Motor Imagery Classification using Wavelet-Based Features and Tensorflow
Sang-Hong Lee1, Seok-Woo Jang2

1Sang-Hong Lee, Department of Computer Science & Engineering, Anyang University, Anyang-si, Republic of Korea.
2Seok-Woo Jang*, Department of Software, Anyang University, Anyang-si, Republic of Korea. 

Manuscript received on October 12, 2019. | Revised Manuscript received on 22 October, 2019. | Manuscript published on November 10, 2019. | PP: 4650-4652 | Volume-9 Issue-1, November 2019. | Retrieval Number: A4930119119/2019©BEIESP | DOI: 10.35940/ijitee.A4930.119119
Open Access | Ethics and 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 (

Abstract: This paper proposes a methodology for making a decision on left and right motor imagery using Tensorflow and wavelet-based feature extraction. Wavelet coefficients are extracted by the Haar wavelet transforms from electroencephalogram (EEG) signals in the first step. In the second step, 60 wavelet-based features are extracted by the frequency distribution and the amount of variability in frequency distribution. In the final step, this paper classified left or right motion imagery using these 60 features as inputs to the Tensorflow. The proposed methodology shows that the performance result is 82.14% with 60 features in accuracy rate.
Keywords:  Motor Imagery, Tensorflow, Wavelet Transform, Keras.
Scope of the Article: Classification