OPTICAL+: a frequency-based deep learning scheme for recognizing brain wave signals

Kumar, Shiu; Sharma, Ronesh; Sharma, Alok

doi:10.7717/peerj-cs.375

Cited by 28 publications

(10 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To demonstrate the validity of the proposed framework, we applied the proposed framework (LMD-CSP and MOGWO-TWSVM) and other recent methods such as the temporal filter parameter optimization with CSP (TFPO-CSP) ( Kumar & Sharma, 2018 ) and the frequency-based deep learning scheme for recognizing brain wave signals (OPTICAL+) ( Kumar, Sharma & Sharma, 2021 ) on the same data sets, this data sets include the EEG data of shoulder abduction and extension. The obtained results are shown in Fig.…”

Section: Resultsmentioning

confidence: 99%

“…That study reported an average error recognition rate of 10.19% on BCI Competition III Dataset IVa (right hand and foot). Recently, Kumar, Sharma & Sharma (2021) used genetic algorithm (GA) for adaptive filtering, combined CSP and long short-term memory network (LSTM) for feature extraction, and applied SVM for classification. It should be noted that these studies focused on binary problems.…”

Section: Introdctionmentioning

confidence: 99%

See 1 more Smart Citation

Discriminating three motor imagery states of the same joint for brain-computer interface

Guan

Wang

et al. 2021

PeerJ

View full text Add to dashboard Cite

The classification of electroencephalography (EEG) induced by the same joint is one of the major challenges for brain-computer interface (BCI) systems. In this paper, we propose a new framework, which includes two parts, feature extraction and classification. Based on local mean decomposition (LMD), cloud model, and common spatial pattern (CSP), a feature extraction method called LMD-CSP is proposed to extract distinguishable features. In order to improve the classification results multi-objective grey wolf optimization twin support vector machine (MOGWO-TWSVM) is applied to discriminate the extracted features. We evaluated the performance of the proposed framework on our laboratory data sets with three motor imagery (MI) tasks of the same joint (shoulder abduction, extension, and flexion), and the average classification accuracy was 91.27%. Further comparison with several widely used methods showed that the proposed method had better performance in feature extraction and pattern classification. Overall, this study can be used for developing high-performance BCI systems, enabling individuals to control external devices intuitively and naturally.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introdctionmentioning

confidence: 99%

Discriminating three motor imagery states of the same joint for brain-computer interface

Guan

Wang

et al. 2021

PeerJ

View full text Add to dashboard Cite

show abstract

“…In recent years, there has been a surge in the use of deep learning techniques for MI-EEG classification tasks. Researchers have introduced various deep learning network models, including Convolutional Neural Networks (CNNs) (Zhang et al, 2020 ), Recurrent Neural Networks (RNNs) (Luo et al, 2018 ; Kumar et al, 2021 ), Deep Belief Networks (DBNs) (Xu et al, 2020 ), and Autoencoder (AE) structures (Hassanpour et al, 2019 ). Among these models, CNNs have been widely adopted, and a variety of CNN network designs have been proposed.…”

Section: Introductionmentioning

confidence: 99%

Bidirectional feature pyramid attention-based temporal convolutional network model for motor imagery electroencephalogram classification

Xie,

Chen,

Qin

et al. 2024

Front. Neurorobot.

View full text Add to dashboard Cite

IntroductionAs an interactive method gaining popularity, brain-computer interfaces (BCIs) aim to facilitate communication between the brain and external devices. Among the various research topics in BCIs, the classification of motor imagery using electroencephalography (EEG) signals has the potential to greatly improve the quality of life for people with disabilities.MethodsThis technology assists them in controlling computers or other devices like prosthetic limbs, wheelchairs, and drones. However, the current performance of EEG signal decoding is not sufficient for real-world applications based on Motor Imagery EEG (MI-EEG). To address this issue, this study proposes an attention-based bidirectional feature pyramid temporal convolutional network model for the classification task of MI-EEG. The model incorporates a multi-head self-attention mechanism to weigh significant features in the MI-EEG signals. It also utilizes a temporal convolution network (TCN) to separate high-level temporal features. The signals are enhanced using the sliding-window technique, and channel and time-domain information of the MI-EEG signals is extracted through convolution.ResultsAdditionally, a bidirectional feature pyramid structure is employed to implement attention mechanisms across different scales and multiple frequency bands of the MI-EEG signals. The performance of our model is evaluated on the BCI Competition IV-2a dataset and the BCI Competition IV-2b dataset, and the results showed that our model outperformed the state-of-the-art baseline model, with an accuracy of 87.5 and 86.3% for the subject-dependent, respectively.DiscussionIn conclusion, the BFATCNet model offers a novel approach for EEG-based motor imagery classification in BCIs, effectively capturing relevant features through attention mechanisms and temporal convolutional networks. Its superior performance on the BCI Competition IV-2a and IV-2b datasets highlights its potential for real-world applications. However, its performance on other datasets may vary, necessitating further research on data augmentation techniques and integration with multiple modalities to enhance interpretability and generalization. Additionally, reducing computational complexity for real-time applications is an important area for future work.

show abstract

“…Sakhavi et al built a classification model with CNN [7] . Kumar et al presented a model that employs a long short-term memory (LSTM) network [8] . In general, CNN has demonstrated superior performance than the recurrent neural network (RNN) and DBN in this field [5] .…”

Section: Introductionmentioning

confidence: 99%

Spatial information considered convolutional neural network for electroencephalogram-based motor imagery classification

Shi

Zhang

Pei

2023

3rd International Conference on Applied Mathematics, Modelling, and Intelligent Computing (CAMMIC 2023)

View full text Add to dashboard Cite

As brain-computer interface (BCI) technology continues to advance in various fields, it has become one of the possible solutions for patients with motor dysfunction who have healthy thinking ability to regain motor ability. The vigorous development of deep learning (DL) provides it with a possible tool to analyze electroencephalogram (EEG) signals.Through analyzing and categorizing EEG signals associated with motor imagery (MI), the system can effectively perceive the patient's motor intentions. Currently, Convolutional Neural Networks (CNN) have exhibited exceptional performance in a variety of fields, including computer vision (CV) and natural language processing (NLP). However, the brain structure has rich spatial information, which was not fully utilized by CNN for MI-EEG signal analysis in the past. This paper introduces SP-CNN, a convolutional neural network that incorporates spatial information from the brain, to address the classification challenge of MI-EEG signals. The experimental findings indicate that this method exhibits stable and robust performance across diverse subjects.

show abstract

OPTICAL+: a frequency-based deep learning scheme for recognizing brain wave signals

Cited by 28 publications

References 52 publications

Discriminating three motor imagery states of the same joint for brain-computer interface

Discriminating three motor imagery states of the same joint for brain-computer interface

Bidirectional feature pyramid attention-based temporal convolutional network model for motor imagery electroencephalogram classification

Spatial information considered convolutional neural network for electroencephalogram-based motor imagery classification

Contact Info

Product

Resources

About