Deep convolutional neural network for decoding motor imagery based brain computer interface

Zhang, Jin; Yan, Chungang; Gong, Xiaoliang

doi:10.1109/icspcc.2017.8242581

Cited by 56 publications

(31 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…al. [45] applied a 7 layer CNN for a 2-class MI task and investigated the influence of the activation functions in the CNN. Three activation functions were tested, the ReLU, exponential linear unit (ELU) and scaled exponential linear unit (SELU).…”

Section: Deep Learningmentioning

confidence: 99%

Brain Computer Interface for Neuro-rehabilitation With Deep Learning Classification and Virtual Reality Feedback

Karácsony

Hansen

Iversen

et al. 2019

Proceedings of the 10th Augmented Human International Conference 2019

View full text Add to dashboard Cite

Though Motor Imagery (MI) stroke rehabilitation effectively promotes neural reorganization, current therapeutic methods are immeasurable and their repetitiveness can be demotivating. In this work, a real-time electroencephalogram (EEG) based MI-BCI (Brain Computer Interface) system with a virtual reality (VR) game as a motivational feedback has been developed for stroke rehabilitation. If the subject successfully hits one of the targets, it explodes and thus providing feedback on a successfully imagined and virtually executed movement of hands or feet. Novel classification algorithms with deep learning (DL) and convolutional neural network (CNN) architecture with a unique trial onset detection technique was used. Our classifiers performed better than the previous architectures on datasets from PhysioNet offline database. It provided fine classification in the real-time game setting using a 0.5 second 16 channel input for the CNN architectures. Ten participants reported the training to be interesting, fun and immersive. "It is a bit weird, because it feels like it would be my hands", was one of the comments from a test person. The VR system induced a slight discomfort and a moderate effort for MI activations was reported. We conclude that MI-BCI-VR systems with classifiers based on DL for real-time game applications should be considered for motivating MI stroke rehabilitation. CCS CONCEPTS • Human-centered computing → Empirical studies in HCI; Virtual reality; Usability testing.

show abstract

Section: Deep Learningmentioning

confidence: 99%

Brain Computer Interface for Neuro-rehabilitation With Deep Learning Classification and Virtual Reality Feedback

Karácsony

Hansen

Iversen

et al. 2019

Proceedings of the 10th Augmented Human International Conference 2019

View full text Add to dashboard Cite

show abstract

“…Applications using convolutional neural networks (CNN) are getting increasingly popular in the last few years, and this trend also reached the processing of EEG signals. J. Zhang et al [34] developed a method that uses deep-learning convolutional neural networks to classify imagined hand movements. X. Li et al [35] used CNN-s and RNN-s (recurrent neural networks) for recognition of human emotions.…”

Section: Processing Data With Neural Network 1) Neural Network Amentioning

confidence: 99%

Processing EEG signals acquired from a consumer grade BCI device

Monori

Oniga

2018

Carpathian Journal of Electronic and Computer Engineering

View full text Add to dashboard Cite

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.

show abstract

“…For building 2D-maps in discrimination of MI tasks, several algorithms of feature extraction are employed in CNN models, including the following: common spatial patterns due to the high recognition rate and computational simplicity [16]; event-related synchronization to capture the channel-wise temporal dynamics of the power signal [17]; empirical mode decomposition to deal with EEG nonstationarity [18,19]; and time-frequency planes using the Fourier and wavelet transforms are frequently extracted because they allow a more straightforward interpretation [20][21][22][23], the latter decomposition being better suited to deal with sudden changes in EEG signals. Nonetheless, the extracted 2D images tend to have substantial variability in patterns across trials due to inherent nonstationarity, artifacts, a poor signal-to-noise ratio of EEG signals, individual differences in cortical functioning (like subjects exhibiting activity in different frequency bands).…”

Section: Introductionmentioning

confidence: 99%

CNN-based framework using spatial dropping for enhanced interpretation of neural activity in motor imagery classification

et al. 2020

View full text Add to dashboard Cite

Interpretation of brain activity responses using motor imagery (MI) paradigms is vital for medical diagnosis and monitoring. Assessed by machine learning techniques, identification of imagined actions is hindered by substantial intra-and inter-subject variability. Here, we develop an architecture of Convolutional Neural Networks (CNN) with an enhanced interpretation of the spatial brain neural patterns that mainly contribute to the classification of MI tasks. Two methods of 2D-feature extraction from EEG data are contrasted: Power Spectral Density and Continuous Wavelet Transform. For preserving the spatial interpretation of extracting EEG patterns, we project the multi-channel data using a topographic interpolation. Besides, we include a spatial dropping algorithm to remove the learned weights that reflect the localities not engaged with the elicited brain response. We evaluate two labeled scenarios of MI tasks: bi-class and three-class. Obtained results in an MI database show that the thresholding strategy combined with Continuous Wavelet Transform improves the accuracy and enhances the interpretability of CNN architecture, showing that the highest contribution clusters over the sensorimotor cortex with a differentiated behavior of rhythms µ and β.

show abstract

Deep convolutional neural network for decoding motor imagery based brain computer interface

Cited by 56 publications

References 8 publications

Brain Computer Interface for Neuro-rehabilitation With Deep Learning Classification and Virtual Reality Feedback

Brain Computer Interface for Neuro-rehabilitation With Deep Learning Classification and Virtual Reality Feedback

Processing EEG signals acquired from a consumer grade BCI device

CNN-based framework using spatial dropping for enhanced interpretation of neural activity in motor imagery classification

Contact Info

Product

Resources

About