Abstract
Each person has his or her own distinct event-related potential (ERP) signals. Thus, traditional brain-computer interface (BCI) systems require a calibration process in which the subject's data are extracted in order to train machine-learning classifiers. Despite past efforts to eliminate this process, often referred to as “zero-training,” BCI systems' best performance is achievable only with some level of calibration. This tedious process is one of the factors that have limited the use of BCI systems in the real world. Meanwhile, convolutional neural networks (CNN) have been proven to be useful in distinguishing neurophysiological features. In this study, we investigated whether an existing convolutional neural network (CNN) combined with large ERP samples (n = 99,000) can achieve zero-training in a P300 BCI speller system. As a result, the zero-trained CNN achieved comparable performance (89%, p 0.05) with calibration. Additionally, we illustrate a hybrid approach in order to further enhance performance, which adaptively updates a linear classifier using label information generated from a zero-trained CNN. With this technique, the hybrid approach achieved reasonable performance (92%), showing no statistical difference (p > 0.05) when compared to the traditional approach in the same offline data.
Highlights
Brain-computer interface (BCI) applications have begun to increasingly find their way into our lives through areas such as prosthesis, rehabilitation, and games [1], [2]
The primary goal of this study is to see if a neural network, convolutional neural networks (CNN), could achieve zero-training in the P300 BCI system when fed a large dataset from different subjects
Our questions would be: ‘‘How much data would be needed in order to achieve optimal performance?’’ and ‘‘What kind of data would be suitable to be used as a training set for such an approach?’’ We investigated these issues through a thorough analysis, and to the best of our knowledge, this is the first study that has attempted to use a CNN with such a large number of event-related potential (ERP) samples from multiple subjects in order to achieve zero-training in a P300 BCI, as well as to investigate the impact that the amount of data has on the performance of neural network-based transfer learning in zerotraining
Summary
Brain-computer interface (BCI) applications have begun to increasingly find their way into our lives through areas such as prosthesis, rehabilitation, and games [1], [2]. A large portion of these applications use event-related potential (ERP) elicited from the brain [3], [4]. They often use visual, tactile, or auditory stimulus in order to elicit ERP signals, as well as hybrid stimulus [5]–[8]. With a sufficiently large inter-stimulus interval (ISI), such difference is not of great importance. Applications such as the P300 speller have a small ISI with which to increase the information transfer rate, making it susceptible to individual differences [11]
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
