Investigating EEG Images of Cognitive Actions for Robotic Arm

DOI

10.2991/978-94-6463-196-8_7How to use a DOI?

Keywords

Brain Computer Interface; Emotiv EPOC; Cognitive events; Event Related Spectral Perturbation; ICA

Abstract

Brain Computer Interface (BCI) systems works with brain signals. The brain activities are taken into consideration and are used to control external devices These signals are processed to extract features which are then translated to discrete command set to operate some external device like a wheel chair or an application like a speller application, a gaming system etc. In this study an activity of robotic Arm movement (Arm up, Arm down and neutral) is performed. The brain imaging signals are acquired with a low-cost EEG machine as EMOTIV EPOC whereas EEGlab software developed in MATLAB is used for processing the signals. ICA technique is used for pre-processing the acquired data. ICA works on multichannel data and the data used in this study is 14 channels. ICA Algorithm has also helped to find the active components along with the brain area where neural activity was prominently noticed. The study was carried with four participants and a dataset of 1200 events was created and used to obtain the result. During active imagination of the Arm up, Arm down and neutral (the cognitive event i.e. push, pull, and neutral of Emitiv EPOC) movement of the robotic arm the activation was observed in the electrodes F3, F4, FC3, and FC4 placed in the frontal region. Event-related spectral perturbation (ERSP), are noticed in the inter-trial coherence (ITC) which were related to baseline interval. During the imagined movement ERD (Event Related Desynchronization) are observed and ERS (Event Related Synchronization) after the occurrence of imagined movement is noticed in the mentioned electrodes. While performing the study overall 79% accuracy was obtained during arm up, down, and neutral movement. The recognition of pattern on the bases of component map activation is also done to understand the dominant part of the brain while performing a specific movements and it was found that left frontal region is more active during Arm up movement and left & right frontal part is active during an Arm down movement.

Copyright

© 2023 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Shashibala Tarigopula
AU  - Dipali Chaudhari
AU  - Bharti Gawali
PY  - 2023
DA  - 2023/08/10
TI  - Investigating EEG Images of Cognitive Actions for Robotic Arm
BT  - Proceedings of the First International Conference on Advances in Computer Vision and Artificial Intelligence Technologies (ACVAIT 2022)
PB  - Atlantis Press
SP  - 69
EP  - 87
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-196-8_7
DO  - 10.2991/978-94-6463-196-8_7
ID  - Tarigopula2023
ER  -