scholarly journals Emotion brain-computer interface using wavelet and recurrent neural networks

2020 ◽  
Vol 6 (1) ◽  
pp. 1 ◽  
Author(s):  
Esmeralda Contessa Djamal ◽  
Hamid Fadhilah ◽  
Asep Najmurrokhman ◽  
Arlisa Wulandari ◽  
Faiza Renaldi
Keyword(s):  
Neural Networks ◽  
Recurrent Neural Networks ◽  
Short Term Memory ◽  
Brain Computer Interface ◽  
Computing Time ◽  
Extraction Methods ◽  
Training Data ◽  
Computer Interface ◽  
Eeg Signal ◽  
Eeg Signals

Brain-Computer Interface (BCI) has an intermediate tool that is usually obtained from EEG signal information. This paper proposed the BCI to control a robot simulator based on three emotions for five seconds by extracting a wavelet function in advance with Recurrent Neural Networks (RNN). Emotion is amongst variables of the brain that can be used to move external devices. BCI's success depends on the ability to recognize one person’s emotions by extracting their EEG signals. One method to appropriately recognize EEG signals as a moving signal is wavelet transformation. Wavelet extracted EEG signal into theta, alpha, and beta wave, and consider them as the input of the RNN technique. Connectivity between sequences is accomplished with Long Short-Term Memory (LSTM). The study also compared frequency extraction methods using Fast Fourier Transform (FFT). The results showed that by extracting EEG signals using Wavelet transformations, we could achieve a confident accuracy of 100% for the training data and 70.54% of new data. While the same RNN configuration without pre-processing provided 39% accuracy, even adding FFT would only increase it to 52%. Furthermore, by using features of the frequency filter, we can increase its accuracy from 70.54% to 79.3%. These results showed the importance of selecting features because of RNNs concern to sequenced its inputs. The use of emotional variables is still relevant for instructions on BCI-based external devices, which provide an average computing time of merely 0.235 seconds.

scholarly journals Processing EEG signals acquired from a consumer grade BCI device

2018 ◽  
Vol 11 (2) ◽  
pp. 29-34 ◽  
Author(s):  
Fanny Monori ◽  
Stefan Oniga
Keyword(s):  
Neural Networks ◽  
Feature Extraction ◽  
Human Brain ◽  
Brain Computer Interface ◽  
Extraction Methods ◽  
Multiclass Classification ◽  
Computer Interface ◽  
Clinical Settings ◽  
Eeg Signals ◽  
Complex Information

Abstract BCI (Brain-Computer Interface) is a technology which goal is to create and manage a connection between the human brain and a computer with the help of EEG signals. In the last decade consumer-grade BCI devices became available thus giving opportunity to develop BCI applications outside of clinical settings. In this paper we use a device called NeuroSky MindWave Mobile. We investigate what type of information can be deducted from the data acquired from this device, and we evaluate whether it can help us in BCI applications. Our methods of processing the data involves feature extraction methods, and neural networks. Specifically, we make experiments with finding patterns in the data by binary and multiclass classification. With these methods we could detect sharp changes in the signal such as blinking patterns, but we could not extract more complex information successfully.

CLASSIFICATION OF EEG-BASED HAND GRASPING IMAGINATION USING AUTOREGRESSIVE AND NEURAL NETWORKS

2015 ◽  
Vol 78 (6-6) ◽  
Author(s):  
Esmeralda Contessa Djamal ◽  
Suprijanto Suprijanto ◽  
Steven J. Setiadi
Keyword(s):  
Neural Networks ◽  
Classification System ◽  
Brain Computer Interface ◽  
Small Error ◽  
Training Data ◽  
Ar Model ◽  
Computer Interface ◽  
Eeg Signal ◽  
The Mind

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.  

P300 Feature Extraction of Visual and Auditory Evoked EEG Signal

2014 ◽  
Vol 490-491 ◽  
pp. 1374-1377 ◽  
Author(s):  
Xiao Yan Qiao ◽  
Jia Hui Peng
Keyword(s):  
Feature Extraction ◽  
Wavelet Transform ◽  
Evoked Potentials ◽  
Brain Computer Interface ◽  
Auditory Stimulation ◽  
Computer Interface ◽  
Eeg Signal ◽  
Significant Issue ◽  
Eeg Signals ◽  
Electroencephalogram Eeg

It is a significant issue to accurately and quickly extract brain evoked potentials under strong noise in the research of brain-computer interface technology. Considering the non-stationary and nonlinearity of the electroencephalogram (EEG) signal, the method of wavelet transform is adopted to extract P300 feature from visual, auditory and visual-auditory evoked EEG signal. Firstly, the imperative pretreatment to EEG acquisition signals was performed. Secondly, respectivly obtained approximate and detail coefficients of each layer, by decomposing the pretreated signals for five layers using wavelet transform. Finally, the approximate coefficients of the fifth layer were reconstructed to extract P300 feature. The results have shown that the method can effectively extract the P300 feature under the different visual-auditory stimulation modes and lay a foundation for processing visual-auditory evoked EEG signals under the different mental tasks.

scholarly journals Deep Learning Methods for EEG Signals Classification of Motor Imagery in BCI

2019 ◽  
Vol 3 (3) ◽  
pp. 80
Author(s):  
Muhammad Fawaz Saputra ◽  
Noor Akhmad Setiawan ◽  
Igi Ardiyanto
Keyword(s):  
Deep Learning ◽  
Motor Imagery ◽  
Short Term Memory ◽  
Brain Computer Interface ◽  
Correction Method ◽  
Computer Interface ◽  
Eeg Signals ◽  
Common Spatial Pattern ◽  
Learning Methods ◽  
Motor Movements

EEG signals are obtained from an EEG device after recording the user's brain signals. EEG signals can be generated by the user after performing motor movements or imagery tasks. Motor Imagery (MI) is the task of imagining motor movements that resemble the original motor movements. Brain Computer Interface (BCI) bridges interactions between users and applications in performing tasks. Brain Computer Interface (BCI) Competition IV 2a was used in this study. A fully automated correction method of EOG artifacts in EEG recordings was applied in order to remove artifacts and Common Spatial Pattern (CSP) to get features that can distinguish motor imagery tasks. In this study, a comparative studies between two deep learning methods was explored, namely Deep Belief Network (DBN) and Long Short Term Memory (LSTM). Usability of both deep learning methods was evaluated using the BCI Competition IV-2a dataset. The experimental results of these two deep learning methods show average accuracy of 50.35% for DBN and 49.65% for LSTM.

Precise Temporal P300 Detection in Brain Computer Interface EEG Signals Using a Long-Short Term Memory

2021 ◽  
pp. 457-468
Author(s):  
Christian Oliva ◽  
Vinicio Changoluisa ◽  
Francisco B. Rodríguez ◽  
Luis F. Lago-Fernández
Keyword(s):  
Short Term Memory ◽  
Brain Computer Interface ◽  
Computer Interface ◽  
Eeg Signals ◽  
Short Term ◽  
Term Memory ◽  
Long Short Term Memory

scholarly journals Brain-Computer Interface for Control of Wheelchair Using Fuzzy Neural Networks

2016 ◽  
Vol 2016 ◽  
pp. 1-9 ◽  
Author(s):  
Rahib H. Abiyev ◽  
Nurullah Akkaya ◽  
Ersin Aytac ◽  
Irfan Günsel ◽  
Ahmet Çağman
Keyword(s):  
Neural Networks ◽  
Brain Activity ◽  
Brain Computer Interface ◽  
Fuzzy Neural Networks ◽  
Training Data ◽  
Computer Interface ◽  
Human Control ◽  
Fuzzy Neural ◽  
Physically Disabled People

The design of brain-computer interface for the wheelchair for physically disabled people is presented. The design of the proposed system is based on receiving, processing, and classification of the electroencephalographic (EEG) signals and then performing the control of the wheelchair. The number of experimental measurements of brain activity has been done using human control commands of the wheelchair. Based on the mental activity of the user and the control commands of the wheelchair, the design of classification system based on fuzzy neural networks (FNN) is considered. The design of FNN based algorithm is used for brain-actuated control. The training data is used to design the system and then test data is applied to measure the performance of the control system. The control of the wheelchair is performed under real conditions using direction and speed control commands of the wheelchair. The approach used in the paper allows reducing the probability of misclassification and improving the control accuracy of the wheelchair.

Convolutional and Recurrent Neural Networks for Physical Action Forecasting by Brain-Computer Interface

2021 ◽  
Author(s):  
Kostiantyn Kostiukevych ◽  
Sergii Stirenko ◽  
Nikita Gordienko ◽  
Oleksandr Rokovyi ◽  
Oleg Alienin ◽  
...  
Keyword(s):  
Neural Networks ◽  
Recurrent Neural Networks ◽  
Brain Computer Interface ◽  
Computer Interface ◽  
Physical Action

scholarly journals Artifact Elimination from EEG Signals using Error Normalized algorithms for Brain Computer Interface Systems

2019 ◽  
Vol 9 (1) ◽  
pp. 4444-4448
Keyword(s):  
Brain Computer Interface ◽  
Computer Interface ◽  
Complex Signal ◽  
Eeg Signal ◽  
Eeg Signals ◽  
Health Tracking ◽  
Signal Activity ◽  
Convergence Performance ◽  
Adaptive Noise ◽  
Computational Difficulty

In this paper some efficient and low computation complex signal conditioning algorithms are proposed in distant health tracking applications, for improvement of the electroencephalogram (EEG) signal. Few artifacts are contaminated also mask small characteristics underlying EEG signal activity in medical environments during extraction of EEG signal. Low computational difficulty filters are appealing especially within distant healthcare surveillance. Therefore, we provided several effective and less computing adaptive noise cancellers (ANCs) in this work to improve EEG signal. Most of these techniques use easy addition as well as shift calculations also attain significant convergence performance compared to other standard techniques. Real EEG signals collected using emotional EEG systems are verified for proposed implementations. Using several performances measures our studies demonstrate that techniques suggested provides best performance than prevailing methods. This methodology is suitable in the analysis of brain computer interface (BCI) applications.

Sign in / Sign up

Export Citation Format

Share Document