Enhancing performance of subject-specific models via subject-independent information for SSVEP-based BCIs

📝 Abstract

Recently, brain-computer interface (BCI) systems developed based on steady-state visual evoked potential (SSVEP) have attracted much attention due to their high information transfer rate (ITR) and increasing number of targets. However, SSVEP-based methods can be improved in terms of their accuracy and target detection time. We propose a new method based on canonical correlation analysis (CCA) to integrate subject-specific models and subject-independent information and enhance BCI performance. We propose to use training data of other subjects to optimize hyperparameters for CCA-based model of a specific subject. An ensemble version of the proposed method is also developed for a fair comparison with ensemble task-related component analysis (TRCA). The proposed method is compared with TRCA and extended CCA methods. A publicly available, 35-subject SSVEP benchmark dataset is used for comparison studies and performance is quantified by classification accuracy and ITR. The ITR of the proposed method is higher than those of TRCA and extended CCA. The proposed method outperforms extended CCA in all conditions and TRCA for time windows greater than 0.3 s. The proposed method also outperforms TRCA when there are limited training blocks and electrodes. This study illustrates that adding subject-independent information to subject-specific models can improve performance of SSVEP-based BCIs.

💡 Analysis

Recently, brain-computer interface (BCI) systems developed based on steady-state visual evoked potential (SSVEP) have attracted much attention due to their high information transfer rate (ITR) and increasing number of targets. However, SSVEP-based methods can be improved in terms of their accuracy and target detection time. We propose a new method based on canonical correlation analysis (CCA) to integrate subject-specific models and subject-independent information and enhance BCI performance. We propose to use training data of other subjects to optimize hyperparameters for CCA-based model of a specific subject. An ensemble version of the proposed method is also developed for a fair comparison with ensemble task-related component analysis (TRCA). The proposed method is compared with TRCA and extended CCA methods. A publicly available, 35-subject SSVEP benchmark dataset is used for comparison studies and performance is quantified by classification accuracy and ITR. The ITR of the proposed method is higher than those of TRCA and extended CCA. The proposed method outperforms extended CCA in all conditions and TRCA for time windows greater than 0.3 s. The proposed method also outperforms TRCA when there are limited training blocks and electrodes. This study illustrates that adding subject-independent information to subject-specific models can improve performance of SSVEP-based BCIs.

📄 Content

1

Enhancing Performance of Subject-Specific Models via Subject- Independent Information for SSVEP-Based BCIs Mohammad Hadi Mehdizavareh1, Sobhan Hemati1, Hamid Soltanian-Zadeh1,2 1CIPCE, School of Electrical and Computer Engineering, College of Engineering, University of Tehran, Tehran, Iran 2Medical Image Analysis Laboratory, Departments of Radiology and Research Administration, Henry Ford Health System, Detroit, MI 48202, USA

Abstract Recently, steady-state visual evoked potential (SSVEP)-based brain-computer interface (BCI) has attracted much attention due to its high information transfer rate (ITR) and increasing number of targets. However, the performance of SSVEP-based methods in terms of accuracy and time length required for target detection can be improved. We propose a new canonical correlation analysis (CCA)-based method to integrate subject-specific models and subject-independent information and enhance BCI performance. To optimize hyperparameters for CCA-based model of a specific subject, we propose to use training data of other subjects. An ensemble version of the proposed method is also developed and used for a fair comparison with ensemble task-related component analysis (TRCA). A publicly available 35-subject SSVEP benchmark dataset is used to evaluate different methods. The proposed method is compared with TRCA and extended CCA methods as reference methods. The performance of the methods is evaluated using classification accuracy and ITR. Offline analysis results show that the proposed method reaches highest ITR compared with TRCA and extended CCA. Also, the proposed method significantly improves performance of extended CCA in all conditions and TRCA for time windows greater than 0.3 s. In addition, the proposed method outperforms TRCA for low number of training blocks and electrodes. This study illustrates that adding subject-independent information to subject-specific models can improve the performance of SSVEP-based BCIs.

Keywords: brain-computer interface (BCI); steady-state visual evoked potential (SSVEP); information transfer rate (ITR); canonical correlation analysis (CCA); subject-specific training; subject-independent training.

2

1. Introduction Brain-computer interface (BCI) systems have been recognized as a new Communication channel for humans, especially severely disabled individuals [1-3]. One of the most important applications of BCI is character speller system which allows disabled individuals to communicate with their surrounding environment [2]. Electroencephalography (EEG) is a noninvasive, low cost, and simple modality, widely used to implement BCI spellers [4]. In recent years, steady-state visual evoked potential (SSVEP)-based BCI spellers have attracted much more attention compared with other BCI systems including motor imagery and P300. This is because of their high information transfer rate (ITR), less user training, and the ability to deal with problems with a large number of classes [4-7]. There are many target coding methods in SSVEP-based BCIs, among which frequency coding is a popular method to encode targets [8, 9]. Several methods have been proposed to combine phase and frequency coding approaches [10-12]. The most discriminative method is joint frequency- phase modulation (JFPM) method which assigns different frequencies and phases to two adjacent targets [12]. Target identification is another crucial issue in SSVEP-based BCIs, for which numerous methods have been proposed. Initially, single-channel methods were presented based on power spectral density analysis (PDSA) [13-14] and then multiple channel methods were introduced to improve the signal to noise ratio (SNR) of SSVEP response. In these methods, channels are combined using appropriate spatial filters so that common noises in the channels are reduced and the quality of SSVEP response is improved. Some powerful examples of such methods are minimum energy combination (MEC) [15], Maximum contrast combination (MCC) [15], and canonical correlation analysis (CCA) [16]. Although these methods are widely used because of their simplicity and free training attribute, they only detect frequency. They are unable to discriminate two different phases [11], and their performance degrades in short time windows due to the presence of the background noise in the EEG signal. To solve these problems, incorporating individual calibration data has been proposed [12, 17-20]. Extended CCA method was introduced to combine CCA coefficient with the Pearson correlation coefficients among the test and training data [12]. Multiway CCA (MwayCCA) [17], L1-regularized MwayCCA [18], and multiset CCA (MsetCCA) [19] were proposed to optimize artificial sine-cosine reference signals embedded in CCA using training trials of each subject. Also, task-related component analysis (TRCA) was suggested to enhance the SNR of SSVEP response using optimized spatial

This content is AI-processed based on ArXiv data.