Instance Transfer Subject-Dependent Strategy for Motor Imagery Signal Classification Using Deep Convolutional Neural Networks

Abstract

In the process of brain-computer interface (BCI), variations across sessions/subjects result in differences in the properties of potential of the brain. This issue may lead to variations in feature distribution of electroencephalogram (EEG) across subjects, which greatly reduces the generalization ability of a classifier. Although subject-dependent (SD) strategy provides a promising way to solve the problem of personalized classification, it cannot achieve expected performance due to the limitation of the amount of data especially for a deep neural network (DNN) classification model. Herein, we propose an instance transfer subject-independent (ITSD) framework combined with a convolutional neural network (CNN) to improve the classification accuracy of the model during motor imagery (MI) task. The proposed framework consists of the following steps. Firstly, an instance transfer learning based on the perceptive Hash algorithm is proposed to measure similarity of spectrogram EEG signals between different subjects. Then, we develop a CNN to decode these signals after instance transfer learning. Next, the performance of classifications by different training strategies (subject-independent- (SI-) CNN, SD-CNN, and ITSD-CNN) are compared. To verify the effectiveness of the algorithm, we evaluate it on the dataset of BCI competition IV-2b. Experiments show that the instance transfer learning can achieve positive instance transfer using a CNN classification model. Among the three different training strategies, the average classification accuracy of ITSD-CNN can achieve 94.7±2.6 and obtain obvious improvement compared with a contrast model p<0.01. Compared with other methods proposed in previous research, the framework of ITSD-CNN outperforms the state-of-the-art classification methods with a mean kappa value of 0.664.

Subject-Specific Cognitive Workload Classification Using EEG-Based Functional Connectivity and Deep Learning

“…The subject-dependent classifiers can extract subject-dependent features and can effectively tackle the issue of accuracy and generalization encountered in subject-independent EEG classifiers. However, it also gives rise to the issues of long collaboration sessions and collection of large quantities of data [ 38 , 39 ]. Lastly, the choice of 16 brain regions for computing the connectivity matrices.…”

“…Given this evidence, subject specific classification of workload has been aimed at in this study. In Zhang et al [ 38 ], the authors compared the subject-dependent and independent approach and highlighted that variations in feature distribution of EEG across subjects reduces the generalization ability of a classifier and at the same time subject-dependent approach provides a promising way to solve the problem of personalized classification. In Neto et al [ 39 ], the authors discussed various subject specific characteristics and data splitting techniques for EEG data.…”

An Efficient Signal Processing Algorithm for Detecting Abnormalities in EEG Signal Using CNN

“…In this work, the variables lambda, rate of learning, and velocity are set at 0.7, 1 × 10 −3 , and 0.3, respectively. ese values were discovered through experimental and fault error [25]. is study is the initial application of CNN for the EEG signal analysis in overall and appropriation identification specifically, to the authors' knowledge.…”

Motor Imagery EEG Classification Based on Transfer Learning and Multi-Scale Convolution Network

“…In recent years, some scholars have proposed various isomorphism and heterogeneous transfer learning methods to solve the problem of fewer EEG signals. Zhang et al [19] proposed an instance-based transfer learning framework, which does not change the feature space and properties of motion imagery task signals, measures the similarity between the source domain and target domain signal features by perceptual hash algorithm, calculates the transfer weight coefficient, and extends the training set of the target domain. Later, Zhang and his team [20] proposed to use all the data of other subjects to train the model on the basis of Deep ConvNets network, fine-tuning and adaptive pre-training model with a small amount of target data, and compared the transfer and adaptive adjustment results of each layer of the network.…”