A CNN based graphical user interface controlled by imagined movements

An electroencephalogram (EEG) based brain-computer interface (BCI) enables the control of some external activity directly from the brain, without any physical movement/overt action. The external activity can be the cursor control of a computer or it can provide commands to the devices to perform certain functions. This work proposes a movement imagery (MI) based graphical user interface (GUI) for typing 26 English alphabets and tasks like food, water, medicine along with cancel and confirm commands. Convolutional Neural Network (CNN) is used to extract the spatial features from the recorded EEG signals. These features are fed to an ensemble-based extreme gradient (XG) boost classifier in a five-classification framework. By varying the hyper-parameters of the classification model, the highest accuracy of 84.7% for CNN and 92.87% for the cascaded structure of CNN and the XG boost classifier is achieved. The minimum execution time taken is 1.18 s for CNN and 3.24 s using both CNN and XG boost classifier. The work shows that it is possible to classify the information embedded in MI signals and can serve as a basis for an alternate communication channel to patients in advanced stages of Amyotrophic lateral sclerosis.

[1]  K S Srujan.  Classification of Synchronized Brainwave Recordings using Machine Learning and Deep Learning Approaches , 2018, 2018 IEEE 9th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON).

[2]  Anikó Ekárt,et al.  A Study on Mental State Classification using EEG-based Brain-Machine Interface , 2018, 2018 International Conference on Intelligent Systems (IS).

[3]  Luca Faes,et al.  Critical Comments on EEG Sensor Space Dynamical Connectivity Analysis , 2016, Brain Topography.

[4]  Xiaohang Wu,et al.  The combination of brain-computer interfaces and artificial intelligence: applications and challenges , 2020, Annals of translational medicine.

[5]  Alex Krizhevsky,et al.  Learning Multiple Layers of Features from Tiny Images , 2009 .

[6]  Kwang Suk Park,et al.  Enhancing the Usability of Brain-Computer Interface Systems , 2019, Comput. Intell. Neurosci..

[7]  Zhiyong Chen,et al.  Fast Automatic Optimisation of CNN Architectures for Image Classification Using Genetic Algorithm , 2019, 2019 IEEE Congress on Evolutionary Computation (CEC).

[8]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[9]  E. M. Dogo,et al.  A Comparative Analysis of Gradient Descent-Based Optimization Algorithms on Convolutional Neural Networks , 2018, 2018 International Conference on Computational Techniques, Electronics and Mechanical Systems (CTEMS).

[10]  A. Guillot,et al.  Motor Imagery in Clinical Disorders: Importance and Implications , 2015, Front. Psychiatry.

[11]  T. Sheela,et al.  Analysis of Collaborative Brain Computer Interface (BCI) based Personalized GUI for Differently Abled , 2017 .

[12]  Philip Sedgwick,et al.  Pearson’s correlation coefficient , 2012, BMJ : British Medical Journal.

[13]  Qiang Chen,et al.  Deep Convolutional Neural Network-Based Epileptic Electroencephalogram (EEG) Signal Classification , 2020, Frontiers in Neurology.

[14]  N. Birbaumer,et al.  BCI2000: a general-purpose brain-computer interface (BCI) system , 2004, IEEE Transactions on Biomedical Engineering.

[15]  Jinchuang Zhao,et al.  Research on extraction and classification of EEG features for multi-class motor imagery , 2019, 2019 IEEE 4th Advanced Information Technology, Electronic and Automation Control Conference (IAEAC).

[16]  J. Satheesh Kumar,et al.  Analysis of Electroencephalography (EEG) Signals and Its Categorization–A Study , 2012 .

[17]  David Moloney,et al.  Size/Accuracy Trade-Off in Convolutional Neural Networks: An Evolutionary Approach , 2019, INNSBDDL.

[18]  Kalervo Kiianmaa,et al.  Enhanced Extracellular Glutamate and Dopamine in the Ventral Pallidum of Alcohol-Preferring AA and Alcohol-Avoiding ANA Rats after Morphine , 2015, Front. Psychiatry.

[19]  Anurag Tiwari,et al.  A Multiclass EEG Signal Classification Model using Spatial Feature Extraction and XGBoost Algorithm , 2019, 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[20]  Sandeep Kumar,et al.  Silent speech classification based upon various feature extraction methods , 2020, 2020 7th International Conference on Signal Processing and Integrated Networks (SPIN).

[21]  M. R. Stalin John,et al.  Brain robot interface using artificial neural network , 2018 .

[22]  Nalan Ozkurt,et al.  Emotion Classification from EEG Signals in Convolutional Neural Networks , 2019, 2019 Innovations in Intelligent Systems and Applications Conference (ASYU).

[23]  Luca Maria Gambardella,et al.  Max-pooling convolutional neural networks for vision-based hand gesture recognition , 2011, 2011 IEEE International Conference on Signal and Image Processing Applications (ICSIPA).

[24]  Lina Yao,et al.  Converting Your Thoughts to Texts: Enabling Brain Typing via Deep Feature Learning of EEG Signals , 2017, 2018 IEEE International Conference on Pervasive Computing and Communications (PerCom).

[25]  Marie Chavent,et al.  EEG classification for the detection of mental states , 2015, Appl. Soft Comput..