Classification of Eog Signal using Elman Recurrent Neural Network for Different Age Groups
S. Ramkumar1, J. MacklinAbraham Navamani2, K. Sathesh Kumar3, V. Vasanthi4, G. Emayavaramban5, P. Sriramakrishnan6, M. Illayaraja7
1S. Ramkumar, School of Computing, Kalasalingam Academy of Research and Education, Krishnankoil (Tamil Nadu), India.
2J. MacklinAbraham Navamani, Department of Computer Applications, Karunya Institute of Technology and Sciences, Coimbatore (Tamil Nadu), India.
3K. Sathesh Kumar, School of Computing, Kalasalingam Academy of Research and Education, Krishnankoil (Tamil Nadu), India.
4V. Vasanthi, Department of IT & BCA, Adithya College of Arts and Science, Coimbatore (Tamil Nadu), India.
5G. Emayavaramban, Department of Electric and Electronic Engineering, Karpagam Academy of Higher Education, Coimbatore (Tamil Nadu), India.
6P. Sriramakrishnan, School of Computing, Kalasalingam Academy of Research and Education, Krishnankoil (Tamil Nadu), India.
7M. Illayaraja, School of Computing, Kalasalingam Academy of Research and Education, Krishnankoil (Tamil Nadu), India.
Manuscript received on 08 December 2019 | Revised Manuscript received on 20 December 2019 | Manuscript Published on 30 December 2019 | PP: 842-847 | Volume-9 Issue-2S2 December 2019 | Retrieval Number: B11311292S219/2019©BEIESP | DOI: 10.35940/ijitee.B1131.1292S219
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open-access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Disabled people in the world population were increasing constantly, So need of rehabilitative system also increasing every day. To overcome such wretched condition, we can use the biosignal techniques to device the rehabilitative devices. Rehabilitative devices may be called as Brain Computer Interface (BCI) or Human Computer Interface (HCI). We studied the performances of ten male subjects between the age group of 18 to 25 using mean features and Elman Recurrent Neural Network (ERNN). We conducted our study with two different age group from 18 to 21 and 22 to 25. The average classification accuracy of 91.00%, 93.57% were attained for the age group of 18 to 21 and 22 to 25. From the individual analysis we identified that performances from the age group 22 to 25 were appreciated then that of the age group from 18 to 21. In between the study we analyzed that subject s from the age group 22 to 25 performed all the following five tasks neatly and accurately without any deviation and disturbance compared with age group from 18 to 21. Finally from the obtained result we concluded that subject from the age group 22 to 25 was higher than that of age group from 18 to 21.
Keywords: Locked in State, Mean, Spinal Cord Injury, Brain Computer Interface, Human Computer Interface, Elman Recurrent Neural Network.
Scope of the Article: Classification