotics,Electrical and Signal ProcessingTechniques (ICREST), Dhaka, Bangladesh, 2019, pp. [5] Sekhavat, Y.A. (2019).Battle of minds: a new interactionapproach in BCI games through competitive reinforcement. Multimedia Tools and Applications,79(5-6),pp.3449–3464. [6] Forenzo, D., Zhu, H. and He, B. (2024). A continuous pursuit dataset for online deep learning-based EEG brain-computer interface. Scientific Data, 11(1).doi:https://doi.org/10.1038/s41597-024-04090-6. [7] Lei, D., Dong, C., Guo, H., Ma, P., Liu, H., Bao, N., Kang, H., Chen, X. and Wu, Y. (2024). A fused multi-subfrequency bands and CBAM SSVEP-BCIclassification method based on convolutional neural network. Scientific Reports, 14(1). doi:https://doi.org/10.1038/s41598-024-59348-1. [8] Morshad,S.,Mazumder,Md.R.andAhmed,F.(2020).AnalysisofBrainWaveData UsingNeuroskyMindwaveMobileII.Proceedings oftheInternationalConference on Computing Advancements. doi:https://doi.org/10.1145/3377049.3377053. [9] Zhang,Z.,Ding,X.,Bao,Y.,Zhao,Y.,Liang, X.,Qin,B.andLiu,T.(2024).Chisco: AnEEG-basedBCIdataset fordecodingofimaginedspeech.Scientificdata, [online] 11(1), p.1265. doi:https://doi.org/10.1038/s41597-024-04114-1. [10] Aigerim Keutayeva, Nail Fakhrutdinovand Berdakh Abibullaev (2024).Compact convolutional transformer for subject-independent motor imagery EEG-based BCIs. Scientific Reports, 14(1). doi:https://doi.org/10.1038/s41598-024-73755-4. [11] Mercado,J.,Espinosa-Curiel,I.,Escobedo,L.andTentori,M.(2018).DevelopingandevaluatingaBCI videogamefor neurofeedback training:thecaseofautism. Multimedia Tools and Applications, 78(10), pp.13675–13712. doi:https://doi.org/10.1007/s11042-018-6916-2. [12] Chiang,H.-S.,Hsiao, K.-L. andLiu, L.-C.(2017).EEG-Based Detection Model for EvaluatingandImprovingLearning Attention. Journal of Medical andBiological Engineering, 38(6), pp.847–856. doi:https://doi.org/10.1007/s40846-017-0344-z. [13] KübraErat,ElifBilge?ahin,FurkanDo?an,NurMerdano?lu, Ahmet AkcakayaandP?narOnayDurdu(2024).EmotionrecognitionwithEEG-basedbrain-computer interfaces: a systematic literature review. Multimedia tools and applications. doi:https://doi.org/10.1007/s11042-024-18259-z. [14] Bird,J.J.andLotfi,A.(2023).FallcompensationdetectionfromEEGusingneuroevolutionandgenetichyperparameter optimisation.GeneticProgrammingand Evolvable Machines, 24(1). doi:https://doi.org/10.1007/s10710-023-09453-3. [15] Jiang, H., Stieger, J., Kreitzer, M.J., Engel, S. and He, B. (2021). Frontolimbic alpha activity tracks intentional rest BCI control improvement throughmindfulness meditation. Scientific Reports, 11(1). doi:https://doi.org/10.1038/s41598-021-86215-0. [16] Krueger,J., Krauth, R.,Reichert, C., Perdikis, S., Vogt, S., Huchtemann,T., Dürschmid, S., Almut Sickert, Lamprecht, J., Almir Huremovic, Görtler, M.,Nasuto,S.J.,Tsai,I.-C., Knight,R.T.,Hinrichs,H.,Heinze,H.-J.,Lindquist,S.,Sailer,M.,JoseandSweeney-Reed,C.M.(2024).Hebbianplasticityinducedbytemporally coincident BCI enhances post-stroke motor recovery. Scientific Reports, 14(1). doi:https://doi.org/10.1038/s41598-024-69037-8. [17] Mitsukura, Y., Sumali, B., Watanabe, H., Ikaga, T. and Nishimura, T. (2022). Frontotemporal EEG as potential biomarker for early MCI: a case–controlstudy. BMC Psychiatry, 22(1). doi:https://doi.org/10.1186/s12888-022-03932-0.

Copyright

Copyright © 2025 J. Clament Vijay, Prof. Mr. V. Victor Remy . This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.