A Novel Two-Stage Refine Filtering Method for EEG-Based Motor Imagery Classification

Abstract

Cerebral stroke is a common disease across the world, and it is a promising method to recognize the intention of stroke patients with the help of brain–computer interface (BCI). In the field of motor imagery (MI) classification, appropriate filtering is vital for feature extracting of electroencephalogram (EEG) signals and consequently influences the accuracy of MI classification. In this case, a novel two-stage refine filtering method was proposed, inspired by Gradient-weighted Class Activation Mapping (Grad-CAM), which uses the gradients of any target concept flowing into the final convolutional layer to highlight the important part of training data for predicting the concept. In the first stage, MI classification was carried out and then the frequency band to be filtered was calculated according to the Grad-CAM of the MI classification results. In the second stage, EEG was filtered and classified for a higher classification accuracy. To evaluate the filtering effect, this method was applied to the multi-branch neural network proposed in our previous work. Experiment results revealed that the proposed method reached state-of-the-art classification kappa value levels and acquired at least 3% higher kappa values than other methods This study also proposed some promising application scenarios with this filtering method.

DeepKOA: a deep-learning model for predicting progression in knee osteoarthritis using multimodal magnetic resonance images from the osteoarthritis initiative

“…A pixel in the feature map corresponded to a region in the raw images. The contribution of a pixel to the final prediction was shown as the intensity of the pixel value in the heatmap, with the region with a higher pixel value indicating a greater influence ( 49 ). To further eliminate the influence of noise on the results, the pixel value of the heatmap was sorted in descending order, and pixels with the top 10% value were selected, whereas the other pixel values were set to zero.…”

A Comprehensive Survey of EEG Preprocessing Methods for Cognitive Load Assessment

“…Moreover, it was proved robust among different subjects. This promising denoising approach was proposed for denoising EEG signals across contexts because the filtering range is determined by the performance of the network [45]. In general, filtering strongly impacts the signal and requires further consideration.…”

NIRS Data Augmentation Technique to Detect Hemodynamic Peaks During Self-Paced Motor Imagery

“…This method has been used to identify the class discriminative time periods of MI for EEG. [21]. Applying Guided Grad-CAM on time-series NIRS data could provide crucial time-spatial hemodynamic features that may be valuable for understanding brain function during self-paced MI.…”