Comparison of LSTM And SVM For Classification of Eye Movements in EOG Signals

  • Aya R. Abih Computer Science Department, College of Education for pure Sciences, University of Thi-Qar , Iraq
  • Mustafa J. Hayawi Computer Science Department, College of Education for pure Sciences, University of Thi-Qar , Iraq
Keywords: EOG, Eye Movement, LSTM, SVM

Abstract

People with disabilities suffer from inability to communicate with their surroundings, so Human-Computer Interaction (HCI) technologies are used to have a means of communication for people with disabilities with their surroundings. HCI is an emerging technology in the disciplines of Artificial Intelligence and Biomedical Engineering. To power an external device, HCI technology uses several basic signals such as ECG, EMG, and EEG. Electrooculography (EOG) is a technique for measuring the potential difference between the cornea and the retina located between the front and back of the human eye, and the main application of EOG is to determine the directions of different eye movements. This study aims to assess eye movement for communication by persons with disabilities using electrocardiogram (EOG) data. In this study, the Supporting Vector Machine (SVM)  and Long- Short term memory (LSTM)  classification techniques was used and two types of features (statistical and time domain features) were used. Classification accuracy was 90.7% and 93.9% when using SVM with statistical domain and time domain features, respectively ,whereas  Classification accuracy was 90.1%  when using LSTM .

Downloads

Download data is not yet available.

References

F. Cincotti et al., “Non-invasive brain–computer interface system: towards its application as assistive technology,” Brain Res. Bull., vol. 75, no. 6, pp. 796–803, 2008.
[2] R. Barea, L. Boquete, M. Mazo, and E. López, “System for assisted mobility using eye movements based on electrooculography,” IEEE Trans. Neural Syst. Rehabil. Eng., vol. 10, no. 4, pp. 209–218, Dec. 2002, doi: 10.1109/TNSRE.2002.806829.
[3] J. Keegan, E. Burke, J. Condron, and E. Coyle, “Improving electrooculogram-based computer mouse systems: The accelerometer trigger,” Bioeng. Irel., vol. 201, no. 1, 2011.
[4] R. Barea, L. Boquete, M. Mazo, and E. López, “Wheelchair guidance strategies using EOG,” J. Intell. Robot. Syst., vol. 34, no. 3, pp. 279–299, 2002.
[5] T. Wissel and R. Palaniappan, “Considerations on strategies to improve EOG signal analysis,” Int. J. Artif. Life Res., vol. 2, no. 3, pp. 6–21, 2011.
[6] G. Teng, Y. He, H. Zhao, D. Liu, J. Xiao, and S. Ramkumar, “Design and Development of Human Computer Interface Using Electrooculogram With Deep Learning,” Artif. Intell. Med., vol. 102, p. 101765, 2020, doi: 10.1016/j.artmed.2019.101765.
[7] R. Barea, L. Boquete, J. M. Rodriguez-Ascariz, S. Ortega, and E. López, “Sensory system for implementing a human—computer interface based on electrooculography,” Sensors, vol. 11, no. 1, pp. 310–328, 2010.
[8] N. Itakura and K. Sakamoto, “A new method for calculating eye movement displacement from AC coupled electro-oculographic signals in head mounted eye–gaze input interfaces,” Biomed. Signal Process. Control, vol. 5, no. 2, pp. 142–146, 2010.
[9] T. Gandhi, M. Trikha, J. Santosh, and S. Anand, “VHDL based electro-oculogram signal classification,” in 2007 15th International Conference on Advanced Computing and Communications, 2007, pp. 153–158.
[10] A. Banerjee, M. Pal, S. Datta, D. N. Tibarewala, and A. Konar, “Eye movement sequence analysis using electrooculogram to assist autistic children,” Biomed. Signal Process. Control, vol. 14, pp. 134–140, 2014.
[11] F. E. Samann and M. S. Hadi, “Human to Television Interface for Disabled People Based on EOG,” J. Duhok Univ., vol. 21, no. 1, pp. 54–64, 2018.
[12] P. Majaranta and A. Bulling, “Eye tracking and eye-based human–computer interaction,” in Advances in physiological computing, Springer, 2014, pp. 39–65.
[13] R. Barea, L. Boquete, S. Ortega, E. López, and J. M. Rodríguez-Ascariz, “EOG-based eye movements codification for human computer interaction,” Expert Syst. Appl., vol. 39, no. 3, pp. 2677–2683, 2012.
[14] A. U. Kabir, F. Bin Shahin, and M. Kafiul Islam, “Design and Implementation of an EOG-based Mouse Cursor Control for Application in Human-Computer Interaction,” J. Phys. Conf. Ser., vol. 1487, no. 1, 2020, doi: 10.1088/1742-6596/1487/1/012043.
[15] T. Ravichandran, N. Kamel, A. A. Al-Ezzi, K. Alsaih, and N. Yahya, “Electrooculography-based Eye Movement Classification using Deep Learning Models,” Proc. - 2020 IEEE EMBS Conf. Biomed. Eng. Sci. IECBES 2020, pp. 57–61, 2021, doi: 10.1109/IECBES48179.2021.9398730.
[16] https://www.um.edu.mt/cbc/ourprojects/EOG/EOGdataset .
[17] L. J. Qi and N. Alias, “Comparison of ANN and SVM for classification of eye movements in EOG signals,” J. Phys. Conf. Ser., vol. 971, no. 1, 2018, doi: 10.1088/1742-6596/971/1/012012.
[18] S. Roy, A. De, and N. Panigrahi, “Saccade and Fix detection from EOG signal,” Proc. - 2019 IEEE Int. Symp. Smart Electron. Syst. iSES 2019, pp. 406–408, 2019, doi: 10.1109/iSES47678.2019.00099.
[19] R. Zebari, A. Abdulazeez, D. Zeebaree, D. Zebari, and J. Saeed, “A Comprehensive Review of Dimensionality Reduction Techniques for Feature Selection and Feature Extraction,” J. Appl. Sci. Technol. Trends, vol. 1, no. 2, pp. 56–70, 2020, doi: 10.38094/jastt1224.
[20] S. Aungsakul, A. Phinyomark, P. Phukpattaranont, and C. Limsakul, “Evaluating feature extraction methods of electrooculography (EOG) signal for human-computer interface,” Procedia Eng., vol. 32, no. January, pp. 246–252, 2012, doi: 10.1016/j.proeng.2012.01.1264.
[21] Y. LeCun, K. Kavukcuoglu, and C. Farabet, “Circuits and systems (ISCAS),” in Proceedings of 2010 IEEE International Symposium on, 2010, pp. 253–256.
[22] N. Michielli, U. R. Acharya, and F. Molinari, “Cascaded LSTM recurrent neural network for automated sleep stage classification using single-channel EEG signals,” Comput. Biol. Med., vol. 106, no. January, pp. 71–81, 2019, doi: 10.1016/j.compbiomed.2019.01.013.
[23] M. M. Hasan, C. N. Watling, and G. S. Larue, “Physiological signal-based drowsiness detection using machine learning: Singular and hybrid signal approaches,” J. Safety Res., vol. 80, pp. 215–225, 2022, doi: 10.1016/j.jsr.2021.12.001.
Published
2022-09-24
How to Cite
Abih, A., & Hayawi, M. (2022). Comparison of LSTM And SVM For Classification of Eye Movements in EOG Signals. Journal of Al-Qadisiyah for Computer Science and Mathematics, 14(3), Comp Page 130-143. https://doi.org/10.29304/jqcm.2022.14.3.1024
Section
Computer article