Motor Imagery Classification Using Rough Neural Network

J Anila Maily, C Velayutham, M Mohamed Sathik


Brain Computer Interface is a system which provides a communication channel between the user and a computer without using the normal neuromuscular pathways. With BCI a user will be able to communicate with the mind. In a BCI system the brain activities are measured using EEG acquisition system. The acquired brain signals are analyzed and classified to identify the user’s intention. Motor imagery BCI works by making the user imagine their body parts without actually moving it. Prominent features are extracted from the acquired brain signals and the extracted features are classified to find the motor imagery performed by the user. This study uses datasets are provided by the Dr. Cichocki's Lab (Lab for Advanced Brain Signal Processing). We propose the Rough Neural Network (RNN) for Motor imagery classification. The experimental results show that RNN classifier gives higher accuracy than Backpropagation Classifier


BCI, EEG, Motor Imagery, RNN

Full Text:



N. Birbaumer, T. Hinterberger, A. Kubler, N. Neumann. The thought-translation device (ttd): neurobehavioral mechanisms and clinical outcome, IEEE Trans. Neural Systems Rehab. Eng. 11 120–123, 2003

J. Wolpaw, N. Birbaumer, D. McFarland, G.Pfurtscheller, T.Vaughana, Brain–Computer Interfaces for communication and control, Clin.Neurophysiol.113 767–79,12002.

Mak, Joseph N, and Jonathan R Wolpaw, “Clinical Applications of Brain-Computer Interfaces: Current State and Future Prospects.” IEEE reviews in biomedical engineering vol. 2: 187-199. doi:10.1109/RBME.2009.2035356,2009.

Velayutham, C., and K. Thangavel, "Improved Rough set algorithms for optimal attribute reduct. “Journal of Electronic Science and Technology 9.2 (2011): 108-117,2011.

R. Jensen, and Q. Shen, “Computational Intelligence and Feature Selection: Rough and Fuzzy Approaches”, IEEE Press/Wiley & Sons,2008.

C. Velayutham, and K. Thangavel, “Unsupervised Feature Selection Using Rough Set”, Proceedings of the International Conference on Emerging Trends in Computing (ICETC 2011), Coimbatore, pp. 307-315,2011.

Simon Haykin, “Neural Networks”, Second edition by, Prentice Hall of India, 2005.

Weidong Zhao, and Guohua Chen, “A survey for the integration of rough set theory with neural networks”, Systems engineering and electronics, vol. 24, no. 10, pp. 103-107,2002.

Hong K-S, Khan MJ and Hong MJ (2018) Feature Extraction and Classification Methods for Hybrid fNIRS-EEG Brain-Computer Interfaces. Front. Hum.Neurosci. 12:246.doi:10.3389/fnhum.2018.00246,2018.

Sakhavi, Siavash & Guan, Cuntai & Yan, Shuicheng, Learning Temporal Information for Brain-Computer Interface Using Convolutional Neural Networks. IEEE Transactions on Neural Networks and Learning Systems. PP. 1-11. 0.1109/TNNLS.2018.2789927,2018.

Vladimir A. Maksimenko, Semen A. Kurkin, Elena N. Pitsik, et al., “Artificial Neural Network Classification of Motor-Related EEG: An Increase in Classification Accuracy by Reducing Signal Complexity,” Complexity, vol. 2018, Article ID 9385947, 10 pages,

Han, C., Kim, Y., Kim, D.Y. et al., “Electroencephalography-based endogenous brain–computer interface for online communication with a completely locked-in patient. JNeuroEngineering Rehabil 16, 18 (2019) doi:10.1186/s12984-019-0493-0

Kumar, S., Sharma, A. & Tsunoda. T, Brain wave classification using long short-term memory network based OPTICAL predictor. Sci Rep 9, 9153 doi:10.1038/s41598-019-45605 ,2019.



  • There are currently no refbacks.

Copyright (c) 2022 J Anila Maily, C Velayutham, M Mohamed Sathik

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.

Ratio Mathematica - Journal of Mathematics, Statistics, and Applications. ISSN 1592-7415; e-ISSN 2282-8214.