A Ternary Bi-Directional LSTM Classification for Brain Activation Pattern Recognition Using fNIRS
This work addresses the need for more accurate and efficient brain-computer interface systems using fNIRS data, though it appears incremental as it applies an existing deep learning method to this domain.
The paper tackled the problem of low accuracy and complex preprocessing in fNIRS-based brain activation pattern classification by proposing a Bi-Directional LSTM deep learning architecture, achieving 81.48% accuracy for tasks like mental arithmetic and motor imagery.
Functional near-infrared spectroscopy (fNIRS) is a non-invasive, low-cost method used to study the brain's blood flow pattern. Such patterns can enable us to classify performed by a subject. In recent research, most classification systems use traditional machine learning algorithms for the classification of tasks. These methods, which are easier to implement, usually suffer from low accuracy. Further, a complex pre-processing phase is required for data preparation before implementing traditional machine learning methods. The proposed system uses a Bi-Directional LSTM based deep learning architecture for task classification, including mental arithmetic, motor imagery, and idle state using fNIRS data. Further, this system will require less pre-processing than the traditional approach, saving time and computational resources while obtaining an accuracy of 81.48\%, which is considerably higher than the accuracy obtained using conventional machine learning algorithms for the same data set.