An RNN-based Hybrid Model for Classification of Electrooculogram Signal for HCI


  • Kowshik Sankar Roy
  • Sheikh Md. Rabiul Islam



EOG, RNN, GRU, Bi-GRU, HCI, Vertical channel, Horizontal channel


In recent years, there has been a rise in the amount of research conducted in the field of human-computer interaction (HCI) employing electrooculography (EOG), which is a technology that is effectively and widely used to detect human eye activity. The use of EOG signals as a control signal for HCI is essential for understanding, characterizing, and classifying eye movements, which can be applied to a wide range of applications including virtual mouse and keyboard control, electric power wheelchairs, industrial assistive robots, and patient rehabilitation or communication purposes. In the field of HCI, EOG signals classification has continuously been performed to make the system more effective and reliable than ever. In this paper, a Recurrent neural network model is proposed for classifying eye movement directions utilizing several informative feature extraction methods and noise filtering. Our classification model is comprised of Gated Recurrent Unit (GRU) with a Bidirectional GRU followed by dense layers. The classifier is investigated to find a better classification performance of four directional eye movements: Up and Down for the vertical channel, along with Left and Right for the horizontal channel of EOG signals. The classifier achieved 99.77% and 99.74% accuracy for vertical and horizontal channels, respectively, which outperforms the compared state-of-the-art studies. The proposed classifier allows disabled people to make life-improving decisions using computers, achieving the highest classification performance for rehabilitation and other applications.


L. J. Qi, N. Alias, N, “Comparison of ANN and SVM for classification of eye movements in EOG signals,” Journal of Physics. Conference Series, vol. 971, 012012, 2018.

L. Y. Deng, C. L. Hsu, T. C. Lin, J. S. Tuan, S. M. Chang, “EOG-based human-computer interface system development,” Expert Systems with Applications, vol. 37, issue 4, pp. 3337–3343, 2011.

A. Banerjee, M. Pal, S. Datta, D. N. Tibarewala, A. Konar, “Eye movement sequence analysis using electrooculogram to assist autistic children,” Biomedical Signal Processing and Control, vol. 14, pp. 134–140, 2014.

E. Fars, M. S. Samann, “Human to television interface for disabled people based on EOG,” Journal of University of Duhok, vol. 21, issue 1, pp. 53–64, 2018.

T. Wissel, R. Palaniappan, “Considerations on strategies to improve EOG signal analysis,” Investigations into Living Systems, Artificial Life, and Real-World Solutions, IGI Global, 2013, pp. 204–217.

T. Gandhi, M. Trikha, J. Santhosh, S. Anand, “Development of an expert multitask gadget controlled by voluntary eye movements,” Expert Systems with Applications, vol. 37, issue 6, pp. 4204–4211, 2010. ttps://

Z. Hossain, M. M. H. Shuvo, P. Sarker, “Hardware and software implementation of real time electrooculogram (EOG) acquisition system to control computer cursor with eyeball movement,” Proceedings of the 2017 4th International Conference on Advances in Electrical Engineering (ICAEE), 2017, pp. 132-137.

S. Aungsakul, A. Phinyomark, P. Phukpattaranont, C. Limsakul, “Evaluating feature extraction methods of electrooculography (EOG) signal for human-computer interface,” Procedia Engineering, vol. 32, pp. 246–252, 2012.

J. Martínez-Cerveró, et al., “Open software/hardware platform for human-computer interface based on electrooculography (EOG) signal classification,” Sensors, Basel, Switzerland, vol. 20, issue 9, 2443, 2020.

A.-G. A. Abdel-Samei, A. S. Ali, F. E. A. El-Samie, A. M. Brisha, “Efficient classification of horizontal and vertical EOG signals for human computer interaction,” Research Square, 2021.

N. Barbara, T. A. Camilleri, K. P. Camilleri, “A comparison of EOG baseline drift mitigation techniques,” Biomedical Signal Processing and Control, vol. 57, 101738, 2020.

J. Tsai, C. Lee, C. Wu, J. Wu, and K. Kao, “A feasibility study of an eye-writing system based on electro-oculography,” Journal of Medical and Biological Engineering, vol. 28, pp. 39–46, 2008.

R. Barea, L. Boquete, L. M. Bergasa, E. López, and M. Mazo, “Electro-oculographic guidance of a wheelchair using eye movements codification,” Int. J. Rob. Res., vol. 22, no. 7–8, pp. 641–652, 2003.

S. Yathunanthan, L. U. R. Chandrasena, A. Umakanthan, V. Vasuki, S. R. Munasinghe, “Controlling a wheelchair by use of EOG signal,” Proceedings of the 4th International Conference on Information and Automation for Sustainability, 2008, pp. 283-288.

N. Barbara, T. A. Camilleri, and K. P. Camilleri, “EOG-based eye movement detection and gaze estimation for an asynchronous virtual keyboard,” Biomedical Signal Processing and Control, vol. 47, pp. 159–167, 2019.

J. Heo, H. Yoon, and K. S. Park, “A novel wearable forehead EOG measurement system for human computer interfaces,” Sensors, (Basel), vol. 17, no. 7, 1485, 2017.

M. Merino, O. Rivera, I. Gomez, A. Molina, and E. Dorronzoro, “A method of EOG signal processing to detect the direction of eye movements,” Proceedings of the 2010 First International Conference on Sensor Device Technologies and Applications, 2010, pp. 100-105.

H. Erkaymaz, M. Ozer, and İ. M. Orak, “Detection of directional eye movements based on the electrooculogram signals through an artificial neural network,” Chaos Solitons Fractals, vol. 77, pp. 225–229, 2015.

Z. Lv, Y. Wang, C. Zhang, X. Gao, and X. Wu, “An ICA-based spatial filtering approach to saccadic EOG signal recognition,” Biomedical Signal Processing and Control, vol. 43, pp. 9–17, 2018.

P. B. Udas, M. E. Karim, and K. S. Roy, “SPIDER: A shallow PCA based network intrusion detection system with enhanced recurrent neural networks,” J. King Saud Univ. – Comput. Inf. Sci., vol. 34, issue 10, part. B., pp. 10246-10272, 2022.

“Eye movement EOG Data,” Centre for Biomedical Cybernetics, EOG Dataset, L-Università ta’ Malta.

K. Sankar Roy, M. Ebtidaul Karim and P. Biswas Udas, "Exploiting Deep Learning Based Classification Model for Detecting Fraudulent Schemes over Ethereum Blockchain," 2022 4th International Conference on Sustainable Technologies for Industry 4.0 (STI), Dhaka, Bangladesh, pp. 1-6, 2022.

P. B. Udas, K. S. Roy, M. E. Karim and S. M. Azmat Ullah, "Attention-based RNN architecture for detecting multi-step cyber-attack using PSO metaheuristic," 2023 International Conference on Electrical, Computer and Communication Engineering (ECCE), Chittagong, Bangladesh, pp. 1-6, 2023.

K. S. Roy, T. Ahmed, P. B. Udas, M. E. Karim, and S. Majumdar, “MalHyStack: A Hybrid Stacked Ensemble Learning Framework with Feature Engineering Schemes for Obfuscated Malware Analysis,” Intelligent Systems with Applications, 2023.

A. Bulling, J. A. Ward, H. Gellersen, G. Tröster, “Eye movement analysis for activity recognition using electrooculography,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 33, issue 4, pp. 741–753, 2011.

A. B. Usakli, S. Gurkan, “Design of a novel efficient human–computer interface: An electrooculagram based virtual keyboard,” IEEE Transactions on Instrumentation and Measurement, vol. 59, issue 8, 2099–2108, 2011.




How to Cite

Roy, K. S., & Islam, S. M. R. (2023). An RNN-based Hybrid Model for Classification of Electrooculogram Signal for HCI. International Journal of Computing, 22(3), 335-344.