1,502 Hits in 8.5 sec

Selection of Proper EEG Channels for Subject Intention Classification Using Deep Learning [article]

Ghazale Ghorbanzade, Zahra Nabizadeh-ShahreBabak, Shadrokh Samavi, Nader Karimi, Ali Emami, Pejman Khadivi
2021 arXiv   pre-print
We are proposing a deep learning-based method for selecting an informative subset of channels that produce high classification accuracy.  ...  The proposed network could be trained for an individual subject for the selection of an appropriate set of channels.  ...  However, in the classification of EEG signals based on deep learning, determining channel selection criteria is not simple.  ... 
arXiv:2007.12764v2 fatcat:ofjpbtjdenchpklrowrp2szi7a

An Investigation of Insider Threat Mitigation Based on EEG Signal Classification

Jung Hwan Kim, Chul Min Kim, Man-Sung Yim
2020 Sensors  
This study proposes a scheme to identify insider threats in nuclear facilities through the detection of malicious intentions of potential insiders using subject-wise classification.  ...  Based on electroencephalography (EEG) signals, a classification model was developed to identify whether a subject has a malicious intention under scenarios of being forced to become an insider threat.  ...  Additionally, many deep learning models with various feature sets have been investigated for EEG classification.  ... 
doi:10.3390/s20216365 pmid:33171609 fatcat:mwqselihejfddj2zonnrlxyhri

Towards Best Practice of Interpreting Deep Learning Models for EEG-based Brain Computer Interfaces [article]

Jian Cui, Bin Weng
2022 arXiv   pre-print
In order to fill this research gap, we conduct the first quantitative evaluation and explore the best practice of interpreting deep learning models designed for EEG-based BCI.  ...  Our work presents a promising direction of introducing deep learning interpretability to EEG-based BCI.  ...  Datasets and models 1) Deep learning models for EEG-based BCI In this study, we select two benchmark deep learning models for the test.  ... 
arXiv:2202.06948v2 fatcat:dzt26evqyjajdp6q25t4otg55m

Signal processing techniques for motor imagery brain computer interface: A review

Swati Aggarwal, Nupur Chugh
2019 Array  
In recent studies, the researchers are using deep neural networks for the classification of motor imagery tasks.  ...  This paper provides a comprehensive review of dominant feature extraction methods and classification algorithms in brain-computer interface for motor imagery tasks.  ...  [32] competition 75.11%, Subject-3 57.76% Classification of Motor Imagery for Ear-EEG based Brain-Computer CSP RLDA BCI-III 74.28% Interface [70] competition A Deep Learning Approach for Motor Imagery  ... 
doi:10.1016/j.array.2019.100003 fatcat:tlkzqreshzgfpeusxub3f5h4bq

DAL: Feature Learning from Overt Speech to Decode Imagined Speech-based EEG Signals with Convolutional Autoencoder [article]

Dae-Hyeok Lee, Sung-Jin Kim, Seong-Whan Lee
2021 arXiv   pre-print
We proposed the Deep-autoleaner (DAL) to learn EEG features of overt speech for imagined speech-based EEG signals classification.  ...  To the best of our knowledge, this study is the first attempt to use EEG features of overt speech to decode imagined speech-based EEG signals with an autoencoder.  ...  This research was supported by the Defense Challengeable Future Technology Program of Agency for Defense Development, Republic of Korea.  ... 
arXiv:2107.07064v1 fatcat:yepv7em5tvfvpjjsbw3p7zxyca

Motor Imagery Classification of Single-Arm Tasks Using Convolutional Neural Network based on Feature Refining [article]

Byeong-Hoo Lee, Ji-Hoon Jeong, Kyung-Hwan Shim, Dong-Joo Kim
2020 arXiv   pre-print
One of EEG paradigms, motor imagery (MI) is commonly used for recovery or rehabilitation of motor functions due to its signal origin.  ...  Hence, we demonstrate that the decoding of user intention is possible by using only EEG signals with robust performance using BFR-CNN.  ...  Cho for their help with the dataset construction and discussion of the data analysis.  ... 
arXiv:2002.01122v1 fatcat:vvbg4xlpszfwbnkpptmt6cix4u

SessionNet: Feature Similarity-based Weighted Ensemble Learning for Motor Imagery Classification

Byeong-Hoo Lee, Ji-Hoon Jeong, Seong-Whan Lee
2020 IEEE Access  
The traditional MI-BCI problem is to obtain enough EEG data samples for adopting deep learning techniques, as electroencephalography (EEG) data have intricate and non-stationary properties that can cause  ...  Hence, our approach could demonstrate the possibility of using feature similarity based on a novel ensemble learning method to train generality from multiple session data for better MI classification performance  ...  We performed MI classification using a deep learning strategy across healthy subjects. We also presented a novel approach for robust MI classification.  ... 
doi:10.1109/access.2020.3011140 fatcat:ayohrpxzxra6viw5yn4pvfydde

Decoding of Grasp Motions from EEG Signals Based on a Novel Data Augmentation Strategy [article]

Jeong-Hyun Cho, Ji-Hoon Jeong, Seong-Whan Lee
2020 arXiv   pre-print
As a result, we obtained the average classification accuracy of 52.49% for motor execution (ME) and 40.36% for motor imagery (MI).  ...  For implementation, we recorded EEG and EMG simultaneously. The data augmentation over the original EEG data concluded higher classification accuracy than other competitors.  ...  Evaluation (IITP) grant funded by the Korean government (No. 2017-0-00451, Development of BCI based Brain and Cognitive Computing Technology for Recognizing Users Intentions using Deep Learning).  ... 
arXiv:2005.04881v1 fatcat:5s4arew6ufgypnbmwpzk7gvlpq

Classification of Upper Arm Movements from EEG signals using Machine Learning with ICA Analysis [article]

Pranali Kokate, Sidharth Pancholi, Amit M. Joshi
2021 arXiv   pre-print
Classification of Cognitive-Motor Imagery activities from EEG signals is a critical task.  ...  Following the selection of appropriate feature vectors that provided acceptable accuracy. The same method was used on all nine subjects.  ...  The intra-subject validation scheme was used to validate on different subjects. Finally, resembled the execution of the proposed model with the deep learning model.  ... 
arXiv:2107.08514v1 fatcat:4aijbhssk5dejehq2uuvx4527e

Discriminative Feature Selection-Based Motor Imagery Classification Using EEG Signal

Md. Khademul Islam Molla, Abdullah Al Shiam, Md. Rabiul Islam, Toshihisa Tanaka
2020 IEEE Access  
This paper presents a supervised approach to select discriminative features for the enhancement of MI classification using multichannel electroencephalography (EEG) signal.  ...  The selected features are used to train the support vector machine for classification.  ...  The deep learning approach with variational autoencoder is employed in [14] for EEG classification.  ... 
doi:10.1109/access.2020.2996685 fatcat:5gnxvcy75rgxhfqtdslcnqul2e

Classification of Drowsiness Levels Based on a Deep Spatio-Temporal Convolutional Bidirectional LSTM Network Using Electroencephalography Signals

Ji-Hoon Jeong, Baek-Woon Yu, Dae-Hyeok Lee, Seong-Whan Lee
2019 Brain Sciences  
Hence, we demonstrated the feasibility of classifying five drowsiness levels with high accuracy using deep learning.  ...  We evaluated the classification performance using Karolinska sleepiness scale (KSS) values for two mental states and five drowsiness levels.  ...  Conclusions and Future Works In this paper, we presented the feasibility of classification for five pilot's drowsiness levels using deep learning technique.  ... 
doi:10.3390/brainsci9120348 pmid:31795445 pmcid:PMC6956039 fatcat:jw5mjma4cnfcdcmfdlmk3k6dfy

Gradual Relation Network: Decoding Intuitive Upper Extremity Movement Imaginations Based on Few-Shot EEG Learning [article]

Kyung-Hwan Shim, Ji-Hoon Jeong, Seong-Whan Lee
2020 arXiv   pre-print
To avoid this problem, we adopt the metric based few-shot learning approach for decoding intuitive upper-extremity movement imagination (MI) using a gradual relation network (GRN) that can gradually consider  ...  We acquired the MI data of the upper-arm, forearm, and hand associated with intuitive upper-extremity movement from 25 subjects.  ...  [34] proposed a novel deep learning approach using a data augmentation method for MI classification with small amounts of EEG data.  ... 
arXiv:2005.02602v1 fatcat:e3376n4lq5h2hoh5lpuati4mai

A Survey and Tutorial of EEG-Based Brain Monitoring for Driver State Analysis [article]

Ce Zhang, Azim Eskandarian
2020 arXiv   pre-print
First, the commonly used EEG system setup for driver state studies is introduced.  ...  However, many improvements are still required in EEG artifact reduction, real-time processing, and between-subject classification accuracy.  ...  For regression analysis, the selected reference channels may also provide useful EEG information.  ... 
arXiv:2008.11226v1 fatcat:fbsmjgk6sre3dnunnmjfh65ccm

An Evaluation of Different Fast Fourier Transform - Transfer Learning Pipelines for the Classification of Wink-based EEG Signals

Jothi Letchumy Mahendra Kumar, Mamunur Rashid, Rabiu Muazu Musa, Mohd Azraai Mohd Razman, Norizam Sulaiman, Rozita Jailani, Anwar PP Abdul Majeed
DenseNet169, DenseNet121 and DenseNet201 in extracting features for the classification of wink-based EEG signals.  ...  More often than not, the control of such devices exploits the use of Electroencephalogram (EEG) signals.  ...  A deep learning-based method that automatically exploits the time-frequency spectrum of the EEG signal was investigated in [13] .  ... 
doi:10.15282/mekatronika.v2i1.5939 fatcat:3kj5cemy5rahfpe3vpumd6y35u

Multi-Domain Convolutional Neural Networks for Lower-Limb Motor Imagery Using Dry vs. Wet Electrodes

Ji-Hyeok Jeong, Jun-Hyuk Choi, Keun-Tae Kim, Song-Joo Lee, Dong-Joo Kim, Hyung-Min Kim
2021 Sensors  
In this study, we propose a multi-domain convolutional neural networks (MD-CNN) model that learns subject-specific and electrode-dependent EEG features using a multi-domain structure to improve the classification  ...  Motor imagery (MI) brain–computer interfaces (BCIs) have been used for a wide variety of applications due to their intuitive matching between the user's intentions and the performance of tasks.  ...  number of channels and identical subject conditions.  ... 
doi:10.3390/s21196672 pmid:34640992 fatcat:zi7tr3k2ffbafbvbxw7byzblna
« Previous Showing results 1 — 15 out of 1,502 results