650 Hits in 5.4 sec

Classification of Hand Movements from EEG using a Deep Attention-based LSTM Network

Guangyi Zhang, Vandad Davoodnia, Alireza Sepas-Moghaddam, Yaoxue Zhang, Ali Etemad
2019 IEEE Sensors Journal  
This paper proposes a novel solution for classification of left/right hand movement by exploiting a Long Short-Term Memory (LSTM) network with attention mechanism to learn the electroencephalogram (EEG  ...  To this end, a wide range of time and frequency domain features are extracted from the EEG signals and used to train an LSTM network to perform the classification task.  ...  In this paper, a deep learning solution for Left/Right (L/R) hand movement classification using an LSTM network with attention mechanism is proposed.  ... 
doi:10.1109/jsen.2019.2956998 fatcat:hgjx7cv63ngbnlisnf36azej2y

Imaginary Finger Movements Decoding Using Empirical Mode Decomposition and a Stacked BiLSTM Architecture

Tat'y Mwata-Velu, Juan Gabriel Avina-Cervantes, Jorge Mario Cruz-Duarte, Horacio Rostro-Gonzalez, Jose Ruiz-Pinales
2021 Mathematics  
This study proposes a method for decoding finger imagined movements of the right hand.  ...  Therefore, a method based on Empirical Mode Decomposition (EMD) is used to tackle the problem of noisy signals.  ...  Conflicts of Interest: The authors declare that they have no conflict of interest.  ... 
doi:10.3390/math9243297 fatcat:5uacyepjgbhwpetezpfbrabluu

Deep Learning in Physiological Signal Data: A Survey

Rim, Sung, Min, Hong
2020 Sensors  
The objective of this paper is to conduct a detailed study to comprehend, categorize, and compare the key parameters of the deep-learning approaches that have been used in physiological signal analysis  ...  We taxonomize the research works using deep-learning method in physiological signal analysis based on: (1) physiological signal data perspective, such as data modality and medical application; and (2)  ...  Boltzmann Machine DBLSTM-WS Bi-directional LSTM network-based wavelet sequences DBM Deep Boltzmann Machine DBN Deep belief network DBN-GC Deep belief networks with glia chains DCNN Deep convolution neural  ... 
doi:10.3390/s20040969 pmid:32054042 pmcid:PMC7071412 fatcat:5ga4um5zsfddtpp47csw2dkyce

Multimodal Classification with Deep Convolutional-Recurrent Neural Networks for Electroencephalography [chapter]

Chuanqi Tan, Fuchun Sun, Wenchang Zhang, Jianhua Chen, Chunfang Liu
2017 Lecture Notes in Computer Science  
We train a deep neural network (DNN) with convolutional neural network (CNN) and recurrent neural network (RNN) for the EEG classification task by using EEG video and optical flow.  ...  Herein, we propose a novel approach to modeling cognitive events from EEG data by reducing it to a video classification problem, which is designed to preserve the multimodal information of EEG.  ...  Thanks to the contributors of the open source software used in our system.  ... 
doi:10.1007/978-3-319-70096-0_78 fatcat:k3dhx6drjrgxdpdkn6ekycj56m

A Motor-Imagery BCI System Based on Deep Learning Networks and Its Applications [chapter]

Jzau-Sheng Lin, Ray Shihb
2018 Evolving BCI Therapy - Engaging Brain State Dynamics  
Then two deep learning (DL) models named Long-short term memory (LSTM) and gated recurrent neural networks (GRNN) are used to classify MI-EEG data.  ...  Motor imagery brain-computer interface (BCI) by using of deep-learning models is proposed in this paper.  ...  Acknowledgements In this chapter, the research was sponsored by the Ministry of Science and Technology of Taiwan under the Grant 106-2221-E-167-031.  ... 
doi:10.5772/intechopen.75009 fatcat:djadkjgq3ff2vmo7uxzbemoimm

Deep Learning in EEG: Advance of the Last Ten-Year Critical Period

Shu Gong, Kaibo Xing, Andrzej Cichocki, Junhua Li
2021 IEEE Transactions on Cognitive and Developmental Systems  
We hope that this paper could serve as a summary of past work for deep learning in EEG and the beginning of further developments and achievements of EEG studies based on deep learning.  ...  We first briefly mention the artifacts removal for EEG signal and then introduce deep learning models that have been utilized in EEG processing and classification.  ...  Apart from the purposes of deep learning-based EEG classification, deep learning may also be a useful tool to reveal neural mechanisms of the brain.  ... 
doi:10.1109/tcds.2021.3079712 fatcat:5rck4hvysfhe5o2tfjywytr5o4

Efficacy of Transformer Networks for Classification of Raw EEG Data [article]

Gourav Siddhad, Anmol Gupta, Debi Prosad Dogra, Partha Pratim Roy
2022 arXiv   pre-print
First, a classifier using a transformer network is built to classify the age and gender of a person with raw resting-state EEG data.  ...  Results indicate that the transformer-based deep learning models can successfully abate the need for heavy feature-extraction of EEG data for successful classification.  ...  Attention-based networks have also been used for EEG classification. Zhu et al. [40] proposed a neural network based on CNN and attention mechanism to perform automatic sleep staging.  ... 
arXiv:2202.05170v1 fatcat:nz2mpq7f2bgttfwlbc2rpvzooa

Attention-Based DSC-ConvLSTM for Multiclass Motor Imagery Classification

Li Li, Nan Sun, Pietro Aricò
2022 Computational Intelligence and Neuroscience  
In order to improve the accuracy of EEG classification, a DSC-ConvLSTM model based on the attention mechanism is proposed for the multi-classification of motor imagery EEG signals.  ...  Secondly, the internal structure of the Long Short-Term Memory (LSTM) unit is improved by using convolution and attention mechanism, and a novel bidirectional convolution LSTM (ConvLSTM) structure is proposed  ...  model based on attention mechanism is proposed to extract the effective features of motor imagery EEG signals for classification.  ... 
doi:10.1155/2022/8187009 pmid:35571721 pmcid:PMC9098272 fatcat:acjgkkyxnnarfmg3ls6eqjgpoq

Deep Learning the EEG Manifold for Phonological Categorization from Active Thoughts [article]

Pramit Saha, Muhammad Abdul-Mageed, Sidney Fels
2019 arXiv   pre-print
As a step towards full decoding of imagined speech from active thoughts, we present a BCI system for subject-independent classification of phonological categories exploiting a novel deep learning based  ...  Our model framework is composed of a convolutional neural network (CNN), a long-short term network (LSTM), and a deep autoencoder.  ...  In [18] , Zhao et al. used manually handcrafted features from EEG data, combined with speech audio and facial features to achieve classification of the phonological categories varying based on the articulatory  ... 
arXiv:1904.04358v1 fatcat:yss6glhdpbfdlp7jvvhelwtfmy

DeepBrain: Towards Personalized EEG Interaction through Attentional and Embedded LSTM Learning [article]

Di Wu and Huayan Wan and Siping Liu and Weiren Yu and Zhanpeng Jin and Dakuo Wang
2021 arXiv   pre-print
Our contributions are two folds: 1) We present a stacked long short term memory (Stacked LSTM) structure with specific pre-processing techniques to handle the time-dependency of EEG signals and their classification  ...  . 2) We propose personalized design to capture multiple features and achieve accurate recognition of individual EEG signals by enhancing the signal interpretation of Stacked LSTM with attention mechanism  ...  The embedding layer is the first layer of attention-based enhanced stacked LSTM. And then, we use stacked LSTM to capture the long-dependency.  ... 
arXiv:2002.02086v2 fatcat:bacjz5kpzjaajdmjfvmms6v6ue

SPEAK YOUR MIND! Towards Imagined Speech Recognition With Hierarchical Deep Learning [article]

Pramit Saha, Muhammad Abdul-Mageed, Sidney Fels
2019 arXiv   pre-print
The proposed network is composed of hierarchical combination of spatial and temporal CNN cascaded with a deep autoencoder.  ...  In order to infer imagined speech from active thoughts, we propose a novel hierarchical deep learning BCI system for subject-independent classification of 11 speech tokens including phonemes and words.  ...  We did not find any no- Baselines We use two baselines, one based on an individual LSTM and another based on an individual CNN.  ... 
arXiv:1904.05746v1 fatcat:6gqhqy3yyrefpiyjjyevw22l6q

CAttSleepNet: Automatic End-to-End Sleep Staging Using Attention-Based Deep Neural Networks on Single-Channel EEG

Tingting Li, Bofeng Zhang, Hehe Lv, Shengxiang Hu, Zhikang Xu, Yierxiati Tuergong
2022 International Journal of Environmental Research and Public Health  
Then, a two-layer bidirectional-Long Short-Term Memory (Bi-LSTM) is used to encode the global correlations of successive epochs.  ...  We add an attention module to the convolutional neural network (CNN) that can learn the weights of local sequences of EEG signals by exploiting intra-epoch contextual information.  ...  In addition, Bi-LSTM was used to extract coarsegrained features from the significant fine-grained features extracted by the attention-based CNN network.  ... 
doi:10.3390/ijerph19095199 pmid:35564593 pmcid:PMC9104971 fatcat:wvdcnfvcurfpngdqlq5icu2i6u

Spatio-Temporal EEG Representation Learning on Riemannian Manifold and Euclidean Space [article]

Guangyi Zhang, Ali Etemad
2022 arXiv   pre-print
memory network with a soft attention mechanism.  ...  Moreover, our proposed method learns the temporal information via differential entropy and logarithm power spectrum density features extracted from EEG signals in Euclidean space using a deep long short-term  ...  Temporal information are obtained from features extracted from different time-steps in EEG sequences through our deep LSTM network with attention.  ... 
arXiv:2008.08633v2 fatcat:mwrfflxnhfbmthpdqdyjad3yfu

Deep Learning in Automatic Sleep Staging With a Single Channel Electroencephalography

Mingyu Fu, Yitian Wang, Zixin Chen, Jin Li, Fengguo Xu, Xinyu Liu, Fengzhen Hou
2021 Frontiers in Physiology  
In this study, we proposed a deep learning-based network by integrating attention mechanism and bidirectional long short-term memory neural network (AT-BiLSTM) to classify wakefulness, rapid eye movement  ...  The AT-BiLSTM network outperformed five other networks and achieved an accuracy of 83.78%, a Cohen's kappa coefficient of 0.766 and a macro F1-score of 82.14% on the PhysioNet Sleep-EDF Expanded dataset  ...  Aside from that, there is a lack of comparison between the performance of deep learning based and conventional feature extraction based models.  ... 
doi:10.3389/fphys.2021.628502 pmid:33746774 pmcid:PMC7965953 fatcat:vgemimsmxvaxtlxws4jeqhvliy

Capsule Attention for Multimodal EEG-EOG Representation Learning with Application to Driver Vigilance Estimation [article]

Guangyi Zhang, Ali Etemad
2021 IEEE transactions on neural systems and rehabilitation engineering   accepted
Memory (LSTM) network.  ...  To enable the system to focus on the most salient parts of the learned multimodal representations, we propose an architecture composed of a capsule attention mechanism following a deep Long Short-Term  ...  While capsule networks can be used on their own for learning, in this paper, we use it as a form of attention mechanism successive to a deep LSTM network.  ... 
doi:10.1109/tnsre.2021.3089594 pmid:34129500 arXiv:1912.07812v4 fatcat:4raxianeiveapgepvfvqgzx2mi
« Previous Showing results 1 — 15 out of 650 results