[vc_empty_space][vc_empty_space]
Classification of EEG-based hand grasping imagination using autoregressive and neural networks
Djamal E.C.a, Suprijantob, Setiadi S.J.b
a Jurusan Informatika Universitas Jenderal Achmad Yani, Cimahi, Indonesia
b Kelompok Keahlian Instrumentasi dan Control, Fakultas Teknologi Industri, Institut Teknologi Bandung, Indonesia
[vc_row][vc_column][vc_row_inner][vc_column_inner][vc_separator css=”.vc_custom_1624529070653{padding-top: 30px !important;padding-bottom: 30px !important;}”][/vc_column_inner][/vc_row_inner][vc_row_inner layout=”boxed”][vc_column_inner width=”3/4″ css=”.vc_custom_1624695412187{border-right-width: 1px !important;border-right-color: #dddddd !important;border-right-style: solid !important;border-radius: 1px !important;}”][vc_empty_space][megatron_heading title=”Abstract” size=”size-sm” text_align=”text-left”][vc_column_text]© 2016 Penerbit UTM Press. All rights reserved.In the development of Brain Computer Interface (BCI), one important issue is the classification of hand grasping imagination. It is helpful for realtime control of the robotic or a game of the mind. BCI uses EEG signal to get information on the human. This research proposed methods to classify EEG signal against hand grasping imagination using Neural Networks. EEG signal was recorded in ten seconds of four subjects each four times that were asked to imagine three classes of grasping (grasp, loose, and relax). Four subjects used as training data and four subjects as testing data. First, EEG signal was modeled in order 20 Autoregressive (AR) so that got AR coefficients being passed Neural Networks. The order of the AR model chosen based optimization gave a small error that is 1.96%. Then, it has developed a classification system using multilayer architecture and Adaptive Backpropagation as training algorithm. Using AR made training of the system more stable and reduced oscillation. Besides, the use of the AR model as a representation of the EEG signal improved the classification system accuracy of 68% to 82%. To verify the performance improvement of the proposed classification scheme, a comparison of the Adaptive Backpropagation and the conventional Backpropagation in training of the system. It resulted in an increase accuracy of 76% to 82%. The system was validated against all training data that produced an accuracy of 91%. The classification system that has been implemented in the software so that can be used as the brain computer interface.[/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Author keywords” size=”size-sm” text_align=”text-left”][vc_column_text][/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Indexed keywords” size=”size-sm” text_align=”text-left”][vc_column_text]Adaptive backpropagation,Autoregressive,Brain computer interface,Grasping imagination[/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Funding details” size=”size-sm” text_align=”text-left”][vc_column_text][/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”DOI” size=”size-sm” text_align=”text-left”][vc_column_text]https://doi.org/10.11113/jt.v78.9035[/vc_column_text][/vc_column_inner][vc_column_inner width=”1/4″][vc_column_text]Widget Plumx[/vc_column_text][/vc_column_inner][/vc_row_inner][/vc_column][/vc_row][vc_row][vc_column][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][/vc_column][/vc_row]