Classification of EEG Signal by STFT-CNN Framework: Identification of Right-/left-hand Motor Imagination in BCI Systems

Lu, Yao; Jiang, Huiping; Liu, Wenqiang

doi:10.22323/1.299.0001

Cited by 15 publications

(11 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the ConvNet, the first convolutional layer works as a frequential filter, in which the outcome consists of four different band‐pass filters that minimize the error at the output. In accordance with the input structures used in image processing, the EEG input to a ConvNet is usually reshaped into a 2D distribution, by arranging channels along the rows and time samples in the columns (Schirrmeister et al., 2017; Tang, Li, & Sun, 2016) or by transforming the input into a new space (Uktveris & Jusas, 2017), e.g., to a time‐frequency domain through Fourier transform and averaging along the channels (Lu, Jiang, & Liu, 2017; Soare, 2016). Taking this into consideration, only minimal and automatic pre‐processing (baseline correction and notch filtering) was performed in this study prior to the classification stage, and no epochs were removed.…”

Section: Discussionmentioning

confidence: 99%

Decoding kinetic features of hand motor preparation from single‐trial EEG using convolutional neural networks

Gatti

Atum

Schiaffino

et al. 2020

Eur J of Neuroscience

View full text Add to dashboard Cite

Building accurate movement decoding models from brain signals is crucial for many biomedical applications. Predicting specific movement features, such as speed and force, before movement execution may provide additional useful information at the expense of increasing the complexity of the decoding problem. Recent attempts to predict movement speed and force from the electroencephalogram (EEG) achieved classification accuracies at or slightly above chance levels, highlighting the need for more accurate prediction strategies. Thus, the aims of this study were to accurately predict hand movement speed and force from single‐trial EEG signals and to decode neurophysiological information of motor preparation from the prediction strategies. To these ends, a decoding model based on convolutional neural networks (ConvNets) was implemented and compared against other state‐of‐the‐art prediction strategies, such as support vector machines and decision trees. ConvNets outperformed the other prediction strategies, achieving an overall accuracy of 84% in the classification of two different levels of speed and force (four‐class classification) from pre‐movement single‐trial EEG (100 ms and up to 1,600 ms prior to movement execution). Furthermore, an analysis of the ConvNet architectures suggests that the network performs a complex spatiotemporal integration of EEG data to optimize classification accuracy. These results show that movement speed and force can be accurately predicted from single‐trial EEG, and that the prediction strategies may provide useful neurophysiological information about motor preparation.

show abstract

Section: Discussionmentioning

confidence: 99%

Decoding kinetic features of hand motor preparation from single‐trial EEG using convolutional neural networks

Gatti

Atum

Schiaffino

et al. 2020

Eur J of Neuroscience

View full text Add to dashboard Cite

show abstract

“…In this model, the first convolutional layer works as a frequential filter, in which the outcome consists of four different band-pass filters that minimise the error at the output. In accordance with the input structures used in image processing, the EEG input to a ConvNet is usually reshaped into a 2D distribution, by arranging channels along the rows and time samples in the columns [49,50] or by transforming the input into a new space [8], e.g., to a time-frequency domain through Fourier transform and averaging along the channels [51,52]. The ConvNet implemented in this study considered the localisation of the electrodes in order to keep the spatial relationship between them.…”

Section: Methodological Aspects Of Movement Predictionmentioning

confidence: 99%

Prediction of Hand Movement Speed and Force from Single-trial EEG with Convolutional Neural Networks

Gatti

Atum

Schiaffino

et al. 2018

Preprint

View full text Add to dashboard Cite

Building accurate movement decoding models from brain signals is crucial for many biomedical applications. Decoding specific movement features, such as speed and force, may provide additional useful information at the expense of increasing the complexity of the decoding problem. Recent attempts to predict movement speed and force from the electroencephalogram (EEG) achieved classification accuracy levels not better than chance, stressing the demand for more accurate prediction strategies. Thus, the aim of this study was to improve the prediction accuracy of hand movement speed and force from single-trial EEG signals recorded from healthy volunteers. A strategy based on convolutional neural networks (ConvNets) was tested, since it has previously shown good performance in the classification of EEG signals. ConvNets achieved an overall accuracy of 84% in the classification of two different levels of speed and force (4class classification) from single-trial EEG. These results represent a substantial improvement over previously reported results, suggesting that hand movement speed and force can be accurately predicted from single-trial EEG.

show abstract

“…Our research works are specializing in building up induced file database for generating different emotions, EEG database, and facial expression database, and in researching on emotion recognition, and intelligent HCI. Based on the study that we have done previously [25]- [27], we have proposed the approach to building up DEVI to construct ground truth dataset for EEG-based emotion recognition.…”

Section: Related Workmentioning

confidence: 99%

“…Inspired by such a common sense, we have proposed an approach to building up "Ground Truth Dataset for EEGbased Emotion Recognition with Visual Indication" (DEVI) based on what we have done previously [25]- [27], in order to set up an accurate ground truth dataset for the training and test of the EEG-based emotion recognition models. This paper is organized as follows: we describe some works closely related with building up labeled dataset for EEG-based emotion recognition to highlight our proposal in Section II.…”

Section: Introductionmentioning

confidence: 99%

Ground Truth Dataset for EEG-Based Emotion Recognition With Visual Indication

et al. 2020

Self Cite

View full text Add to dashboard Cite

Along with extensive and successive applications, emotion recognition based on electroencephalogram has attracted more and more researchers. However, how to acquire sufficient and high-quality real emotion electroencephalogram to train emotion recognition model has always been a bottleneck issue in the electroencephalogram-based emotion recognition research field. Because the subject's emotion is easy to be affected by many factors and subjects do not always evoke emotion well, it's very hard to determine whether the real emotion electroencephalogram appears or not in the experiments. On the contrary to electroencephalogram, facial expression obtained without any intentional control is easy to be recognized by computers, and is also one of the primary and reliable cues for understanding emotions. Inspired by such a common sense, we proposed an approach to building up ground truth electroencephalogram dataset with visual indication. Firstly, the relationship between facial expression and electroencephalogram is analyzed in details from the viewpoints of biophysics and correlation. Secondly, based on the analysis result that when the subject's facial expression is evoked, it should be accompanied by the emotional electroencephalogram corresponding to it, the method of building up the ground truth electroencephalogram dataset with visual indication is put forward along with the computer automatic implementation. Thirdly, we have built up a ground truth electroencephalogram dataset which covers 3 kinds of emotions (i.e. joy, sadness, and neutral) of the subjects who are undergraduate and graduate students from Minzu University of China. Lastly, the validation of the established dataset is tested by the comparative experiments between the long short term memory emotion recognition models trained with two different datasets respectively. One dataset contains both truth and false electroencephalograms and another one only contains the truth data.

show abstract

Classification of EEG Signal by STFT-CNN Framework: Identification of Right-/left-hand Motor Imagination in BCI Systems

Cited by 15 publications

References 9 publications

Decoding kinetic features of hand motor preparation from single‐trial EEG using convolutional neural networks

Decoding kinetic features of hand motor preparation from single‐trial EEG using convolutional neural networks

Prediction of Hand Movement Speed and Force from Single-trial EEG with Convolutional Neural Networks

Ground Truth Dataset for EEG-Based Emotion Recognition With Visual Indication

Contact Info

Product

Resources

About