Key result
The OPTICAL+ deep learning predictor achieved an overall average classification error rate of 30.41% for recognizing brain wave signals, significantly outperforming the OPTICAL method (p=0.0015).
Why the study?
Real-time implementation, computational complexity, and accuracy remain concerns in developing human-computer interaction systems using brain wave signals, particularly in selecting appropriate filtering frequency bands.
Does the OPTICAL+ predictor improve the classification of brain wave signals compared to state-of-the-art methods in healthy subjects?
Does the OPTICAL+ predictor improve the classification of brain wave signals compared to state-of-the-art methods in healthy subjects?
Answers are grounded in this paper and cite their sources.
The OPTICAL+ predictor using adaptive filtering and LSTM improves the classification accuracy of motor imagery EEG signals compared to existing methods.
A human-computer interaction (HCI) system can be used to detect different categories of the brain wave signals that can be beneficial for neurorehabilitation, seizure detection and sleep stage classification. Research on developing HCI systems using brain wave signals has progressed a lot over the years. However, real-time implementation, computational complexity and accuracy are still a concern. In this work, we address the problem of selecting the appropriate filtering frequency band while also achieving a good system performance by proposing a frequency-based approach using long short-term memory network (LSTM) for recognizing different brain wave signals. Adaptive filtering using genetic algorithm is incorporated for a hybrid system utilizing common spatial pattern and LSTM network. The proposed method (OPTICAL+) achieved an overall average classification error rate of 30.41% and a kappa coefficient value of 0.398, outperforming the state-of-the-art methods. The proposed OPTICAL+ predictor can be used to develop improved HCI systems that will aid in neurorehabilitation and may also be beneficial for sleep stage classification and seizure detection.
No takes yet. Share an insight, caveat, or question.
Kumar et al. (2021) studied Healthy subjects (Motor imagery EEG classification) (n=52). OPTICAL+ predictor vs. Other state-of-the-art methods (e.g., OPTICAL, CSP) was evaluated on Classification error rate (p=0.0015). The OPTICAL+ deep learning predictor achieved an overall average classification error rate of 30.41% for recognizing brain wave signals, significantly outperforming the OPTICAL method (p=0.0015).
Synapse has enriched 10 related papers. Consider them for comparative context: